50 results about "Natural language question answering" patented technology

Provided herein are systems, methods, and computer-readable media for generating one or more database queries based on a natural language input data. An example method comprises configuring, using a conversational artificial intelligence (AI) editing module, information for a task. Moreover, the method may further comprise parsing the configured information based on a database schema to obtain a parsed database schema. Further, the method may further comprise generating, using a natural language question-answering system, one or more database queries based on the parsed database schema and natural language input data.

The invention discloses a natural language question and answer method, system and device, a medium and a product, and relates to the technical field of semantic recognition. The method comprises the steps that a user question is recognized based on a named entity recognition model, and a key entity is determined; the key entity comprises a place name, a distance and an orientation in the question; performing text classification on the user question based on a user intention recognition model, and determining the intention of the user; determining a structured query statement based on a preset language model according to the key entity and the intention; obtaining multi-dimensional geographic space data in the Internet map; converting the multi-dimensional geographic space data into a triple, and constructing a structured knowledge graph; and according to the structured query statement and the structured knowledge graph, determining an answer to the user question. According to the method, the intention of the question of the user is accurately and intelligently understood, and the accurate answer is returned.

The invention discloses a knowledge base knowledge association fusion method based on a knowledge graph, and the method comprises the steps: integrating structured, semi-structured and non-structured data through a cross-modal alignment technology, and constructing a multi-source heterogeneous data association network of a unified semantic space; newly added external data are fused to a multi-source heterogeneous data association network in real time by using a dynamic attention mechanism, and entity conflicts are eliminated by combining rule reasoning and a machine learning model; hidden association among entities in the multi-source heterogeneous data association network is mined based on the graph neural network, and a knowledge graph logic chain is complemented; based on the knowledge graph, intelligent question and answer and risk assessment decision scenes are supported through a hybrid retrieval architecture and an inference engine; and automatically updating and associating the knowledge base of the network extension knowledge graph by adopting an incremental learning technology. Natural language questions and answers are supported, accurate answers are generated through knowledge reasoning, and user experience is remarkably enhanced.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

The invention relates to the technical field of large language models, in particular to a natural language question and answer framework, method and device based on self-reflection, and can solve the problem that large language models LLMs (Language Models) such as ChatGPT and PaLM in the prior art show excellent performance in various language understanding and generation tasks to a certain extent, and the problem that the Language Models are difficult to understand and generate can be solved to a certain extent. However, the ability of the method in the aspects of complex reasoning and complex knowledge utilization is still lower than the human level. The framework comprises: a thinking chain module for receiving an input question, outputting a model thinking process according to the input question, and obtaining and outputting an answer at the end; the persuaser module firstly evaluates the correctness of the answer and the reasoning step, and outputs a corrected reasoning path to the responder module if an error exists in the reasoning step; and the answerer module is used for providing answers according to the corrected reasoning path and self-prompted question type information, and optimizing the output accuracy of the large model through repeated iteration.

The invention discloses a question and answer method based on medical institution internal knowledge base retrieval enhancement generation, electronic equipment and a storage medium. The method comprises the following steps: S100, constructing a medical institution internal knowledge base; s110, collecting an original document, preprocessing the original document, dividing the original document into text blocks, and storing the text blocks into a database; s120, establishing vectorization and indexing based on abstracts for the text blocks; s200, based on the questions of the user, performing retrieval to generate answers; s210, rewriting and expanding the original query to obtain an expanded query; s220, performing multi-path mixed retrieval, namely performing preliminary retrieval on the original query and the extended query to obtain N candidate text blocks; s230, rearrangement and careful selection are carried out, and M most relevant text blocks are selected by adopting a rearrangement model; and S240, answer generation and source tracing: integrating the original query, the M text blocks and the instruction large language model to generate a section of natural language question and answer to obtain an answer result. Accurate, efficient and traceable natural language question and answer service is provided for medical care and management personnel, and standardization, accuracy and efficiency of medical work are improved.

The invention discloses a business database natural language question and answer processing method fused with a large model technology. The method comprises the following steps: S1, receiving an emergency query request input by a user in a natural language form; and S2, carrying out analysis and intention recognition on the emergency query request based on a large language model, and generating a group of candidate query intentions arranged in a descending order according to matching degree scores and corresponding key entity information. According to the method, a core link can be optimized by introducing a large language model technology: in an intention recognition stage, intention recognition accuracy is improved through a formula of fusing semantic similarity and entity type matching degree; a priority-based asynchronous execution strategy is adopted to improve the response efficiency; the response reliability is guaranteed through real-time and conflict verification; meanwhile, the system performance is continuously improved in combination with an offline model optimization link, the defects of an existing processing method are finally overcome, and an accurate, efficient and reliable solution is provided for business database natural language question answering in an enterprise emergency scene.

A method of using a computing device to improve an answer generated by a natural language question and answer system includes receiving, by a computing device, multiple questions in a natural language question and answer system. The computing device further generates multiple answers to the multiple questions. The computing device still further constructs a new training set with the generated multiple answers, where each answer is compared with a corresponding question of the multiple questions. The computing device additionally augments the new training set with one or more tokens delimiting a span of one or more of the generated multiple answers. The computing device further trains a new natural language question and answer system with the augmented new training set.

The invention provides a dialogue method, device and equipment based on a large language model, and relates to the technical field of natural language processing, and the method comprises the steps: obtaining a natural language query statement input by a user and historical dialogue information of the user; generating an enhanced query vector corresponding to the natural language query statement according to the natural language query statement and the historical dialogue information; according to the enhanced query vector, determining a related target FAQ fragment from a preset common question and answer FAQ knowledge graph; the target FAQ fragment comprises a question and an answer; and according to the target FAQ fragment, adopting a preset large language model to generate a natural language dialogue text corresponding to the natural language query statement. By adopting the method, the accuracy and response speed of natural language question answering can be improved.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions with respect to network-based services or computing domains. A natural language question answering service may receive a natural language question from a client computing device. An aggregator of a natural language question answer service may retrieve paragraphs from a search system and generate prompts based on questions. A Large Language Model (LLM) of a natural language question answer service may receive cues and provide answers. The answer may be verified by a verifier of the natural language question answering service. Attributes may be applied to answers and retrieved paragraphs to generate references, embedded references, and similar questions. A watermarking module of the natural language question answering service can watermark the answer under the condition that the answer is verified.

Some embodiments relate to a method for generating one or more database queries based on natural language input data, the method comprising: using a dialog stream editor to configure or define information required to complete a task-oriented dialog; parsing the configured information based on a database schema to obtain a parsed database schema; and, using a natural language question answering system, using the parsed database schema and the natural language input data to generate the one or more database queries.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

Techniques for finetuning a large language model (LLM) are described. The finetuned LLM is generated by sequentially tuning a trained LLM using: (i) pairs of questions and corresponding context received from at least one source different from the trained LLM; and (ii) the questions without the context. The finetuned LLM may be used to generate an answer to a question, and user feedback and context may be used to update a trained machine learning (ML) configured to determine context for input to the finetuned LLM at inference. The updated trained ML model may thereafter process a question to determine context usable to answer the question; the question and the context may be processed by the finetuned LLM to determine an answer to the question; and the question, context, and answer may be used to further finetune the LLM.

This disclosure describes techniques and architecture for enriching dataset metadata of datasets arranged in tabular form comprising rows and columns, wherein each column has a name. The dataset metadata is enriched with business semantics for natural language question answering. The techniques include one or more of generating one or more synonyms for each name; ranking the names with respect to a likelihood that a column includes possible data to be returned to a user in response to a received NLQ from the user; predicting a date granularity for each column; and predicting a semantic type to describe values in the columns.

The present invention discloses a method for evaluating the significance of knowledge graph triples based on natural language question answering. The steps are as follows: First, for a given knowledge graph triple, extract the relationship it contains; then, according to the question generation templates corresponding to different pre-set relationship types, convert the triple into the form of a natural language question; based on the generated question sequence, the original task of evaluating the significance of knowledge graph triples can be transformed into a natural language question answering task, and then the existing large-scale pre-trained language model is further fine-tuned through the method proposed by the present invention, and finally the evaluation result of the significance of knowledge graph triples is output. This method significantly improves the accuracy of evaluating the significance of knowledge graph triples without relying on any external knowledge base and graph representation learning.

The invention discloses a method for identifying focus words in a natural language question for an intelligent question answering system, and relates to the technical field of natural language question answering. The invention provides a method for identifying focus words in natural language questions, so that a question answering system can more accurately understand concern points of a user; a prefix tree structure dominated by decision items is provided, an algorithm for mining strong focus association rules to identify focus words is further introduced based on the prefix tree, and the algorithm is more efficient than a classical association rule mining algorithm Apriori; an inverted index for a strong focus association rule is provided, and an algorithm for identifying focus words is further introduced based on the inverted index and is more efficient than sequential search; and a focus item set, a frequent focus item set, a focus association rule and a strong focus association rule are defined so as to better express information related to focus words.

The application provides a kind of operation and maintenance scene visualization report generation method and system based on natural language question and answer, belongs to intelligent operation and maintenance technical field, method includes: receiving the natural language query input by user;Through the pre-training of large language model and the preset operation and maintenance terminology dictionary, the natural language query is parsed and entity is extracted, and the entity-field association table containing demand type is generated;According to demand type and semantic feature, the query type is judged to be data query or visual query;Based on the judgment result, generate structured query language sentence or visual instruction;Query is executed to the interface business database to obtain raw data;Raw data is processed and analyzed to obtain analysis result data;Call data feature adaptation algorithm to match chart type, generate and output visual report.The application realizes the full-link automation from natural language input to visual report output, reduces the operation and maintenance data interaction threshold, improves the operation and maintenance data processing efficiency and accuracy.

A method for improving responses generated by a natural language question answering system using a computing device, including receiving, by the computing device, a plurality of questions in the natural language question answering system. The computing device also generates a plurality of responses to the plurality of questions. The computing device further utilizes the generated plurality of responses to construct a new training set, wherein each response is compared with the corresponding question among the plurality of questions. The computing device additionally augments the new training set with one or more markers that delimit one or more spans of the generated plurality of responses. The computing device also trains a new natural language question answering system with the augmented new training set.

Systems and procedures are provided for a natural language question answering service to deliver answers to natural language questions about network-based services or computer domains. The natural language question answering service can receive the natural language question from a client computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service can receive the prompt and provide an answer. The answer can be verified by a verifier of the natural language question answering service. Attribution can be applied to the answers and the retrieved passages to generate references, embedded quotes, and similar questions.A watermarking module of the natural language question answering service can watermark the answer when it is verified.

This invention discloses a method and system for power operation safety monitoring and question answering based on a multimodal large model. The method includes the following steps: a data acquisition step, acquiring visual data and safety regulation text data from the power operation site; a multimodal semantic fusion step, generating a unified fused semantic vector through feature extraction and cross-modal alignment fusion technology; a knowledge reasoning step, matching the fused semantic vector with a pre-constructed power safety knowledge graph and performing compliance reasoning based on a graph neural network; and an intelligent question answering generation step, inputting the fused semantic vector and the reasoning results into a large language model to generate natural language question answering information. This invention, through the synergistic innovation of multimodal semantic fusion, knowledge graph reasoning, and a large language model, solves the technical problems of insufficient semantic understanding, disconnect between the question answering system and the field, and unstructured knowledge representation in existing technologies, achieving fully automated and interpretable intelligent safety supervision from perception to cognition.

The invention discloses a chemical text attribute extraction method and system based on inverse reinforcement learning, and the method comprises the steps: reconstructing a chemical text attribute extraction task into a generative question and answer task, converting an input text and a target attribute into a question and answer pair, and extracting attribute information through the semantic understanding and generation capability of a question and answer model; a BioBART model is selected as a basic model, and fine tuning is carried out on a public biomedical question and answer data set, so that the model preliminarily adapts to a question and answer task; constructing a reward model comprising a plurality of sub-reward components; and performing model training by using maximum entropy inverse reinforcement learning, and alternately performing reward model updating and question and answer model updating. According to the method, the attribute extraction task is converted into the natural language question and answer task, and the BioBART model and inverse reinforcement learning are utilized to optimize the multi-target award function, so that the understanding and generation capability of the model on complex scientific texts is remarkably improved, implicit attributes in chemical texts can be effectively extracted, and powerful support is provided for customs to quickly identify suspicious substances.

The embodiment of the invention relates to a processing method and device for retrieving an enhanced language model based on a variational auto-encoder architecture. The method comprises the following steps: introducing a low-rank enhancer for a basic model to obtain a basic revision model; performing data acquisition on the public question and answer data set to obtain a first data set training basic revision model; constructing a second data set according to the target text library after training is finished, and combining the first data set and the second data set to obtain a third data set; constructing a feature vector library of the target text library; a retriever and a feature aggregation module are introduced into the basic revision model to form a retrieval enhancement language model, and the retrieval enhancement language model is in butt joint with the feature vector library; training a retrieval enhancement language model based on the third data set; and after the training is finished, processing a natural language question and answer task by using a retrieval enhanced language model. The quality of the generated text can be improved.

The invention discloses a fine tuning method based on a fluid mechanics natural language question and answer model. The fine tuning method comprises the steps of collecting a question and answer corpus data set, preprocessing the data set, constructing a dynamic pressure self-adaptive network, training the dynamic pressure self-adaptive network, testing the dynamic pressure self-adaptive network and adjusting and optimizing parameters. According to the dynamic pressure adaptive network provided by the invention, a network structure is constructed based on a fluid mechanics principle and is used for simulating dynamic flowing, distribution and adjustment processes of information in a neural network, adaptive control and compression of feature information flow are realized by simulating a path adjustment rule of fluid in a pressed environment, and the expression efficiency of the model is improved. The constructed dynamic pressure adaptive network shows excellent performance in a natural language processing scene. By performing low-rank modeling and dynamic compression on the high-dimensional feature representation, the model parameter volume is reduced, the training time is shortened, the GPU video memory is reduced, the operation speed is improved, and the method can be used for natural language question answering.

The invention discloses a data query method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a target question in response to triggering of a data query event; determining a preset question matched with the target question based on a preset vector database, and determining a reference query parameter set corresponding to the preset question; determining a target query parameter set corresponding to the target question based on the preset question and the reference query parameter set; and generating a target query statement based on the target query parameter set, and performing data query based on the target query statement to obtain a data query result. According to the scheme, instant and accurate natural language question and answer type data query can be provided, and the accuracy and query efficiency of data query are improved.

A method and system for extracting and organizing knowledge from historically accumulated data using AI assistance includes the following steps: unified preprocessing of multi-source heterogeneous aviation maintenance data to output unified JSON structured data; inputting the structured data into a large language model fine-tuned from aviation maintenance corpus for knowledge triple extraction; constructing a multimodal interaction and query interface supporting structured queries, natural language question answering, historical case retrieval, and maintenance solution recommendations; and establishing an incremental update mechanism to update newly submitted repair reports and batch-uploaded documents to the knowledge graph after preprocessing, extraction, and manual review. This invention effectively solves the problems of difficult standardization of multi-source heterogeneous aviation maintenance data, low reliability of knowledge extraction from large language models, and limited query and interaction methods, achieving efficient knowledge utilization and intelligent knowledge services from historical maintenance data.

The application belongs to the technical field of artificial intelligence and food safety information, and discloses a question and answer system of a meat product whole-chain safety knowledge graph based on deep learning, which is composed of a knowledge graph construction module and a system question and answer module; wherein the knowledge graph construction module comprises a data acquisition unit, a data processing unit, an entity recognition unit, a relationship extraction unit, a critical control point selection unit and a knowledge graph construction unit; the system question and answer module comprises a user question analysis unit, a query statement generation unit, a standard answer generation unit and an intelligent question and answer Web system construction unit. The question and answer system of the meat product whole-chain safety knowledge graph based on deep learning is adopted, a more easy-to-use and more intelligent natural language question and answer system is developed by constructing the meat product whole-chain safety knowledge graph, and finally the professional, scattered and complex meat product safety knowledge is efficiently, accurately and friendly provided to the end users.

The application relates to a hierarchical table data visualization intelligent construction method and device based on natural language question answering. The method comprises the following steps: uploading hierarchical table data in an Excel format by a user; a user proposes a visualization demand for the hierarchical table by using a natural language interactive mode; a system analyzes the natural language to determine a data region and a visualization task; the system extracts an auxiliary hierarchical table transformation according to a data screening result and data insight; and the system defines row / column descriptor priorities according to a table unit specified by the user, and then realizes the visualization in an interactive mode. The method can make the user propose a data analysis demand in a natural language mode by using a natural language processing technology, help the user find valuable information in data by using automatic data insight recognition, and quickly generate a user-satisfactory visualization result by using an intelligent data visualization construction process. The application reduces a data analysis threshold, and improves data analysis efficiency and accuracy.

This invention relates to a query graph generation method and system for question answering in complex knowledge bases. The method includes: selecting top-ranking historical questions from historical cases based on the semantic similarity between the target question and historical questions; forming a candidate relation set from the relations in the standard query graphs corresponding to the selected historical questions; generating a query graph based on the candidate relation set using a retrieval-based semantic parsing method; converting the query graph into an executable query statement according to the syntax rules of knowledge base query statements; and executing the query on the knowledge base to obtain the answer to the target question. This invention proposes a method to significantly reduce the retrieval space in the reasoning process by utilizing historical cases and pre-screening the retrieved candidate relations, which can significantly improve the efficiency of question answering while keeping the impact on the performance of natural language question answering within an acceptable range.

A domain-focused natural language question and answer system. The system includes one or more electronic processors. The one or more electronic processors are configured to create, from a plurality of files, a plurality of fine-tuning data examples, each respective fine-tuning data example of the plurality of fine-tuning data examples including a question, an answer, and a supporting citation. The one or more electronic processors are further configured to fine-tune a pre-trained foundational machine learning model using the plurality of fine-tuning data examples to generate a fine-tuned machine learning model, input a natural language question to the fine-tuned machine learning model, and retrieve, from the fine-tuned machine learning model, a natural language answer to the natural language question and an indication of one or more files, one or more relevant sections, or both that the natural language answer is based on.

The present application relates to a ship port real-time information analysis method and system based on a model context protocol framework, which comprises: determining the user query intention and data requirement through large language model semantic analysis; identifying and labeling the ship port entity class content and shipping professional term class content according to the shipping proper noun identification rule; encapsulating multiple external ship port real-time dynamic data open interfaces into multiple tool functions through the model context protocol framework to form a tool set; the large language model adopts the React inference mechanism to decompose the single round natural language query into multiple logical subtasks, and sequentially executes the inference of the required data, generates the calling instruction, and judges whether the user intention is met; the model context protocol framework forwards the structured real-time return data, which is sequentially executed by the large language model for field analysis, feature extraction and information summarization; and finally generates the ship port real-time dynamic information analysis result, effectively improving the accuracy and timeliness of natural language question and answer and real-time data analysis in the shipping field.