64 results about "Verbal expression" patented technology

The invention discloses a middle and primary school test question intelligent generation method based on an education big model. The method comprises the steps of generating a structured education data set; constructing an education large model specially used for intelligent generation of middle and primary school test questions; inputting target knowledge points, question types, difficulty and grade parameters, and generating a candidate test question set; setting a test question fitness function, comprehensively evaluating the knowledge coverage rate, difficulty distribution and language expression indexes of the candidate test questions, screening and optimizing the candidate test question set, and generating an optimized candidate test question set; detecting semantic accuracy, logic preciseness and teaching conformity of the test questions by using an automatic quality evaluation mechanism, and outputting test question evaluation results; and continuous optimization and self-adaptive updating of test question generation are realized. According to the method, the optimal multi-question type test question set can be automatically output on the premise of ensuring comprehensive coverage of knowledge points, reasonable difficulty distribution and excellent language quality, and the quality, balance and diversity of automatically generated test questions are greatly improved.

The invention provides a mathematical proposition automatic formalization method and device based on reinforcement learning, and relates to the technical field of mathematics, and the method comprises the steps: obtaining a to-be-formalized mathematical proposition expressed by a natural language; inputting a mathematical proposition to be formalized into the target automatic formalized model to generate formalized language expression; according to the target automatic formalized model, after a sample data set of a mathematical proposition is input into an initial automatic formalized model to obtain formalized language expression corresponding to the sample data set, a reward signal is generated based on the formalized language expression corresponding to the sample data set through a grammar checker and a semantic consistency check model; and a group relative strategy optimization algorithm is adopted to carry out multi-round iteration updating on the model parameters of the initial automatic formalization model by using the reward signal. According to the method, the requirement for training data is greatly reduced, the training efficiency is improved, the training effect of an automatic form model is improved, and then the accuracy of automatic formalization of the mathematical proposition is improved.

The invention discloses an AI-based online homework correction method and system, and the method comprises the steps: carrying out the feature extraction of text content, logic structure and language expression through a multi-dimensional feature extraction model according to the homework data submitted by a student; according to the multi-dimensional feature vectors, a subject knowledge base and logical reasoning rules are combined, and error detection and correction are conducted through a logical reasoning network; according to the homework feature vector, in combination with a teacher scoring standard and a student ability evaluation index, performing scoring and ability analysis by using a dynamic scoring and ability evaluation model; and generating a personalized feedback report by using a generative adversarial network according to a scoring result and a capability evaluation result. According to the embodiment of the invention, various errors in the homework can be efficiently and accurately identified and corrected, personalized feedback is provided, and the quality and effect of online education are improved.

The invention relates to the technical field of intelligent education, in particular to an interactive English teaching method and system based on AI vision, and the method comprises the steps: obtaining the voice and mouth dynamic image frame segments of a student, extracting an offset frame segment to generate a semantic motion disjunction interval, analyzing the time sequence consistency of a behavior signal and a motion cause word triggering frame segment, and calculating the motion matching degree. Time synchronism of the speech output and the visual action is evaluated. According to the invention, through real-time analysis of the voice and mouth dynamic image of the student, the alignment offset of the pronunciation and the mouth action is identified, and in combination with behavior signals such as eye fixation and head rotation of the student, the interactivity between the language action and the behavior of the learner is comprehensively evaluated, so that the efficient alignment of the language expression and the standard template is ensured; by analyzing the distribution frequency and the matching degree of the voice behaviors, a personalized teaching path is optimized. In addition, delay frames and contour offset are deeply analyzed, the synchronism of voice and visual actions is enhanced, and the real-time feedback and interaction effect in the learning process is improved.

The invention provides a word meaning sentence construction method and system based on speech thinking, and relates to the technical field of natural language processing, and the method comprises the steps: 1, obtaining an initial statement input by a user, a preset rhetorical manipulation type and literature style preference, and analyzing a semantic core and an emotional tendency in the initial statement, based on the semantic core, calling a rhetorical knowledge base of a Uygur's speech thinking theory, including a metaphor mapping matrix, a symbol association network and a grammar deformation rule set, and matching an adaptive composite rhetorical structure; step 2, constructing a three-dimensional situation semantic field based on the semantic core and the emotional tendency, and extracting and acquiring initial weight parameters of each dimension of an author cognition dimension, a reader acceptance dimension and a text function dimension through multi-modal features; according to the method, word meaning sentence construction is performed in combination with a speech thinking theory, so that image coordination and language adaptation of candidate sentence patterns are realized, and language expression is improved.

The invention discloses a multi-language advertisement creative generation system, and the system comprises a data collection and preprocessing module which is responsible for collecting text travel and language data, and carrying out the cleaning and marking. The culture feature analysis and modeling module extracts culture features in the data and constructs a culture model to map features and language expressions. The creativity generation module constructs a semantic understanding model based on deep learning, is in butt joint with the culture model, and generates creativity themes and plots. And the language generation module inputs the creative theme and the target language into a language generation model and outputs an advertisement copywriting. And the multi-language optimization and integration module optimizes the copywriting of each language and integrates the copywriting into an advertisement creative set. And the user interaction and feedback module provides an interface, inputs text travel items, target languages and parameters, outputs copywriting, and optimizes the system according to user feedback. According to the invention, the generation efficiency of the advertisement creativity can be improved, the adaptability of the advertisement copywriting in different language culture environments is enhanced, and the limitation of traditional advertisement creativity generation can be broken through.

The application discloses a recruitment interview evaluation method and system based on artificial intelligence and a storage medium, relates to the technical field of recruitment interview evaluation, and solves the technical problem that the prior art only completes morphological analysis and pragmatic reasoning through voice recognition and corpus comparison, does not deeply mine dynamic characteristics of voice signals, and does not perform correlation analysis on personality descriptions in resumes and real-time emotional performances in interviews, so that the evaluation dimension is single, and it is difficult to comprehensively and objectively reflect the language expression ability, psychological state and personality matching degree of a job seeker; the application obtains voice data and emotional data of a job seeker; the voice data is preprocessed to obtain a formant sequence corresponding to the voice data; a voice evaluation coefficient is calculated based on the formant sequence; an emotional similarity is calculated based on the emotional data; an interview evaluation coefficient is calculated based on the voice evaluation coefficient and the emotional similarity; and whether the job seeker is qualified is judged based on the interview evaluation coefficient, so that the above technical problem is solved.

The invention discloses a news standard term detection and correction method based on a large language model, which is characterized in that a generator-detector cooperative training architecture is adopted, a Qwen2.5-7B-Instruct model is used as a generator, a detector module is assisted to finely screen implicit vectors, the generator is guided to avoid excessive sensitivity and false change, and the accuracy of the news standard term detection and correction is improved. And the problem of news expression deformity caused by improper use of words, nonstandard language expression and noun errors in the news manuscript is effectively solved. Compared with the prior art, the method has the advantage that the problem of news expression deformity caused by improper use of words, nonstandard language expression and political noun errors in news manuscripts is solved. Experimental results show that the method obtains an ideal F0.5 index on the news term correction task, and shows that the large language model has a wide application prospect in the fields of text quality control and intelligent editing.

The invention relates to the technical field of intelligent scoring, in particular to a teacher teaching skill multi-dimensional intelligent scoring method and system.The method comprises the following steps that based on a teaching behavior multi-dimensional evaluation system, scoring standard connectivity strength is recognized, behavior consistency and language stability are analyzed, a feature behavior set is extracted, adjacent areas are expanded, interference nodes are removed, and the scoring standard connectivity strength is obtained; marking isolated point and breakpoint complementation structures, combining small regions, removing fragments, extracting behavior coding sequences, clustering and distributing labels, identifying index mapping, and outputting a teacher teaching skill classification and partition identification label set. The judgment of behavior consistency and language expression stability on skill features is enhanced, the accuracy and real-time performance of an evaluation result are improved, particularly, the strength and deficiency of teachers are meticulously analyzed and fed back in a complex teaching scene, teacher growth and teaching quality optimization are effectively supported, the high efficiency and unbiasedness of an evaluation framework are improved, and the evaluation efficiency is improved. And valuable education decision support is provided.

An emotional intelligence method, system, and apparatus is trained on a multi-modal basis to infer emotional states of users from visual, language-based, and / or tactile-based cues. The inferred emotional states then inform the system's interactions with users, which may take the form of language-based expressions in textual or audio form and / or visual-based expressions in the form of images such as within video and / or in the form of physical contact. The system automatically learns multi-modally from its interactions with users, which may be performed by applying a reinforcement learning process, updates its emotional state inferencing models, and adapts its subsequent interactions with users accordingly.

Techniques are described herein that are capable of using a complex value-bearing language expression to generate metadata associated with an artifact. The artifact is configured to define a type and to further define the complex value-bearing language expression. The artifact is built from source code. The type defines functionality of the artifact. The complex value-bearing language expression describes a configuration of the artifact or of a function of the artifact. The functionality and the configuration are defined in the source code, are written in a same computer language, and are included in a same software project. A constant value is extracted from the complex value-bearing language expression at build time of the artifact by evaluating a syntax of the complex value-bearing language expression. During a build of the artifact, the metadata is generated to include the constant value.

The invention relates to the technical field of virtual reality, in particular to a foreign language situational teaching intelligent management system and method based on virtual reality, in the system, a dynamic learning portrait generation module comprises a semantic feature extraction unit, a language expression feature extraction unit and a portrait construction unit, user dialogue information is obtained in real time, and semantic features of a user are extracted based on a language recognition technology; the language expression feature extraction unit obtains user dialogue information in real time in the situational teaching process and extracts language expression features of a user based on the eye movement tracking technology. According to the semantic feature and language expression feature extraction result of the user dialogue information, the dynamic learning portrait of the user is constructed, the differentiation demand of the user is analyzed, and the scene group learning thermodynamic distribution diagram in the historical data is combined, so that the dialogue content in the foreign language teaching process is automatically adjusted.

The invention relates to the technical field of cerebral palsy language education, and discloses a cerebral palsy language slow intervention-oriented situational interactive teaching tool, which comprises a situational interaction module used for constructing a virtual scene and realizing language training through a multi-modal interaction technology; the personalized adaptation module is used for carrying out personalized adjustment on the interaction mode and the difficulty level in the situation interaction module according to the physical condition and the language ability evaluation result of the user; the reward and feedback module is used for monitoring operation and performance of the user in real time and giving corresponding rewards according to a preset rule; the user management module is used for storing personal information, training records and evaluation data of the user; and an intelligent analysis module. By means of the voice, gesture and eye movement multi-mode interaction technology, a natural interaction mode matched with the physical condition of a patient is constructed, language training is stimulated in an all-round mode in a scene contact interaction mode, the language expression and communication ability of the patient is remarkably improved, and the training enthusiasm is enhanced.

To provide a technology that enables the context behind a person's behavior to be verbalized at low cost with a rich amount of information as a background. [Solution] A natural language generation device includes a control unit that generates natural language indicating attributes of the behavior of a target person based on history data indicating the behavior history of the target person.

The application discloses a text intention recognition method, an electronic device, a storage medium and a program product; the method comprises the following steps: obtaining a to-be-recognized user question; if there is no corresponding target natural language expression text of the to-be-recognized user question, determining a target structured language text corresponding to the to-be-recognized user question and a first target prompt text, and the first target prompt text is determined according to the vertical field type corresponding to the to-be-recognized user question; inputting the target structured language text and the first target prompt text into a pre-trained intention recognition large model to perform intention recognition, and determining a target natural language expression text corresponding to the to-be-recognized user question, wherein the intention recognition large model is generated by training according to prompt texts corresponding to different vertical field types, thereby solving the problems of low efficiency and low accuracy of structured language intention recognition; the intention recognition large model is used for intention recognition, the target natural language expression text is accurately determined, and the speed, the efficiency and the cost are low.

The invention relates to the technical field of infant intelligent toys, in particular to an infant early intelligence development intelligent toy which comprises a robot body, an electric push rod is mounted on the inner bottom wall of the robot body, a first supporting plate is fixedly connected to the telescopic end of the electric push rod, and a projector is mounted at the top of the first supporting plate. The top of the projector is fixedly connected with a second supporting plate, and the top of the second supporting plate is provided with a voice module. The clamp is matched with a mechanical arm to perform writing and drawing teaching demonstration, and infants are helped to learn basic writing and drawing; the projector can visually present teaching contents in the forms of animations, graphs and the like, so that learning interestingness and knowledge understanding are enhanced; the voice module realizes question and answer interaction, develops language expression and logical thinking ability of infants, and combines various teaching modes to meet comprehensive intelligence development requirements.

Training data for a speech-to-text service can be generated according to a variety of techniques. For example, synthetic speech audio recordings for training a speech-to-text service can be generated in an automated system via linguistic expression templates that are input to a text-to-speech service. Pre-generation characteristics and post-generation adjustments can be made. The resulting adjusted synthetic speech audio recordings can then be used for training and validation. A large number of recordings can easily be generated for development, leading to a more robust service. Domain-specific vocabulary can be supported, resulting in a trained speech-to-text service that functions well within the targeted domain.

Techniques are described herein that are capable of using a complex value-bearing language expression to generate metadata associated with an artifact. The artifact is configured to define a type and to further define the complex value-bearing language expression. The artifact is built from source code. The type defines functionality of the artifact. The complex value-bearing language expression describes a configuration of the artifact or of a function of the artifact. The functionality and the configuration are defined in the source code, are written in a same computer language, and are included in a same software project. A constant value is extracted from the complex value-bearing language expression at build time of the artifact by evaluating a syntax of the complex value-bearing language expression. During a build of the artifact, the metadata is generated to include the constant value.

The present invention provides a multi-modal speech interaction method, an electronic device and a storage medium based on a large model, including: performing speech recognition on speech data in a first language input by a user to obtain a first language text; performing language translation on the first language text to translate it into a second language text; performing semantic analysis on the second language text to obtain a semantic analysis result; constructing a multi-modal knowledge graph based on a preset large model for the semantic analysis result to obtain an enhanced semantic understanding result; wherein the multi-modal knowledge graph integrates multi-modal information related to the second language text; generating a dialogue strategy for the enhanced semantic understanding result; and performing speech synthesis based on the dialogue strategy to generate reply speech data expressed in the first language. In the present invention, multi-language interaction is realized, and at the same time, various modal information is integrated.

We provide the system. [Solution] A means of supporting education using machine learning that enables two-way dialogue using a first language and a second language, A means for creating individual learning plans based on the user's native language and target language, A means of providing users with simulated dialogue using a virtual reality environment, A means of collecting and analyzing user learning progress information and providing real-time feedback, A means of displaying subtitles through the user interface to make the dialogue easier to understand, A means of using a robotic device that supports language learning through dialogue in daily life within a home environment, A system that includes means for analyzing a user's question using speech recognition and natural language processing technologies and generating appropriate linguistic expressions.

The present invention provides a method for marking subjective test papers based on large models, belonging to the field of teacher examination evaluation. First, collect and preprocess subjective question answer data from the self-owned examination database to construct a high-quality data set; secondly, design a detailed scoring standard, manually annotate dimensions such as the accuracy, logic, and language expression of the answer content to generate weighted average score labels; then, select a marking and scoring large model based on the Transformer architecture, and utilize its powerful semantic representation ability to construct a marking model including modules such as multi-head attention; finally, design a two-way semantic matching calculation method to measure the similarity between the answer and the reference answer as the basis for scoring. Through the above steps, the model can achieve efficient, accurate, and objective automatic marking of subjective questions, improving the intelligent level of teacher evaluation.

The application discloses a composition automatic scoring method based on multi-stage learning, and the method comprises the following steps: S1, extracting the shallow language features, emotional features and theme relevance features of the composition; S2, theme relevance feature extraction; S3, construction of a beautiful sentence identification model and extraction of composition style features; S4, training of a base learning machine; and S5, composition vector distributed representation and feature fusion model training and prediction. The application is applied to the field of automatic composition scoring, and a comprehensive and multi-dimensional composition scoring feature is designed for Chinese composition scoring, the detection and discovery of beautiful sentences in the composition are realized, and the beauty degree of language expression in the composition is better considered; meanwhile, the composition automatic scoring based on multi-stage learning is proposed, and multi-angle composition features are effectively combined for composition scoring.

The invention discloses a teaching skill evaluation process video acquisition and evaluation method. The method comprises the following steps: S1, uploading lesson preparation data; s2, inputting a tentative video; s3, analyzing the teaching content; s4, analyzing language expression; s5, analyzing the classroom atmosphere; s6, analyzing a teaching mode; s7, analyzing blackboard writing; and S8, generating an analysis report. The method can promote the rapid improvement and growth of teaching skills of normal teachers, and improves the overall teaching level. The invention also discloses a teaching skill evaluation system.

The embodiment of the invention provides a dialogue processing method and device, equipment, a storage medium and a program product. The method comprises the steps that for current user input to be processed in dialogue interaction, target summary information of a context associated with the current user input is determined on the basis of the current user input and historical summary information of the context associated with the dialogue interaction, and the dialogue interaction relates to a target field; based on the current user input and the target summary information, determining at least one reference knowledge associated with the target domain and at least one reference reply strategy for the current user input, the reference reply strategy indicating reply to a language expression strategy input by the current user; and generating a target reply for the current user input based on the at least one reference knowledge and the at least one reference reply strategy.

It provides information processing to support more effective conversational learning. [Solution] Using an information processing device, data of the user's voice in a language conversation with the user using artificial intelligence is acquired, and an evaluation result is output that evaluates the language expressions spoken by the user in the conversation based on the acquired voice data. The language expressions selected by the user from the output evaluation result are stored in the memory as stock information for later learning. After the stock information is stored in the memory, data of the user's voice in a language conversation with the user using artificial intelligence is acquired, and using the acquired voice data and the stored stock information, it is determined whether the expression from the stock information was used in the language conversation with the user using artificial intelligence. If it is determined that the expression from the stock information was used, evaluation information that the expression from the stock information was used is output.

The one or more embodiments of the specification provide a speech unit prediction model training method, a speech synthesis method and an electronic device. The training method comprises: obtaining a first training sample and a second training sample; wherein the first training sample comprises a plurality of texts, and the second training sample comprises a plurality of texts and speech units thereof; the number of texts in the first training sample is greater than the number of texts in the second training sample; a preset neural network model is pre-trained in a self-supervised manner by using the first training sample, to obtain a language model learning language expression information from the first training sample; the language model is supervised trained by using the second training sample, to obtain a speech unit prediction model; and the speech unit prediction model is used for processing input texts to obtain a speech unit sequence. In this embodiment, the language model learning language expression information is obtained by pre-training, and then the language model is supervised trained, which is beneficial to improve the prediction accuracy of the speech unit prediction model.

The application provides a man-machine collaborative English long difficult sentence interactive translation and optimization system and method, relates to the English translation technical field, first carries out syntax semantic double-layer initial deconstruction processing to the English long difficult sentence, generates initial deconstruction text containing basic syntax constituent unit splitting result information and the like, then receives the structured adjustment instruction of interactive subjects, cooperatively adjusts the initial deconstruction text, generates intermediate deconstruction text, receives the semantic optimization opinion of interactive subjects again, fuses the related information in the opinion and intermediate deconstruction text, executes translation text semantic adaptation checking and logic coherence iterative optimization, and finally generates a translation text meeting target language expression habits and complete semantics, so that the quality and efficiency of English long difficult sentence translation are effectively improved through man-machine collaboration.

Traditional conversational AIs often focus on non-semantic elements in the user's natural language utterances, such as word endings and silences. Unable to respond to the characteristics, it was not possible to achieve "responses based on the atmosphere," such as not responding at all or responding based on the nuance of the words. . [Solution] This invention provides a dialogue generation structure that classifies the user's dialogue interaction state into index bands based on non-semantic features such as word endings, intonation, intervals between words, and utterance frequency, and controls the presence or absence of responses, word endings, nuances, and timing according to these index bands. This enables intuitive responses such as silent replies or replies based solely on nuance.

The application discloses a speech processing method and a terminal device, and relates to the technical field of artificial intelligence. The terminal device acquires a speech segment in a speech stream. When a first speech segment in the acquired speech segment has first language expression content and corresponds to a first semantic, if the first semantic matches a target semantic, the terminal device performs speech enhancement processing on the first speech segment. When a second speech segment in the acquired speech segment has second language expression content and corresponds to a second semantic, if the second semantic matches the target semantic, the terminal device performs speech enhancement processing on the second speech segment. The first language expression content and the second language expression content are not completely identical.