152 results about "Multi domain" patented technology

The invention discloses a multi-field part size and appearance defect intelligent detection system, and relates to the field of image analysis. The system comprises an image acquisition module, an image preprocessing module, a feature extraction module, a defect identification and size measurement module, a data processing and analysis module, an automatic control module and a man-machine interaction module. According to the method, CNN and LBP, Hough transform and SIFT algorithms are fused, high-level semantics and bottom-level texture / geometric features are considered, 2304-dimensional fusion feature vectors are formed through feature splicing, the feature extraction integrity of parts in multiple fields is improved, texture detail features can be accurately extracted, geometric shape features can be accurately obtained, and the method is suitable for large-scale popularization and application. Meanwhile, the adaptive feature selection mechanism dynamically optimizes the feature combination according to the detection result, the problem of calculation redundancy is reduced, and the detection precision is ensured while the detection efficiency is improved.

The invention provides a knowledge base question-answering system optimization method and device based on hybrid fine tuning and multi-dimensional evaluation and a readable storage medium thereof, and provides the following scheme: constructing a hybrid progressive fine tuning framework, fusing low rank adaptation (LoRA) and direct preference optimization (DPO), and realizing domain knowledge migration through hierarchical dynamic parameter configuration; establishing a logic-semantic-knowledge three-dimensional quantitative evaluation system, and forming closed-loop optimization by using dynamic weight fusion and a visual decision system; and designing a multi-domain prompt template library with layered parameter freezing, sparse constraint and attention driving, and realizing model lightweight and cross-domain logic constraint. According to the method, the adaptive bottleneck of a general model and domain characteristics is broken through, the small sample training efficiency and the generated content compliance are improved, the computing resource consumption is reduced, an efficient and reliable knowledge service base is provided for professional scenes such as laws, medical treatment and finance, and the technical advantages of specialization, light weight and interpretability are achieved.

The invention belongs to the technical field of remote sensing inversion, and aims to provide an automatic remote sensing inversion method and system, electronic equipment and a program product. The method comprises the following steps: acquiring full-modal remote sensing data and multi-field external data; performing space-time alignment processing on the multi-field external data to obtain multi-field space-time aligned external data in space-time matching with the fused remote sensing feature data; performing cross-modal feature fusion processing on the full-modal remote sensing data to obtain fused remote sensing feature data; inputting the fused remote sensing feature data into a preset remote sensing inversion model to obtain an initial remote sensing inversion result; and performing local correction on the initial remote sensing inversion result according to the external data after multi-field space-time alignment to obtain a final remote sensing inversion result. According to the method, high-precision and automatic inversion of the surface physical parameters in the remote sensing image can be realized, and the method is suitable for application in a complex environment.

The present application provides a multi-domain knowledge fusion method for intelligent customer service, which relates to the technical field of data processing. The method includes: determining multi-domain data sources based on big data and performing knowledge extraction, connecting multi-domain knowledge according to association mapping rules, retrieving the target needs of users, formulating a fusion strategy, screening according to the target needs, performing knowledge fusion according to the fusion strategy, complementing knowledge for the fused data according to knowledge associations, then performing knowledge domain adaptation, and optimizing according to feedback information. Through the present application, the limitations existing in the prior art in semantic understanding can be solved. For complex or ambiguous problems, the intention of the user cannot be accurately understood. The user's questions can be understood more comprehensively, the accuracy and comprehensiveness of the answers can be improved, and it can be made closer to the level of human customer service.

A scalable expert foundry system enables creation, management, and coordination of multiple specialized expert domains, each developing autonomous cognitive capabilities through geometric manifold formation while maintaining hierarchical oversight and cross-domain knowledge transfer. The system utilizes a Persistent Cognitive Machine architecture with hierarchical supervisory networks that provide multi-layered coordination, conflict resolution, and quality management across distributed expert domains. Cross-domain coordinators orchestrate communication and knowledge sharing between domains through geometric abstraction and manifold projection techniques that preserve semantic integrity while enabling beneficial knowledge propagation. Executive manifold supervisors implement second-order control architectures managing meta-cognitive capabilities and system-wide reasoning strategies. The system supports enterprise deployment across multiple geographic regions with distributed computing resources. Expert domains achieve operational readiness through statistical observables monitoring including cache hit rates, distance distribution shifts, and trajectory coherence measurements that validate manifold maturity. The architecture enables scalable expert-level performance across diverse knowledge domains while maintaining coordination effectiveness and quality standards.

The invention provides a cross-domain collaborative information tracking and positioning auxiliary method and system, and the method comprises the steps: firstly collecting an original data set generated by a target event in a plurality of associated domains, carrying out the cross-domain identifier matching processing to obtain a standardized event data set, and then carrying out the information association processing of the standardized event data set, according to the method, context semantic features and cross-domain time sequence behavior features of a target event are generated, then collaborative analysis is performed on the features based on a preset collaborative analysis model, a cross-domain collaborative tracking index set is generated, and a dynamic tracking path topology is constructed according to the cross-domain collaborative tracking index set. According to the method and the device, the target event is tracked and positioned, the positioning auxiliary strategy matched with the target event is generated, and finally the positioning auxiliary strategy is synchronized to the cross-domain tracking system to activate the cooperative positioning operation, so that the cooperative processing of multi-domain information is realized, and the target event tracking and positioning accuracy and efficiency are improved.

The invention discloses a dynamic routing parameter efficient fine tuning method and system based on LoRA-MoE, and relates to the technical field of large model fine tuning. The method comprises the following steps: firstly, constructing a heterogeneous expert architecture-based LoRA module pool based on a multi-field data set; and secondly, coding the hidden layer features of the task through a dynamic gating network, realizing continuous differentiable expert activation, and improving the balance of expert allocation by adopting temperature attenuation and entropy regularization constraint. And then, dynamically selecting and carrying out weighted fusion on a plurality of LoRA parameter increments according to task semantics in a reasoning stage, so as to realize low-cost model adaptive updating. Finally, the module pool is continuously optimized through the confusion degree and manual evaluation feedback, low-efficiency modules are automatically eliminated, and a new LoRA module is generated to maintain task coverage. According to the method, the accuracy and generalization ability of the model in a complex scene can be remarkably improved on the premise of ensuring light weight, and rapid adaptation and dynamic optimization of a large model under a low-resource condition are realized.

The invention discloses a cross-domain collaboration-oriented database integration method, system and device, and relates to the technical field of data processing, the method comprises the following steps: acquiring emergency management data of multiple fields; marking data belonging to an emergency disaster event in the emergency management data as a plurality of target entities, and determining a plurality of candidate associated words corresponding to the target entities; on the basis of the possible association degree between the target entities and the candidate associated words, the fusion matching degree between the target entities from different fields is calculated; based on the fusion matching degree, performing fusion processing on the data corresponding to each target entity to obtain fusion data; and carrying out integration processing on the emergency management data and the fusion data to obtain an emergency database. The accuracy of multi-field data fusion is improved.

The invention discloses a time prediction method and system based on double-domain feature fusion. The method and system adapt to long and short term time series prediction requirements of multiple scenes such as weather forecast, energy scheduling, traffic flow and financial exchange rate. The method comprises the steps that a multi-field data set is obtained and preprocessed, and instance normalization is carried out; performing double-domain multi-scale characteristic decomposition by adopting down-sampling and discrete wavelet transform to obtain continuous trend and high-frequency mutation details; a local unit is obtained through patch cutting and embedding, local time sequence association is mined through depth separable convolution, cross-patch global interaction is achieved in combination with a multi-layer perceptron, and local-to-global progressive fusion is completed; and constructing bidirectional attention flow enhanced cross-domain and cross-scale collaboration, and combining with standardized data training to obtain a prediction model. According to the invention, the method can improve the depiction capability of non-stable and non-linear complex time sequence data containing abrupt change and multi-period superposition, gives consideration to the adaptability of long and short term prediction, remarkably improves the accuracy of multi-field time sequence prediction, and promotes the application of the prediction technology in multiple scenes.

The invention discloses a model multiplexing-based image-text retrieval graph network method, which comprises the following steps of: firstly, constructing a multi-field image-text pair data set from an internet public data source according to a user demand, performing multi-stage data cleaning by utilizing a pre-training model to ensure the data quality, and secondly, multiplexing a large-scale pre-trained multi-modal model as a feature extractor to obtain a multi-domain image-text pair data set; the deep semantic representation of the image text pair is efficiently obtained, and the model training cost is remarkably reduced. Then, a heterogeneous topological structure is designed, image text nodes respectively form same-proton graphs, and cross-modal edges are dynamically generated through learnable attention weights; and finally, by utilizing the constructed image text semantic relation graph, completing context information supplementation of a retrieval target through graph sampling and aggregation, further generating retrieval features, and completing a retrieval task of multi-modal combination. According to the method, the pre-training model features are multiplexed, so that the process is more efficient, and the model convergence speed is greatly improved.

The invention discloses a distributed simulation platform elastic scheduling method and system based on cloud computing, and relates to the technical field of computer systems. According to the distributed simulation platform elastic scheduling method and system based on cloud computing, a cross-domain dynamic dependency processing module, a real-time task top-speed scheduling module, a mixed cloud resource adaptation module and an elastic scheduling core engine are included; and the cross-domain dynamic dependency processing module is used for realizing dynamic processing of a dependency relationship in multi-domain collaborative simulation, cross-domain collaborative allocation of resources and breakpoint self-healing of a task chain. According to the distributed simulation platform elastic scheduling method and system based on cloud computing, dynamic analysis of a multi-domain dependency relationship, cross-domain collaborative allocation of resources and breakpoint self-healing of a task chain are achieved through the cross-domain dynamic dependency processing module, the problem that a cross-domain dependency processing mechanism is rigid in the prior art is solved, and the distributed simulation platform elastic scheduling method and system based on cloud computing are high in practicability. The cross-domain data synchronization delay is reduced, and the resource utilization rate and the stability of the task chain are improved.

The invention relates to the technical field of computer programming languages, and particularly discloses a computer language programming method based on business logic. Aiming at the defects of deep coupling of business logic and technology implementation, high cross-domain adaptation cost, hardware operation code redundancy, high asynchronous programming complexity and the like in the prior art, the invention provides the following core schemes: a modularized development framework, a cross-platform adaptive mechanism, an event hierarchical model, a hardware intention analysis engine and a code, namely a document system. According to the method, the development complexity of a multi-field system is remarkably reduced, the business logic expression efficiency and maintainability are improved, the method is suitable for cloud micro-services, embedded equipment and mixed language scenes, and a technical basis is provided for intelligent programming.

The invention provides a multi-field text-oriented hierarchical semantic understanding and intelligent question and answer generation method, which relates to the technical field of text understanding, and comprises the following steps of: preprocessing an input text, performing field identification through a multi-field text classification pre-training model, and calling a corresponding knowledge graph; a hierarchical semantic comprehension model based on a bidirectional long and short term memory neural network is adopted to obtain hierarchical semantic representation of a text, entity and relation attention calculation is performed on a knowledge graph in combination with a multi-hop reasoning method of a graph attention network to extract related knowledge paths, and finally question and answer pairs are generated based on a bidirectional decoding strategy. Through multi-domain knowledge integration and hierarchical semantic understanding, the accuracy and generalization ability of the intelligent question and answer system are improved, and question and answer requirements of different domains can be met.

Automatically generating sentences that a user can say to invoke a set of defined actions performed by a virtual assistant are disclosed. A sentence is received and keywords are extracted from the sentence. Based on the keywords, additional sentences are generated. A classifier model is applied to the generated sentences to determine a sentence that satisfies a threshold. In the situation a sentence satisfies the threshold, an intent associated with the classifier model can be invoked. In the situation the sentences fail to satisfy the classifier model, the virtual assistant can attempt to interpret the received sentence according to the most likely intent by invoking a sentence generation model fine-tuned for a particular domain, generate additional sentences with a high probability of having the same intent and fulfill the specific action defined by the intent.

The invention discloses a metal surface defect detection and evaluation method of a mixed domain adaptive DCNN architecture, and the method comprises the steps: building a multi-stage feature extraction network through the fusion of a state space model and an adversarial learning technology, and strengthening the feature consistency of the same field and the feature alignment of a source-target field through the space-channel adaptive dynamic modeling cross-field difference. An entropy-driven knowledge distillation strategy is further proposed, noise is suppressed by using a Margin ReLU function, feature expression of a target domain is enhanced, and efficient deployment is realized in combination with lightweight distillation; pixel-level and feature-level adversarial training is carried out through a gradient inversion layer, and domain invariance is improved; an entropy-guided random multilayer disturbance mechanism is designed, multi-field features are adaptively fused, the anti-noise capability of the model is enhanced, in addition, a regression activation graph is integrated to visualize a defect attention region, the decision interpretability is improved, and a high-precision, high-robustness and interpretable defect detection evaluation scheme is provided for intelligent manufacturing.

The invention discloses a multi-field review method and system driven by dynamic rules, and belongs to the technical field of intelligent review. Comprising the steps of dynamic rule engine configuration, expert management configuration, automatic grouping matching, expert online review and meeting voting. And full-dimension coverage of cross-project type, cross-organization department and cross-business scene is realized. For talent selection, technical evaluation of scientific research projects and title evaluation, dynamic construction and flexible adjustment of a differentiated evaluation process can be completed based on the same platform, so that the evaluation efficiency and scientificity are effectively improved, and a standardized and intelligent technical solution is provided for multi-subject and multi-scene collaborative evaluation business; the problems of flow stiffness, weak functions, extensive management, lack of transparency and security vulnerability of an existing review system are solved.

The invention discloses a self-service terminal large model task processing system and method, and the system comprises a multi-mode perception fusion unit which is integrated with an infrared multi-point touch screen, an MEMS microphone array, and an industrial grade code scanning module. A medical diagnosis knowledge graph and a financial transaction ontology industry exclusive graph are built in the multi-field intention classification model; the dynamic demand matching engine is used for analyzing a cross-domain task link by adopting a Transform-XL long sequence modeling technology; a Petri net simulator and a conflict detection algorithm are built in the task arrangement middleware, and the task arrangement middleware is used for guaranteeing the consistency of execution time sequences of multiple sub-tasks; the self-adaptive response generation module is used for supporting automatic conversion from a natural language instruction to a PLC control code; according to the method, the task identification accuracy can be improved based on multi-modal fusion; the dynamic demand matching engine supports processing of a large number of concurrent requests per second, and response delay is low.

The invention discloses a multi-modal rumor detection system based on multi-field perception, relates to the technical field of rumor detection, and is used for solving the technical problem of low multi-field rumor detection precision in the prior art. The rumor detection system comprises a multi-view feature extraction module, a multi-domain perception module, a multi-level knowledge fusion module and a final classifier. Wherein the multi-view feature extraction module is used for respectively extracting corresponding single-mode features from a text mode and an image mode, and acquiring aligned image and text features as multi-mode view features; the multi-domain sensing module is used for learning cross-domain shared knowledge and domain specific knowledge at a text view angle, an image view angle and a multi-mode view angle; the multi-level knowledge fusion module is used for fusing cross-domain shared knowledge and domain specific knowledge of a text view angle, an image view angle and a multi-mode view angle; and the final classifier is used for obtaining a prediction result according to the cross-domain shared knowledge and the domain specific knowledge obtained by the multi-level knowledge fusion module.

The invention relates to an MBSE multi-field-based virtual-real fusion simulation platform and method, and the method comprises the steps: an intelligent matching module is used for receiving a to-be-detected algorithm model according to a user interface module, determining an MBSE multi-field model from a model management module, and achieving the MBSE multi-field model through the MBSE multi-field model; the virtual-real fusion test module is used for determining a plurality of test scenes constructed according to real scene data according to the MBSE multi-field model, performing full-life-cycle verification on the MBSE multi-field model and the to-be-detected algorithm model according to each test scene to obtain a corresponding verification result, and when the verification result meets a preset condition, executing the virtual-real fusion test on the to-be-detected algorithm model. The to-be-detected algorithm model is stored in the model management module, the full-life-cycle automatic verification process is achieved through the virtual-real fusion test module, the problems that virtual simulation and real object test are separated, and evaluation standards are not uniform are solved, and the method has the advantages that the test efficiency is improved, and the virtual-real fusion test capability is enhanced.

The invention discloses a lightweight cross-domain recommendation method and system based on user alignment Agent driving. The method comprises the following steps: firstly, acquiring historical behavior data of a user in multiple fields, fusing multi-modal contents such as texts and images, generating a fine-grained interest prototype through a cross-domain semantic encoder, and constructing a personalized Agent to simulate the intention of the user; then, in a multi-field collaborative environment, an Agent behavior strategy is optimized by utilizing reinforcement learning and a mixed reward mechanism, general preference and field specific preference are modeled through a hierarchical strategy network, and knowledge fusion is realized through a gating mechanism; and then, in combination with a preference distillation technology, extracting transferable characterization from Agent behaviors, and constructing a lightweight cross-domain knowledge graph. Finally, behavior track compression and cross-domain preference mapping are adopted, and efficient and low-consumption personalized recommendation is achieved. According to the method, the problems of cross-domain data sparsity and model complexity are effectively relieved, recommendation accuracy and system response efficiency are improved, and the method is suitable for real-time recommendation service of multiple scenes.

The invention discloses a cluster fault management method and apparatus, an electronic device and a medium. The method comprises the steps of obtaining performance index data of a multi-field unit in a cluster; constructing a dynamic fault propagation model of the cluster through the performance index data based on the graph model; according to the dynamic fault propagation model, constructing four-dimensional fault visualization based on a time sequence; and cluster fault analysis is carried out through four-dimensional fault visualization. Therefore, on the basis of the time sequence, the performance index data of the different field units are constructed into the dynamic fault propagation model, cross-domain fault positioning, analysis, monitoring and deduction based on the time axis are realized, cross-domain fault space-time correlation splitting caused by independent fault monitoring of each field unit is avoided, and the fault positioning efficiency and accuracy are improved. In addition, based on the four-dimensional fault visualization expression of the time sequence, the multi-screen switching monitoring complexity of operation and maintenance personnel is reduced, and the cluster fault management efficiency is improved.

The invention discloses an intelligent knowledge base system based on multi-domain model collaboration and a construction method, and relates to the field of artificial intelligence knowledge management. The system realizes accurate generation and dynamic management of cross-domain knowledge through a three-level driving architecture of an intelligent scheduling layer, a knowledge production layer and an intelligent knowledge base. The intelligent scheduling layer schedules professional field models such as medical treatment (such as Med-PaLM 2) and law (such as a power law intelligent contract review model) at a millisecond level through a field intention analysis engine and a three-dimensional matching matrix; the knowledge production layer completes format standardization, conflict verification and timeliness marking by using a knowledge cleaning assembly line; the intelligent knowledge base adopts a three-level storage system of a core library (high frequency and high reliability), an expansion library (medium confidence) and a temporary library (to be verified), and combines a dynamic weight algorithm of dominant score (60%), recessive behavior score (30%) and domain expert calibration (10%) to realize real-time optimization and upgrading and downgrading of knowledge.

There is provided a method for automatically generating a cyber crisis scenario, performed by a computing system. The method may comprise classifying types of content included in a cyber crisis report and extracting image data and text data from the cyber crisis report, inputting the image data into an image processing model and extracting attack procedure / behavior information included in the image data, inputting the text data into a text processing model and generating structured attack procedure-related data from each attack procedure included in the text data, generating threat behavior data corresponding to the attack procedure-related data, and merging the threat behavior data with the attack procedure-related data, matching the attack procedure-related data to the attack procedure / behavior information and generating a cyber crisis scenario template and automatically generating a cyber crisis scenario based on the attack procedure-related data and the cyber crisis scenario template.

The invention discloses a multi-level and multi-field model assembly and fusion method and system, which adopt an advanced data fusion algorithm to fuse data from different sensors, improve the accuracy and comprehensiveness of the data and provide a more reliable basis for the construction of a digital twinborn model. Machine learning and deep learning algorithms are utilized to construct a data-driven digital twinborn model, so that the future state and performance of the equipment can be accurately predicted, and powerful support is provided for intelligent management and maintenance of the urban rail field equipment; and a set of complete virtual-real consistency verification index system and verification method is designed, so that the accuracy and reliability of the digital twin model can be effectively ensured, and a guarantee is provided for the application of the digital twin technology in the urban rail field.

A method may include generating a test set of prompts; executing a generative artificial intelligence (GenAI) machine learning model using the test set of prompts; in response to the executing, receiving a plurality of generated answers; classifying the plurality of generated answers into a first group and a second group; calculating a percentage of generated answers in the first group compared to a total number of answers of the first group and second group; determining the percentage exceeds a value; based on the determining, updating a bias metric the GenAI machine learning model; and presenting the bias metric on a user interface.

The invention discloses an immersive culture and art experience system based on a virtual reality technology, which not only has a virtual scene construction module, a multi-field culture scene data storage module and the like, but also supports a user to autonomously set a scene and a figure image on an APP (Application) to meet the personalized immersive culture and art experience demand, and comprises a virtual scene construction module, a multi-field culture scene data storage module and the like, the virtual environment building module is used for building a vivid virtual environment through a virtual reality technology and a simulation scene building algorithm; the multi-field culture scene database is used for storing various culture experience scene data including historical scenes, artistic atmosphere scenes, learning scenes and medical scenes; the user interaction module is used for receiving user input and realizing interaction between the user and the virtual scene; the multimedia integration engine is used for coordinating synchronous presentation of scene visual elements, sound effects and light effects; and a data processing unit. The invention belongs to the field of immersive experience systems, and particularly relates to an immersive culture and art experience system based on a virtual reality technology.

The invention discloses a special ship system-oriented architecture model integration method and system. The method comprises the steps of constructing a meta-model library of a special ship system based on a GOPPRR-E meta-model; instantiating the meta-model in the meta-model library according to a demand-function-logic-physical RFLP modeling process, and constructing a full-process architecture model of the special ship system; analyzing the architecture model based on an OSLC standard, and establishing a semantic mapping rule between a model element corresponding to the architecture model and an OSLC standard resource; performing resource identification on the model elements through a uniform resource identifier (URI), and providing standardized service access of the model elements based on a RESTful interface; according to the method, standardized expression, semantic analysis and service access of the special ship system architecture model can be realized, and multi-field collaborative design is supported.

The invention discloses a knowledge graph quality evaluation method and device, computing equipment and a storage medium, and relates to the technical field of machine learning. Based on the fact that a large model has multi-domain knowledge and strong semantic understanding ability, a computing device adopts the large model to process reference examples of a target triple and a target triple, the relation confidence degree of knowledge described by the target triple is directly estimated, and objective quantitative evaluation of the knowledge graph quality is achieved. Moreover, the input of the large model not only comprises the target triad, but also comprises the reference example of the target triad, and the relationship attribute of the relationship in the reference triad included in the reference example is matched with the relationship attribute of the relationship in the target triad. And the prediction performance of a large model on the relation confidence coefficient in the target triad based on the relations in the reference triads can be improved.

The invention provides a game scene dynamic generation method and system for multi-domain cooperative combat. The method comprises the following steps: firstly, acquiring multi-field service dynamic data, then, generating an initial cross-field game scene according to the multi-field service dynamic data and a preset service cooperation strategy, initializing key decision parameters, and then, fusing market fluctuation parameters updated in real time; and adjusting the conflict response logic of the initial cross-domain game scene to form an adjusted conflict response logic, and finally dynamically optimizing the key decision parameters of the initial cross-domain game scene according to the adjusted conflict response logic and a preset business rule base to generate an optimal cross-domain game scene. According to the technical scheme provided by the invention, the problem that decision and risk conduction are disjointed in a federated learning multi-agent decision system in the prior art is solved, meanwhile, the dynamic response hysteresis defect is eliminated, and the out-of-control risk of cross-domain conflicts is solved.

A model pipeline has been created that allows an organization to gain a clear understanding of contents of a collection of documents despite varying lengths and multiple domain content. A collection of documents with content of different domains are normalized by summarizing the documents. For summarizing, the pipeline uses a language model that has been trained for text summarization across domains to a constrained summary length or length limit. The pipeline extracts embeddings of the summaries and clusters the summary embeddings. The pipeline uses the summaries to label the clusters using another language model that has been trained to generate a label or name for a cluster based on a set of summaries corresponding to a sample of cluster members. The labeled clusters can then be used to generate an organized presentation of the content of the documents in the document collection.