An intelligent learning and translation system and method for English words

Abstract

The present invention discloses an intelligent learning and translation system and method for English words, which relates to the field of data processing. The system includes: a historical learning data indexing module for obtaining target words, collecting target context information, and indexing historical learning data; a historical context information classification module for classifying historical context information to obtain a set of historical learning scores; a historical learning score set optimization and dimensionality reduction module for optimizing dimensionality reduction and arranging them in chronological order; a learning trend analysis module for performing learning trend analysis based on the historical learning score sequence; a correction module for matching historical contexts and correcting the learning rate and degradation rate; and an auxiliary translation hint module for providing auxiliary translation hints. It solves the technical problem of insufficient pertinence and accuracy of auxiliary translation in existing English word learning and translation, and achieves the technical effect of improving the pertinence and accuracy of auxiliary translation.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular, to an intelligent learning and translation system and method for English words. Background Art

[0002] Today, with the increasing globalization, English, as an international common language, its learning and application have become particularly important. Traditional English learning methods often focus on vocabulary memorization and grammar learning. However, in actual language use, the understanding and application of words highly depend on the specific context. Therefore, how to intelligently learn and translate English words according to the context has become the key to improving the efficiency and quality of English learning. Most existing English word learning systems use static vocabulary lists or simple example sentences to assist learning. This method often provides unified learning materials or basic vocabulary substitutions during translation, lacking the ability to provide intelligent translation prompts according to the actual level and context of learners, resulting in insufficient auxiliary translation ability.

[0003] In the current related technologies, there are technical problems of insufficient pertinence and accuracy in the auxiliary translation of English word learning and translation. Summary of the Invention

[0004] This application provides an intelligent learning and translation system and method for English words. By obtaining the target word and its context information that the user is currently learning, indexing the historical learning data of the user for this target word, classifying the historical context information, extracting the semantic information and learning data in different contexts, processing the learning score data through an optimized dimensionality reduction technique, reducing the dimensions and arranging them in time sequence, analyzing the learning trend based on the historical learning score sequence to obtain the learning rate and degradation rate, correcting the learning rate and degradation rate according to the deviation between the target context and the matched historical context, and making an auxiliary translation decision according to the corrected learning rate and degradation rate, providing a personalized translation prompt scheme and other technical means, it realizes personalized and intelligent English word learning and translation prompts, and achieves the technical effect of improving the pertinence and accuracy of auxiliary translation.

[0005] This application provides an intelligent learning and translation system for English words, including:

[0006] Historical learning data indexing module, which is used to obtain the target word that the user is currently learning, collect the target context information where the target word is currently located, and index the historical learning data of the target word by the user within the historical time according to the target word; historical context information classification module, which is used to classify the historical context information in the historical learning data to obtain multiple classified historical contexts, extract the historical semantic information sets and multiple historical learning data sets under the multiple classified historical contexts, and process to obtain multiple historical learning score sets; historical learning score set optimization and dimensionality reduction module, which is used to optimize and reduce the dimensionality of the multiple historical learning score sets respectively to obtain multiple reduced-dimensional historical learning score sets, and arrange them in time sequence to obtain multiple historical learning score sequences; learning trend analysis module, which is used to perform learning trend analysis according to the multiple historical learning score sequences to obtain the learning rate and degradation rate; correction module, which is used to match the target context information with the multiple classified historical contexts to obtain the matching historical context, and correct the learning rate and degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain the corrected learning rate and corrected degradation rate; auxiliary translation hint module, which is used to make an auxiliary translation decision according to the corrected learning rate and corrected degradation rate to obtain an auxiliary translation hint scheme and perform auxiliary translation hint.

[0007] In a possible implementation manner, to obtain the target word that the user is currently learning, collect the target context information where the target word is currently located, and index the historical learning data of the target word by the user within the historical time according to the target word, the following processing is performed:

[0008] Obtain the target word that the user is currently learning, collect the upper context content and lower context content of the target word as the target context information; index in the historical learning record of the user according to the target word to obtain the historical learning data of the target word.

[0009] In a possible implementation manner, to classify the historical context information in the historical learning data to obtain multiple classified historical contexts, extract the historical semantic information sets and multiple historical learning data sets under the multiple classified historical contexts, and process to obtain multiple historical learning score sets, the following processing is performed:

[0010] Obtain multiple historical context information within the historical learning data, perform classification processing to obtain multiple classified historical contexts; extract the standard meanings of target words in the historical learning data under the multiple classified historical contexts to obtain a historical meaning information set, and extract multiple historical translation semantic information sets and multiple historical translation submission time sets submitted by the user under the multiple classified historical contexts; classify to obtain multiple historical basic learning score sets according to the deviation range between the multiple historical translation semantic information sets and the historical meaning information set; perform correction calculation on the multiple historical basic learning score sets according to the ratio of a preset submission time threshold and the multiple historical translation submission time sets to obtain multiple historical learning score sets.

[0011] In a possible implementation manner, respectively perform optimization and dimensionality reduction on the multiple historical learning score sets to obtain multiple dimensionality-reduced historical learning score sets, and arrange them in time sequence to obtain multiple historical learning score sequences, and perform the following processing:

[0012] In the first historical learning score set within the multiple historical learning score sets, select to obtain a first reference learning score; distribute distribution probabilities according to the difference between other historical learning scores and the first reference learning score within the first historical learning score set to obtain a first basic probability distribution, where the size of the difference is negatively correlated with the size of the distribution probability; perform optimization and dimensionality reduction on the first historical learning score set according to the first basic probability distribution to obtain a first dimensionality-reduced learning score set; sort according to the timestamp information of multiple historical learning scores within the first dimensionality-reduced historical learning score set to obtain a first historical learning score sequence; perform optimization and dimensionality reduction and time sequence arrangement on other multiple historical learning score sets to obtain multiple historical learning score sequences.

[0013] In a possible implementation manner, perform optimization and dimensionality reduction on the first historical learning score set according to the first basic probability distribution to obtain a first dimensionality-reduced learning score set, and perform the following processing:

[0014] Randomly extract a preset number of dimensionality-reduced historical learning scores within the first historical learning score set to obtain a first dimensionality-reduced historical learning score set; distribute distribution probabilities according to the difference between the historical learning scores within the first dimensionality-reduced historical learning score set and the first reference learning score to obtain a first dimensionality-reduced probability distribution; calculate the similarity between the first dimensionality-reduced probability distribution and the first basic probability distribution as the first dimensionality-reduced fitness; randomly extract a preset number of dimensionality-reduced historical learning scores within the first historical learning score set again to obtain a second dimensionality-reduced historical learning score set, and process to obtain a second dimensionality-reduced fitness; continue to perform optimization and dimensionality reduction until convergence, and output the dimensionality-reduced historical learning score set with the largest dimensionality-reduced fitness as the first dimensionality-reduced learning score set.

[0015] In a possible implementation, learning trend analysis is performed based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate, and the following processing is executed:

[0016] According to the sample learning data of multiple users, a set of sample learning score sequences is collected, and a set of sample learning rates and a set of sample degradation rates are obtained based on the learning score change identifiers within each sample learning score sequence; using the set of sample learning score sequences as classification inputs and the set of sample learning rates and the set of sample degradation rates as classification outputs, a learning trend analyzer is constructed; based on the learning trend analyzer, learning trend classification is performed on the multiple historical learning score sequences to obtain multiple context learning rates and multiple context degradation rates; the similarity between the target context information and the multiple classified historical contexts is analyzed, and based on the magnitudes of multiple context similarities, weighted calculations are performed on the multiple context learning rates and the multiple context degradation rates to obtain a learning rate and a degradation rate.

[0017] In a possible implementation, the target context information is matched with the multiple classified historical contexts to obtain a matching historical context, and based on the deviation between the target context information and the standard matching context information of the matching historical context, the learning rate and the degradation rate are corrected to obtain a corrected learning rate and a corrected degradation rate, and the following processing is executed:

[0018] Select the classified historical context with the highest similarity as the matching historical context, and obtain the standard matching context information of the matching historical context; based on the deviation between the target context information and the standard matching context information of the matching historical context, a learning correction coefficient is set; using the learning correction coefficient, correction calculations are performed on the learning rate and the degradation rate to obtain a corrected learning rate and a corrected degradation rate.

[0019] In a possible implementation, based on the corrected learning rate and the corrected degradation rate, auxiliary translation decision-making is performed to obtain an auxiliary translation hint scheme for auxiliary translation hint, and the following processing is executed:

[0020] A set of sample corrected learning rates and a set of sample corrected degradation rates are collected, and based on the magnitudes of each sample corrected learning rate and sample corrected degradation rate, a sample auxiliary translation hint scheme is set to obtain a set of sample auxiliary translation hint schemes, where each sample auxiliary translation hint scheme includes a hint ratio, and the magnitudes of the sample corrected learning rate and the sample corrected degradation rate are negatively correlated with the magnitude of the hint ratio; using the set of sample corrected learning rates and the set of sample corrected degradation rates as decision inputs and the set of sample auxiliary translation hint schemes as decision outputs, an auxiliary translation decision-making device is constructed; using the auxiliary translation decision-making device, auxiliary translation decision-making is performed on the corrected learning rate and the corrected degradation rate to obtain an auxiliary translation hint scheme.

[0021] The present application also provides an intelligent learning and translation method for English words, including:

[0022] Obtain the target word that the user is currently learning, and collect the target context information where the target word is currently located. According to the target word, index the historical learning data of the target word by the user within the historical time; classify the historical context information in the historical learning data to obtain multiple classified historical contexts, extract the historical semantic information sets and multiple historical learning data sets under the multiple classified historical contexts, and process to obtain multiple historical learning score sets; optimize and reduce the dimension of each of the multiple historical learning score sets respectively to obtain multiple reduced-dimension historical learning score sets, and arrange them in time sequence to obtain multiple historical learning score sequences; perform learning trend analysis based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate; match the target context information with the multiple classified historical contexts to obtain a matching historical context, and correct the learning rate and the degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate; make an auxiliary translation decision according to the corrected learning rate and the corrected degradation rate to obtain an auxiliary translation prompt scheme and perform auxiliary translation prompting.

[0023] It is intended to propose an intelligent learning and translation system and method for English words through the present application. The historical learning data indexing module obtains the target word that the user is currently learning, and collects the target context information where the target word is currently located. According to the target word, it indexes the historical learning data of the target word by the user within the historical time. The historical context information classification module classifies the historical context information in the historical learning data to obtain multiple classified historical contexts, extracts the historical semantic information sets and multiple historical learning data sets under the multiple classified historical contexts, and processes to obtain multiple historical learning score sets. The historical learning score set optimization and dimension reduction module optimizes and reduces the dimension of each of the multiple historical learning score sets respectively to obtain multiple reduced-dimension historical learning score sets, and arranges them in time sequence to obtain multiple historical learning score sequences. The learning trend analysis module performs learning trend analysis based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate. The correction module matches the target context information with the multiple classified historical contexts to obtain a matching historical context, and corrects the learning rate and the degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate. The auxiliary translation prompt module makes an auxiliary translation decision according to the corrected learning rate and the corrected degradation rate to obtain an auxiliary translation prompt scheme and perform auxiliary translation prompting, achieving the technical effect of improving the pertinence and accuracy of auxiliary translation. Brief Description of the Drawings

[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly introduced below. In this application, flowcharts are used to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations described above or below do not necessarily need to be performed precisely in order. On the contrary, as needed, various steps can be performed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0025] Figure 1 It is a schematic structural diagram of an intelligent learning and translation system for English words provided by an embodiment of the present application.

[0026] Figure 2 It is a schematic flowchart of an intelligent learning and translation method for English words provided by an embodiment of the present application.

[0027] Explanation of reference numerals: Historical learning data indexing module 10, historical context information classification module 20, historical learning score set optimization and dimensionality reduction module 30, learning trend analysis module 40, correction module 50, auxiliary translation hint module 60. Detailed implementation manners

[0028] The above description is only an overview of the technical solutions of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0030] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0031] An embodiment of this application provides an intelligent English word learning and translation system, as Figure 1 shown, the system includes:

[0032] A historical learning data indexing module 10, which is used to obtain the target word that the user is currently learning, and collect the target context information where the target word is currently located, and index the historical learning data of the target word by the user within the historical time according to the target word. Specifically, the user inputs or selects a target word through an interface (such as an input box, clicking on a word list, etc.), that is, the target word is the English word that the user is currently learning or querying, and is the starting point for querying and indexing. Detect the environment where the user is currently located or require the user to manually input the context information where the target word is located. The target context information is the specific context where the target word is located, which can be a sentence, paragraph, article or any text segment containing the target word, and is used to understand the specific meaning and usage of the target word. Store the collected target context information as metadata associated with the target word.

[0033] Initiate a query in the user's personal learning database according to the target word. The personal learning database contains all the learning records of the user on the target word (and other words) before. The query request can include strategies such as exact matching, fuzzy matching (such as considering different forms or spelling mistakes of the word) of the word. After retrieving all the historical learning records related to the target word in the personal learning database, index these records. The indexing can be based on multiple dimensions, such as the user's historical translation results (such as correct / wrong, score, etc.), the time taken for translation, historical context (such as reading, listening, writing practice, etc.), and quickly extract and organize the historical learning data most relevant or useful to the target word through indexing.

[0034] In a possible implementation, the target word that the user is currently learning is obtained, and the target context information in which the target word is currently located is collected. According to the target word, the historical learning data of the target word by the user in the historical time is indexed, including: obtaining the target word that the user is currently learning, collecting the upper context content and the lower context content of the target word as the target context information; indexing in the historical learning records of the user according to the target word to obtain the historical learning data of the target word.

[0035] Specifically, the user selects or starts learning a specific word on the learning platform or application program, and the system captures this selection through interface interaction and records the word as the target word for current learning. Analyze the context in which the target word appears in the user's current learning environment, extract the text content before the target word as the upper context (used to understand the prepositional information and meaning of the target word in a sentence or paragraph), extract the text content after the target word as the lower context (used to understand the subsequent information and context background of the target word), and combine these two parts of content to form the complete target context information of the target word. Use the target word as a keyword to search in the user's historical learning database and retrieve all historical learning records (records of all learning activities generated by the user on the learning platform in the past) containing the target word, including information such as learning time, learning times, learning effectiveness (such as test scores), and usage scenarios. This implementation method helps the system to more accurately understand the user's current learning needs by collecting the context information of the target word, achieving the technical effect of improving the accuracy of subsequent context matching.

[0036] The historical context information classification module 20 is used to classify the historical context information in the historical learning data to obtain multiple classified historical contexts, extract the historical semantic information set and multiple historical learning data sets under the multiple classified historical contexts, and process to obtain multiple historical learning score sets. Specifically, the context information in each record is extracted from the historical learning data, and these context information are sentences, paragraphs or article fragments containing the target word. Preprocess the extracted context information, including removing irrelevant characters, standardizing punctuation marks, lemmatization (such as reducing different tenses and voices of words to the basic form), etc., and apply natural language processing (NLP) techniques, such as text similarity algorithms (such as cosine similarity, Jaccard similarity, etc.), to evaluate the similarity between different context information. According to the evaluation results of the context similarity, the historical context information is classified into multiple classified historical contexts. Among them, the classification standard can be hard clustering based on a similarity threshold or soft clustering based on a probability distribution. Each classified historical context represents a group of context information that is similar in content, theme or emotional color.

[0037] For each classification historical context, with the help of dictionary resources or context-based word sense disambiguation techniques, extract all the word sense information in which the target word appears, and organize the word sense information in each classification historical context into a historical word sense information set. In addition to the word sense information, extract relevant historical learning data from each classification historical context, such as translation results, translation time, etc., and organize these data into multiple historical learning data sets, each set corresponding to a classification historical context. Based on the historical learning data set in each classification historical context, calculate the learning score. The learning score is a quantitative indicator to measure the user's learning and translation effectiveness of the target word in a specific context, and can be calculated based on multiple factors, such as translation accuracy rate, translation time, etc. Organize the calculated learning scores into multiple historical learning score sets, each set representing the learning and translation effectiveness in a classification historical context.

[0038] In a possible implementation manner, classify the historical context information in the historical learning data to obtain multiple classification historical contexts, extract the historical word sense information set and multiple historical learning data sets under the multiple classification historical contexts, and process to obtain multiple historical learning score sets, including: obtaining multiple historical context information in the historical learning data, performing classification processing to obtain multiple classification historical contexts; extracting the standard word senses of the target word in the historical learning data under the multiple classification historical contexts to obtain a historical word sense information set, and extracting multiple historical translation semantic information sets and multiple historical translation submission time sets submitted by the user under the multiple classification historical contexts; classifying to obtain multiple historical basic learning score sets according to the deviation range between the multiple historical translation semantic information sets and the historical word sense information set; performing correction calculation on the multiple historical basic learning score sets according to the ratio of a preset submission time threshold and the multiple historical translation submission time sets to obtain multiple historical learning score sets.

[0039] Specifically, parse the context in each piece of historical learning data, identify the key elements in the context (such as the theme, scenario, conversation object, etc.), and use clustering algorithms (such as K-means, hierarchical clustering, etc.) to classify the historical context information into different groups according to the similarity of the context. Each group represents a classified historical context. For each classified historical context, determine the standard meaning of the target word in that context, that is, the correct or expected meaning that the target word is generally considered in a specific context (the standard meaning may be multiple, depending on the complexity of the context). Collect the standard meanings under each classified historical context to form a historical meaning information set. Extract the semantic information of each translation attempt from the user's historical translation records (the meaning of the word or phrase given during the translation attempt), and record the submission time of each translation attempt. Organize the translation semantics and historical translation submission times under the same classified historical context into sets respectively. Calculate the deviation degree between the semantic information of each translation attempt and the standard meaning (a similarity algorithm such as cosine similarity can be used). According to the deviation degree, assign a basic learning score to each translation attempt (the smaller the deviation, the higher the score). Organize the basic learning scores under the same classified historical context into a set. Preset a submission time threshold, indicating how long it is considered acceptable to submit the translation result. Calculate the ratio of the preset submission time threshold to the submission time of each translation attempt, and correct the basic learning score according to the time ratio (for example, the smaller the ratio, the longer the translation time, and the lower the corrected score). Update the corrected learning score to the corresponding historical learning score set. This implementation method compares the standard meaning with the historical translation semantics, reflects the user's learning and translation effect of the target word, corrects the learning and translation effect through the translation submission time, and more accurately reflects the user's mastery of the target word, achieving the technical effect of accurately quantifying and evaluating the user's mastery of the target word.

[0040] Historical learning score set optimization and dimensionality reduction module 30, where the historical learning score set optimization and dimensionality reduction module 30 is used to optimize and reduce the dimensions of the multiple historical learning score sets respectively, obtain multiple dimensionality-reduced historical learning score sets, and arrange them in time series to obtain multiple historical learning score sequences. Specifically, according to the characteristics of the historical learning score sets (such as the size of the data volume, score distribution, etc.), apply specific optimization and dimensionality reduction methods, for example, principal component analysis (PCA), linear discriminant analysis (LDA), t-SNE (t-distributed Stochastic Neighbor Embedding), etc. Through dimensionality reduction processing, the original high-dimensional historical learning score data is converted into a low-dimensional representation, while trying to retain the internal structure and key features of the data. The dimensionality-reduced data forms multiple dimensionality-reduced historical learning score sets. The dimensions of the historical learning scores in each set are reduced, but the information density increases. Arrange the historical learning scores in each dimensionality-reduced historical learning score set in chronological order (mark the timestamps of the data in the set and sort according to the timestamps). The data arranged in time series forms multiple historical learning score sequences, and each sequence reflects the changing trend of the user's learning and translation effectiveness of the target word in different time periods.

[0041] In a possible implementation, optimizing and reducing the dimensions of the multiple historical learning score sets respectively, obtaining multiple dimensionality-reduced historical learning score sets, and arranging them in time series to obtain multiple historical learning score sequences includes: selecting and obtaining a first reference learning score in the first historical learning score set within the multiple historical learning score sets; distributing distribution probabilities according to the differences between other historical learning scores and the first reference learning score in the first historical learning score set to obtain a first basic probability distribution, where the size of the difference is negatively correlated with the size of the distribution probability; optimizing and reducing the dimensions of the first historical learning score set according to the first basic probability distribution to obtain a first dimensionality-reduced learning score set; sorting according to the timestamp information of the multiple historical learning scores in the first dimensionality-reduced learning score set to obtain a first historical learning score sequence; optimizing and reducing the dimensions and arranging in time series for the other multiple historical learning score sets to obtain multiple historical learning score sequences.

[0042] Specifically, the first historical learning score set is any one of the multiple historical learning score sets. From the first historical learning score set, a representative score is selected as the first benchmark learning score. For example, the first benchmark learning score can be the average value, median value of the first historical learning score set, or a score calculated based on a certain algorithm (such as the cluster center). Each historical learning score in the first historical learning score set is traversed, and the difference between it and the first benchmark learning score is calculated. According to the magnitude of the difference, a distribution probability is assigned. The assignment method can be specifically implemented through Gaussian functions, exponential functions, etc. Among them, the smaller the difference (that is, the closer the historical learning score is to the benchmark learning score), the higher the assigned distribution probability; the larger the difference, the lower the assigned distribution probability. According to the assigned probability distribution, dimensionality reduction processing is performed on the first historical learning score set, including retaining historical learning scores with high distribution probabilities, removing or merging historical learning scores with low distribution probabilities, or recalculating historical learning scores in a way weighted by distribution probabilities, etc. The timestamp information of each historical learning score in the first dimensionality-reduced learning score set is obtained, and the historical learning scores are sorted in the order of timestamps to form the first historical learning score sequence. Repeat the above steps to perform the same processing on other multiple historical learning score sets, and each set obtains an optimized and dimensionality-reduced historical learning score sequence. This implementation method retains historical learning scores with high similarity to the benchmark point by assigning distribution probabilities, removes or reduces the weights of historical learning scores with low distribution probabilities, reduces the interference of noise data on the analysis results, and achieves the technical effect of improving the accuracy of dimensionality reduction.

[0043] In a possible implementation manner, according to the first basic probability distribution, the first historical learning score set is optimized and dimensionally reduced to obtain a first dimensionally-reduced learning score set, including: randomly extracting a preset number of historical learning scores for dimensionality reduction within the first historical learning score set to obtain a first dimensionally-reduced historical learning score set; assigning distribution probabilities according to the differences between the historical learning scores in the first dimensionally-reduced historical learning score set and the first benchmark learning score to obtain a first dimensionally-reduced probability distribution; calculating the similarity between the first dimensionally-reduced probability distribution and the first basic probability distribution as the first dimensionally-reduced fitness; randomly extracting a preset number of historical learning scores for dimensionality reduction within the first historical learning score set again to obtain a second dimensionally-reduced historical learning score set, and processing to obtain a second dimensionally-reduced fitness; continue to perform optimized dimensionality reduction until convergence, and output the dimensionally-reduced historical learning score set with the largest dimensionally-reduced fitness as the first dimensionally-reduced learning score set.

[0044] Specifically, according to actual requirements, a preset number of historical learning scores are randomly selected from the first historical learning score set. The preset number is the number of historical learning scores that are expected to be retained after dimensionality reduction. The randomly selected historical learning scores form the first dimensionality-reduced historical learning score set. Calculate the difference between each historical learning score in the first dimensionality-reduced historical learning score set and the first reference learning score. According to the size of the difference, assign a distribution probability to each historical learning score, ensuring that the smaller the difference, the higher the assigned distribution probability; the larger the difference, the lower the assigned distribution probability. Use a similarity measurement method (such as KL divergence, JS divergence, correlation coefficient, etc.) to calculate the similarity between the first dimensionality-reduced probability distribution and the first basic probability distribution. The similarity value reflects the degree of closeness of the dimensionality-reduced historical learning score set to the original historical learning score set in terms of probability distribution. Take the calculated similarity value as the first dimensionality-reduction fitness. The higher the dimensionality-reduction fitness, the better the dimensionality-reduced historical learning score set performs in retaining the characteristics of the original data. Randomly select the preset dimensionality-reduction number of historical learning scores again within the first historical learning score set to obtain the second dimensionality-reduced historical learning score set, and perform the same processing on the second dimensionality-reduced historical learning score set, including assigning distribution probabilities, calculating the similarity with the first basic probability distribution, and obtaining the second dimensionality-reduction fitness. Repeat this process multiple times. During the multiple random selections and optimizations, record the dimensionality-reduction fitness obtained each time. When the dimensionality-reduction fitness changes very little or no longer changes significantly for several consecutive times, it is considered that the algorithm has converged, and select the result with the largest dimensionality-reduction fitness as the final first dimensionality-reduced learning score set. This implementation method evaluates the dimensionality-reduction effect by calculating the similarity between the dimensionality-reduced probability distribution and the original probability distribution, ensuring that the dimensionality-reduced historical learning score set performs as well as possible in retaining the characteristics of the original data, achieving the technical effect of improving the accuracy of dimensionality reduction.

[0045] Learning trend analysis module 40, which is used to perform learning trend analysis based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate. Specifically, data cleaning and formatting are performed on the historical learning score sequences to ensure the accuracy and consistency of the data, handle problems such as missing values and outliers, and convert the historical learning score sequences into a form suitable for trend analysis. According to the characteristics of the historical learning score sequences, a trend analysis method is selected, such as time series analysis (such as ARIMA model, exponential smoothing method, etc.), regression analysis, machine learning models, etc. The selected trend analysis method is applied to perform learning trend analysis on the multiple historical learning score sequences, that is, a systematic analysis of the changes in the learning effectiveness of users over a period of time, aiming to discover the change laws, influencing factors, and potential problems of learning effectiveness. During the analysis process, factors such as the change trend, periodicity, and volatility of the historical learning scores are concerned, as well as how these factors change over time. The learning rate and degradation rate are calculated. Among them, the learning rate represents the learning degree of the user for the target words, is an indicator of the learning speed or efficiency, and refers to the degree of mastery of the target words per unit time. For example, it can be represented by the ratio of the mean value of the historical learning scores per unit time to the full score; the degradation rate represents the rate of decline of the learning results over time, reflecting the decline of the user's memory or understanding of the target words over a period of time. For example, it can be represented by the reduction amplitude from the highest value of the historical learning scores per unit time to the current latest learning score.

[0046] In a possible implementation manner, performing learning trend analysis based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate includes: collecting a set of sample learning score sequences according to the sample learning data of multiple users, and obtaining a set of sample learning rates and a set of sample degradation rates according to the learning score change identifiers within each sample learning score sequence; using the set of sample learning score sequences as classification inputs, and using the set of sample learning rates and the set of sample degradation rates as classification outputs to construct a learning trend analyzer; based on the learning trend analyzer, performing learning trend classification on the multiple historical learning score sequences to obtain multiple context learning rates and multiple context degradation rates; analyzing the similarity between the target context information and the multiple classified historical contexts, and performing weighted calculation on the multiple context learning rates and the multiple context degradation rates according to the magnitudes of the multiple context similarities to obtain the learning rate and the degradation rate.

[0047] Specifically, a learning score sequence is extracted from the historical learning data of multiple users. The learning score sequence is a series of learning scores arranged in chronological order, reflecting the dynamic changes in users' learning performance. For the sample learning score sequence of each user, by comparing the changes in learning scores at adjacent time points, the learning rate (the speed at which the learning score increases) and the degradation rate (the speed at which the learning score decreases) are calculated. The learning rate refers to the speed of learning score improvement, and the degradation rate refers to the speed of learning score decline. Using machine learning or statistical learning methods, with the sample learning score sequence as the input feature and the sample learning rate and sample degradation rate as the output targets, a model (such as a classifier or a regressor) is trained. This model can predict the learning rate and degradation rate corresponding to a new learning score sequence.

[0048] Using the constructed learning trend analyzer, multiple historical learning score sequences are classified to obtain the learning rate and degradation rate corresponding to each sequence. Since each historical learning score sequence corresponds to a context, multiple context learning rates and multiple context degradation rates are obtained. The context learning rate and context degradation rate reflect the influence of context factors on learning effects. Analyze the similarity between the target context information and multiple classified historical contexts. The context similarity is used to evaluate the applicability of the historical context to the target context. According to the magnitude of the similarity, weighted calculations are performed on multiple context learning rates and context degradation rates to obtain the final learning rate and degradation rate. This implementation method comprehensively reflects the dynamic changes in learning effects by considering the historical learning data of multiple users and their performances in different contexts, achieving the technical effect of improving the accuracy of calculating the learning rate and degradation rate.

[0049] Correction module 50, which is used to match the target context information with the multiple classified historical contexts to obtain a matching historical context, and correct the learning rate and degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context, so as to obtain a corrected learning rate and a corrected degradation rate. Specifically, the target context information is matched with the multiple classified historical contexts, and the similarity between the target context and each classified historical context is calculated. For example, text similarity algorithms (such as cosine similarity, Jaccard similarity, etc.) or semantic similarity calculation based on word embeddings are used, and the classified historical context with the highest similarity is selected as the matching historical context. The standard matching context information is extracted from the matching historical context. The standard matching context information is a set of representative context information sets with a high similarity to the target context. Analyze the differences between the target context information and the standard matching context information, and calculate the deviation. The deviation can include multiple aspects, such as the complexity of the context, the usage of the target word in the context, the emotional color of the context, etc. According to the calculated deviation, the learning rate and degradation rate are corrected. The correction can be a simple linear adjustment (such as adding or subtracting the learning rate or degradation rate according to the size of the deviation), or a non-linear model or machine learning algorithm. Through correction, the learning rate and degradation rate are made more in line with the actual situation of the current target context, improving the accuracy and practicality of the analysis.

[0050] In a possible implementation manner, matching the target context information with the multiple classified historical contexts to obtain a matching historical context, and correcting the learning rate and degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate includes: selecting the classified historical context with the largest similarity as the matching historical context, and obtaining the standard matching context information of the matching historical context; setting a learning correction coefficient according to the deviation between the target context information and the standard matching context information of the matching historical context; using the learning correction coefficient to perform a correction calculation on the learning rate and degradation rate to obtain a corrected learning rate and a corrected degradation rate.

[0051] Specifically, calculate the similarity between the target context information and each classified historical context. Among all the calculated similarities, select the classified historical context with the highest similarity as the matching historical context. According to the matching historical context, query its corresponding standard matching context information, that is, a set of information representing the core features of the classified historical context, including keywords, topic tags, sentiment tendency, etc. Compare the target context information with the standard matching context information of the matching historical context, and calculate the deviation between the two. The deviation can be the sum of the difference degrees based on specific attributes or a certain comprehensive score. According to the calculated deviation, set the learning correction coefficient, which is used to adjust the learning rate and the degradation rate to cope with the differences between the introduction of new context information and the old context information. Apply the learning correction coefficient to the learning rate and the degradation rate respectively. The specific formula for the correction calculation can be designed according to actual needs. Through the correction calculation, the corrected learning rate and degradation rate are obtained. This implementation method accurately identifies the differences between the target context and the known historical context by matching the historical context and calculating the deviation, thereby adjusting the learning rate and the degradation rate in a targeted manner, achieving the technical effects of improving the pertinence and accuracy of the correction.

[0052] An auxiliary translation hint module 60, which is used to make an auxiliary translation decision according to the corrected learning rate and the corrected degradation rate, obtain an auxiliary translation hint scheme, and perform auxiliary translation hint. Specifically, the corrected learning rate and the corrected degradation rate reflect the user's mastery of the target word in the current target context, analyze the user's translation needs, including target context information, translation purposes (such as reading comprehension, writing expression, oral communication, etc.), the user's language level, etc., combine the corrected learning rate and the corrected degradation rate, evaluate the translation difficulties and challenges encountered by the user at the current stage, and make an auxiliary translation decision accordingly. The decision can include selecting appropriate translation methods (such as literal translation, free translation, phrase replacement, etc.), providing example sentences or context support, recommending learning resources, etc. Transform the auxiliary translation decision into a specific hint scheme, including word meaning selection, grammar hint, translation suggestion, example sentence display, context simulation, learning resource link, etc. Present the generated auxiliary translation hint scheme to the user in an appropriate way, such as displaying on the learning interface, prompting through a pop-up window, sending an email or a text message, etc., to assist the user in completing the translation task. The hint content can point out the user's translation difficulties and provide specific solutions or suggestions. In addition, during the hint process, the user's feedback can be collected. Through the user's feedback, evaluate the effect of the auxiliary translation hint, including the user's acceptance level, the improvement of translation accuracy, etc. According to the evaluation results, adjust and optimize the auxiliary translation hint scheme to better meet the user's needs. The embodiment of the present application adopts technical means such as obtaining the target word currently learned by the user and its context information, indexing the user's historical learning data of the target word, classifying the historical context information, extracting word meaning information and learning data in different contexts, processing the learning score data through an optimized dimensionality reduction technology, reducing the dimension and arranging it in time sequence, analyzing the learning trend according to the historical learning score sequence, obtaining the learning rate and the degradation rate, correcting the learning rate and the degradation rate according to the deviation between the target context and the matched historical context, and making an auxiliary translation decision according to the corrected learning rate and the corrected degradation rate, providing a personalized translation hint scheme, etc., to achieve personalized and intelligent English word learning and translation hint, and achieve the technical effect of improving the pertinence and accuracy of auxiliary translation.

[0053] In a possible implementation, based on the corrected learning rate and the corrected degradation rate, an auxiliary translation decision is made to obtain an auxiliary translation hint scheme for auxiliary translation hint, including: collecting a set of sample corrected learning rates and a set of sample corrected degradation rates, and setting an auxiliary translation hint scheme for each sample according to the magnitudes of the sample corrected learning rate and the sample corrected degradation rate, to obtain a set of sample auxiliary translation hint schemes, where each sample auxiliary translation hint scheme includes a hint ratio, and the magnitudes of the sample corrected learning rate and the sample corrected degradation rate are negatively correlated with the magnitude of the hint ratio; using the set of sample corrected learning rates and the set of sample corrected degradation rates as decision inputs, and using the set of sample auxiliary translation hint schemes as decision outputs, an auxiliary translation decision maker is constructed; using the auxiliary translation decision maker, an auxiliary translation decision is made on the corrected learning rate and the corrected degradation rate to obtain an auxiliary translation hint scheme.

[0054] Specifically, data on the corrected learning rate and the corrected degradation rate are collected from the historical data of multiple translation tasks, translators, or translation systems, and organized into a set of corrected learning rates containing all samples and a set of corrected degradation rates containing all samples. A hint ratio is defined for each sample, which determines how much auxiliary information (such as translation suggestions, vocabulary hints, etc.) is provided during translation. According to the magnitudes of the sample corrected learning rate and the sample corrected degradation rate, an association rule is formulated, that is, the higher the learning rate and the lower the degradation rate, the lower the hint ratio; conversely, the lower the learning rate and the higher the degradation rate, the higher the hint ratio. According to the association rule, an auxiliary translation hint scheme is generated for each sample, and these auxiliary translation hint schemes are combined into a set of sample auxiliary translation hint schemes. According to the characteristics of the set of sample corrected learning rates and the set of sample corrected degradation rates, a machine learning or deep learning algorithm (such as a decision tree, neural network, etc.) is selected, and the set of sample corrected learning rates and the set of sample corrected degradation rates are used as inputs, and the set of sample auxiliary translation hint schemes are used as outputs to train the auxiliary translation decision maker. The new corrected learning rate and corrected degradation rate are passed as input data to the trained auxiliary translation decision maker, and the auxiliary translation decision maker outputs the corresponding auxiliary translation hint scheme according to the input data. During translation, corresponding auxiliary information is provided to the user according to the obtained auxiliary translation hint scheme to improve translation efficiency and accuracy. This implementation achieves the technical effect of improving the efficiency and accuracy of obtaining the auxiliary translation hint scheme by constructing an auxiliary translation decision maker.

[0055] In the above text, with reference to Figure 1 a smart learning and translation system for English words according to an embodiment of the present invention is described in detail. Next, with reference to Figure 2 a smart learning and translation method for English words according to an embodiment of the present invention will be described.

[0056] An intelligent learning and translation method for English words according to an embodiment of the present invention is used to solve the technical problems of insufficient pertinence and accuracy of auxiliary translation existing in the existing English word learning and translation, and achieve the technical effect of improving the pertinence and accuracy of auxiliary translation. An intelligent learning and translation method for English words includes:

[0057] Obtain the target word that the user is currently learning, and collect the target context information where the target word is currently located. According to the target word, index the historical learning data of the target word within the user's historical time; classify the historical context information in the historical learning data to obtain multiple classified historical contexts, extract the historical semantic information sets and multiple historical learning data sets under the multiple classified historical contexts, and process them to obtain multiple historical learning score sets; optimize and reduce the dimension of each of the multiple historical learning score sets respectively to obtain multiple reduced-dimensional historical learning score sets, and arrange them in time sequence to obtain multiple historical learning score sequences; perform learning trend analysis based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate; match the target context information with the multiple classified historical contexts to obtain a matching historical context, and correct the learning rate and the degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate; make an auxiliary translation decision according to the corrected learning rate and the corrected degradation rate to obtain an auxiliary translation prompt scheme and perform auxiliary translation prompts.

[0058] Among them, obtaining the target word that the user is currently learning, and collecting the target context information where the target word is currently located. According to the target word, indexing the historical learning data of the target word within the user's historical time can be further included: obtaining the target word that the user is currently learning, collecting the upper context content and the lower context content of the target word as the target context information; indexing in the user's historical learning record according to the target word to obtain the historical learning data of the target word.

[0059] Among them, classifying the historical context information in the historical learning data to obtain multiple classified historical contexts, extracting the historical semantic information sets and multiple historical learning data sets under the multiple classified historical contexts, and processing to obtain multiple historical learning score sets may further include: obtaining multiple historical context information in the historical learning data, performing classification processing to obtain multiple classified historical contexts; extracting the standard semantic meanings of target words in the historical learning data under the multiple classified historical contexts to obtain a historical semantic information set, and extracting multiple historical translation semantic information sets and multiple historical translation submission time sets submitted by the user under the multiple classified historical contexts; classifying to obtain multiple historical basic learning score sets according to the deviation range between the multiple historical translation semantic information sets and the historical semantic information set; performing correction calculation on the multiple historical basic learning score sets according to the ratio of a preset submission time threshold and the multiple historical translation submission time sets to obtain multiple historical learning score sets.

[0060] Among them, respectively performing optimized dimensionality reduction on the multiple historical learning score sets to obtain multiple dimensionality-reduced historical learning score sets, and arranging them in time series to obtain multiple historical learning score sequences may further include: selecting and obtaining a first reference learning score in a first historical learning score set in the multiple historical learning score sets; distributing distribution probabilities according to the differences between other historical learning scores and the first reference learning score in the first historical learning score set to obtain a first basic probability distribution, where the magnitudes of the differences and the magnitudes of the distribution probabilities are negatively correlated; performing optimized dimensionality reduction on the first historical learning score set according to the first basic probability distribution to obtain a first dimensionality-reduced learning score set; sorting according to the timestamp information of multiple historical learning scores in the first dimensionality-reduced historical learning score set to obtain a first historical learning score sequence; performing optimized dimensionality reduction and time series arrangement on the other multiple historical learning score sets to obtain multiple historical learning score sequences.

[0061] Among them, according to the first basic probability distribution, optimizing and reducing the dimension of the first historical learning score set to obtain a first reduced-dimension learning score set may further include: randomly extracting a preset number of historical learning scores within the first historical learning score set to obtain a first reduced-dimension historical learning score set; allocating distribution probabilities according to the differences between the historical learning scores within the first reduced-dimension historical learning score set and the first benchmark learning score to obtain a first reduced-dimension probability distribution; calculating the similarity between the first reduced-dimension probability distribution and the first basic probability distribution as the first reduced-dimension fitness; randomly extracting a preset number of historical learning scores within the first historical learning score set again to obtain a second reduced-dimension historical learning score set and processing to obtain a second reduced-dimension fitness; continuing to perform optimization and dimension reduction until convergence, and outputting the reduced-dimension historical learning score set with the maximum reduced-dimension fitness as the first reduced-dimension learning score set.

[0062] Among them, performing learning trend analysis according to the multiple historical learning score sequences to obtain a learning rate and a degradation rate may further include: collecting a set of sample learning score sequences according to the sample learning data of multiple users, and obtaining a set of sample learning rates and a set of sample degradation rates according to the learning score change identifiers within each sample learning score sequence; using the set of sample learning score sequences as classification inputs and using the set of sample learning rates and the set of sample degradation rates as classification outputs to construct a learning trend analyzer; based on the learning trend analyzer, performing learning trend classification on the multiple historical learning score sequences to obtain multiple context learning rates and multiple context degradation rates; analyzing the similarity between the target context information and the multiple classified historical contexts, and performing weighted calculation on the multiple context learning rates and the multiple context degradation rates according to the magnitudes of the multiple context similarities to obtain a learning rate and a degradation rate.

[0063] Among them, matching the target context information with the multiple classified historical contexts to obtain a matching historical context, and correcting the learning rate and the degradation rate according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate may further include: selecting the classified historical context with the maximum similarity as the matching historical context and obtaining the standard matching context information of the matching historical context; setting a learning correction coefficient according to the deviation between the target context information and the standard matching context information of the matching historical context; using the learning correction coefficient to perform correction calculation on the learning rate and the degradation rate to obtain a corrected learning rate and a corrected degradation rate.

[0064] Among them, according to the corrected learning rate and the corrected degradation rate, an auxiliary translation decision is made to obtain an auxiliary translation prompt scheme. The auxiliary translation prompt can further include: collecting a set of sample corrected learning rates and a set of sample corrected degradation rates, and setting a sample auxiliary translation prompt scheme according to the magnitudes of each sample corrected learning rate and sample corrected degradation rate, so as to obtain a set of sample auxiliary translation prompt schemes. Each sample auxiliary translation prompt scheme includes a prompt ratio, and the magnitudes of the sample corrected learning rate and the sample corrected degradation rate are negatively correlated with the magnitude of the prompt ratio; using the set of sample corrected learning rates and the set of sample corrected degradation rates as decision inputs, and using the set of sample auxiliary translation prompt schemes as decision outputs, an auxiliary translation decision maker is constructed; using the auxiliary translation decision maker to make an auxiliary translation decision on the corrected learning rate and the corrected degradation rate to obtain an auxiliary translation prompt scheme.

[0065] The English word intelligent learning and translation system provided by the embodiments of the present invention can execute the English word intelligent learning and translation method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0066] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0067] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or consecutive order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An intelligent learning and translation system for English words, characterized in that: The system comprises: A historical learning data indexing module, which is used to obtain a target word that the user is currently learning, and to collect target context information of the target word, and to index the historical learning data of the target word within the user's historical time according to the target word; A historical context information classification module, the historical context information classification module is used to classify the historical context information in the historical learning data, obtain multiple classified historical contexts, extract historical word meaning information sets and multiple historical learning data sets under the multiple classified historical contexts, and process to obtain multiple historical learning score sets; A historical learning score set optimization and dimensionality reduction module, wherein the historical learning score set optimization and dimensionality reduction module is used to optimize and reduce the dimensions of the multiple historical learning score sets respectively to obtain multiple reduced-dimensional historical learning score sets, and arrange them in time sequence to obtain multiple historical learning score sequences; A learning trend analysis module, the learning trend analysis module is used to perform learning trend analysis according to the multiple historical learning score sequences to obtain a learning rate and a degradation rate, wherein the learning rate represents the user's learning degree of the target word, is an indicator of learning speed or efficiency, and refers to the mastery of the target word per unit time, specifically represented by the ratio of the mean of the historical learning score per unit time to the full score; the degradation rate represents the rate at which the learning achievement decays over time, reflects the decay of the user's memory or understanding of the target word over a period of time, and is specifically represented by the reduction range from the highest value of the historical learning score per unit time to the current latest learning score; A correction module, the correction module is used to match the target context information with the multiple classified historical contexts to obtain a matching historical context, and to correct the learning rate and the degradation rate according to a deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate, wherein the corrected learning rate and the corrected degradation rate reflect the user's mastery of the target word in the current target context; An auxiliary translation prompt module, the auxiliary translation prompt module is used to make an auxiliary translation decision according to the modified learning rate and the modified degradation rate, obtain an auxiliary translation prompt scheme, and perform auxiliary translation prompts; The historical context information in the historical learning data is classified to obtain a plurality of classified historical contexts, a historical word meaning information set and a plurality of historical learning data sets under the plurality of classified historical contexts are extracted, and a plurality of historical learning score sets are obtained by processing, including: Acquire multiple historical context information in the historical learning data, perform classification processing, and obtain multiple classified historical contexts; Extracting the standard meanings of the target words in the historical learning data under the multiple classified historical contexts to obtain a historical meaning information set, and extracting multiple historical translation semantic information sets and multiple historical translation submission time sets submitted by users under the multiple classified historical contexts; According to the deviation extents of the multiple historical translation semantic information sets and the historical word meaning information set, a plurality of historical basis learning score sets are obtained by classification; According to the ratio of the preset submission time threshold and the plurality of historical translation submission time sets, the plurality of historical basic learning score sets are corrected and calculated to obtain a plurality of historical learning score sets; The step of performing a learning trend analysis based on the plurality of historical learning score sequences to obtain a learning rate and a degradation rate includes: According to the sample learning data of multiple users, a set of sample learning score sequences is collected, and a set of sample learning rates and a set of sample degradation rates are obtained according to a learning score change identifier in each sample learning score sequence; Using the sample learning score sequence set as classification input, using the sample learning rate set and the sample degradation rate set as classification output, to construct a learning trend analyzer; Based on the learning trend analyzer, the multiple historical learning score sequences are classified into learning trend categories to obtain multiple context learning rates and multiple context degradation rates, wherein the context learning rates and the context degradation rates reflect the influence of context factors on the learning effect; Analyzing the similarity between the target context information and the multiple classified historical contexts, and performing weighted calculation on the multiple context learning rates and the multiple context degradation rates according to the magnitude of the multiple context similarities to obtain a learning rate and a degradation rate; The target context information is matched with the multiple classified historical contexts to obtain a matching historical context, and the learning rate and the degradation rate are corrected according to the deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate, including: Selecting the classified historical context with the greatest similarity as the matching historical context, and obtaining standard matching context information of the matching historical context; Setting a learning correction coefficient according to a deviation between the target context information and the standard matching context information of the matching historical context; The learning correction coefficient is used to perform correction calculation on the learning rate and the degradation rate to obtain a corrected learning rate and a corrected degradation rate.

2. The English word intelligent learning and translation system according to claim 1, characterized in that: Obtaining the target word that the user is currently learning, and collecting the target context information of the target word, and indexing the historical learning data of the target word within the user's historical time according to the target word, including: Acquire a target word that the user is currently learning, and collect the upper context content and the lower context content of the target word as target context information; According to the target word, an index is performed in the historical learning record of the user to obtain the historical learning data of the target word.

3. The English word intelligent learning and translation system according to claim 1, characterized in that: The multiple historical learning score sets are optimized and reduced in dimension respectively to obtain multiple reduced-dimensional historical learning score sets, and are arranged in time sequence to obtain multiple historical learning score sequences, including: Selecting to obtain a first benchmark learning score from a first historical learning score set in the plurality of historical learning score sets; According to the difference between other historical learning scores in the first historical learning score set and the first benchmark learning score, a distribution probability is allocated to obtain a first basic probability distribution, wherein the size of the difference is negatively correlated with the size of the distribution probability; According to the first basic probability distribution, optimizing and reducing the dimension of the first historical learning score set to obtain a first reduced-dimensionality learning score set; Sort the multiple historical learning scores in the first dimensionality-reduced historical learning score set according to timestamp information to obtain a first historical learning score sequence; Optimize dimensionality reduction and time series arrangement for other multiple historical learning score sets to obtain multiple historical learning score sequences.

4. The English word intelligent learning and translation system according to claim 3 is characterized in that: According to the first basic probability distribution, optimizing and reducing the dimension of the first historical learning score set to obtain a first reduced-dimensional learning score set includes: Randomly extracting a preset number of reduced-dimensionality historical learning scores from the first historical learning score set to obtain a first reduced-dimensionality historical learning score set; According to the difference between the historical learning scores in the first dimensionality reduction historical learning score set and the first benchmark learning score, a distribution probability is assigned to obtain a first dimensionality reduction probability distribution; Calculating the similarity between the first dimensionality reduction probability distribution and the first basic probability distribution as a first dimensionality reduction fitness; Randomly extracting a preset number of reduced-dimension historical learning scores from the first historical learning score set again to obtain a second reduced-dimension historical learning score set, and processing to obtain a second reduced-dimension fitness; Continue to optimize the dimensionality reduction until convergence, and output the dimensionality reduction history learning score set with the largest dimensionality reduction fitness as the first dimensionality reduction learning score set.

5. The English word intelligent learning and translation system according to claim 1, characterized in that: According to the modified learning rate and the modified degradation rate, an auxiliary translation decision is made, an auxiliary translation prompt scheme is obtained, and an auxiliary translation prompt is performed, including: Collecting a set of sample correction learning rates and a set of sample correction degradation rates, and setting a sample-assisted translation prompting scheme according to the size of each sample correction learning rate and sample correction degradation rate, to obtain a set of sample-assisted translation prompting schemes, wherein each sample-assisted translation prompting scheme includes a prompting ratio, and the size of the sample correction learning rate and the sample correction degradation rate is negatively correlated with the size of the prompting ratio; Using the sample correction learning rate set and the sample correction degradation rate set as decision inputs, using the sample auxiliary translation prompt scheme set as decision outputs, and constructing an auxiliary translation decision maker; The auxiliary translation decision maker is used to make auxiliary translation decisions on the modified learning rate and the modified degradation rate to obtain an auxiliary translation prompt solution.

6. An intelligent learning and translation method for English words, characterized in that: The method is used for an English word intelligent learning and translation system according to any one of claims 1 to 5, and the method comprises: Obtain the target word that the user is currently learning, and collect the target context information of the target word, and index the historical learning data of the target word within the historical time according to the target word; Classifying the historical context information in the historical learning data to obtain a plurality of classified historical contexts, extracting a set of historical word meaning information and a plurality of historical learning data sets under the plurality of classified historical contexts, and processing to obtain a plurality of historical learning score sets; Optimizing and reducing the dimensions of the multiple historical learning score sets respectively to obtain multiple reduced-dimensional historical learning score sets, and arranging them in chronological order to obtain multiple historical learning score sequences; Performing a learning trend analysis based on the multiple historical learning score sequences to obtain a learning rate and a degradation rate, wherein the learning rate indicates the user's learning degree of the target word, is an indicator of learning speed or efficiency, and refers to the mastery of the target word per unit time, specifically expressed by the ratio of the average of the historical learning scores per unit time to the full score; the degradation rate indicates the rate at which the learning results decay over time, and reflects the decay of the user's memory or understanding of the target word over a period of time, specifically expressed by the reduction range from the highest value of the historical learning score per unit time to the current latest learning score; Matching the target context information with the multiple classified historical contexts to obtain a matching historical context, and correcting the learning rate and the degradation rate according to a deviation between the target context information and the standard matching context information of the matching historical context to obtain a corrected learning rate and a corrected degradation rate, wherein the corrected learning rate and the corrected degradation rate reflect the user's mastery of the target word in the current target context; According to the modified learning rate and the modified degradation rate, an auxiliary translation decision is made, an auxiliary translation prompt scheme is obtained, and an auxiliary translation prompt is performed.

Images