155 results about "Natural language generation" patented technology

The invention belongs to the technical field of artificial intelligence and educational informatization, and relates to a multi-mode knowledge graph enhanced intelligent teaching-assistant question-answering system. According to the method, the knowledge graph construction technology, the multi-modal content analysis technology and the large language model reasoning enhancement technology are comprehensively applied, and the semantic understanding, knowledge integration and reasoning generation capabilities of the intelligent teaching assisting system in an education and teaching scene are improved. The related technology comprises layout analysis of textbook documents, semantic description generation of image content, entity and relation extraction of text content, multi-modal knowledge graph construction and question and answer reasoning and natural language generation combined with the knowledge graph. Through cooperative application of the technologies, semantic interconnection can be carried out on various modal information such as texts, images and tables in the textbook, and a searchable and traceable textbook-level knowledge network is formed.

The invention provides a mathematical question and answer process teaching system, which comprises a user interaction module, a question analysis and standardization module, a cognitive diagnosis engine, a generative teaching module, a mathematical knowledge graph database and a user portrait database, teaching content and guiding questions are presented to the user in a multi-mode form; the question analysis and standardization module is used for performing semantic understanding and structured analysis on mathematical questions and generating standardized question description and at least one standard question solving path; according to the method, the structured reasoning of the knowledge graph is combined with the natural language generation ability of the generative AI, so that a closed loop from'problem solving 'to'diagnosis' to'heuristic teaching 'is realized, thinking blockage points of students can be accurately positioned and personalized tutoring can be provided like human teachers, and the learning efficiency and the autonomous thinking ability are remarkably improved.

The invention provides a method and device for generating an SQL instruction through a dialogue type natural language, and relates to the technical field of language processing.The method comprises the steps that a natural language query request input by a user is received; calling a neural symbol reasoning module to extract a query intention and a key entity list, generating a plurality of candidate SQL instructions through symbol reasoning, and evaluating confidence; if the highest confidence coefficient is lower than a set threshold value, multiple rounds of dialogue clarification are initiated and fed back to the neural symbol reasoning module; calling an adaptive SQL reconstruction engine to perform screening, reconstruction or optimization based on a dynamic data environment on the target candidate SQL instruction; and executing the final SQL instruction, obtaining a query result and returning the query result to the user. By means of the method and device, the technical problem that in the prior art, due to fuzziness of natural language query and dynamic complexity of a data environment, SQL instruction generation accuracy is low, and then query execution efficiency is affected is solved, and the query execution efficiency is improved while SQL semantic accuracy is guaranteed.

The invention discloses a marketing copywriting generation method and device and a storage medium, and relates to the technical field of natural language generation, and the method comprises the steps: obtaining a to-be-optimized original marketing copywriting, a structured tag and environment variable information; inputting the original marketing copywriting, the structured tag and the environment variable information into a causal reasoning generation model; in response to a virtual intervention instruction of a user on at least one target intervention label in the structured labels, executing anti-factual reasoning through a causal reasoning generation model, generating an optimized marketing copywriting corresponding to the virtual intervention instruction, and calculating a corresponding predicted interaction amount; and outputting the optimized marketing copywriting and the predicted interaction amount. According to the method, the anti-factual causal reasoning and the large language model generation capability are fused, the user is supported to preview and optimize the copywriting and the interaction effect in real time through the virtual intervention label, multi-strategy low-cost and efficient simulation evaluation is realized on the premise that real delivery is not needed, and the intelligent level, the decision-making efficiency and the result interpretability of copywriting optimization are remarkably improved.

The invention relates to a power grid multi-modal data compliance monitoring method based on a knowledge graph, and the method comprises the following steps: S1, obtaining multi-source heterogeneous data of a power grid, carrying out the preprocessing, and generating structured and semantic data representation; s2, constructing an initial knowledge graph according to the produced structured and semantic data representation; s3, according to the initial knowledge graph, combining a time perception mechanism TGN to identify compliance standards and laws of a power grid operation environment changing with time, combining rule-based logical reasoning with a deep neural model through neural symbol fusion, realizing compliance judgment under a fuzzy condition, and constructing a knowledge agent; s4, based on the knowledge agent, performing multi-modal compliance analysis in combination with deep learning and symbolic reasoning to obtain an analysis result; and S5, based on an analysis result, in combination with a natural language generation technology, automatically generating an interpretation report for the violation event. According to the invention, dynamic intelligent compliance analysis is realized, and the intelligent and automatic level of power grid management is significantly improved.

The invention relates to the technical field of power dispatching, and discloses an energy-carbon platform multi-source early warning information generation method, system and device based on a large language model, and a medium, and the method comprises the steps: collecting multi-source energy data of a monitoring region, and carrying out the data preprocessing; performing data fusion through a multi-modal data fusion method, and performing anomaly identification through an anomaly prediction model to obtain a predicted value and a composite anomaly score; and constructing a structured context based on the predicted value and abnormal associated data obtained by composite abnormal score analysis, and generating natural language early warning information by constructing a large language model. According to the method, by fusing multi-source data and combining the natural language generation capability and the numerical value verification mechanism of the large language model, intelligent identification and accurate description of abnormal conditions and automatic generation of executable suggestions are realized.

The invention provides a structure multi-type apparent damage identification and detection report generation method based on a multi-modal large model. According to the method, the image recognition result and a natural language generation technology are fused, so that full-process automation from damage detection to report generation is realized, and the intelligent level of building structure health monitoring is remarkably improved. According to the method, automatic identification and accurate positioning of multi-type damage of the appearance of civil engineering structures such as buildings and bridges can be realized, and objective and normalized maintenance suggestions and detection reports are generated in combination with a vision-language multi-modal modeling method, so that the intelligence and automation level of structural appearance damage detection and operation and maintenance management is improved.

The present invention relates to Smart visual sign language translator, interpreter, and generator. The invention is a process of two-way real time communication between person with hearing and / or speech disabilities (PwD) and normal person, wherein sign language of PwD (100) is captured as video, converted into image frames, interpreted using DCN trained model (104) and context based Natural language generation (105); and then converted into text (106) and speech (107) for a normal person to understand; similarly, communication of normal person is captured using mic (108), and is converted to text using speech to text converter (109) wherein speech recognition is done using Deep Stack Network. Module of Text and context analysis using Natural Language Understanding (110) analyses text received from (109). Interpreted text from (110) is used for predicting text to nearest sign image. These sign images are used for creating meaningful sequence of sign language gestures in (112).

The embodiment of the invention provides a form generation method and related equipment, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining form item configuration from a form item knowledge base; acquiring a natural language input by a user; generating a current question word based on form item configuration and a natural language; inputting the current question word into the large language model to obtain a form configuration JSON (JavaScript Object Notation) content; analyzing the form configuration JSON content through a JSON analyzer to obtain a current front-end page; in response to the first instruction, a current front-end page is displayed in the designer. According to the embodiment of the invention, the visual form configuration can be generated and previewed through the natural language, the user operation is reduced, the development threshold is lowered, and the development efficiency and the user experience are improved.

The invention discloses a dynamic adaptive management system for road traffic safety planning driven by artificial intelligence. According to the system, multi-source data are acquired through a data acquisition and preprocessing layer and are cleaned and standardized; the knowledge engineering layer constructs a policy knowledge graph and a rule engine; the large model service layer realizes natural language generation, semantic understanding and multi-modal reasoning; the intelligent generation layer uses a GAN model to generate multi-modal planning content and dynamically adapts the multi-modal planning content; the implementation process management layer monitors planning implementation, middle-stage evaluation and last-stage summarization in real time; and the interaction and output layer provides visual editing and multi-format output. The system integrates the technologies of deep learning, generative adversarial network and the like, realizes intelligent planning generation and dynamic supervision, has the capabilities of multi-modal data processing, dynamic self-adaption and full-process management, can effectively improve the scientificity, high efficiency and adaptability of road traffic safety planning, and provides powerful support for road traffic safety management.

The invention relates to the technical field of knowledge maps, in particular to a personalized question and answer recommendation method based on a knowledge map and two-layer attention, and the method comprises the steps: constructing and storing a structured knowledge network containing a plurality of entities and association relationships thereof, analyzing an input natural language query, and recognizing query elements; based on semantic comprehension, calculating a semantic matching degree between the query elements and candidate answers extracted from the structured knowledge network, and further identifying a deep semantic intention of the natural language query; and based on the identified query elements and semantic intentions, in combination with the semantic matching degree, performing retrieval in the structured knowledge network to obtain an initial result, performing structured recombination and natural language generation on the initial result, and outputting a readable answer. The method has higher question and answer matching precision and query generation quality in a data sparse and relation complex scene, and is widely applied to the fields of education question and answer, intelligent recommendation, knowledge retrieval and the like.

The invention belongs to the field of cross technologies of natural language processing and database query technologies, and provides a method for generating database query through a natural language. Comprising the steps that table names and field names of all data tables are obtained, a Schema attribute graph used for describing the incidence relation between the tables is constructed based on the table names and the field names, and a structured Schema index database is established; receiving a query request input by a user, and calling an entity recognition model to recognize entity information related to the business from the query request to obtain corresponding candidate table names and candidate field names; determining an associated sub-graph structure, and constructing a local structured Schema index database; constructing a candidate association path set, and determining a target association path according to a preset priority rule; performing grammar and logic verification on the structured query statement to obtain an executable structured query statement; and updating to obtain the target local structured Schema index database. According to the invention, the stability and accuracy of query execution are improved.

The invention discloses an information fusion and reasoning method and system based on multi-agent collaborative networking search, and relates to the technical field of network information, and the method comprises the steps: a deep research strategy scheduling agent deconstructs an unstructured request through a task formalization mechanism, generates a high-dimensional instruction code, and dynamically optimizes an execution path. And the network intelligence index generation agent extracts and screens the trusted URL by using a rule engine and a semantic evaluator based on the code, and generates a structured link instruction stream. The structured analysis intelligent agent implements multi-level semantic distillation and conversion on an original document to obtain key value pair representations, and the key value pair representations are packaged into machine readable data. And generating a comprehensive intelligence abstract with consistent logic through the information fusion analysis agent. And the natural language generation engine converts the information into a professional report, and returns the professional report to the scheduling module through a feedback interface to realize cognitive closed-loop iterative optimization. The technical problem that in the prior art, it is difficult for geologists to obtain accurate, comprehensive and credible professional conclusions is solved.

A computer implemented method for generating video content based on natural language input is disclosed. The method includes receiving a natural language instruction describing one or more desired characteristics of a video. A structured script file comprising at least one story beat is generated using a natural language processing engine. A storyboard comprising one or more storyboard frames is created based on the structured script file. One or more virtual components are generated based on the storyboard. An intermediate video sequence comprising a visual component and an auditory component is created using virtual components and the storyboard. The intermediate video sequence is then refined to produce a modified video sequence by applying one or more post-processing effects.

A dialogue-based artificial intelligence system for interaction management in digital commerce, consisting of: a housing that encloses an arrangement of interconnected printed circuit boards; a conversation processing unit arranged on a first circuit board, comprising a syntactic parsing processor for generating hierarchical parse structures from user input texts, a semantic embedding processor for generating high-dimensional semantic vectors from the parsed structures, and a dialogue state calculation circuit for managing a multi-level conversation memory using clocked recurrent memory buffers; a retrieval augmentation unit arranged on a second circuit board, comprising a vector indexing processor for storing and retrieving domain-specific embedding vectors, a similarity calculation processor for calculating cosine-based semantic distances between the semantic vectors and vectors stored in a knowledge store, and a document reconstruction structure for merging retrieved text segments into a unified context representation; a generative response unit arranged on a third circuit board, comprising a transformer execution processor for executing a quantized transformer architecture for natural language generation, a context fusion circuit for merging the unified context representation with the semantic vectors to generate response conditioning data, and a hallucination suppression circuit for comparing the generated text with retrieved text segments and attenuating content divergence beyond a predetermined semantic threshold; a domain integrity check unit that is communicatively connected to the generative response unit, wherein the domain integrity check unit includes a regulatory restriction store that stores domain-driven rules, and a conformance assessment processor configured to check generated responses for conformance with the domain-driven rules, blocking non-conforming segments or replacing them using verified text content from the retrieval extension unit; a knowledge storage array comprising at least one static domain repository for storing commercial specifications, regulatory guidelines, product descriptions, and domain documents, a dynamic interaction buffer for storing anonymized conversation state data, and a vector storage partition for storing embedding vectors that can be retrieved by the vector indexing processor; and a multi-interaction device consisting of a touchscreen panel, an array microphone, a speaker structure and a contactless communication interface, each configured to receive multimodal user inputs or generate multimodal system outputs.

A system is provided.SOLUTION: A system, comprising: means for initializing and loading a generative AI model; means for receiving a conversational request from a user; means for analyzing the received conversational request; means for generating a response based on the analysis; means for transmitting the generated response to the user; and means for storing the conversational history in a database for use in continuous learning.SELECTED DRAWING: Figure 1

The application belongs to the cross technical field of natural language processing and database query technology, and provides a method for generating a database query from a natural language. The method comprises the following steps: obtaining table names and field names of each data table, constructing a Schema attribute graph for describing the association relationship between tables based on the table names and the field names, and establishing a structured Schema index library; receiving a query request input by a user, calling an entity recognition model to identify entity information related to a business from the query request, and obtaining corresponding candidate table names and candidate field names; determining an associated subgraph structure, and constructing a local structured Schema index library; constructing a candidate association path set, determining a target association path according to a preset priority rule; performing syntax and logic checking on a structured query statement, and obtaining an executable structured query statement; and updating the target local structured Schema index library. The application improves the stability and accuracy of query execution.

The application relates to the field of communication. The application provides a LoRa gateway management method, system, device and product. The method comprises the following steps: an instance creation module creates a first agent instance according to a first key, the first agent instance is used for isolation with other agent instances, the first agent instance sends a first natural language instruction input by a user to an inference model, the inference model selects one or more first target skills from a skill set according to the first natural language instruction, and generates according to the one or more first target skills and the first natural language instruction; and an application module verifies a first command line set according to the first key, and executes a first operation on a first gateway set based on the first command line set in the case of passing the verification.

The application discloses a specific field pipeline task type dialogue system based on an LLM, which comprises an inquiry subsystem and an answering subsystem, wherein: the inquiry subsystem parses and guides a user to supplement key information of a question according to user input task text, the answering subsystem summarizes key information of a dialogue task, and performs vector matching through a built-in vertical field local vector database to generate a final answer to the dialogue task. The application uses a large language model to realize natural language understanding, dialogue state tracking and natural language generation modules in a task type dialogue system pipeline, simultaneously realizes a rule matching-based strategy learning module, understands and replies to user input text, and combines the content of a local knowledge base, so that the whole process is more interpretable, the illusion problem of the large language model is reduced, only a small amount of sample prompt learning is needed, a large amount of data training or fine tuning is not needed, and the workload during field migration is reduced.

The invention relates to the technical field of natural language generation, in particular to an efficient and safe reasoning method and system for a natural language generation model based on Transform, and the method comprises the steps: inputting a general corpus data set into a pre-training generation model in an offline stage, calculating the importance of each attention head of the model on the general corpus data set; pruning operation is carried out on the attention head of the model based on importance, a pruned generation model is obtained, and Transform is adopted in the generation model; in the online stage, to-be-processed text data is input into the pruned generation model, the importance of Tokens is evaluated layer by layer by utilizing a composite evaluation index, the Tokens are pruned by utilizing a pruning threshold based on the importance of the Tokens, a generation sequence of the to-be-processed text data is obtained through forward propagation of the remaining Tokens, and the to-be-processed text data is obtained. The composite evaluation index is obtained by weighting the importance of a model attention head and a Token attention accumulation score in an off-line stage. According to the method, the safety reasoning efficiency of the natural language generation task is improved through an offline-online collaborative optimization framework.

This application discloses an intelligent question-answering method, apparatus, computer device, storage medium, and product, belonging to the field of artificial intelligence technology. It includes: displaying an intelligent question-answering interface; obtaining input question information based on input operations on the intelligent question-answering interface; performing a statement matching query in a structured database based on the question information to obtain a first query result; performing a semantic similarity query in an unstructured knowledge base based on the question information to obtain a second query result, wherein the unstructured knowledge base includes multiple unstructured knowledge items, and the second query result includes the retrieved candidate unstructured knowledge items; determining candidate answer information based on the first and second query results; and performing logical reasoning and natural language generation on the candidate answer information to obtain a first target answer information, wherein the first target answer information is used to describe the candidate answer information using natural language, and the first target answer information contains the logical reasoning process of the candidate answer information.

This invention relates to the field of exercise prescription generation and recommendation technology, and discloses an LLM-based generative recommendation method for exercise prescriptions. The method involves acquiring and preprocessing data, constructing a knowledge graph based on the preprocessed data (S1), pre-training the LLM model, inputting the constructed knowledge graph into the LLM model, and optimizing it through reinforcement learning. The PPO algorithm is used to optimize the LLM model's output strategy. Based on the optimized LLM model, the exercise prescription is derived and generated in natural language using FITT parameters. This method combines user characteristics and scenario information to generate high-quality, personalized exercise prescriptions. The invention utilizes a multi-dimensional reward function framework to quantify prescription quality and optimize the generation strategy, ensuring that the generated exercise prescriptions are not only scientifically sound but also conform to the user's actual situation and preferences. Synthetic data is generated through a user simulator, achieving an upgrade from static recommendation to dynamic adaptation, improving user experience and the level of intelligence in exercise and health management.

We provide the system. [Solution] A generation method for generating the first draft of a report using natural language generation technology, A means of accumulating and analyzing past revision history and feedback, An interaction mechanism that presents correction suggestions to users and collects feedback from them, A learning method that improves the accuracy of proposed generation methods using feedback, A system that includes this.

The application discloses a kind of achievement transformation report intelligent generation method and system, comprising: constructing achievement transformation corpus;Based on corpus, use five-element prompt word framework to extract entity and relationship, check, implicit completion and weight update are carried out in combination with achievement transformation value evaluation model, and optimized knowledge graph is constructed;Knowledge cluster is divided to graph, and dual-mode index network of paragraph vector index and structured knowledge index is constructed;After receiving user input, core entity set is obtained by semantic coding and entity recognition;With the set as center, structured knowledge enhancement retrieval is executed, and evidence fragment is screened by fusing semantic similarity and knowledge correlation degree score;Finally, sort constructs input context, calls natural language generation model to generate structured report, simultaneously extracts reasoning path and is associated with evidence source and outputs.The application solves the problems of poor precision in manual writing, poor adaptation of general model and insufficient semantic mining, and improves the scientificity, pertinence and traceability of the report.

The invention relates to a self-adaptive voice dialogue generation system of an intelligent toy and a use method thereof, and belongs to the technical field of voice dialogues of intelligent toys, the self-adaptive voice dialogue generation system comprises a voice acquisition module, a voice recognition module, a user portrait module, a dialogue management module, a natural language generation module, a safety filtering module and a voice synthesis module, the voice acquisition module acquires user voice signals, the voice recognition module is connected with the voice acquisition module and converts the voice signals into text information, and the user portrait module establishes and dynamically updates personalized user portraits corresponding to users. The user portrait at least comprises a cognitive level quantized value, an interest preference vector and an emotion mode label which are calculated on the basis of interaction historical data. According to the method, a high-fault-tolerance voice processing chain is formed from directional pickup of a beam forming algorithm at a hardware end to a CNN-LSTM acoustic model optimized for children at a software end, so that the smoothness and the stability of an interaction process in a real children use scene are fundamentally guaranteed.

Example solutions for zero-shot domain transfer with a text-to-text model train a text-to-text model for a target domain using unlabeled in-domain text training data, and concurrently train the model using labeled general-domain task training data. The in-domain training comprises masked language modeling (MLM) training, and the task training comprises both natural language generation (NLG) training and natural language understanding (NLU) training. The NLG training comprises natural language inference (NLI) training and the NLU training comprises summarization training. The trained model acquires domain-specific task competency, sufficient to perform a language task within the target domain. Suitable target domains include radiology, biomedical, and other medical, legal, and scientific domains. This approach leverages large volumes of general-domain task training data and plentiful unlabeled in-domain text, even as labeled in-domain training data may be unavailable or prohibitively expensive for certain specialized domains.

We provide the system. [Solution] Means for obtaining information on salary receipts, expenses, and savings, A means of integrating the acquired information to create a user profile, A means of analyzing spending patterns and proposing the optimal budget allocation, A means of automatically allocating the remaining amount after deducting fixed expenses and budget from the aforementioned salary to savings or investments, A means of generating and providing financial data as a report in natural language, A means of generating answers to user questions and providing educational content, A system that includes this.

This invention discloses a temporally enhanced knowledge graph-driven dialogue agent and its implementation method, belonging to the fields of artificial intelligence and natural language processing technology. The dialogue agent includes a dialogue interface, natural language understanding, a temporal knowledge graph, a temporal reasoning engine, dynamic update and failure management, and a natural language generation module. It includes designing the basic representation unit of the knowledge graph as a temporal quintuple; designing a temporal reasoning engine and a dynamic update and failure management method; designing a method for matching, verifying, and performing multi-hop reasoning of temporal information in natural language problems with temporal facts in the knowledge graph; achieving accurate parsing of temporal constraints in dialogue, real-time adaptation of dynamic knowledge, rigorous temporal logic reasoning, and continuous maintenance of contextual temporal consistency; and outputting a temporally accurate, knowledge-reliable, and logically coherent intelligent response, capable of meeting the needs of complex scenarios such as vertical industry decision support and high-reliability intelligent interaction.

The invention discloses a data dictionary name intelligent standardization method based on natural language generation, which relates to the technical field of natural language processing, combines a deep reinforcement learning technology, analyzes input context information through a generation model, generates candidate terms, and compares the candidate terms with predefined standardized terms to obtain a data dictionary name intelligent standardization result. Three reward mechanisms including precision reward, recall reward and context consistency reward are adopted, and through the comprehensive action of the three mechanisms, the generation model continuously optimizes the strategy and adjusts the generation process, so that more accurate term generation is realized. The method can flexibly adapt to terms in the emerging field, the standardization of the terms is ensured by automatically adjusting the generation strategy, and particularly, the efficiency and accuracy of term generation can be effectively improved in the technical field of constantly changing and updating of the terms, so that the requirement of rapid change is met.

The invention discloses an electric power field-oriented large language model evaluation method based on multi-identity play, and the method comprises two parts: a first part: distributing a suitable identity for each model from a preset electric power field role identity library according to the relevancy with a task; in the second part, firstly, each piece of data in the data set is rewritten by using a data rewriting method, and training data with similar or opposite semantics is generated to serve as preference data; then scoring the data through a plurality of scoring models, and dynamically adjusting the weight of each model according to the label of the data; and performing subsequent natural language generation evaluation on the multi-identity model after the weight adjustment is completed. Compared with evaluation of a traditional large language model, the method provided by the invention has the advantages that firstly, a plurality of identity models are integrated, so that possible deviation of a single model is reduced, and meanwhile, due to the fact that weight adjustment is performed, the adjusted multi-identity model can be closer to human preferences during evaluation.