50 results about "Teaching assistant" patented technology

The present invention provides a deep learning-based natural language understanding method and an intelligent teaching assistant system. First, it involves constructing a knowledge database and a question database, where learning material documents are saved into the knowledge database and preprocessed natural language information is saved into the question database. The method then involves learning and understanding the natural language information in the question database, searching for related knowledge points in the knowledge database based on the understood content, selecting the best-matched learning materials corresponding to these knowledge points as samples to respond to the natural language information, and generating a record that includes the question, response, and evaluation, which is saved into the knowledge database. Finally, it generates multiple forms of responses and outputs them according to the corresponding requirements.

Generator neural networks are trained to produce synthetic samples that mimic training data used to train pretrained neural network models, respectively. Teaching assistant neural networks that learn from the pretrained neural network models are trained through knowledge distillation using samples produced by the generator neural networks. A student neural network that learns from the pretrained neural network models is trained through knowledge distillation using the synthetic samples produced by the trained generator neural networks.

The invention provides an intelligent teaching-assistant system base LLM training method for a drilling simulator, and belongs to the technical field of petroleum drilling large language model training, and the method comprises the steps: obtaining the simulation data of the drilling simulator based on an intelligent teaching-assistant system base large language model, and carrying out the field self-adaptive pre-training; performing fine adjustment on the original weight by utilizing low-rank self-adaption, and performing operation steps and fault diagnosis generation; the method comprises the following steps: constructing an enterprise private knowledge base, training a large language model by utilizing retrieval enhancement generation, and obtaining a trained verification header through explicit supervision; a direct preference optimization loss function is defined, a direct preference optimization loss function of retrieval perception is obtained in combination with the verification head, the large language model is optimized, and large language model training is completed; according to the invention, an external professional knowledge base can be fused, an equipment operation mechanism can be understood, an intelligent assistant architecture with teaching guidance and error diagnosis capabilities is provided, and the intelligent level of the drilling simulator is improved.

The invention discloses a rotary steerable drilling trajectory prediction method based on deep learning and knowledge distillation, and belongs to the technical field of drilling trajectory prediction, and the method comprises the following steps: collecting rotary steerable drilling site ground data and while-drilling well logging data, and carrying out data preprocessing; constructing a teacher model and training; the teacher model comprises a well drilling feature enhancement module and a sequence change prediction module; a teaching assistant model is constructed and trained, and the teacher model is assisted to carry out multi-interlayer data adaptive compression; a composite knowledge distillation framework and a student model are built, the student model is trained, and the trained student model is a lightweight borehole trajectory prediction model; during field application, ground data and logging-while-drilling data are preprocessed and then sent into the lightweight well track prediction model, a well track prediction value in the rotary steering drilling process is obtained, and therefore drilling operation parameters are adjusted in time according to a prediction result. According to the method, high-precision and light-weight well track prediction is realized.

The invention relates to the technical field of intelligent education and Internet of Things fusion, in particular to a multi-modal interaction control method and system of a multifunctional teaching-assistant robot and the robot. According to the system, a tablet AI processor runs an Android system as a core, a display module, a man-machine interaction module, an audio input module, an audio output module, an image acquisition module, a temperature and humidity sensor module, a WIFI or Bluetooth module, an Ethernet module and an Internet of Things module are connected, and the Internet of Things module supports RS485 wired access and Zigbee wireless access at the same time; the tablet AI processor executes voice interaction, video call, face recognition, environment monitoring, network interaction and equipment linkage, and provides a face recognition alignment and depth feature matching algorithm and an annular microphone array beam forming and sound source direction estimation algorithm, so that multi-modal interaction and multi-equipment linkage in a teaching scene are realized. The convenience and the safety are improved; and the equipment access cost is reduced.

The invention discloses a physical, chemical and student experiment AI teaching assistant for adaptive learning path planning and an implementation method, and the method comprises the steps: carrying out the planning of a first learning path for a student, carrying out the analysis of the hand tracking data of the student in an experiment process, obtaining the scoring data, and carrying out the re-planning of the learning path, analysis can be carried out according to the conditions of students and the operation performance in the experiment, so that adaptive change of subsequent experiments is carried out according to the experiment quality of the students, it is guaranteed that the students can obtain experiment guidance conforming to the students, and the defect that in the prior art, targeted experiment guidance cannot be carried out according to the students is overcome; the first learning path is used for adjusting the preset standard value of each experiment of the student, the preset standard value is in positive correlation with the academic record, the learning ability of the student is matched by adjusting the preset standard value, and the teaching strategy can be dynamically adjusted according to the learning progress and the academic record change of the student so as to adapt to the constantly changing learning requirements of the student.

The invention discloses an intelligent teaching assisting method and system integrated with the whole process and total elements of education and teaching, and relates to the field of education and teaching. According to the method, misunderstanding concept classification models are integrated, and a dynamic knowledge graph containing target subject knowledge is established; clustering knowledge concepts in the dynamic knowledge graph by adopting a Mapper algorithm of topological data analysis to obtain a course map; when the user completes interaction of the selected theme cluster, a cognitive state matrix is obtained by adopting a graph knowledge tracking model, an emotion category probability distribution vector is obtained by adopting an emotion classification model, and a learner state vector is obtained; a large language model optimized through process supervision and reinforcement learning is adopted as an inference engine; and outputting a targeted teaching strategy and teaching content by using an inference engine according to the learner state vector. According to the method, a personalized teaching environment which can perform smooth and dynamic natural language interaction and can accurately diagnose and effectively correct the specific deep-level cognition mistake of students in a target subject can be created.

The invention relates to the technical field of dynamic learning resource recommendation. The invention relates to a dynamic learning resource recommendation system driven by an intelligent behavior analysis teaching aid. The system comprises a resource library establishment unit, an initial resource updating unit, an examination prediction unit, a resource selection unit and a resource stage management unit. The resource library establishing unit is used for establishing a resource library in the teaching assistant machine, and collecting grade information of each student, teaching progress of a teacher and examination data of the student at the same time; by calculating the knowledge point matching degree of the wrong questions and the learning resources, it is ensured that knowledge points corresponding to the wrong questions can be matched with related content in a resource library, accurate mapping is formed, low learning efficiency caused by generalization recommendation is avoided, by integrating multi-dimensional data portrait support, the recommendation resources are made to accurately match individual demands of students, and the learning efficiency is improved. Resource difficulty is prevented from being disjointed with student level.

The invention discloses a teaching-oriented multi-modal interactive digital human teaching-assisted generation method, and belongs to the technical field of artificial intelligence education, and the method comprises the steps: generating a structured answer through multi-modal input (voice, text and portrait graph) in combination with a semantic enhancement question and answer model (SE-QA); generating personalized voice by using an emotion adaptive voice synthesis technology; constructing a teaching action video library, extracting action features by using a space-time diagram convolutional network (ST-GCN), generating a video through a time sequence convolutional network (TCN), and optimizing audio-lip synchronization and micro expressions; and a'generation-evaluation-optimization 'closed loop is realized through a multi-modal evaluation and reinforcement learning optimization generation process. According to the teaching-oriented multi-mode interactive digital human teaching-assistant generation method, the technical bottlenecks of semantic-action mismatch, single emotion expression and the like of a traditional digital human system are broken through, the knowledge transmission efficiency and the interaction reality sense can be remarkably improved, and an innovative solution is provided for an intelligent education tool.

The application relates to the technical field of teaching, and particularly discloses a nursing intelligent teaching auxiliary system and method, which comprises a cloud server, a plurality of teacher terminals and a plurality of student terminals; the cloud server comprises a knowledge base construction module, which is used for acquiring teaching documents of adult nursing science, and establishing structured course knowledge graph data based on the teaching documents; a model construction module, which is used for acquiring a general large language model, and performing field adaptability training on the general model by using the course knowledge graph data, and outputting a special model fused with adult nursing knowledge; a teaching assistant module, which is used for accepting a lesson preparation request of the teacher terminal, inputting the special model, and generating lesson preparation information; and a student assistant module, which is used for receiving an auxiliary request of the student terminal, calling the special model according to the content input by the student, and generating auxiliary teaching content. The technical scheme of the application can meet the learning needs of different students and effectively improve the teaching quality.

The invention discloses an edge side model parameter adjustment method, which comprises the following steps of: firstly, selecting a model to be trained as a main model, and constructing a corresponding data set for model training, verification and testing; setting initial key parameters for the to-be-detected model based on the constructed data set, and training the to-be-trained model; performing model evaluation by using a verification set according to a first training result; performing parameter fine tuning based on the evaluation result, and continuing iteration for a plurality of times until the model precision meets the requirement; loading the trained model parameters to a main model, and deploying the main model to an edge-side intelligent mobile practical training terminal; the trained main model can be directly deployed on an end side mobile terminal, the requirement of a mobile teaching assistant is met, and a more intelligent question answering service can be provided for students.

The invention discloses an edge-end collaborative continuous learning method and system based on multi-step knowledge distillation. The method is executed on the basis of an edge-end collaborative architecture comprising an end side (a preset student model) and an edge side (a preset teaching assistant and teacher model): the end side collects a data frame, part of the data frame is transmitted to the edge side according to a dynamic frame unloading rate, and the end side and the edge side are reasoned through corresponding models respectively; the edge side monitors the difference between the inference results of the assistant model and the teacher model, and retraining is started if the difference is lower than a preset threshold value; through hierarchical knowledge distillation, the scale gap between teacher and student models is filled up, and the training and reasoning effects of the student models are effectively improved. And then the incidence relation between the reasoning precision and the GPU resources is determined through mathematical modeling, an optimal resource allocation scheme is solved by means of a dynamic programming algorithm, and the precision benefit is maximized. According to the continuous learning scheme, computing resources can be flexibly allocated in a dynamic environment, the demand of reasoning precision maximization is accurately met, and the continuous learning scheme is suitable for scenes with double requirements for resource efficiency and reasoning performance.

1. Name of the product in this design: English Teaching Assistant. 2. Purpose of this design: For English learning. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The invention provides a model training method and device, electronic equipment and a storage medium, and relates to the field of artificial intelligence. The model training method comprises the following steps: acquiring a training sample set which comprises at least one image sample; inputting the image sample into a student model to obtain a first feature of the image sample; inputting the image sample into a teacher model to obtain a second feature of the image sample; inputting the image sample into a teaching assisting network, and performing feature extraction on the image sample by using a first feature extraction network; performing feature dimension conversion and mapping on the features extracted by the first feature extraction network by using a conversion network; performing feature extraction on the converted features by using a second feature extraction network to obtain third features; determining a first loss function according to the first feature, the second feature and the third feature; and performing parameter updating on the student model according to the first loss function to obtain a trained student model. According to the embodiment of the invention, the accuracy of cross-structure knowledge distillation can be improved.

The application discloses a teaching assistant system and a related teaching interaction method and device, equipment and a storage medium, wherein the teaching assistant system comprises a pre-class subsystem, a class subsystem and an after-class subsystem. The pre-class subsystem at least comprises a teaching design module, which is used for generating a teaching plan document based on first interaction information of a teacher. The class subsystem comprises a plurality of class interaction modules, which are used for outputting third interaction information for assisting teaching based on second interaction information of at least one of the teacher and students at least in a demonstration process of the teaching plan document. The after-class subsystem at least comprises a teaching analysis module, which is used for analyzing to obtain a learning condition file of different students based on the second interaction information of the students in a teaching process. The above scheme can provide teaching assistance for the teacher in the whole process of pre-class, class and after-class, and help to improve the teaching quality as much as possible from the technical point of view of the teacher teaching.

The invention relates to the technical field of intelligent teaching assistance, and discloses a teaching assistance decision intelligent auxiliary system based on RAG, comprising: a resource index module for converging course resources and teaching materials, constructing a course knowledge base index, and maintaining a historical sample library divided according to a networking search path, a tool path and a retrieval enhancement generation path; the relevance evaluation module is used for obtaining tool relevance items through semantic matching of input questions and tool names or tool descriptions; an intelligent auxiliary decision-making module; executing the integration module; checking a combined scale block; and loading the feedback persistence module. Historical items, tool correlation items and knowledge base matching items are subjected to linear combination according to configurable weights, tool generation, RAG and networking three-path scoring, path offset and cross suppression are set, under the constraint of a difference threshold value, a comparison threshold value and a minimum confidence threshold value, only a single path is output, a scoring result is written back to a historical sample library and is subjected to periodic persistence, and the result is obtained. And online adaptive decision making is realized.

1. Name of the product in this design: Teaching Assistant Robot (K12). 2. Purpose of this design: A robot used to assist in teaching. 3. The key design elements of this product are the combination of shape, pattern, and color. 4. The image or photograph that best illustrates the design's key points: 3D view 1. 5. The design for which protection is sought includes color. 6. The bottom view of this product is for parts that are not easily seen or cannot be seen during use, so the bottom view is omitted.

The present invention belongs to the technical field of image recognition, and particularly relates to a knowledge distillation kiwifruit visual counting method with a 1+2+1 distillation mode. This method constructs a student model using the YOLOv11 network model; takes the SEAM attention module as the detection head of the YOLOv11 network model to obtain a teacher model; adds the SBA adaptive attention module and the SOEP module to the neck network of the YOLOv11 network model to obtain two teaching assistant models; uses the teacher model to distill the two teaching assistant models to obtain two distillation loss functions; uses the sum of the two distillation loss functions to distill and train the student model, and then performs self-distillation operation on the student model. The distilled and trained student model is used to detect and count the input kiwifruit images. The present invention can solve the problem of too large a gap between the teacher model and the student model, improve the reliability and accuracy of the model, and achieve efficient kiwifruit counting.

The application provides an intelligent teaching assistant system, a learning path optimization method, equipment and a medium. Multi-modal sensors are used to collect multi-channel learning behavior data of students when they interact with an intelligent teaching assistant terminal for personalized learning. The sequence dependency relationship between learning content units is obtained based on a preset teaching knowledge graph. For each teaching stage, learning behavior features are extracted from the multi-channel learning behavior data, a structured feature vector is constructed based on the inherent attributes of the learning content units, and a joint representation vector is generated through multi-modal fusion. The joint representation vectors are aggregated to generate a teaching stage representation vector. The teaching effectiveness is evaluated based on the teaching stage representation vector to obtain a learning state deviation. The learning state deviation is used to filter teaching stages with substandard teaching effectiveness, and the learning path is optimized and adjusted based on the sequence dependency relationship. The application can realize closed-loop dynamic optimization of the intelligent learning path.

The application discloses a nursing education traceable, interpretable and verifiable large model intelligent teaching assistant system and method, which comprises an input capture and semantic analysis module, a multi-source knowledge retrieval and versioned traceability module, an executable reference and piece-by-piece binding module, a causal evidence graph and structured explanation generation module, an evidence consistency and counterfactual stability verification module, and a replayable decoding and evidence storage module; the input analysis module generates a standardized problem template and risk level information; the knowledge retrieval and traceability module outputs a candidate evidence set with source segment fingerprints; the information binding module binds answer units and evidence fingerprints to generate reference mapping; the causal evidence graph module constructs a structured explanation graph; the multi-dimensional verification module performs logical consistency and counterfactual stability tests and outputs verification results; and the decoding and evidence storage module stores replayable decoding information. The application realizes answer segment level traceability, structured machine verifiable explanation and deterministic result replay through the construction of a modular system.

The application discloses a student model training method, an image forgery detection method and computer equipment, and belongs to the image detection field. The image forgery detection method comprises the following steps: determining a target image to be detected; calling a trained student model based on the target image to generate a detection result; wherein the student model is trained by fusing a synthetic forgery feature, training images and intermediate features; the training images are provided by more than two domains; the intermediate features are generated by calling a corresponding teacher model based on the training images; the synthetic forgery feature is generated by calling a teaching assistant model based on all the intermediate features; and the synthetic forgery feature refers to a feature corresponding to common information in all the intermediate features. The method can improve the accuracy of identifying whether an image is a forged image.

The application provides a drilling simulator-oriented intelligent teaching assistant system base LLM training method, and belongs to the technical field of large language model training of oil drilling, and the method comprises the following steps: based on the intelligent teaching assistant system base large language model, drilling simulator simulation data is acquired, and field self-adaption pre-training is carried out; low-rank self-adaption is utilized to fine-tune the original weight, and operation steps and fault diagnosis generation are carried out; by constructing an enterprise private knowledge base, a large language model is trained by using retrieval enhancement, and a trained verification head is obtained through explicit supervision; a direct preference optimization loss function is defined, a retrieval-aware direct preference optimization loss function is obtained by combining the verification head, a large language model is optimized, and the large language model training is completed; the intelligent assistant framework capable of fusing external professional knowledge base, understanding equipment operation mechanism and having teaching guidance and error diagnosis capability is obtained, and the intelligent level of the drilling simulator is improved.

The invention discloses an implementation method, device and equipment of a teaching assistant, a medium and a product. The method comprises the following steps: receiving a calling request for a synthetic API generated by a teaching large model according to a student assistance request; calling a preset API (Application Program Interface) of virtual simulation training software and / or PID (Proportion Integration Differentiation) setting software according to the calling request; and feeding back a calling result to the teaching large model, wherein the calling result is used for indicating the teaching large model to generate assistance feedback according to the calling result. According to the embodiment of the invention, the training efficiency of virtual simulation training can be improved.

The invention discloses a middle and primary school language learning auxiliary method based on interaction of an education large model and a digital human, and the method comprises the steps: collecting middle and primary school language learning data, and carrying out the preprocessing of the collected language learning data; generating a corresponding student personalized language learning file; a language knowledge graph is constructed, the language knowledge graph covers multi-dimensional knowledge information of vocabularies, grammar and sentence patterns, and a mapping relation is established between the language knowledge graph and language learning features; forming an adaptive teaching scheme; the digital human virtual teaching assistant performs real-time voice, text and expression interaction with the students by using a multi-mode interaction technology, and adjusts an interaction strategy according to real-time feedback of the students; and the called language knowledge graph dynamically supplements the context of the students, so that situational language teaching is realized, and a real communication environment is simulated in a multi-language application scene. The language migration ability and the communication application level of students are effectively improved.

The application discloses an implementation method, device, equipment, medium and product of a teaching assistant. The method comprises the following steps: receiving a calling request of a synthetic API generated by a large teaching model according to a student assistance request; calling a preset API of a virtual simulation training software and / or a PID setting software according to the calling request; feeding back a calling result to the large teaching model, so as to instruct the large teaching model to generate an assistance feedback according to the calling result. The embodiment of the application can improve the training efficiency of virtual simulation training.

The system according to this embodiment aims to provide individually customized learning plans based on the learner's progress and level of understanding. [Solution] The system according to the embodiment comprises an analysis unit, a provision unit, a content unit, an assistant unit, and a reporting unit. The analysis unit analyzes the learner's progress and level of understanding. The provision unit provides an individually customized learning plan based on the data analyzed by the analysis unit. The content unit provides interactive content. The assistant unit provides an AI teaching assistant. The reporting unit visualizes the learning progress and provides a report.

This invention discloses an intelligent test question analysis and feedback method, storage medium, and device. By introducing visual-semantic joint segmentation, dynamic structure tree generation, cross-modal answer matching, and real-time error correction feedback mechanisms, it achieves high-precision analysis and intelligent grading of complex test questions. This invention can automatically identify and distinguish key elements such as text, formulas, and answer areas without relying on manual annotation or fixed templates, improving segmentation accuracy. It enhances the understanding of the logical hierarchy of questions by constructing a semantic structure tree through graph neural networks. It effectively supports the identification of open-ended and non-unique answers by employing an answer matching strategy that integrates embedded representation and symbolic reasoning. It generates targeted feedback by combining an error cause knowledge base and a large language model, significantly improving the system's teaching interactivity and practicality. This invention possesses good robustness, scalability, and feasibility for implementation, and is suitable for various application scenarios such as online education, intelligent homework systems, and AI teaching assistants.

The invention relates to the technical field of online education, in particular to a network online personnel management system based on online education entrepreneurship guidance, which comprises a vocabulary construction module, a student-tutor intelligent matching module and an entrepreneurship intention and teaching resource optimization module, according to the method, the word vectors corresponding to the entrepreneurial intention and the guidance experience are matched, the cosine similarity between the word vectors is calculated, and mutually adaptive tutors are recommended for different students, so that the students can efficiently and accurately find the tutor adaptive to the own entrepreneurial intention from the numerous tutors, the burden of processing a large number of invalid screening requests by the system is reduced, and the efficiency of screening the entrepreneurial intention is improved. The operation efficiency of the online education entrepreneurship guidance system is improved, and the entrepreneurship intention and teaching resource optimization module calculates the cosine similarity between the communication information and the teaching content by adopting the vocabulary again before a tutor selects an assistant, and determines the intention student who can take charge of the assistant.

1. The name of the product of this design: English teaching assistant. 2. Purpose of this design product: This design product is used to assist English teaching and display teaching materials. 3. The design key point of this appearance design product lies in the shape. 4. The picture or photo that best illustrates the design points: Stereoscopic diagram 1.

The invention discloses a metering device inspector training system based on artificial intelligence, and relates to the technical field of practical training devices, a personal center module generates a trainee portrait based on the reply of a pre-stored questionnaire and a deep learning algorithm, and inputs the trainee portrait into a knowledge graph module through a main control module; the knowledge graph module carries out online learning and testing based on the trainee portrait; questions generated by the students are sent to the AI teaching assisting module through the main control module, and questions are answered based on resources pre-stored by the knowledge graph module; and the virtual simulation module is in line connection with the main control module, and performs student operation scoring based on a pre-stored scene in combination with an operation sequence, operation time and scene key points in actual operation of the student. The invention provides a set of efficient and intelligent training system, online training of related personnel is realized, and the urgent task of the industry for the requirements of professional metering device inspectors is met.