Digital learning auxiliary method and system

Abstract

The invention provides a digital learning auxiliary method and system, and belongs to the technical field of digital education, and the method comprises the steps: setting a knowledge point prompt request key in an exercise of an education platform, and obtaining preset knowledge point information related to a knowledge point of a current question through clicking the knowledge point prompt request key; obtaining prompt times of the preset knowledge point information, and judging whether the prompt times are greater than a threshold value; if it is judged that the prompt frequency is larger than the threshold value, preset knowledge point information and auxiliary memory information generated according to the preset knowledge point information are displayed, and the auxiliary memory information is a pithy formula containing harmonic tones. Meanwhile, a pithy formula containing harmonic sound is adopted as auxiliary memory information, so that students can be effectively helped to remember knowledge points.

Description

Technical Field

[0001] The present invention belongs to the field of digital education technology, and in particular relates to a digital learning auxiliary method and system. Background Art

[0002] With the development of information technology, digital education platforms have become an important part of modern teaching. These platforms support students' learning process by providing online courses, exercises and instant feedback.

[0003] However, on traditional digital education platforms, when students encounter difficult questions, they can only rely on guessing or answering randomly, which is not conducive to students truly mastering knowledge. In addition, if students answer questions incorrectly, the platform will push more related exercises for students to practice, but this method is inefficient and may cause students to misunderstand the knowledge points. Summary of the invention

[0004] Based on this, an embodiment of the present invention provides a digital learning assistance method and system, which aims to provide relevant materials that aid memory when students encounter difficult problems in the process of doing exercises, so as to improve learning efficiency.

[0005] A first aspect of an embodiment of the present invention provides a digital learning assistance method, which is applied to a scenario with an education platform, and the method includes: A knowledge point prompt request button is set in the exercises of the education platform, and preset knowledge point information associated with the knowledge point of the current question is obtained by clicking the knowledge point prompt request button; Obtaining the number of prompts for the preset knowledge point information, and determining whether the number of prompts is greater than a threshold; If it is determined that the number of prompts is greater than a threshold, the preset knowledge point information and auxiliary memory information associated with the knowledge point are displayed, wherein the auxiliary memory information is a formula containing homophones, a static picture, a dynamic picture or a video.

[0006] Furthermore, the step of generating auxiliary memory information associated with the knowledge point includes: Obtaining elements in the preset knowledge point information, wherein the elements at least include time, person, and place; According to the attributes of the elements, the corresponding elements are expanded according to preset rules to obtain corresponding element libraries; A word is randomly extracted from each element library, and the extracted word is input into the trained neural network model to output the formula.

[0007] Furthermore, in the step of expanding the corresponding elements according to preset rules based on the attributes of the elements to obtain corresponding element libraries, when the element is time, the expanded element library at least includes the denoised time entity and the homophonic words derived from the denoised time entity; when the element is a person, the expanded element library at least includes various titles of the person and the homophonic words derived from the various titles; when the element is a place, the expanded element library at least includes several names of the place and the homophonic words derived from the several names.

[0008] Furthermore, a word is randomly extracted from each element library, and the extracted word is input into the trained neural network model. Before the step of outputting the formula, if the elements in the preset knowledge point information include characters, when training the neural network model, the background information of the character is trained as a part of the text corpus.

[0009] Furthermore, the neural network model adopts one or a combination of RNN network model, LSTM network model, GRU network model, and Transformer network model.

[0010] Furthermore, the step of setting a knowledge point prompt request key in the exercises of the education platform includes: Determine whether there is a cursor in the display screen of the education platform; When it is determined that there is a cursor in the display screen of the education platform, a knowledge point prompt request key is set according to the position of the cursor in the display screen of the education platform; When it is determined that there is no cursor in the display screen of the education platform, a knowledge point prompt request key is set at a preset position in the display screen of the education platform, and changes with the answering time.

[0011] Furthermore, the step of setting a knowledge point prompt request key according to the position of the cursor in the display screen of the education platform includes: Acquire the position of the cursor in the display screen of the education platform in real time to determine whether the cursor is in a stationary state; If it is determined that the cursor is in a stationary state, a knowledge point prompt request key is set according to the current position of the cursor in the display screen of the education platform and the position of the exercise, so that the knowledge point prompt request key is close to the cursor and does not block the exercise; If it is determined that the cursor is not in a stationary state, obtaining a moving track of the cursor, and inferring a next moving area according to the moving track; Set the knowledge point prompt request key according to the next moving area and the position of the exercise.

[0012] A second aspect of an embodiment of the present invention provides a digital learning assistance system, which is used to implement the digital learning assistance method provided in the first aspect, and the system includes: A setting module, used to set a knowledge point prompt request key in the exercises of the education platform, and obtain preset knowledge point information associated with the knowledge point of the current question by clicking the knowledge point prompt request key; A judgment module, used to obtain the number of prompts of the preset knowledge point information, and judge whether the number of prompts is greater than a threshold; The display module is used to display the preset knowledge point information and the auxiliary memory information associated with the knowledge point if it is determined that the number of prompts is greater than a threshold value, wherein the auxiliary memory information is a formula containing homophones, a static picture, a dynamic picture or a video.

[0013] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the digital learning assistance method provided in the first aspect.

[0014] A fourth aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the digital learning assistance method provided in the first aspect is implemented.

[0015] A digital learning assistance method and system are provided in an embodiment of the present invention. The method sets a knowledge point prompt request key in the exercises of an education platform, and obtains preset knowledge point information associated with the knowledge point of the current question by clicking the knowledge point prompt request key; obtains the number of prompts for the preset knowledge point information, and determines whether the number of prompts is greater than a threshold; if the number of prompts is greater than the threshold, the preset knowledge point information and auxiliary memory information generated according to the preset knowledge point information are displayed, wherein the auxiliary memory information is a formula containing homophones. Specifically, through the above method, students can obtain correct knowledge point guidance in a timely manner when doing questions, and using formulas containing homophones as auxiliary memory information can effectively help students remember knowledge points. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a digital learning assistance method provided in the first embodiment of the present invention; Figure 2 A structural block diagram of a digital learning assistance system provided in Embodiment 2 of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0017] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0018] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0019] 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 the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0020] Embodiment 1 According to an embodiment of the present invention, a digital learning assistance method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0021] In the first embodiment, a digital learning assistance method is provided, which can be used in electronic devices, such as computers. It should be noted that the method is applied in a scenario with an education platform.

[0022] See also Figure 1 , Figure 1 A flowchart of an implementation of a digital learning assistance method provided in the first embodiment of the present invention is shown, which specifically includes steps S01 to S03.

[0023] Step S01, setting a knowledge point prompt request key in the exercises of the education platform, and obtaining preset knowledge point information associated with the knowledge point of the current question by clicking the knowledge point prompt request key.

[0024] Specifically, the knowledge point prompt request key can be a prompt button. It can be understood that when students encounter difficulties in answering questions, they can obtain knowledge point information related to the current question by clicking the prompt button to ensure that students can answer based on correct understanding.

[0025] In this embodiment, compared with the knowledge point prompt request key set at a traditional fixed position, by setting a non-fixed knowledge point prompt request key, students can be given a certain amount of thinking time to click the knowledge point prompt request key nearby to obtain preset knowledge point information and / or auxiliary memory information. At the same time, by hiding the knowledge point prompt request key, the user's usage experience can be improved. Specifically, the steps of setting the knowledge point prompt request key in the exercises of the education platform include: When the student's answering time reaches the preset time, it means that the student does not understand or is not familiar with the question. At this time, the student needs to obtain the preset knowledge point information and / or auxiliary memory information by clicking the knowledge point prompt request key, and determine whether there is a cursor in the display screen of the education platform, where the cursor can be understood as a mouse cursor or other indicator mark; When it is determined that there is a cursor in the display screen of the education platform, a knowledge point prompt request key is set according to the position of the cursor in the display screen of the education platform. It should be noted that the position of the cursor in the display screen of the education platform is obtained in real time to determine whether the cursor is in a stationary state. It can be understood that when the cursor stays for more than a preset time, it can be determined that it is in a stationary state; If it is determined that the cursor is in a stationary state, a knowledge point prompt request key is set according to the current cursor position in the display screen of the education platform and the position of the exercise, so that the knowledge point prompt request key is close to the cursor without blocking the exercise. Specifically, the border of the knowledge point prompt request key is determined according to the preset size of the knowledge point prompt request key. At the same time, the border of the exercise is determined according to the exercise, and it is determined whether the border of the knowledge point prompt request key interferes with the border of the exercise. If it is determined that the border of the knowledge point prompt request key interferes with the border of the exercise, the position of the border of each part of the exercise is determined. It can be understood that the exercise may include the question stem and options, etc., and it is determined whether there is space in the border of each part of the content to accommodate the knowledge point prompt request key. If it is determined that there is space for accommodating the knowledge point prompt request key in the borders of each part of the content, the shortest distance from the cursor to the space for accommodating the knowledge point prompt request key and the blank area of ​​the exercise is obtained, and the knowledge point prompt request key is set according to the shortest distance. In addition, if it is determined that there is no space for accommodating the knowledge point prompt request key in the borders of each part of the content, the borders of each part of the content in the exercise are combined to obtain an overall border, and the knowledge point prompt request key is set on the border on the side with the shortest cursor movement distance. It should be noted that if it is determined that there is no interference between the border of the knowledge point prompt request key and the border of the exercise, the knowledge point prompt request key is set on the side of the cursor away from the exercise; If it is determined that the cursor is not in a stationary state, the movement trajectory of the cursor is obtained, and the next moving area is inferred based on the movement trajectory. Generally, if the cursor is not in a stationary state, it is usually because the student uses the cursor to slide on the exercise to read the question during the answering process. Specifically, when the exercise frame is known, it is determined whether the cursor moves in the frame according to the reading order. If it is determined that the cursor moves in the frame according to the reading order, the knowledge point prompt request key is set at the beginning or end of the frame according to the distance between the cursor and the beginning and end of the frame. If it is determined that the cursor does not move in the frame according to the reading order, it may be that the student moves the cursor unconsciously. In this case, refer to the operation when the cursor is in a stationary state and set the knowledge point prompt request key nearby; Set the knowledge point prompt request key according to the next moving area and the position of the exercise; When it is determined that there is no cursor in the display screen of the education platform, a knowledge point prompt request key is set at a preset position in the display screen of the education platform, and the key changes with the answering time. In this embodiment, a hidden knowledge point prompt request key can be set at a preset position in the display screen of the education platform. When the answering time reaches a certain time, the knowledge point prompt request key is displayed for the user to click. Furthermore, as the answering time increases, the possibility of giving a correct answer decreases, and usually only guessing or answering randomly can be relied on. In this way, correct learning guidance cannot be provided, so the user needs to click the knowledge point prompt request key to master the knowledge points. To this end, as the answering time increases, the click area of ​​the knowledge point prompt request key is gradually expanded until the click area reaches a size that can display auxiliary memory information. Furthermore, when the click area reaches a size that can display auxiliary memory information, if the user still does not click after a period of time, the auxiliary memory information is actively displayed.

[0026] Step S02, obtaining the number of prompts of the preset knowledge point information, and determining whether the number of prompts is greater than a threshold, if so, executing step S03.

[0027] Among them, if students frequently request to review the same knowledge point (such as more than twice), it means that the students may not have fully mastered the knowledge point and need auxiliary memory. It should be noted that the questions for the same knowledge point may be different or the same.

[0028] Step S03, displaying the preset knowledge point information and the auxiliary memory information generated according to the preset knowledge point information, wherein the auxiliary memory information is a formula containing homophones, a static picture, a dynamic picture or a video.

[0029] Specifically, the step of generating auxiliary memory information according to the preset knowledge point information includes: Obtaining elements in the preset knowledge point information, the elements at least including time, person, and place; According to the attributes of the elements, the corresponding elements are expanded according to the preset rules to obtain the corresponding element libraries. Specifically, when the element is time, the expanded element library at least includes the denoised time ontology and the words corresponding to the homophones derived from the denoised time ontology. For example, the time is May 5, 1818, and the denoised time ontology is "181855". The words corresponding to the derived homophones can be "Yiba", "Wuwu", etc. "Yiba" represents "18", "Wuwu" represents "55". In addition, the words corresponding to the derived homophones can be derived again, for example, "Yiba" is derived into "Yibazhang"; when the element is a person, the expanded element library at least includes various names of the person and the words corresponding to the homophones derived from the various names. It can be understood that the various names of the person can be full names, nicknames, nicknames, etc.; when the element is a place, the expanded element library at least includes several names of the place and the words corresponding to the homophones derived from several names; A word is randomly extracted from each element library, and the extracted word is input into the trained neural network model to output the formula. It should be noted that the neural network model adopts one or a combination of RNN network model, LSTM network model, GRU network model and Transformer network model. In addition, before training the neural network model, if the elements in the preset knowledge point information include characters, the background information of the character is used as part of the text corpus for training when the neural network model is trained. The advantage of this is that the auxiliary memory information can be further optimized according to the representative events of the character to help students remember.

[0030] In this embodiment, the neural network model adopts the RNN network model, and the specific algorithm flow can be as follows: Data preprocessing stage: 1. Collect a large-scale text corpus, including news articles, novels, academic papers, blogs and other types of text to ensure the richness and diversity of the corpus. The corpus is then cleaned to remove noise data, such as special symbols, garbled codes, HTML tags, etc. 2. Perform word segmentation on the cleaned corpus to divide the text into individual words or phrases. Existing word segmentation tools can be used, such as the Chinese Jieba word segmenter and the English NLTK word segmenter. Build a vocabulary based on the word segmentation results and count the frequency of each word in the corpus. In order to control the size of the vocabulary, a frequency threshold can be set to retain only words with a frequency higher than the threshold. At the same time, add some special tags, such as <start>Indicates the beginning of a sentence. <end>Indicates the end of a sentence. <unk>Represents unknown words (used to process words outside the vocabulary). 3. In order to better represent the semantic information of words, the word vector model can be used to train the words in the vocabulary. Common word vector models include Word2Vec (including CBOW and Skip-Gram models), GloVe, etc. Through training, each word is mapped to a low-dimensional vector space, so that words with similar semantics are closer in the vector space.

[0031] Model training phase: 1. Build the RNN network structure, including the input layer, hidden layer, and output layer. The input layer receives the vector representation of the word, the hidden layer is used to process the sequence information and pass the state, and the output layer outputs the predicted probability distribution of the next word. Then initialize the weights and bias parameters of the network, which can be initialized using random initialization or the parameters of the pre-trained model. 2. Convert the sentences in the corpus into word sequences and replace each word with its corresponding word vector. During the training process, input a sentence each time, <start>The token starts and is input into the RNN network word by word. At each time step, the RNN calculates the hidden state of the current time step based on the word vector of the current input word and the hidden state of the previous time step. The calculation formula for the hidden state is: ,in is the hidden state at the current time step, is the word vector of the current input word, and is the weight matrix from input to hidden layer and from hidden layer to hidden layer, is the bias vector of the hidden layer. The output layer calculates the predicted probability distribution of the next word based on the hidden state of the current time step. Assuming the vocabulary size is , the calculation formula of the output layer is: ,in is the predicted probability distribution of the next word, is the weight matrix from the hidden layer to the output layer, is the bias vector of the output layer, The function is used to convert the output into a probability distribution so that the sum of the probabilities of all words is 1. The specific calculation formula can be expressed as , represents the input vector, , Represents the first elements, is a natural constant. 3. Calculate the loss function based on the predicted probability distribution and the actual next word. The commonly used loss function is the cross entropy loss function, and the calculation formula is: , where T is the length of the sentence. Use the backpropagation algorithm to calculate the gradient of the loss function with respect to the network parameters. Starting from the output layer, calculate the gradient of each layer in turn, and update the weights and bias parameters of the network according to the gradient. You can use optimization algorithms such as stochastic gradient descent (SGD), Adagrad, Adadelta, Adam, etc. to control the update step size of the parameters. 4. Repeat the above process of data input, forward propagation, loss calculation, backpropagation and parameter update, and perform multiple rounds of training on the entire corpus until the loss function of the model converges or reaches the preset number of training rounds. During the training process, you can use the validation set to monitor the performance of the model, such as calculating the loss function value or accuracy on the validation set to avoid overfitting of the model. If the model is found to be overfitting, some regularization techniques, such as L1 regularization, L2 regularization, Dropout, etc., can be used to reduce the overfitting phenomenon.

[0032] In the sentence generation stage, 1. Select a starting word or phrase, convert it into a word vector, and use it as the initial input of the RNN network. At the same time, initialize the hidden state of the network to an all-zero vector or a random vector. 2. Input the word vector and hidden state of the current input word into the RNN network, and calculate the predicted probability distribution of the next word through forward propagation. Select the next word according to the predicted probability distribution. A variety of selection strategies can be adopted, such as the greedy strategy, that is, selecting the word with the highest probability; the random sampling strategy, that is, randomly selecting a word according to the probability distribution; the beam search strategy, that is, retaining the top k words with higher probabilities, and performing subsequent predictions and searches on each word, and finally selecting the word sequence with the highest comprehensive score as the generated sentence. 3. Add the selected words to the generated sentence, and update the input words and hidden states. Repeat the above word prediction and selection process until the generated sentence reaches the preset length or encounters a problem. <end>Mark until. Post-process the generated sentences, such as removing <start>and <end>Tokenizing, converting words into raw text form, etc., to get the final generated sentence.

[0033] In summary, the digital learning assistance method in the above-mentioned embodiment of the present invention sets a knowledge point prompt request key in the exercises of the education platform, and obtains preset knowledge point information associated with the knowledge point of the current question by clicking the knowledge point prompt request key; obtains the number of prompts for the preset knowledge point information, and determines whether the number of prompts is greater than a threshold; if the number of prompts is greater than the threshold, the preset knowledge point information and the auxiliary memory information generated according to the preset knowledge point information are displayed, wherein the auxiliary memory information is a formula containing homophones. Specifically, through the above-mentioned method, students can obtain correct knowledge point guidance in time when doing questions, and at the same time, using formulas containing homophones as auxiliary memory information can effectively help students remember knowledge points.

[0034] Embodiment 2 See also Figure 2 , Figure 2 It is a structural block diagram of a digital learning assistance system provided in the second embodiment of the present invention. The digital learning assistance system 200 is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0035] Specifically, the digital learning assistance system 200 includes: a setting module 21, a judgment module 22 and a display module 23, wherein: A setting module 21, used to set a knowledge point prompt request key in the exercises of the education platform, and obtain preset knowledge point information associated with the knowledge point of the current question by clicking the knowledge point prompt request key; A judgment module 22, used to obtain the number of prompts of the preset knowledge point information, and judge whether the number of prompts is greater than a threshold; The display module 23 is used to display the preset knowledge point information and the auxiliary memory information associated with the knowledge point if it is determined that the number of prompts is greater than a threshold value, wherein the auxiliary memory information is a formula containing homophones, a static picture, a dynamic picture or a video.

[0036] Furthermore, in some optional embodiments of the present invention, the display module 23 includes: An acquisition unit, configured to acquire elements in the preset knowledge point information, wherein the elements at least include time, person, and place; The expansion unit is used to expand the corresponding elements according to the preset rules according to the attributes of the elements, and obtain the corresponding element libraries respectively, wherein when the element is time, the expanded element library at least includes the denoised time body and the homophonic words derived from the denoised time body; when the element is a person, the expanded element library at least includes various names of the person and the homophonic words derived from the various names; when the element is a place, the expanded element library at least includes several names of the place and the homophonic words derived from the several names; The input unit is used to randomly extract a word from each element library, input the extracted word into the trained neural network model, and output a formula. The neural network model adopts one or a combination of RNN network model, LSTM network model, GRU network model, and Transformer network model. If the elements in the preset knowledge point information include characters, when training the neural network model, the background information of the character is trained as part of the text corpus.

[0037] Further, in some optional embodiments of the present invention, the setting module 21 includes: A first determination unit, used to determine whether there is a cursor in the display screen of the education platform; A first setting unit is used to set a knowledge point prompt request key according to the position of the cursor in the display screen of the education platform when it is determined that there is a cursor in the display screen of the education platform; The second setting unit is used to set a knowledge point prompt request key at a preset position in the display screen of the education platform when it is determined that there is no cursor in the display screen of the education platform, and the key changes with the answering time.

[0038] Further, in some optional embodiments of the present invention, the first setting unit includes: A judging subunit, used for obtaining the position of the cursor in the display screen of the education platform in real time, and judging whether the cursor is in a stationary state; The first setting subunit is used for setting a knowledge point prompt request key according to the current position of the cursor in the display screen of the education platform and the position of the exercise if it is determined that the cursor is in a stationary state, so that the knowledge point prompt request key is close to the cursor and does not block the exercise; an inference subunit, configured to obtain a moving track of the cursor if it is determined that the cursor is not in a stationary state, and infer a next moving area according to the moving track; The second setting subunit is used to set the knowledge point prompt request key according to the next moving area and the position of the exercise.

[0039] Embodiment 3 Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor, wherein the processor 10 implements the above-mentioned digital learning assistance method when executing the computer program 30.

[0040] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0041] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as a hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of an electronic device, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 can also include both an internal storage unit of the electronic device and an external storage device. The memory 20 can not only be used to store application software and various types of data of the electronic device, but also can be used to temporarily store data that has been output or is to be output.

[0042] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0043] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the digital learning assistance method as described above is implemented.

[0044] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0045] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0046] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0047] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0048] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.< / end> < / start> < / end> < / start> < / unk> < / end> < / start>

Claims

1. A digital learning assistance method, characterized in that: Applied in a scenario with an education platform, the method includes: A knowledge point prompt request button is set in the exercises of the education platform, and preset knowledge point information associated with the knowledge point of the current question is obtained by clicking the knowledge point prompt request button; Obtaining the number of prompts for the preset knowledge point information, and determining whether the number of prompts is greater than a threshold; If it is determined that the number of prompts is greater than a threshold, the preset knowledge point information and auxiliary memory information associated with the knowledge point are displayed, wherein the auxiliary memory information is a formula containing homophones, a static picture, a dynamic picture or a video.

2. The digital learning assistance method according to claim 1, characterized in that: The step of generating auxiliary memory information associated with the knowledge point includes: Obtaining elements in the preset knowledge point information, wherein the elements at least include time, person, and place; According to the attributes of the elements, the corresponding elements are expanded according to preset rules to obtain corresponding element libraries; A word is randomly extracted from each element library, and the extracted word is input into the trained neural network model to output the formula.

3. The digital learning assistance method according to claim 2, characterized in that: In the step of expanding the corresponding elements according to preset rules based on the attributes of the elements to obtain corresponding element libraries, when the element is time, the expanded element library at least includes the denoised time body and the homophonic words derived from the denoised time body; when the element is a person, the expanded element library at least includes various titles of the person and the homophonic words derived from the various titles; when the element is a place, the expanded element library at least includes several names of the place and the homophonic words derived from the several names.

4. The digital learning assistance method according to claim 3, characterized in that: The step of randomly extracting a word from each element library and inputting the extracted word into the trained neural network model before outputting the formula, if the elements in the preset knowledge point information include characters, then when training the neural network model, the background information of the characters is trained as part of the text corpus.

5. The digital learning assistance method according to claim 4, characterized in that: The neural network model adopts one or a combination of RNN network model, LSTM network model, GRU network model and Transformer network model.

6. The digital learning assistance method according to claim 5, characterized in that: The step of setting a knowledge point prompt request key in the exercises of the education platform includes: Determine whether there is a cursor in the display screen of the education platform; When it is determined that there is a cursor in the display screen of the education platform, a knowledge point prompt request key is set according to the position of the cursor in the display screen of the education platform; When it is determined that there is no cursor in the display screen of the education platform, a knowledge point prompt request key is set at a preset position in the display screen of the education platform, and changes with the answering time.

7. The digital learning assistance method according to claim 6, characterized in that: The step of setting a knowledge point prompt request key according to the position of the cursor in the display screen of the education platform includes: Acquire the position of the cursor in the display screen of the education platform in real time to determine whether the cursor is in a stationary state; If it is determined that the cursor is in a stationary state, a knowledge point prompt request key is set according to the current position of the cursor in the display screen of the education platform and the position of the exercise, so that the knowledge point prompt request key is close to the cursor and does not block the exercise; If it is determined that the cursor is not in a stationary state, obtaining a moving track of the cursor, and inferring a next moving area according to the moving track; Set the knowledge point prompt request key according to the next moving area and the position of the exercise.

8. A digital learning assistance system, characterized in that: For implementing the digital learning assistance method according to any one of claims 1 to 7, the system comprises: A setting module, used to set a knowledge point prompt request key in the exercises of the education platform, and obtain preset knowledge point information associated with the knowledge point of the current question by clicking the knowledge point prompt request key; A judgment module, used to obtain the number of prompts of the preset knowledge point information, and judge whether the number of prompts is greater than a threshold; The display module is used to display the preset knowledge point information and the auxiliary memory information associated with the knowledge point if it is determined that the number of prompts is greater than a threshold value, wherein the auxiliary memory information is a formula containing homophones, a static picture, a dynamic picture or a video.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the digital learning assistance method as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the digital learning assistance method according to any one of claims 1 to 7 is implemented.

Images