271results about How to "Enhance reasoning ability" patented technology

The invention relates to the technical field of big data analysis and artificial intelligence, in particular to a multi-source heterogeneous big data fusion and reasoning method and system based on a knowledge graph, and the method comprises the following steps: constructing mapping interfaces of various data sources, collecting and storing entities in the data sources, and constructing nodes in the knowledge graph; performing representation learning on a graph structure of the knowledge graph based on a graph neural network, extracting an embedded vector of a node, and extracting a fusion node through the embedded vector and a mapping interface; performing knowledge completion on the fusion nodes by using a neural network based on symbolic logic; generating candidate reasoning paths by adopting a depth-first search algorithm based on the knowledge graph; reasoning is carried out based on an attention mechanism and path similarity, candidate reasoning paths are screened and sorted to obtain an optimal reasoning path, a graph neural network is adopted to carry out representation learning of a knowledge graph, symbolic logic and the neural network are combined, the interpretability of the reasoning process is guaranteed, and the learning ability is high.

The invention discloses an old people chronic disease risk prediction method and system based on a time sequence knowledge graph, and belongs to the technical field of medical health information, and the method comprises the following steps: S1, obtaining a health data set of an old people group; s2, on the basis of an ESOA-XGBoost algorithm, performing feature selection and sorting on each piece of health data in the health data set so as to determine correlation among variables, and generating a health data feature set; s3, constructing and training a time sequence knowledge graph prediction model including an STKGR-PR model and a T i PNN model, and predicting a relationship among the target entity, other entities and time sequence information through the time sequence knowledge graph prediction model; s4, predicting the old chronic disease risk of the old people group according to the trained time sequence knowledge graph prediction model; through the method, an elderly chronic disease risk prediction result with a good prediction effect and high accuracy can be obtained.

The invention discloses a vision-language pre-training general framework for realizing multi-granularity cross-modal alignment. Image-text pairs are used as training data to be respectively input into an image encoder and a text encoder to obtain coarse-granularity global features and fine-granularity local features; multi-granularity cross-modal alignment is carried out on the obtained global features and local features, and the aligned global features of the image and the text are used for cross-modal pre-training; the multi-granularity cross-modal alignment is composed of a text perception image block selection module and a cross-granularity alignment module; a text perception image block selection module in the step S3 selects the image block with the highest correlation through the correlation between text words or phrases and the image blocks to form a corresponding region or target object, so that more sufficient fine-grained alignment is realized; the cross-modal pre-training target comprises the multi-granularity cross-modal pre-training target constructed in the step S6 and universal image-text comparison loss, image-text matching loss and mask text modeling loss.

The invention relates to an intelligent semantic analysis knowledge graph system for multi-source heterogeneous data. The system comprises a data preprocessing module used for preprocessing to-be-processed multi-source heterogeneous data to obtain format-standardized text data; the semantic analysis module is used for performing natural language processing on the text data to obtain words, and then performing vocabulary layer, syntactic layer and semantic layer analysis on the text data and the words to obtain structured data; the structured data comprises a triple consisting of entities, relationships and events and a network diagram of the entities and the relationships; the model structure mapping module is used for mapping the structured data into a predefined structure of a knowledge graph to obtain structured graph data; and the knowledge graph module analyzes entities and relationships in the graph data, performs reasoning to obtain potential relationships in the graph data by utilizing a logic rule and a machine learning algorithm, realizes cross-data-source and cross-document deep semantic association, and improves the efficiency of large-scale data processing and knowledge management.

The invention provides a multi-mode intelligent robot control method and device, and the method comprises the steps: obtaining a current mode instruction which at least comprises one of a video instruction, a text instruction, a picture instruction and an audio instruction; on the basis of a pre-trained multi-modal large model, according to the current modal instruction, obtaining post-collapse characterization; on the basis of a pre-trained robot imitation learning network, according to the representation after collapse and current environment observation, predicting an output target action; the multi-mode intelligent robot with the body is controlled to operate according to the target action; wherein the robot imitation learning network is obtained by performing training optimization according to a training sample set formed by single-modal data samples, corresponding environment observation data and real actions of the robot. According to the method, the post-collapse representation is obtained by pre-training the multi-modal large model, and the post-collapse representation is utilized to predict the target action, so that the requirement on multi-modal manual annotation data when a training robot simulates a learning network is avoided in the process, the effect of multi-modal reasoning can be achieved only according to single-modal data training, and the efficiency of multi-modal reasoning is improved. Not only is data collection and labeling cost reduced, but also the reasoning ability of the model is improved.

The invention belongs to the technical field of mechanical arm grabbing, and discloses a visual sense-force sense-based mechanical arm instruction grabbing method, which comprises the following steps of: acquiring an RGB-D image of a scene, performing cutting processing on the RGB-D image through OpenCV, and extracting visual features of each object in the RGB-D image; a text command input by a user is coded through BERT, and language features are output; inputting the language features and the visual features into a CLIP model for fusion and alignment, and performing further alignment by adopting a Co-TRM structure to generate bimodal features; generating a point cloud image according to the depth map of the RGB-D image, and based on the point cloud image, combining visual features of an object, and generating a grabbing attitude through Graspnet; the problem that in the prior art, when grabbing is conducted based on vision and instructions, self-adaptive adjustment on grabbing force is not convenient is solved.

The invention relates to the technical field of natural language processing, in particular to a model distillation method and system based on a teacher model and situational reasoning. By using a multi-teacher learning framework, the student model can draw knowledge from a plurality of large teacher models, and diversified learning paths are provided for the student model; due to the introduction of a context awareness and example generation mechanism, the understanding and reasoning ability of a student model to a complex situation is enhanced by considering context information of input data and an input example; the reasoning chain strategy can ensure that the student model can generate an accurate and deep reasoning process, and the decision process of the teacher model is simulated; a parameter fine adjustment technology is adopted, only key parameters in the student model are adjusted, efficient migration of teacher model knowledge is achieved, and the number of parameters needing to be adjusted in the distillation process of the student model is reduced; the resource consumption in the model deployment and updating process is remarkably reduced, so that the trained model keeps the performance similar to that of the model.

The invention provides a method and a system for intelligently generating a complete dispatch report for financial unfavorable assets, and relates to the technical field of data investigation and arrangement, comprising Sp1, complete dispatch demand acquisition, Sp2, intelligent reasoning planning, Sp3, data acquisition and processing, Sp4, public opinion retrieval and analysis, Sp5, legal information extraction and verification, Sp6, data integration and report generation, and Sp7, report modification and output, and the method comprises the steps of Sp1, complete dispatch demand acquisition, Sp2, intelligent reasoning planning, Sp3, data acquisition and processing, Sp4, public opinion retrieval and analysis, Sp5, legal information extraction and verification, Sp6, data integration and report generation, and Sp7, report modification and output. By integrating a large model, an online retrieval tool, a data table tool and a key point extraction tool, automation and intellectualization of a complete dispatching process are realized. The system can automatically acquire, process and integrate data, greatly improves the efficiency of data acquisition, analysis and report generation, and reduces the probability of manual intervention and errors.

The invention provides a code large model self-evolution method based on Monte Carlo tree search, which comprises the following steps: S1, inputting a code generation task into a pre-training reasoning model, and generating a reasoning step according to a reasoning task; s2, constructing an inference tree, and obtaining an optimal inference path and a reward score according to an improved Monte Carlo tree search algorithm; s3, according to the optimal reasoning path, based on the automatically generated reasoning and reward data, performing pre-training model self-evolution to improve the reasoning model; and S4, enabling the pre-training model to generate a code of the reasoning scheme, and training the pre-training model to obtain a code large model. According to the method, under the condition that a large amount of fine adjustment data is not needed, the capacity and accuracy of large model code generation can be effectively improved, and the adaptability of the model in a complex reasoning task is further enhanced.

The invention discloses a knowledge graph-based knowledge question and answer method and device and a storage medium, and belongs to the technical field of natural language processing. The method comprises the following steps: processing an obtained question statement input by a user to obtain a subject entity and a target question embedding vector; mapping the subject entities to the obtained target knowledge graph and the embedded representation thereof, and generating candidate answer entities according to the subject entities and the proximity relation thereof; performing similarity calculation on the subject entity embedding vector, the candidate answer entity embedding vector and the target question embedding vector to obtain a target candidate answer entity set; extracting a relation path set from the subject entity to the target candidate answer entity from the target knowledge graph, and obtaining a target relation path embedding vector based on the relation path set; and performing similarity calculation on the target question embedding vector and the target relation path embedding vector to complete answer reasoning. According to the method, the accuracy and efficiency of knowledge questions and answers are improved by combining a multi-hop reasoning technology.

The invention relates to a power grid business intelligent auditing method based on AI enhancement, and the method comprises the following steps: S1, collecting data from a power grid SCADA system and a financial system, integrating historical and real-time data, and constructing an auditing knowledge graph; s2, constructing an instruction recognition model by using RoBERTa to analyze a natural language instruction of an auditor, and combining knowledge graph information with a language model to improve the understanding and reasoning ability of an instruction background; s3, constructing a multi-task deep learning framework to realize processing and fusion of multiple auditing tasks; s4, on the basis of a natural language instruction input by an auditor, extracting query targets, conditions and parameters involved in the instruction according to the instruction recognition model, obtaining corresponding auditing data in the database, and obtaining intention classification; and S5, calling a corresponding auditing model based on the intention classification result and the auditing data, and obtaining an analysis result. According to the invention, efficiency and precision in power grid business auditing work are effectively improved.

The invention provides a large model and mapping knowledge domain fusion method, application method and system, and the method comprises the steps: carrying out the mapping knowledge domain embedding of an obtained mapping knowledge domain to generate mapping knowledge domain embedded information, and generating a natural language question based on the mapping knowledge domain embedded information; the knowledge graph embedded information and the natural language question sentences are input into an entity relation learning model, entity expressions and relation expressions corresponding to the natural language question sentences are output, then sub-graphs corresponding to the natural language question sentences are extracted based on the natural language question sentences, the entity expressions and the relation expressions, and the sub-graphs are converted into natural languages one by one. And combining the entity relationship learning model and the knowledge graph embedded information into the large model to generate a target reasoning model so as to realize fusion of the knowledge graph and the large model. Therefore, the model can extract key information and perform deep understanding and reasoning, the reasoning ability of the model in processing complex problems is enhanced, and the definition and interpretability of subsequent output contents of the model are further improved.

The invention discloses an industrial pollution knowledge relation extraction method based on enhanced knowledge retrieval and large language model collaborative optimization, and is applied to the technical field of relation extraction. According to the method, firstly, training data related to a target sentence is obtained through query, the similarity between the data and the target sentence is evaluated through cosine similarity calculation, and retrieval results are sorted; the target sentence and the sentences similar to the target sentence are input into a prompt generator, and an instruction containing the specific entity pair is constructed. Then, in combination with the large language model and a hint generator, potential relationships are predicted and generated. And finally, performing fine tuning on the large language model by adopting a parameter efficient fine tuning framework so as to adapt to a specific relationship extraction task. And the triad relationship in the sentence can be automatically extracted by the fine-tuned large language model according to an input prompt, and a final reasoning result is output in a triad form. By means of the process, the accuracy and efficiency of extracting the Chinese relation in the industrial pollution field are improved.

The invention discloses a visual detection optimization method and system based on data set classification. The method comprises the steps of introducing a scene classification label and carrying out standardization processing on scene features in a data set labeling and preprocessing stage, and carrying out scene classification multi-task learning in a model selection and training stage, so that a model dynamically adjusts feature learning in different scenes, and the multi-scene adaptive capacity is improved. And in the model evaluation and verification stage, scene-based hierarchical evaluation is introduced and corresponding optimization is carried out. In the model deployment and reasoning stage, a dynamic scene is introduced to adapt to reasoning, and the reasoning path of the model is dynamically adjusted to adapt to the characteristics of the scene, so that the reasoning accuracy is improved. In the later optimization, scene feature clustering and transfer learning are used, and the multi-scene performance of the model is optimized. According to the method, under the condition that the model is not jointly trained through multiple data sets, the multi-scene adaptive capacity of the visual detection model is improved through data set classification.

The invention provides an interpretable AI inference method and system for self-supervised neural symbol fusion, and the method comprises the steps: S1, a self-supervised learning module: extracting feature information of unlabeled data, and obtaining a feature vector representing symbol knowledge; s2, a neural symbol fusion module: constructing a deep learning framework by using an AI intelligent learning strategy, and training feature vectors in combination with a reward function to obtain structured knowledge; s3, an explainable reasoning module: constructing an explainable prediction model based on neural symbol fusion, and obtaining a solved reasoning result; in the process of explaining the reasoning result, the complex reasoning process is simplified and displayed. Therefore, not only are the advantages of the neural network in processing complex modes and data association kept, but also the interpretability and logical reasoning ability of symbol reasoning are introduced, so that the performance and interpretability of the whole system are improved. Therefore, the model can optimize feature representation and logical reasoning at the same time in the training process.

The invention discloses an intelligent agent method for complex question and answer reasoning of a figure knowledge graph based on a large model. The method comprises the steps that on the basis of multiple recall modes, corresponding prompt examples are dynamically matched according to questions to be answered, and the multiple recall modes comprise any one of embedded vector similarity matching, character string fuzzy matching and fusion matching; key entity recognition, relation screening and multi-candidate entity recursion search of the question to be answered are carried out by using a large language model in a few-sample prompt mode, and a candidate entity set of each sub-question of the question to be answered is obtained; and on the basis of the to-be-selected entity set, thinking and actions are iteratively generated in an intelligent agent mode by utilizing a large language model, and through an observation result obtained through interaction with the knowledge graph, a final answer is obtained after multiple rounds of interaction. According to the method, the reasoning ability of the large language model is enhanced with high-quality prompts.

The invention discloses a financial knowledge graph reasoning method and system based on multilayer path semantic modeling. The method comprises the steps that a financial knowledge graph to be reasoned is collected; constructing a reasoning model based on multilayer path semantics; and completing the inference of the financial knowledge graph by using the inference model. According to the method, the confidence coefficient of the triple is comprehensively evaluated from two levels of path context semantics; in addition, the understanding ability of the pre-training language model for path semantics is remarkably enhanced. Multiple tests are carried out on a reference data set, and it is shown that the reasoning ability of the model can be effectively improved.

The invention relates to a knowledge graph optimization method based on a large language model. The method is suitable for the field of knowledge graph technology and natural language processing technology. According to the technical scheme, the knowledge graph optimization method based on the large language model is characterized by comprising the steps that entities in a knowledge graph to be optimized are obtained, clustering is carried out based on semantic feature vectors of the entities, and subdivided entity classifications of all the entities are obtained; any two entities belonging to different subdivided entity classifications are subjected to relation description through a large language model, and relation language description between different classification entities is generated; updating the knowledge graph to be optimized on the basis of the generated relational language description among the different classification entities; performing deep reasoning on the updated knowledge graph to further mine and discover implicit relationships among entities in the knowledge graph; and updating the knowledge graph again based on the implicit relationship among the entities to obtain an optimized knowledge graph.

The invention provides an automatic generation method and system for a novel promotion video based on a multi-modal large model in the technical field of digital content creation, and the method comprises the following steps: S1, extracting a novel text through analyzing a URL link, a TXT format, a DOCX format or a PDF format document, performing analysis and segmented structured processing on the novel text through an NLP technology to obtain structured data; s2, performing compliance check and optimization on the structured data to obtain compliance data; s3, analyzing and extracting the compliance data based on a thinking chain to generate a shot script; s4, acquiring subtitles and picture cues based on the shot script, synthesizing an audio based on the subtitles, and generating a picture group based on the picture cues; and S5, automatically generating a promotion video of the novel text based on the audio and the picture group. The novel promotion video generation method has the advantages that the novel promotion video generation efficiency is greatly improved, and the novel promotion video generation cost is greatly reduced.

The embodiment of the invention discloses a dangerous chemical identification method, and the method comprises the steps: obtaining chemical information data, and constructing a dangerous chemical semantic database according to the chemical information data through employing a deep learning multi-modal data fusion algorithm; according to naming rules and attributes of chemicals, defining text variables and numerical variables, extracting hazardous chemical judgment conditions from the chemical information data, and establishing a hazardous chemical rule base according to the text variables, the numerical variables and the hazardous chemical judgment conditions; according to the chemical information data, establishing a hazardous chemical data model based on a graph neural network technology; constructing a hazardous chemical substance identification system by using the hazardous chemical substance semantic library, the hazardous chemical substance rule library and the hazardous chemical substance data model; and obtaining to-be-classified chemical information, and classifying to-be-classified chemicals in the to-be-classified chemical information by using a hazardous chemical identification system to obtain a hazardous chemical judgment result. According to the invention, more intelligent and accurate dangerous chemical identification is realized.

The invention discloses a Text-to-SQL (Structured Query Language) model construction method and device, a Text-to-SQL model generation method and device, equipment and a medium. The construction method specifically comprises the following steps: acquiring an original training data set; performing data enhancement on the original training data set to obtain an enhanced training data set; and training a preset generation model based on the enhanced training data set to obtain an SQL generation model, and determining a Text-to-SQL model based on the SQL generation model. According to the method, the original SQL data in the training data set is expanded into the enhanced SQL data pair, and the enhanced reasoning data pair is formed based on the reasoning process of the original SQL statement, so that manual writing is not needed, and the labor cost and the time cost are reduced.

The invention provides a configurable caching method and system for an artificial intelligence reasoning process. According to the method, a cache interface layer is introduced to be integrated with an artificial intelligence framework, flexible cache strategies including a cache key generation method, a storage mode, cache capacity, an elimination strategy and the like are defined by utilizing a user configuration module, and a cache key generator is used for generating cache keys according to the strategies. The cache storage manager is responsible for managing storage, retrieval and updating of cache data and supports various storage rear ends. In the reasoning process, the cache querying and updating module is responsible for querying and updating the cache. The system can also comprise a performance monitor and a data security module which are respectively used for monitoring cache performance indexes and ensuring data security. The corresponding system comprises a cache interface layer, a user configuration module, a cache key generator, a cache storage manager and a cache query and update module. According to the method, the artificial intelligence reasoning efficiency can be improved, the resource utilization is optimized, a flexible and configurable cache solution is provided, and the method is easy to integrate with a mainstream artificial intelligence framework and adapts to different task requirements.

The invention provides a multi-modal knowledge graph privacy protection embedding method for diagnosis and treatment data, and relates to the technical field of data processing, and the method comprises the steps: carrying out the initialization embedding processing of text information and numerical information based on the diagnosis and treatment data, and carrying out the initialization embedding processing of visual information based on medical image visual data; obtaining a multi-modal attention coefficient of a neighbor entity by using a multi-modal diagram self-attention layer; fusing the structured information of the multi-modal knowledge graph by stacking a plurality of encoder layers; and the multi-modal knowledge graph privacy protection embedding is scored by using the convolution embedding model. According to the method, efficient embedding and deep fusion of multi-modal information are effectively achieved, the processing capacity of heterogeneous data is enhanced, sensitive information is prevented from being leaked through the embedding process, an end-to-end privacy protection mechanism is provided, and the safety and reliability of diagnosis and treatment data in the analysis and reasoning process are ensured.

The invention aims to provide a knowledge graph construction method and system based on large-model multi-agent interaction. The method comprises the following steps: acquiring agricultural data; screening agricultural entity data from the agricultural data; calculating a relationship among the agricultural entity data by adopting an LLM model; the multi-agent interaction module corrects the relationship among the agricultural entity data through role playing; and constructing an agricultural knowledge graph according to the corrected agricultural entity data. According to the method, entity relation extraction and reasoning are enhanced by using a multi-agent interaction and role playing technology, a special model for entity extraction and a large language model (LLM) for relation extraction are combined, and integration is performed through a multi-agent framework.

The invention discloses a data processing method and device, equipment, a medium and a program product in the technical field of computers. In the initialization stage of model reasoning, a first cache region and a second cache region are created; if the model reasoning request is received, contextual information of a preprocessing stage of the model reasoning request is stored in a first cache region; based on the context information in the first cache region, executing each decoding operation in a decoding stage of the model reasoning request; wherein the context information of the previous decoding operation is stored in the second cache region, and the next decoding operation of the previous decoding operation is executed based on the context information in the second cache region. According to the scheme, on the basis of the principle of changing space into reasoning efficiency, the context information of the preprocessing stage and the context information of the decoding stage are stored in the two cache regions respectively, the model reasoning performance and efficiency are improved, the model structure does not need to be changed, and the model can be quickly online and applied.

The invention is suitable for the technical field of inquiry, and particularly relates to a method and system for carrying out artificial intelligence inquiry on pet diseases, and the method comprises the steps: S100, creating a distributed architecture composed of a cloud end and terminal equipment, and deploying a pre-training language model and a knowledge base in the cloud end; s200, pet case data in different formats are collected, the case data at least comprise symptom description, diagnosis results and treatment schemes, the pet case data are preprocessed and segmented into a plurality of single items, semantic extraction is carried out on the single items to obtain key information, and a preset multi-modal fusion model is utilized to carry out multi-modal fusion on the key information; and fusing the single items in different formats, and configuring a corresponding relationship among all the single items. The multi-dimensional knowledge graph is generated, the accuracy and comprehensiveness of diagnosis are greatly improved, the pre-training language model and the knowledge base are integrated, so that the distributed architecture can continuously self-evolve, and the accuracy of diagnosis is gradually improved.

The invention provides a legal text generation method, system and device for artificial intelligence interaction, and belongs to the field of distributed big data, a plurality of query statements are sequentially input into a generative pre-training language model, and the plurality of query statements have a continuous semantic relationship; the generative pre-training language model generates each query statement in sequence to obtain each output statement; performing triple extraction on each output statement by utilizing a legal information extraction model to obtain a legal knowledge triple set corresponding to each output statement; and performing triple knowledge processing on each legal knowledge triple set, and generating a legal text by using the legal argumentation triple. According to the method, the efficiency and accuracy of legal document generation can be remarkably improved, and artificial intelligence can conclude and screen in man-machine interaction multiple questions and answers, long dialogues and complex legal discussion scenes to provide accurate and coherent natural language output.

The invention provides a domestic hardware-oriented visual model operator optimization method and device, which are applied to a visual model, and the method comprises the steps: expanding a plurality of position coding modes of the visual model according to a relative position code and a condition position code of a relative position coding module of the visual model, performing position coding on the visual model based on a plurality of position coding modes to obtain a structure-optimized target visual model corresponding to each position coding mode, inputting a preset target picture into one target visual model, performing operator abstraction on the target visual model to obtain a corresponding abstracted target visual model, and displaying the abstracted target visual model in a display screen. And obtaining a corresponding relationship between the neural network operator and a domestic hardware operator provided by the domestic hardware, and implementing the neural network operator on the domestic hardware based on the corresponding relationship.

The invention discloses a data reasoning method, system and device and a storage medium, and the method comprises the steps that a master node generates a query vector, a key vector and a value vector based on an input lexical element of a current layer of a Transform model, and adds the key vector and the value vector to a local key value cache of the master node; the master node broadcasts query vectors to a plurality of slave nodes through network equipment; the plurality of nodes perform attention calculation based on the query vector and the local key value caches of the plurality of nodes to obtain initial attention vectors corresponding to the plurality of nodes; the plurality of slave nodes send respective initial attention vectors to the master node through the network device; the network device performs aggregation processing on the initial attention vectors corresponding to the plurality of slave nodes to obtain a target attention vector; and the main node performs model reasoning based on the target attention vector through a Transform model to obtain an output lexical element. Therefore, the reasoning time can be reduced, and the network bandwidth requirement is reduced.

The invention discloses an explicit-implicit relationship collaborative extraction method and device based on a large model and a pre-training model, and the method comprises the steps: 1, obtaining a word vector of a text through a pre-training language model, building a word-level table labeling frame based on the word vector of the text, and building a table labeling frame based on the word level; obtaining an explicit entity relationship triple in the text; wherein the pre-training language model is BERT; 2, acquiring implicit knowledge in the text from the GPT model as an external knowledge source; 3, performing instruction fine tuning by fusing the open source large language model with implicit knowledge and prompts, and performing reasoning through texts and implicit knowledge to obtain an implicit entity relationship triple; and 4, systematically integrating the explicit and implicit entity relationship triples obtained from the text by the open source large language model fused with implicit information fine adjustment and the pre-training language model, and finally obtaining a combined triad.