42 results about "Grammatical error" patented technology

The invention provides an execution feedback and iterative optimization-based natural language to SQL (Structured Query Language) conversion method. The method comprises the following steps of: generating a plurality of candidate SQL statements; performing parallel execution on the candidate SQL statements, and capturing grammar error information in execution results and line number classification numbers of different candidate SQL return results; generating an error pattern abstract based on the grammar error information, converting the error pattern abstract into a natural language constraint instruction, and injecting the natural language constraint instruction into a prompt word generated in the next round; when the line number classification number is smaller than or equal to a preset threshold value, a self-consistency voting mechanism is adopted, a candidate SQL set with the largest number of returned same lines is selected, and the SQL with the shortest execution time is selected from the set to serve as final output. According to the method, the accuracy, robustness and execution efficiency of conversion from the natural language to the SQL can be remarkably improved by executing a feedback-driven multi-round iterative optimization mechanism.

The invention discloses an intelligent error correction and style optimization system and method for business English writing, and relates to the technical field of natural language processing and artificial intelligence, and the system comprises the following components: a user interaction module, a data storage module, a language ability evaluation module and a self-adaptive error correction feedback and style optimization module. Through a multi-dimensional evaluation algorithm based on dynamic weight adjustment, historical writing data of a user is deeply analyzed, an evaluation system including four dimensions of grammar errors, vocabulary application, sentence structures and business profession is constructed, the system comprehensively evaluates the language ability of the user, and the user experience is improved. And the evaluation weight is dynamically adjusted according to the capability improvement rates of the users in different dimensions, so that the language capability levels of the users are more accurately divided, and the system can provide personalized error correction feedback and style optimization suggestions for the users with different language levels based on the evaluation result.

The invention discloses a database query system and method for converting a natural language into an SQL (Structured Query Language) statement based on a Transform architecture, and the system captures a long-distance dependency relationship and complex semantic information in the natural language based on the Transform architecture, so that the semantic accuracy is improved, the wrong and repeated operation of generating the SQL statement is reduced, and the data acquisition efficiency is improved. On the other hand, the problems of grammar errors, semantic inconsistency and the like are verified, recognized and corrected through the SQL error correction module, database query failures are reduced, the user operation experience is improved, meanwhile, the error correction module can conduct compensation through reverse verification and correction, the dependence of the system on the precision of a single module is reduced, and the overall stability is improved; and for similar related problems, SQL statements can be directly extracted from the mapping table, so that time-consuming processing links such as Transform semantic analysis and SQL generation are omitted, and the waiting time and the computing power consumption of a user are remarkably reduced.

The invention provides a large language model and semantic feedback iterative optimization process control program generation method, and belongs to the technical field of automatic control. And generating a preference data set through a compiler and semantic expert feedback, and performing model optimization by using the data set. The training bottleneck of a traditional data-driven model is avoided, and the generation capability of the model can be continuously optimized through dynamic adjustment and feedback under the condition of data scarcity; a dynamic iterative optimization mechanism is constructed by introducing the feedback of a compiler and a semantic expert, and the generated process control program can be checked and corrected in real time. The compiler feeds back to ensure the grammar correctness of the generated program, and a semantic expert evaluates from the aspects of logic and task intention. The problems of grammar errors and semantic mismatching in a traditional method are avoided. According to the method, the compiling passing rate and semantic accuracy of the process control program are effectively improved, and the quality and adaptability of the generated process control program are remarkably optimized.

The embodiment of the invention relates to the technical field of information, in particular to an SQL resource estimation method, device and equipment based on a large model, and the method comprises the steps: receiving an SQL statement input by a user, correcting a grammar error, and outputting a correct SQL code; analyzing fields, functions and limiting conditions in the SQL codes by configuring a large language model of a Python code executor tool; python codes are automatically written according to fields and limiting conditions, an operation environment is configured and executed, the size of a source data table is read, data are screened according to the limiting conditions, and the size of a screening table is obtained; according to the static parameters of the function, retrieving the original knowledge content to obtain an original knowledge set containing the Spark principle and historical execution data; and estimating resource parameters based on the SQL static parameters, the double-table dimension information and the original knowledge set. Spark parameters are generated through principle calculation and historical verification, and accurate resource configuration, cluster management and control and multi-field application requirements are met.

The invention discloses a language learning evaluation method based on a deep learning algorithm, and relates to the technical field of language processing, and the method comprises the steps: receiving a voice signal and original text content, constructing a noisy voice sample through an adversarial disturbance generator, inputting a pre-trained voice recognition model, and outputting a voice recognition text and an anti-noise confidence score; constructing a context semantic graph in the semantic analysis path, generating an edge attention weight, calculating a semantic coherence index, and matching a predefined grammar rule base in the activated grammar analysis path to generate a grammar error tag; and dynamically generating feedback content based on the multi-dimensional evaluation matrix, and updating a preset corresponding threshold value and a rule base weight according to the adoption of the user on the feedback content. According to the method, collaborative quantitative analysis of pronunciation, semantics and grammar problems is realized by constructing a multi-dimensional evaluation matrix of an anti-noise confidence score, a semantic coherence index and a grammar error tag.

The invention belongs to the technical field of English teaching methods, and particularly relates to an intelligent English teaching method and system and a storage medium, and the method comprises the steps: constructing a multi-dimensional linguistic feature analysis model, and extracting lexical features, syntactic relationship features and semantic deviation features in a text input by a student through a natural language processing technology; dynamic student portraits are established based on the cognitive psychology theory, cognitive level labels are updated according to real-time learning data, and the data comprise grammar error clustering distribution, spoken language fluency indexes and vocabulary association response time; and generating a personalized teaching path, matching teaching materials from the hierarchical resource library according to the cognitive level label, and dynamically adjusting the complexity and presentation form of a teaching strategy. Lexical, syntactic and semantic deviation features are extracted through a natural language processing technology, student error types can be accurately positioned, the problem that traditional error correction only stays on surface modification is avoided, and cognitive tags are updated based on real-time learning data.

The invention provides an English text grammar error proofreading method paying attention to previous text features, and the method is a verification method composed of a sentence part-of-speech vectorization module, a sentence information feature extraction module, a previous text-source sentence information feature fusion module and a proofreading result screening generation module. According to the method, cross-sentence text modeling and a fine-grained error type recognition mechanism are creatively fused, and the problems that the recognition rate of grammar errors caused by cross sentences in a long text is low, and the capability of distinguishing diversified error types is insufficient are effectively solved.

A method for natural language to SQL (NL2SQL) statements driven by a hybrid approach combining templates and a large language model includes the following steps: constructing a pre-built SQL template library to assist the large language model in quickly matching syntactically correct SQL template skeletons; constructing a database schema information knowledge base to assist the large language model in accurately extracting entities; constructing a large-model natural language parsing and entity extraction engine to extract entity information; constructing a large-model-based template matching engine to match corresponding target SQL templates from the template library using the large language model; and constructing a large-model-based template filling engine to fill the extracted entity information into the corresponding placeholders of the selected target SQL template, generating the final executable SQL statement. By using pre-built SQL templates to ensure syntactic correctness and utilizing the large language model to parse natural language and extract entities to ensure semantic flexibility, this method solves the syntax errors and illusion problems that may occur when generating SQL using pure LLM, significantly improving the practicality and accuracy of NL2SQL technology.

A large model-based text error correction method and apparatus, a device, and a storage medium, relating to the technical field of artificial intelligence. The method comprises: on the basis of a large language model, generating first training data according to a first preset instruction, and manually annotating preset data to generate second training data, so as to construct a training data set; constructing a corresponding target data set by means of second preset instructions corresponding to a preset text error correction task and the training data set, so as to use the target data set to fine-tune the large language model to obtain a target large language model; and acquiring a text to be error-corrected, and determining error correction instructions corresponding to said text, so as to concatenate said text and the error correction instructions and then input the concatenated result into the target large language model to obtain an error-corrected target text. The data generated on the basis of the large language model is mixed with the manually annotated data, and a large model is fine-tuned with different instructions for different tasks, so that spelling error correction and grammatical error correction are chained in series, thereby effectively improving the accuracy of text error correction.

The invention discloses a Chinese grammar error correction multi-task training method based on thinking process distillation, which comprises the following steps: in a data construction stage, guiding a DeepSeek model by utilizing a designed constraint condition and a prompt project, and taking the DeepSeek model as a teacher model, in a training stage, taking a small-volume large language model as a student model to learn knowledge of the teacher model, and taking a small-volume large language model as a student model to learn the knowledge of the teacher model. The semantic comprehension ability of a teacher model is migrated from multiple dimensions by combining structured supervision and a multi-task learning mechanism, so that tasks are mutually enhanced, the same wrong sentence can be trained at the same time in multiple dimensions, and the model is promoted to learn more universal and more robust feature representation; according to the method, an end-to-end interpretable error correction process is realized, a user is helped to understand a model decision basis, and an error correction analysis and display process is added; the features of different dimensions are aligned in the multi-task learning process, so that the model learns more universal and more robust feature representation, and the generalization ability of the model in complex grammar error, composite error and zero sample scenes is remarkably improved.

The invention discloses an intelligent subjective question marking method and system supporting multi-text mixing, relates to the technical field of online education, effectively captures cross-paragraph information fusion and logicality through multi-granularity alignment and nonlinear fusion strategies, and greatly improves the scoring accuracy of complex answers. And in combination with Chinese and English differential quality evaluation, accurate scoring of Chinese coherence and structural integrity is realized, and grammar errors can be accurately marked and word matching can be optimized through English sentence-by-sentence fine batch. And explainable scoring evidences are output, personalized comments and optimized essays are generated in a targeted manner, and students are assisted in accurate improvement. A calibration mechanism and manual rechecking dynamic update parameters guarantee the scoring reliability, the paper marking efficiency is improved, the human deviation is reduced, and intelligent paper marking is promoted to be upgraded from pure scoring to combination of accurate evaluation and personalized guidance. The problems that an existing system is insufficient in multi-text mixed answer processing, lack of personalized comments and optimized essays and lack of English sentence-by-sentence fine batch are effectively solved.

The application discloses a knowledge graph-based English grammar error tracing recognition method, relates to the technical field of natural language processing, and solves the problems of low efficiency and low accuracy of English grammar error tracing. The method comprises the following steps: obtaining a plurality of sentences with grammar errors and defining the sentences as to-be-traced sentences; analyzing the lexical properties of the to-be-traced sentences, and recognizing the sentence structures corresponding to the to-be-traced sentences; analyzing the time clues corresponding to the to-be-traced sentences, and obtaining the tense structures of each to-be-traced sentence; identifying and tracing the errors in the sentences according to the sentence structures of the to-be-traced sentences and combining the knowledge graph; and the method divides the sentence categories of the to-be-traced sentences, then identifies the wrong words in the to-be-traced sentences based on the knowledge graphs of different sentence categories, and reversely searches the knowledge graph, so that the English grammar errors can be efficiently and accurately traced.

The invention provides an intraoperative demanded instrument recognition method and system based on semantic recognition, and relates to the technical field of data processing. The method comprises the following steps: acquiring voice information of a surgeon; converting the voice information into statement information; performing preprocessing including grammar error correction on the statement information to eliminate grammar errors of the statement information; constructing a dual-task model comprising a BERT module, an NER module with a rule filter unit and an identifier identification module; training the double-task model in combination with a Bayesian algorithm improved based on a probability model so as to complete hyper-parameter optimization of the double-task model; inputting the preprocessed statement information into the trained dual-task model, and outputting a target entity identifier of the instrument required by the surgeon; and activating corresponding indication equipment according to the target entity identifier, and indicating the required instrument. The intention of a surgeon can be automatically and accurately identified, and indication of required medical instruments is completed.

An object of a system according to an embodiment is to overcome time and cost constraints and to efficiently learn English conversation.SOLUTION: A system according to an embodiment includes a smartphone application and a user. The smartphone application is equipped with a generation AI. The generated AI serves as a question of English conversation from the user or a conversation partner. The generation AI points out errors in pronunciation and grammar of the user in real time and feeds back improvement points.SELECTED DRAWING: Figure 1

The invention belongs to the field of intelligent voice evaluation, and particularly relates to an intelligent spoken foreign language test method based on BERT and an interactive attention mechanism. Scoring is carried out from multiple aspects of the spoken language pronunciation accuracy and fluency, the vocabulary accuracy and diversity, the grammar accuracy and diversity, the theme accuracy and the scene matching performance of the examinee, the comprehensive total score of the spoken language test of the examinee is obtained through calculation, and the spoken language test result of the examinee is output. Through fusion of multi-modal BERT feature extraction, mouth shape-speech time sequence alignment, interactive attention grammar analysis and deep semantic matching technologies, an automatic spoken language scoring system which covers full dimensions of pronunciation-vocabulary-grammar-theme and has a visual verification capability is constructed, and the limitation of a single modal is broken through. The robustness and accuracy of spoken language test evaluation are improved, and fine-grained positioning of pronunciation errors, voice intonation errors and grammar errors is achieved.

The embodiment of the invention provides a dialogue information processing method and device, equipment and a storage medium. The method includes: in a conversational page, receiving a first set of text units from a language model, the first set of text units being included in a first portion of a response of the language model, the response being a text stream generated by the language model in a streaming manner based on cues; according to the received time sequence of each text unit in the first group of text units, presenting a current response for the cue word; and processing the current response based on syntax check data, the syntax check data indicating a syntax error in the current response. In this way, it can be determined whether a syntax error exists in the received text stream, and in the event that the syntax error exists, the response is processed to obtain a correct response. Therefore, the response accuracy can be improved.

A computing system includes a memory; and processing circuitry in communication with the memory. The processing circuitry is configured to: receive a paraphrase comprising a paraphrase text sample corresponding to an original text sample; and calculate a paraphrase metric value corresponding to the paraphrase, wherein the paraphrase metric value is calculated based on an adequacy score, a novelty score, and a fluency score of the paraphrase, the adequacy score indicating an extent to which the paraphrase text sample preserves a meaning of the original text sample, the novelty score indicating a level of difference between words and characters of the paraphrase text sample and words and characters of the original text sample, and the fluency score indicating an extent to which the paraphrase text sample is devoid of repetition, spelling, and grammatical mistakes.

An object of a system according to an embodiment is to efficiently and effectively generate examination questions and correct a paper.SOLUTION: A system includes an examination question generation part and a paper correction part. The examination question generation section learns past examination questions and generates examination questions based on parameters set by a teacher. The essay correction department analyzes essays and reports created by students, detects syntax errors, missing information, jumps in logic, citation errors, and the like, and makes concrete improvement proposals.SELECTED DRAWING: Figure 1

The application provides a data enhancement method for Chinese text proofreading, and relates to the technical field of artificial intelligence. The method judges the position and type of errors prone to occur in the correct source sentence through a sequence labeling model, makes up for the defects of current methods of randomly selecting error positions and error types, and makes the data closer to existing training data; in generating multi-word errors, syntax error data generated by using the model BERT is added, so that the semantic correlation of the generated error sentences is stronger; in the process of generating spelling errors, syntax error data generated by using the model BERT is added to simulate the situation of vocabulary selection errors in writing; at the same time, the spelling errors caused by pressing the wrong key when entering the text by using the keyboard in the real entry process are considered; the generated pseudo data contains common syntax error types, which can improve the robustness of the syntax correction model and the spelling correction model to a certain extent, and make the model learn more diverse and similar error sentence features to the real data.

The system according to the embodiment aims to provide efficient and continuous conversation practice in a language other than one's native language. [Solution] A system according to an embodiment includes a selection unit, a start unit, a response unit, a correction unit, and a scenario providing unit. The selection unit selects the language in which the user wishes to converse. The start unit starts the conversation in the language selected by the selection unit. The response unit understands what the user says to the generated AI and returns a response. The correction unit points out and corrects the user's pronunciation and grammar errors based on the response provided by the response unit. The scenario providing unit practices conversation on a specific topic based on the correction provided by the correction unit.

A grammatical error correction method incorporating component syntactic information belongs to the field of artificial intelligence technology. It includes: extracting component syntactic information from a given statement; using the erroneous statement, its corresponding correct statement, and the component syntactic information as input data; and constructing a multi-task grammatical error correction model that integrates component syntactic information to correct the erroneous statement. This method first extracts component syntactic information from the statement using grammatical analysis, serializes the statement's component syntactic tree to obtain a component syntactic sequence, and constructs triplet pairs as input data. Second, an adapter module is introduced to construct a multi-head attention mechanism model based on multi-task learning, learning the potential relationships between erroneous and correct statements, and between erroneous statements and component syntactic sequences. Finally, through pre-training and lightweight fine-tuning of the adapter module, the features of the erroneous statement, the correct statement, and the component syntactic sequence are fused to complete the grammatical error correction.

The invention discloses a context-based Chinese intelligent error correction and text optimization system, which belongs to the technical field of natural language processing, and comprises a context semantic coding module, a multi-dimensional error detection module, a literary style perception module, a language authentic degree evaluation module and a self-adaptive error correction optimization module, the context semantic coding module realizes multi-granularity semantic coding through a hierarchical attention mechanism; the multi-dimensional error detection module is used for detecting homophone errors, similar character errors, idiom misuse and grammar errors in parallel; the literary style perception module identifies the literary style type of the text and provides targeted optimization; the language tunnel degree evaluation module evaluates the language tunnel degree and recommends alternative expressions; the self-adaptive error correction optimization module synthesizes the output of each module to generate an error correction result, and realizes closed-loop parameter optimization based on user feedback, the error correction accuracy reaches 96%, and the Chinese writing quality is effectively improved.

The invention provides a word segmentation-based Chinese grammar error correction method on an unsupervised synthetic data set, which comprises the following steps of: structuring an operation sequence, firstly segmenting words and then carrying out dynamic mask strategy and consistency training; according to the method, an original Chinese sentence containing errors is mapped into an operation sequence containing four types of labels of KP keeping, RP replacing, IN inserting and DL deleting, and accurate error correction of a model is guided; the method comprises the following steps: randomly masking word units which are marked as KP and do not need to be modified after word segmentation, synchronously generating an MS (masking) label, and forcing a model to depend on context semantics instead of a surface form, so as to efficiently learn sentence semantic information; in addition, a Jensen-Shannon (JS) divergence loss function is adopted to reduce the difference between an operation sequence generated by the low-quality synthetic data and a target operation sequence, and the model robustness is improved. The method aims at improving the performance of an unsupervised Chinese grammar error correction (GEC) task by combining the advantages of seq2Edit and seq2seq series models and utilizing word segmentation to mask.

A computing system includes a memory; and processing circuitry in communication with the memory. The processing circuitry is configured to: receive a paraphrase comprising a paraphrase text sample corresponding to an original text sample; and calculate a paraphrase metric value corresponding to the paraphrase, wherein the paraphrase metric value is calculated based on an adequacy score, a novelty score, and a fluency score of the paraphrase, the adequacy score indicating an extent to which the paraphrase text sample preserves a meaning of the original text sample, the novelty score indicating a level of difference between words and characters of the paraphrase text sample and words and characters of the original text sample, and the fluency score indicating an extent to which the paraphrase text sample is devoid of repetition, spelling, and grammatical mistakes.

The application discloses a subjective question intelligent marking method and system supporting multi-text mixing, and relates to the technical field of online education. Through multi-granularity alignment and nonlinear fusion strategy, cross-paragraph information fusion and logic are effectively captured, and the scoring accuracy of complex answers is greatly improved. Combined with differentiated quality evaluation of Chinese and English, accurate scoring of Chinese coherence and structural integrity is realized, and English sentence-by-sentence fine revision can accurately mark grammatical errors and optimize vocabulary collocation. At the same time, the output of explainable scoring evidence can generate personalized comments and optimize model texts, helping students to improve accurately. The calibration mechanism and artificial review dynamically update the parameters to ensure the reliability of scoring, which not only improves the marking efficiency and reduces the human bias, but also promotes the upgrading of intelligent marking from simple scoring to accurate evaluation and personalized guidance. The problems of insufficient processing of multi-text mixed answers, lack of personalized comments and optimized model texts, and absence of English sentence-by-sentence fine revision in existing systems are effectively solved.

A method of training a text-generating model for grammatical error correction (GEC) includes obtaining a multilingual set of text samples where each text sample includes a monolingual textual representation of a respective sentence. The operations also include, for each text sample of the multilingual set of text samples, generating a corrupted synthetic version of the respective text sample where the corrupted synthetic version of the respective text sample includes a grammatical change to the monolingual textual representation of the respective sentence associated with the respective text sample. The operations further include training the text-generating model using a training set of sample pairs. Each sample pair in the training set of sample pairs includes one of the respective text samples of the multilingual set of text samples and the corresponding corrupted synthetic version of the one of the respective text samples of the multilingual set of text samples.

The application discloses a model training method and device, electronic equipment and a readable storage medium, and belongs to the field of artificial intelligence. The method comprises the following steps: acquiring a first text sequence; inputting the first text sequence and a sign language vocabulary group information table into a sign language grammar error detection model to output N processing labels, one processing label corresponding to one first sign language vocabulary, the processing label comprising a retention label indicating retention of a sign language vocabulary or a deletion label indicating deletion of a sign language vocabulary; the sign language vocabulary group information table comprises multiple groups of sign language vocabularies and historical co-occurrence numbers corresponding to each group of sign language vocabularies; based on the N processing labels, the first text sequence is processed to obtain a third text sequence; in the case that the third text sequence is different from a second text sequence, based on a target sign language vocabulary, the sign language grammar error detection model is trained, the target sign language vocabulary being a different sign language vocabulary in the third text sequence and the second text sequence.

The invention relates to the technical field of artificial intelligence, in particular to a man-machine interaction method and system based on a large language model.The method comprises the following steps that based on user input information, lexical analysis is conducted on words, grammatical information is extracted, multiple components in sentences are recognized, a grammatical structure tree is constructed, the dependency relationship of the multiple words is analyzed, and user intentions are recognized; and generating hierarchical semantic information. According to the method, through lexical analysis and construction of the grammatical structure tree, multiple components and dependency relationships in the text are accurately recognized, a reliable basis is provided for subsequent intention recognition and error detection, user requirements are accurately captured, spelling and grammatical errors are detected and corrected, the ability of understanding a user input request is enhanced, and the user experience is improved. By means of mapping of computer instructions and management of instruction execution sequences, human-computer interaction is effectively promoted, user experience and interaction efficiency are improved, dialogue data are effectively stored and managed in combination with classification of the dialogue data and retrieval label distribution, and human-computer interaction efficiency is improved.

A system is provided.SOLUTION: A system comprising: means for collecting information on the Internet in real time; AI means for analyzing spelling errors, grammatical errors, and reputation information of web sites; means for determining whether a web site is a secure web site or a potentially fraudulent web site; means for scanning a URL to be accessed by a user in real time and issuing a warning to the user if the web site is a potentially fraudulent web site; and means for navigating to a secure official web site.SELECTED DRAWING: Figure 1