489 results about "Inference system" patented technology

The invention provides an operation and maintenance alarm processing method and system based on a knowledge graph enhanced large model, and relates to the technical field of knowledge graphs, and the method comprises the steps: collecting multi-source operation and maintenance alarm historical data, carrying out the adaptive hierarchical structured processing of the data, and constructing a space-time semantic multi-dimensional feature matrix; constructing a multi-dimensional alarm association network based on a dynamic weight fusion algorithm and forming a hierarchical knowledge graph; constructing a root cause inference rule base in combination with time sequence evolution, topology propagation and business dependence characteristics of the alarm; and when a real-time alarm is received, a diagnostic reasoning system is started to analyze a propagation link, a root cause is identified, and a processing suggestion is generated. The method can accurately identify the alarm root cause, improves the operation and maintenance efficiency, and reduces the false alarm rate.

The invention discloses a multi-modal knowledge graph rule reasoning method and device based on a large model, and the method comprises the steps: carrying out the feature extraction and cross-modal alignment of input text data and image data, and generating a multi-modal feature vector of a unified semantic space; performing knowledge graph storage on the emotion entities and the relationships by adopting an attribute graph model to complete construction of an emotion knowledge graph; generating an interpretable inference rule from the emotion knowledge graph by using a large language model, and eliminating a conflict rule in combination with logic verification; calculating the confidence coefficient of a reasoning path based on an attention mechanism, and carrying out quantitative evaluation on a rule reasoning result; the knowledge graph and the rule base are updated online according to user feedback, and the real-time performance and accuracy of the inference system are optimized through weight adjustment and a forgetting mechanism. According to the method, through innovative technologies such as multi-modal data integration, dynamic knowledge evolution and interpretability reasoning, the limitation of a traditional sentiment analysis method in the aspects of evidence dimension, adaptive capacity, interpretability and the like is broken through.

The invention discloses an unmanned ship multi-mode perception and decision support method and system based on fuzzy logic and a rule engine, and the method comprises the steps: obtaining multi-source sensor data, carrying out the standardization processing, calculating a dynamic weight coefficient based on information entropy, and carrying out the data fusion; mapping the fusion data to a feature space, analyzing feature correlation, and evaluating an environmental threat degree; performing fuzzy partitioning on the feature space and generating an initial rule, and optimizing a rule set through information gain; a fuzzy inference system is constructed and cooperatively operated with a rule engine, and collaborative decision parameters are optimized; and performing multi-level risk assessment and generating a level decision, and optimizing a decision instruction through reinforcement learning. According to the method, the sensing accuracy and decision reliability of the unmanned ship in a complex sea condition environment are improved through multi-modal data adaptive fusion and collaborative decision of the fuzzy logic and the rule engine, and the method has good engineering application value.

The invention provides an operation business risk analysis method, device and equipment and a storage medium, and the method comprises the steps: carrying out the multi-modal preprocessing of multi-source heterogeneous data, generating a structured risk feature data set, carrying out the staged training and dynamic optimization of a preset multi-branch deep neural network model, and obtaining a structured risk feature data set; and obtaining a trained risk analysis model. And carrying out distributed deployment and streaming processing configuration on the model, and constructing a real-time risk inference system. And inputting real-time operation business data into the system, and generating a risk analysis result and corresponding feature importance distribution. And through a multi-model integration framework, carrying out comprehensive assessment and interpretability analysis on a risk analysis result and feature importance distribution to form a comprehensive risk assessment report. According to the method, through multi-modal preprocessing of multi-source heterogeneous data, risk features of different data sources are fully mined and fused, and the problem of inaccurate analysis caused by single data and unprocessed heterogeneity in a traditional method is solved.

The invention belongs to the field of data processing, and particularly relates to a dynamic cooperative control system and method for a gas turbine and a micro-grid, and the method comprises the steps: constructing a micro-grid real-time monitoring module, continuously collecting distributed energy real-time output, controllable load demands, bus voltage frequency and equipment state parameters, and carrying out the filtering and noise reduction through a preprocessing unit, thereby guaranteeing the data precision; calculating a real-time power difference value based on the preprocessed data, calling an adaptive neural fuzzy inference system, taking the power difference value, the bus voltage deviation and the frequency deviation as input, and judging whether the power difference value, the bus voltage deviation and the frequency deviation exceed a preset threshold value by means of a fuzzy rule base and a neural network model; if the threshold values are not exceeded, the current states of the gas turbine and the energy storage system are maintained; if any one exceeds the threshold value, a dynamic cooperative control instruction is triggered, precise cooperative control of the gas turbine and the micro-grid is achieved, and the operation stability, the operation efficiency and the reliability of the micro-grid are improved.

The invention discloses a driving behavior risk assessment method and system, and relates to the technical field of intelligent traffic and driving safety, and the method comprises the steps: collecting the operation parameter data of a vehicle, carrying out the feature extraction of the operation parameter data, extracting feature parameters to form a feature vector, and calculating the Mahalanobis distance score of the feature vector; according to the Mahalanobis distance score of the feature vector, carrying out risk grade division by adopting an improved hierarchical fuzzy inference system to obtain a risk grade score; and establishing a driver portrait model according to the risk level score, and when the risk level score exceeds a personalized risk threshold, outputting a driving risk behavior improvement suggestion to complete driving behavior risk assessment. According to the invention, a refined grading basis is provided for individual risk monitoring of the driver, dynamic monitoring and real-time intervention of driver behaviors are realized, traffic accidents can be reduced, and driving safety is improved.

One or more embodiments of the invention provide a load-aware scheduling method of an inference system and the inference system. The method is applied to a global scheduler in the inference system. The inference system further comprises an inference engine. The inference engine comprises at least one computing instance deployed on each computing node in a computing cluster; computing resources of the computing examples comprise GPUs carried on the computing nodes where the computing examples are located; the global scheduler maintains dynamically updated GPU load information of each calculation instance; the method comprises the steps of obtaining a to-be-executed target reasoning request; based on the maintained GPU load information of each calculation instance, determining a target calculation instance of which the GPU load meets a preset condition; and sending the target reasoning request to the target calculation instance, so that the target calculation instance executes the target reasoning request.

A database structure obtained by means of information retrieval, and a reasoning system, which structure and system specifically relate to a gut microbe knowledge graph system, comprising: a gut microbe knowledge graph consisting of a gut microbe knowledge base, a gut microbe and small-molecule drug therapy association knowledge base, and a clinical medicine database; and a multimodal uncertainty reasoning system, using the gut microbe knowledge graph. The gut microbe knowledge graph system predicts potential diseases, drugs, genes, etc., which are associated with gut microbes.

The invention discloses an e-commerce live broadcast real-time interaction quality evaluation system based on edge calculation, and relates to the technical field of e-commerce live broadcast, and the system comprises a multi-modal interaction data collection module which collects multi-modal interaction data of a live broadcast stream in real time through a distributed edge calculation node cluster, and constructs a multi-dimensional quality feature vector, the multi-modal interaction data comprises a video coding parameter, an audio quality index, user interaction behavior data and network transmission state data; according to the invention, the distributed edge computing node cluster collects the multi-modal interaction data of the live stream in real time, the lightweight space-time attention neural network model carries out data fusion processing, the deep reinforcement learning network generates a quality optimization scheme, and the adaptive fuzzy inference system corrects the optimization scheme in real time. And dynamic parameter adjustment is carried out in combination with network bandwidth fluctuation and a terminal device resource state, so that the effect of accurately and comprehensively evaluating the e-commerce live broadcast interaction quality in real time is achieved.

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based electric energy quality disturbance identification and positioning method, which comprises the steps of constructing an electric energy quality disturbance signal data set, performing segmented preprocessing on electric energy quality disturbance voltage data, enhancing time-frequency joint features and encoding disturbance sensitive areas. And constructing a deep learning model for power quality disturbance identification and positioning, and identifying and positioning the power quality disturbance. According to the invention, through adaptive denoising processing, boundary detection and multi-resolution time-frequency feature extraction, the identification precision and positioning precision of power quality disturbance are significantly improved; self-adaptive wavelet denoising and dynamic segmentation are combined, noise interference is effectively suppressed, and the edge characteristics of voltage sudden change points are kept; according to the dual-task sharing network, disturbance identification and positioning tasks are cooperatively optimized, so that the network can consider disturbance classification and time positioning at the same time; and through Bayesian reasoning, the system can output confidence estimation, provides credibility quantification of identification and positioning results, and effectively improves the reliability of the system.

The invention provides a crop planting intelligent decision inference system and method based on multi-source data fusion, and relates to the technical field of agricultural planting, and the system comprises a multi-source data fusion module which is used for extracting key characteristics of target crop growth according to multi-source data; the intelligent sensing module is used for constructing an agricultural knowledge graph according to the multi-source heterogeneous data of crop planting; and the reasoning and decision-making module is used for performing decision-making reasoning on the multi-source data and the key features according to the agricultural knowledge graph, a preset reasoning model and a decision-making model. According to the crop planting decision-making system, the defects that the precision in the planting management process is not high due to the fact that a traditional crop planting decision-making system is insufficient in decision-making ability, and the generalization ability of the system is insufficient due to the fact that most decision-making systems are optimized in a single field or specific crops and lack a cross-field multi-source data cooperative processing mechanism are overcome.

One or more embodiments of the invention provide a load-aware scheduling method of an inference system and the inference system. The method is applied to the inference system comprising a global scheduler and an inference engine. The inference engine comprises a Prefill engine and a Decode engine; the Prefill engine and the Decode engine respectively comprise at least one calculation instance; computing resources of the computing instances comprise GPUs carried on the computing nodes where the computing instances are located; the method comprises the following steps: a global scheduler obtains a target reasoning request to be executed, determines a first calculation instance in a Prefill engine of which the GPU load meets a first preset condition based on maintained GPU load information, and sends the target reasoning request to the first calculation instance to execute reasoning calculation in a Prefill stage; and a first local scheduler corresponding to the first calculation instance in the Prefill engine determines a second calculation instance in the Decode engine with the GPU load meeting a second preset condition based on the maintained GPU load information, and sends an inference calculation result of the Prefill stage to the second calculation instance to execute inference calculation of the Decode stage.

The invention discloses a large language model end-cloud collaborative inference system based on low-rank fine tuning, and belongs to the technical field of inference optimization of end-side cloud computing. Establishing an end-cloud collaborative reasoning architecture, and in an offline stage, performing parameter fine tuning on a large language model by a cloud side based on training data of different downstream tasks; in the online stage, user requests are classified through'variational auto-encoder-Gaussian mixture model 'clustering, whether a low-rank adapter matched with a current task exists in an end side cache is judged, and if yes, reasoning is executed on the end side; and otherwise, forwarding the task to the cloud side. After a plurality of user requests are processed by the architecture, historical user requests and cache states are analyzed based on a Mama model, and an end-side low-rank adapter library is dynamically updated. And monitoring end cloud load and reasoning delay in real time, and issuing the new adapter to the end side according to the task repetition rate increment. According to the method, dynamic balance of the system is realized, and high efficiency and adaptability of the system are ensured while calculation and storage overhead are reduced.

The invention relates to an electric power virtual simulation optimization method based on a digital twin technology, and the method comprises the following steps: S1, deploying sensors at key nodes of an electric power system, and integrating an intelligent electric meter, weather forecast, social media information and market data to form a comprehensive data pool; s2, constructing a digital twinborn model of the power system; s3, optimizing the digital twin physical model based on a Bayesian optimization method and an adversarial neural network; s4, applying a bee colony algorithm to formulate a cooperation strategy, and optimizing transmission and load adjustment of power in different areas; s5, introducing an adaptive neural fuzzy inference system, and further optimizing a cooperation strategy; and S6, based on the optimized digital twinborn model and the operation strategy, performing large-scale distributed simulation by using cloud resources. According to the invention, accurate construction of the electric power simulation model and accurate implementation of electric power virtual simulation are realized.

The invention relates to an inference system and method for a large model. The system comprises a routing component, a pre-fill component, a decoding service component deployed independently of the pre-fill component, and a communication component between the pre-fill component and the decoding service component. The routing component routes the data processing request before long to the pre-filling component for pre-filling processing based on the token information of the current data processing request, and routes the data processing request before short to the decoding service component for decoding processing; and performing load balancing routing based on the load states of the plurality of reasoning forces in the prefill component or the decode service component.

Deep learning inference for imaging systems includes an imaging device comprising an image capture component and a vision processing unit configured to process the image through a first trained inference network to determine a first inference result. A host system trains a neural network for image classification and produces and transmits the first trained inference network to the vision processing unit of the imaging device. The first trained inference network provides stand-alone image classification, an object detection and / or a confidence score to the imaging device. The vision processing unit may further comprise a two or more trained inference networks configured to receive an inference result as an input and output a second inference result. A stereo camera system uses features and / or results from one or more inference network to control processing of three-dimensional data for the detected object.

The invention discloses a multi-agent large-model disease diagnosis knowledge reasoning system based on data dual drive, and relates to the technical field of artificial intelligence assisted medical diagnosis. The system collects patient symptom follow-up records, laboratory test results, observation diagnosis probabilities and expert diagnosis recommendation results in a multi-source manner; time sequence evolution characteristics are extracted, a time sequence diagnosis sensitivity coefficient is calculated, and early recognition of disease risks is achieved; in combination with anti-fact simulation and statistical reasoning, a causal consistency coefficient is obtained and is used for verifying causal reasonability of observation diagnosis and contrast results; based on agent group consensus analysis, calculating a game consistency coefficient for judging the credibility of a diagnosis conclusion; positioning and multi-level verification are carried out on abnormal reasoning steps and knowledge fragments, so that the reliability and safety of a result are guaranteed; continuous optimization of the diagnosis model is realized through a log analysis and knowledge backflow mechanism; according to the invention, the accuracy, interpretability and safety of disease diagnosis can be obviously improved.

The embodiment of the invention discloses an inference method and device for a large language model, which are used for reducing bandwidth consumption of inference of the large language model. The method comprises the steps that a parallel reasoning system receives reasoning tasks of a large language model, wherein the reasoning tasks comprise a calculation-intensive task and a self-attention calculation task; the processor executes calculation-intensive tasks, generates intermediate data and sends the intermediate data to the near-memory calculation module, and the calculation-intensive tasks comprise one or more of the following tasks of the large language model: a feedforward neural network calculation task, a projection task and a layer normalization task. And the near memory calculation module executes a self-attention calculation task according to the intermediate data to generate a near memory calculation result. And the processor generates a reasoning result corresponding to the reasoning task based on the proximity calculation result.

The invention discloses a memory limited device MoE large model reasoning optimization system and method based on dual prediction, and belongs to the technical field of MoE large model reasoning optimization. In order to solve the problem of optimizing the reasoning performance of the LLM based on the MoE on the memory limited equipment, the system comprises a layer-by-layer predictor, a token-by-token predictor and an expert management module, and the expert management module comprises an expert cache, a temporary expert buffer area and an I / O scheduler. The layer-by-layer predictor is connected with the token-by-token predictor, the layer-by-layer predictor and the token-by-token predictor are respectively connected with the I / O scheduler, the token-by-token predictor is connected with the expert cache, and the I / O scheduler is respectively connected with the temporary expert buffer area and the expert cache. According to the method, a predictive expert Cache, a temporary expert buffer area and a token-by-token prefetching technology are innovatively provided; according to the invention, the reasoning system can use fewer memory resources, and the LLM reasoning speed is obviously improved.

The invention discloses an edge end large language model inference system. The system comprises a main computing chip, an LPDDR interconnection resource and a vertically stacked and packaged storage chip stack, the storage chip stack comprises an NAND flash memory chip and a DRAM (Dynamic Random Access Memory) chip, and the NAND flash memory chip and the DRAM chip are paired and share an LPDDR interconnection resource; the NAND flash memory chip comprises a flash memory chip bare chip and a CMOS (Complementary Metal-Oxide-Semiconductor Transistor) chip bare chip which are three-dimensionally interconnected based on hybrid bonding; a flash memory array is arranged on the flash memory chip bare chip; a logic block is arranged on the CMOS chip bare chip; the main calculation chip reads a parameter matrix of a model full connection layer from the NAND flash memory chip and reads other parameters from the DRAM chip for calculation in a pre-filling stage of large language model reasoning; and the NAND flash memory chip performs full connection layer calculation in a decoding stage. The system provided by the invention can improve the external transmission and internal reading bandwidth.

Disclosed in the present invention is a global delay optimization-oriented cloud-edge-end collaborative CNN inference method. A block inference delay prediction model is constructed and trained, theoretical data transmission delay is calculated, a delay loss prediction model is constructed and trained, and a global delay prediction model is constructed; the global delay prediction model is used to calculate the theoretical global delay of each edge server, and the minimization of global delay is taken as an optimization objective, so as to determine the selection of an edge server participating in collaborative inference and the allocation of inference task volumes. The present invention also provides a global delay optimization-oriented cloud-edge-end collaborative CNN inference system. Compared with conventional collaborative inference research work which focuses only on delay optimization of current inference tasks in terms of delay indicator settings, the method takes possible delay influence of processing of current inference tasks on other inference tasks processed in parallel into consideration for decision making. In addition, the present invention further provides a CNN segmentation optimization method, which can effectively reduce the decision-making delay in collaborative inference.

The invention relates to the technical field of network security, and provides an APT attack traceability and path restoration method and system, attack path validity is verified through a dynamic causal element path generator in combination with an anti-factual adversarial network, and fine-grained entity modeling is realized through a hierarchical multi-modal entity inference system. A causal attention mechanism is optimized to improve association analysis precision, a federal incremental learning framework is constructed to realize dynamic updating and privacy protection, and the problems of poor rule adaptability, coarse granularity of entity modeling, insufficient causal association distinguishing and low calculation efficiency in the traditional technology are effectively solved. The method has the technical effects of dynamically generating an effective attack path, improving attack traceability accuracy, reducing calculation overhead and enhancing privacy protection.

Disclosed is an adaptive deep learning inference system that adapts to changing network latency and executes deep learning model inference to ensure end-to-end data processing service latency when providing a deep learning inference service in a mobile edge computing (MEC) environment. An apparatus and method for providing a deep learning inference service performed in an MEC environment including a terminal device, a wireless access network, and an edge computing server are provided. The apparatus and method provide deep learning inference data having deterministic latency, which is fixed service latency, by adjusting service latency required to provide a deep learning inference result according to a change in latency of the wireless access network when at least one terminal device senses data and requests a deep learning inference service.

The invention discloses a cloud-side collaborative inference method and inference system, and the method comprises the steps: edge equipment receives a user task request, and sends a task notification to cloud equipment; the cloud equipment controls a deployed cloud large model to execute a user task, and sends a task intermediate result to the edge equipment; and the edge device executes the user task based on the task intermediate result and the user prompt to obtain a task result, and feeds back the task result to the user side. According to the application, the edge device cooperates with the cloud device, the edge device shares the task intermediate result in the reasoning process of the cloud device, and the user prompting user task with high real-time performance and low resource consumption is processed based on the task intermediate result, so that on one hand, the computing power of the cloud device can be utilized; and on the other hand, communication delay and data transmission quantity can be reduced, so that high delay caused by the fact that data transmission occupies a large amount of bandwidth can be reduced on the premise of ensuring that a user task can be executed.

Various examples, systems, and methods are disclosed relating to an agentic curation pipeline. One system can process questions and other inquiries about video content by using a combination of models and stored information. The system can receive a query related to an event in a video, selects relevant portions of the video using embeddings, and apply the selected video data and a related sub-query to a video model. The output from the video model can be used by a language model, along with stored context, to generate an answer to the original query. The system can returns the answer to the requester.

The invention belongs to the technical field of intelligent question-answering systems, and particularly relates to an intelligent question-answering inference system based on a knowledge graph, which is characterized in that firstly, a knowledge graph construction module fuses multi-source data to generate a structured graph, and after a user inputs a natural language question, a question-answering analysis module completes intention classification and entity disambiguation and converts the question into structured query; an inference engine module fuses symbol rules and graph neural network inference through a hybrid inference sub-module, and a dynamic weight adjustment sub-module optimizes weights according to errors and attenuation factors to generate an inference result; the knowledge updating module incrementally updates the atlas in real time and detects conflicts, the interactive interface module visually presents a result, and the evaluation optimization module iteratively optimizes parameters in combination with offline evaluation and online feedback. The whole process is from user question asking to result output, accurate reasoning and continuous performance improvement are achieved, and multi-field question and answer requirements are met.

The invention provides a vehicle fault diagnosis method and device based on multi-source data fusion and a storage medium. The method comprises the following steps: collecting real-time state data and real-time alarm data of a target part, and obtaining external environment data and map navigation data; preprocessing the data, fusing the preprocessed data to obtain a multi-source data set target feature, inputting the target feature extracted from the multi-source data set into an adaptive neural fuzzy inference system, mapping the target feature to a plurality of fuzzy sets, and fuzzifying by using a member function; calculating the rule weight of each target feature to reflect the fuzzy intensity; and training an inference system by adopting a neural network learning algorithm, adjusting a member function and a rule weight, and converting fuzzy output into a specific numerical value or a fault level by utilizing an output member function in a defuzzification process so as to judge the health state of the part. According to the invention, high-interpretability fault diagnosis output is provided, the accuracy is improved, and fault diagnosis can be carried out in a wide vehicle operation environment.

The invention relates to the technical field of network security and data processing, and discloses a violation short message recognition method and system based on deep semantic understanding, and the method comprises the steps: firstly cleaning an original short message, generating a mixed embedding vector through characters, sub-words and pinyin, and carrying out the recognition of the violation short message; then processing through a double-layer detection engine, wherein the first layer utilizes rules and a lightweight model for rapid preliminary screening; in the second layer, for suspected samples, a double-tower fusion neural network architecture is adopted, local and global features are combined, fusion is carried out through a gating unit, and a large language model is input to carry out deep semantic reasoning. The system executes strategies such as interception or flow limiting according to the risk score, and realizes model iteration through a dynamic knowledge base and incremental learning. According to the method, the resource consumption and the detection precision are balanced through the layered architecture, the antagonistic variants are effectively identified by utilizing multi-dimensional feature fusion, and the method has the adaptive evolution capability for a novel violation mode.

The invention discloses an efficient secret state joint neural network inference method. The method comprises the following steps: S100, a data owner C and a model owner # imgabs0 # respectively send privacy data and a privacy model to computational nodes # imgabs1 # and # imgabs2 # in a secret sharing manner; s200, computing nodes # imgabs3 # and # imgabs4 # to run a secret state joint neural network reasoning algorithm, and respectively calculating secret shares Z0 and Z1 of reasoning results by sequentially executing secret state computing layer protocols, the secret state computing layer protocols comprising: S210: a secret state convolution layer algorithm # imgabs5 #; s220, a function layer algorithm # imgabs6 # is activated in a dense state; the invention further discloses an efficient dense state joint neural network inference system. According to the technical scheme, the ReLU algorithm with few communication rounds is designed based on the function secret sharing technology, so that the communication cost required for calculating the activation function is reduced, the convolutional neural network inference sub-protocol is designed by utilizing bilateral comparison and correct symbol discrimination, the inference accuracy is improved, and the inference result is consistent with a plaintext inference result.

The invention discloses an industrial equipment fault inference system based on a knowledge graph, and the system comprises a knowledge graph construction module, a fault data collection module, an inference analysis module and a response processing module. The entity extraction unit extracts equipment components, fault types and maintenance record entities from an industrial equipment operation document, equipment manual unstructured data supplementation attributes are integrated, the attributes and association weights are marked, and the relationship construction unit establishes a fault causal relationship between the entities and a component association relationship to form a multi-level knowledge network; a knowledge verification unit verifies entity attribute consistency and relation rationality, a dynamic updating unit receives data updating nodes and relation strength of each unit and receives feedback data optimization weights, and in a fault data acquisition module, a real-time monitoring unit acquires operation parameters and state signals and associates equipment identifiers.