335 results about "A domain" patented technology

A system generates domain-expert agents for a particular domain. The system generates a hierarchy of topics for the domain by forming structured query inputs and requesting a machine learning-based language model to produce topics and associated sets of search terms. A knowledge store is built for the domain by identifying, for each topic, facts represented symbolically and / or in natural language. For at least one topic, programs comprising instructions for executing domain-specific procedures are generated and stored as symbolic and / or natural language programs. The knowledge store is evaluated to determine an expertise level for a domain-expert agent. If the knowledge store meets a threshold of knowledge, a deployment package is created comprising the knowledge store, and the domain-expert agent is deployed. The deployed agent utilizes the knowledge store together with a machine learning language model to address and solve problems specific to the domain.

The application relates to the technical field of public security risks, and provides a community public security risk compensation measure generation method and system based on atlas retrieval enhancement generation. The method performs text segmentation and vectorization on obtained domain knowledge data in the field of public security risks, generates knowledge slices in the field of public security risks and corresponding knowledge vectors, and stores the knowledge slices and the knowledge vectors into a vector database; meanwhile, a domain knowledge atlas in the field of community public security risks is constructed, and an index relationship between the domain knowledge atlas and the knowledge vectors is stored in the vector database, so as to construct a domain knowledge base in the field of public security risks; then, a user risk query is analyzed through a large language model, risk elements related to the user risk query are searched in the domain knowledge atlas, and knowledge slices corresponding to the risk elements are searched in the domain knowledge base according to the index relationship, so as to generate public security risk compensation measures corresponding to the user risk query.

The application provides an intelligent parameterized UI generation system and method suitable for professional analysis software, receives UI requirements in the form of natural language or pictures through a user interaction layer, analyzes the requirements by an AI intelligent processing layer, and automatically generates an initial configuration file containing components, styles and logic in combination with a domain knowledge base and a reference style. A user can adjust and analyze the configuration file through a configuration editing and analyzing layer. A parameterized UI generation layer dynamically constructs UI components with tree hierarchical relationships based on the analyzed structured data, automatically configures interaction logic, data binding and professional field processing, realizes two-way synchronization of GUI and backend data, and finally outputs an interactive interface by a UI rendering layer. The application changes highly customized and fragmented UI development into an automated and standardized generation process, greatly improves development efficiency, guarantees the consistency of interface style and operation logic, significantly reduces maintenance cost, and enhances the flexibility of software function expansion.

Technologies for machine learning-based entity understanding and resolution are disclosed. Data for training an entity resolution model is collected to learn semantic relationships associated with entity names. The entity names are provided in a domain of documents that follow the semantic conventions differently from natural language semantic conventions. The data includes entries each specifying an entity name and a label. The entity resolution model is trained using the data to learn and generalizes the semantic relationships and is deployed to serve requests for resolving an entity name from text extract from a document image.

The application provides a training method of a question and answer model and related devices; a structured document sequence is generated by selecting a parsing algorithm according to a document type of an input document; document blocks are obtained by performing document blocking processing according to structural features and semantic features of the structured document sequence; candidate question and answer pairs are generated according to the document blocks, answers of the candidate question and answer pairs are revised according to a domain knowledge base, quality of the revised candidate question and answer pairs is scored, and a target question and answer pair is selected from the revised candidate question and answer pairs according to the score; an initial question and answer model is adjusted according to a data set of the target question and answer pair and a knowledge base domain knowledge base to obtain a target question and answer model; the problems of low efficiency of data automation processing, high threshold of model fine-tuning, and insufficient tool chain cooperation are solved, the quality and efficiency of training of a question and answer model in a vertical field are improved, the application construction threshold is reduced, and the scaling landing of the question and answer model is promoted.

The present application relates to the technical field of artificial intelligence, and more particularly to an AIGC content generation method and system based on a brand knowledge base. The method comprises: obtaining a content generation request carrying a brand identifier and a domain identifier; extracting brand knowledge units from multiple brand knowledge bases according to the brand identifier; identifying the knowledge coverage density of each knowledge base on the domain identifier through domain coverage range annotation; marking the knowledge sources with a coverage density lower than a preset benchmark as sparse knowledge sources, and marking the knowledge sources not lower than the benchmark as dense knowledge sources; taking the knowledge fragment with the nearest neighbor semantics to the domain identifier in the dense knowledge source as an anchor point, performing cross-knowledge migration completion on the sparse knowledge sources, and generating the completed sparse knowledge units by remapping the style of the anchor point brand tone constraint according to the audience portrait of the sparse knowledge sources; and outputting a content generation strategy bound with the brand identifier and the domain identifier.

The application discloses a domain knowledge triple extraction method, system, medium and equipment, and relates to the technical field of knowledge engineering.The domain knowledge triple extraction method and system provided by the application can provide high-quality and efficient data support for triple extraction by analyzing and converting the obtained domain professional text into a structured vector knowledge base which can be efficiently searched, then the domain professional text is subjected to quantitative calculation and fusion screening, the initial entities of domain core high-frequency words which have global high frequency and cross-text universality are mined, the problem of "local optimum and global deviation" caused by traditional single word frequency is avoided, non-core term interference is effectively avoided, and the stability, relevance and efficiency of iterative extraction are improved, and further, the high-frequency word initial entities are subjected to closed-loop iteration through iterative RAG algorithm combined with the structured vector knowledge base, accurate extraction of the large model and iterative correlation entities, the explicit and implicit semantic correlation triples in the text can be mined layer by layer, the strong relevance and structural integrity of the extracted triples are ensured, and the professionalism and accuracy of the model in extracting triples are improved.

The application relates to a government affair cross-domain collaborative response method and system based on a large model and RPA dynamic arrangement. The method converts user appeal into structured instructions by adopting a domain fine-tuning large language model through an intention decoupling module; then, a reinforcement learning agent hub in a dynamic assembly module is generated according to the instruction and the real-time state of an RPA cluster, and a dynamic scheduling strategy is output; further, a cross-domain execution module drives an RPA robot to interact with a heterogeneous government affair system in a non-intrusive manner to execute a task according to the strategy; finally, a work order derivation module generates a standard work order by using a conditional generative adversarial network (cGAN) to aggregate returned data. The application has the beneficial effect that the constructed cognitive-to-execution automation closed loop can effectively improve the efficiency, accuracy and flexibility of government affair services while ensuring the safety of existing systems.

The application relates to the technical field of artificial intelligence, and discloses a multi-dimensional cognitive state analysis method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a cognitive state classification system and a domain sample data set; determining target dialogue text; learning hierarchical structure features of the target dialogue text on a hyperbolic space based on the domain sample data set, and determining cognitive representations of cognitive state dimensions presented by the target dialogue text in the hyperbolic space; the cognitive state dimensions at least comprise four dimensions of emotion, thinking mode, position and intention; performing semantic training on the cognitive representations based on a preset large language model, and reasoning out a cognitive state image satisfying cognitive analysis text constraints and cognitive hierarchical structure constraints; the hierarchical overlap problem of the cognitive state is solved by using exponentially increasing space capacity, and geometric structure knowledge in the hyperbolic space is injected into the large language model, so that the joint modeling and reasoning capability of the model for the multi-dimensional cognitive state in a complex social scene is significantly improved.

This invention discloses a risk quantification method for AI large-scale models in engineering safety production, relating to the field of engineering safety technology. The method includes: S1, acquiring a domain causal template library constructed based on preset engineering safety standards, the domain causal template library including multiple standardized causal chain structure templates; S2, parsing the inference text generated by the main model in real time, and constructing an instance graph reflecting the current safety inference logic; S3, performing structural matching between the instance graph and the templates in the domain causal template library, and determining whether there is a structural deviation in the inference chain of the main model based on the matching result; if so, triggering a backup model to take over; S4, extracting key safety commitments from the inference context or instance graph of the main model, converting the key safety commitments into formal logical constraints, and injecting the formal logical constraints into the backup model; S5, verifying the response generated by the backup model and determining whether it satisfies the formal logical constraints.

This invention discloses a method and system for extracting domain knowledge graphs based on the collaboration of large and small models. First, central entities are extracted and filtered. Then, the text is segmented to generate associated summaries, forming enhanced semantic blocks, which are then vectorized to construct a knowledge base. Next, a large model and a domain segmenter are used in parallel to extract candidate entities, which are then filtered by type discrimination and confidence to generate entities with contextual descriptions. Then, based on entity pairs, the supporting text is retrieved, and usability, relation type, illusion, strength, and direction detection are performed sequentially. If successful, relation triples are generated. Finally, a star graph and similarity support material are constructed for the entities. Through two-stage semantic retrieval and large model judgment, the fusion of entities with the same name is achieved, and the association relationships are updated. This invention can automatically complete the process of constructing a high-quality knowledge graph from text under the condition of a single-machine, relatively parameter-based model.

Systems and methods for performing a medical imaging analysis task conditioned on multi-domain medical images with missing modalities are provided. 1) one or more medical images each in a different domain and 2) a domain code defining a presence of the different domains in a set of predefined domains are received. One or more weights are determined based on the domain code. One or more parameters of a machine learning based encoder are updated based on the one or more weights. Features are extracted from the one or more medical images using the machine learning based encoder with the one or more updated parameters. A medical imaging analysis task is performed based on the extracted features. Results of the medical imaging analysis task are output.

The application discloses a management platform system for supply chain finance and a non-sensing upgrade method thereof, has the effects of local pilot, small flow verification, automatic observation, rapid rollback, and protects the consistency of in-transit instances and the continuity of key transactions. The system comprises: an infrastructure layer, which provides process arrangement, rule and model execution, event driving, configuration management, task compensation, security authentication and full-link observability, supports the non-sensing upgrade core mechanism including multi-version parallel running, shadow verification, gray release and automatic rollback of the upper-layer business, an interaction layer, which provides unified authentication, permission and configurable menu, supports displaying differentiated functions according to organizations / roles, a domain service layer, which is used for encapsulating business logic operations in the platform, coordinating multiple parties to complete cross-entity transactional tasks, and ensuring the consistency and integrity of business rules, and a fund and channel adaptation layer, which abstracts multiple protocols by using a contract / interface definition language, automatically generates basic adapters, and unifies strategies.

The present disclosure provides a domain dictionary constructing method and apparatus, the method including: segmenting a domain corpus sample to obtain a first character segment set, where the first character segment set includes at least one first character segment; calculating an inter-character correlation index of the at least one first character segment; determining a second character segment set according to the correlation index, where the second character segment set includes a first character segment of which the correlation index is greater than or equal to a preset threshold; determining a third character segment set according to the second character segment set, where the third character segment set includes the second character segment set and second character segments of the domain corpus; constructing a domain dictionary according to the third character segment set.

A method, system, and computer system for identifying dangling records are disclosed. The method includes obtaining a domain set, determining whether a record associated with a domain included in the domain set is dangling, and responsive to determining that the record associated with the domain is dangling, providing a notification to a registrar that the record is dangling.

The application relates to the field of natural language processing and decision intelligence, and particularly relates to a large language model reasoning method based on time series difference learning and rule enhancement, which is widely applied to automatic planning, intelligent question answering, embodied intelligence and the like. The method comprises task trajectory sampling, domain knowledge induction, domain rule extraction and large language model reasoning based on rule enhancement. For test task data, the most relevant historical task is matched based on vector retrieval, and a domain rule set corresponding to the task is obtained. The rule is rewritten in natural language by the large language model itself, so that the rule is more interpretable and adaptable. Finally, the optimized rule set is integrated into the large language model reasoning prompt text, so as to optimize the reasoning quality and stability.

The invention discloses a high-precision hybrid expert large model and a fine tuning method thereof. The hybrid expert large model is composed of a domain expert group and a shared expert group. A high-precision data transmission fine tuning module based on each linear network LN in the shared expert, wherein the fine tuning module comprises an extended linear network, a numerical value alignment network, a blocking controller and a precision converter; the extended linear network is of a replicated linear network (LN) structure and converts an input vector into a first data flow vector; the numerical value alignment network performs numerical value coding on the output data flow vector of the extended linear network to generate a second data flow vector; the blocking controller controls whether the extended linear network and the numerical alignment network participate in domain expert group reasoning or not according to binary data signals; the precision converter adjusts the precision of the data stream output by the numerical alignment network and the precision of the data of the shared expert linear network to be consistent; according to the invention, the flexibility and intelligent control capability of the high-precision hybrid expert large model can be enhanced.

This invention relates to the field of natural language processing, specifically to a method for training and optimizing an intelligent translation model based on transfer learning. The method involves acquiring a pre-trained translation model; obtaining the target text to be translated and inputting it into the translation model; analyzing the domain features of the target text using a domain classifier and calculating activation weights based on these features; activating the target adapter among multiple adapters according to the activation weights to adjust the multilingual backbone model; and then translating the target text using the adjusted multilingual backbone model to obtain the target translated text. By acquiring a pre-trained translation model, analyzing the domain features of the target text to calculate activation weights, activating the target adapters to adjust the model, and performing translation, the method achieves dynamic optimization of the model adjustment, thereby solving the problems of domain misjudgment and adapter selection bias in existing technologies and improving translation accuracy.

The application relates to a document intelligent completion method and system based on a domain knowledge base and a large model, and belongs to the technical field of big data processing. The method comprises the following steps: acquiring domain knowledge data from multiple participating ends, and performing data extraction and preprocessing on the domain knowledge data to obtain target domain data. A semantic embedding model is called to map the target domain data into a fixed-dimension semantic embedding vector, and the semantic embedding vector and indexed document metadata are written into a domain knowledge base. A user prompt word and a retrieval instruction are received, and similarity retrieval is performed on the domain knowledge base according to the user prompt word in response to the retrieval instruction, and a retrieval result is output. The retrieval result and the user prompt word are input into a large model to call the large model to complete a target document according to the retrieval result and the user prompt word, and a completed target document is output. The method avoids the risk of data leakage, the construction of the domain knowledge base not only reduces the dependence on large model training, but also improves the intelligent completion accuracy of requirements.

This invention discloses a standard address auditing method and system based on a large model and workflow, belonging to the field of information retrieval technology. The method includes: a workflow engine calling a domain knowledge base to obtain eleven levels of standard address level definitions and auditing rules, constructing an auditing context; cleaning and identifying interference content in the address text to be audited; calling a large model to perform hierarchical parsing and compliance judgment on the cleaned address, outputting the compliance judgment result and a complete corrected address without placeholders; when the element is determined to be missing, uncertain, or abnormal, calling an external address service interface to complete, verify, and update the corrected address; outputting the audit result and recording the process node status, supporting human-machine review and rule iteration. Through the technical solution of this invention, standardized parsing and verifiable completion of address elements are achieved, improving the accuracy and traceability of batch audits, enhancing result consistency, and reducing manual processing costs.

Methods for a system including a detector and a separation media are disclosed. The method may include receiving input data from the detector. The input data may include an observed signal of an unknown sample and a signal of at least one known sample. The method may also include generating one or more deconvolution candidate signals based on the observed signal and using one or more deconvolution processes. The method may further include defining a domain of the detector using the one or more deconvolution processes and based on the observed signal, the calibrated separation media, the input data, or a combination thereof. The method may also include modifying the system based on the domain.

This invention discloses a large-scale reliable fault diagnosis method for aviation maintenance scenarios, comprising: constructing a domain model for aviation troubleshooting tasks; standardizing and retrieving the input fault descriptions, normalizing and weighting the retrieval results to generate a unified-ranked candidate document list; selecting several high-scoring documents to perform dynamic context expansion and semantic relevance verification to obtain a structured evidence set; using this as input to the domain model for aviation troubleshooting tasks to output a troubleshooting solution; structurally decomposing the troubleshooting solution into several sub-steps and quantifying the uncertainty of each sub-step; combining fuzzy representation recognition and uncertainty classification to label the risk level of each sub-step, and forming a credible aviation maintenance diagnosis solution after manual review. This invention also discloses a large-scale reliable fault diagnosis system for aviation maintenance scenarios. This method and system can achieve stable generation, reliable verification, and risk-controlled output of aviation maintenance diagnostic content.

This application relates to a method, system, device, and medium for real-time evaluation of business rules based on a large language model. The method includes: invoking a large language model to convert natural language business rules into structured description data containing entity identifiers, attribute identifiers, and rule constraints; mapping entity identifiers and attribute identifiers to the location information of corresponding program elements in a domain model based on a pre-stored mapping library, generating detailed mapping data; generating source code files implementing a preset evaluator interface based on the structured description data and the detailed mapping data; converting the source code files into an executable form and executing them in an isolated execution environment; invoking the evaluator interface, evaluating the execution results using generated test cases, and generating a verification report. This application achieves fully automated conversion of business rules to executable code, reducing maintenance costs and improving the efficiency of rule deployment.

This application provides a method, storage medium, electronic device, and product for pre-training a large model. The method includes: Step 1: Determining a cognitive dataset based on cognitive information related to the pre-trained large model, and determining a training dataset based on the cognitive dataset and a domain adaptability dataset; Step 2: Adjusting the parameter information of the pre-trained large model based on the training dataset; Step 3: Processing cognitive problems using the adjusted pre-trained large model to obtain test results of the adjusted pre-trained large model; Step 4: Repeating steps 1 to 3 based on the test results until a preset model adjustment stopping condition is met. This application solves the problem of biased cognitive information in large models during pre-training in related technologies.

The application discloses a knowledge question answering method and device based on a domain knowledge graph and electronic equipment, and relates to the fields of artificial intelligence, financial technology or other related fields, wherein the knowledge question answering method comprises the following steps: receiving a target question, processing the target question to obtain question prompt information, extracting a target entity set or a target relationship set based on the target question, retrieving triple information matched with the target entity from a preset domain knowledge graph based on the target entity set to obtain a triple information set, constructing input knowledge information based on the triple information set and the question prompt information, inputting the input knowledge information into a preset reasoning model, and outputting a target answer to the target question. The application solves the technical problem of low accuracy of knowledge question answering reasoning for a question in related technologies.

A cross-subject motion intention recognition method, system and medium relate to the technical field of human motion intention recognition. The foregoing method comprises: collecting physiological signals and / or motion signals of a source subject and a target subject under different motion intentions, and preprocessing the same; extracting time domain features and frequency domain features from the preprocessed signals; constructing a kernel space projection function, mapping the extracted features to a reproducing kernel Hilbert space to realize linear representation of nonlinear relationship; constructing a joint objective function comprising a classification loss, a source subject fusion loss and a domain adaptation loss; and optimizing and solving the joint objective function in the reproducing kernel Hilbert space to obtain a classification model for motion intention recognition. The present application can solve the cross-subject generalization problem.

Systems and methods include generation of a set of n-grams of different lengths from each of a plurality of text portions, determination, for each set of n-grams, of matching topic variants of a domain ontology, determination of a topic associated with each of the matching topic variants, wherein a determined topic is associated with the text portion from which n-grams matching an associated topic variant were generated, generation of first n-grams of different lengths from a first text portion, determination, for each of a plurality of the first n-grams, of first matching topic variants of the domain ontology, determination of a first topic associated with each of the first matching topic variants, and determination of mappings between the first text portion and the plurality of text portions based on the topics associated with the plurality of text portions and the determined first topics.

This invention discloses a method and system for cross-subject motor imagery EEG signal transfer learning, relating to the field of motor imagery EEG recognition technology. The method includes: acquiring EEG signal data, preprocessing and augmenting the data; constructing a cross-subject motor imagery EEG signal recognition framework based on two-stream feature extraction and entropy-weighted conditional domain adversarial mechanisms, including a two-stream feature extraction module, a classifier, and an entropy-weighted conditional domain adversarial module. The entropy-weighted conditional domain adversarial module includes a gradient flipping layer and a domain discriminator, and employs a conditional domain adversarial mechanism and a prediction entropy weighting mechanism. The cross-subject motor imagery EEG signal recognition framework is trained adversarially, and a loss function is designed, including an entropy-weighted domain loss, combined with prototype library constraints, supervised contrastive learning, and minimum entropy regularization as the total loss function. The trained cross-subject motor imagery EEG signal recognition framework is used for target domain discrimination. This invention improves the model's cross-subject generalization ability.

An improved knowledge graph for augmenting queries in a retrieval augmented generation system for generative artificial intelligence is constructed using entity data comprising information regarding a first entity of a first entity type and a second entity of a second entity type, the first and second entity types being defined by a domain-specific ontology for a knowledge domain. Relationship data for the knowledge graph comprises information regarding relationships between the first and second entities using relationship definitions from the domain-specific ontology. The knowledge graph is constructed by adding nodes corresponding to the entities and edges corresponding to the relationships. In some examples, the graph is used to identify cybersecurity threats applicable to a specific context.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining whether to generate sub-domain noise. One of the methods includes, for a message for a downstream system, determining whether to generate noise data that has the same sub-domain as a true value, the true value from a domain that has a plurality of different sub-domains including the sub-domain; using a result of the determination whether to generate noise data that has the same sub-domain as the true value, generating the message for the downstream system; and transmitting, to the downstream system, the message.