594 results about "Tree based" patented technology

The invention provides an RAG knowledge base construction method and system based on hierarchical semantic indexes. The method belongs to the cross technical field of artificial intelligence and information retrieval. The method comprises the following steps: performing multi-level semantic analysis on an input original document set to generate document semantic hierarchical structure data; constructing a hierarchical semantic index tree based on the document semantic hierarchical structure data; performing dynamic knowledge graph initialization according to the hierarchical semantic index tree to generate an initial dynamic cognitive graph; and collecting real-time interaction data through a user feedback interface and a new data access module, and performing incremental updating on the initial dynamic cognitive map to form a knowledge representation system supporting life cycle evolution. Through multi-level semantic analysis and construction of a hierarchical semantic index tree (HSIT), deep semantic analysis can be performed on an original document set, the context integrity of knowledge is ensured, structured storage is realized, the knowledge can be expressed and stored more accurately, and information loss or semantic ambiguity is avoided.

The invention provides a script preservation method which can be applied to the technical field of artificial intelligence. The script preservation method comprises the following steps: carrying out semantic understanding on demand related files by utilizing a large model, extracting core elements, and generating a structured demand change list; analyzing to obtain an abstract syntax tree of an existing script code, and constructing a mapping relationship between the software automation test element and a script code block; dynamically comparing the structured demand change list with an existing script code structure tree based on a mapping relation between software automation test elements and script code blocks, identifying a script range influenced by demand change, and outputting a change influence matrix; and based on the change influence matrix, generating an automatic script code snippet needing to be updated, and realizing preservation of the automatic script. The invention further provides a script preservation device and equipment, a storage medium and a program product.

Techniques are described herein that are capable of performing AI-based entity maliciousness analysis using embedding and sampling. A representative sample of data associated with an entity is selected by comparing embeddings that represent the data. A potentially anomalous data point is identified in at least a portion of the data based on a proximity of a node, which corresponds to the potentially anomalous data point, in a tree to a root node of the tree. A statistically anomalous data point is identified in representative sample data points, which define the representative sample, as a result of the statistically anomalous data point indicating an unexpected occurrence of an event. An AI model is triggered to determine whether the entity exhibits malicious behavior by providing an AI prompt, including the representative sample and a description of the potentially anomalous data point and the statistically anomalous data point, to the AI model.

The invention relates to the field of CIMs, and discloses a method and system for automatically degrading a CIM6-level three-dimensional model to CIM5 based on a semantic rule engine, and the method comprises the steps: obtaining CIM6-level three-dimensional model data, and constructing a scene hierarchical tree based on the three-dimensional model data; identifying the category, the attribute, the service label and the importance constant of each object in the scene hierarchical tree; calculating geometric complexity, semantic importance and topological dependency of each object, and calculating a comprehensive weight; matching the interval of the comprehensive weight and executing a corresponding processing operation based on the matched interval; performing grid merging and texture baking operation on the reserved object; performing grid instantiation on the proxy object after proxy replacement; collision holes in the model are detected through an octree in combination with a GJK algorithm to complete topological consistency verification, a lightweight CIM5-level model data packet is generated, and a difference report is output. According to the method, the consistency of the key semantic information and the topology is kept while the data volume of the CIM6 model is reduced.

The invention discloses a data tracing method and device based on a runtime snapshot. Comprising the steps of generating a runtime memory snapshot file based on report traceability information; analyzing the runtime memory snapshot file, extracting all keys in the first mapping relation to construct a header character set, and querying N metadata identifiers corresponding to N header characters according to the first mapping relation; accessing a report data result storage area based on the N metadata identifiers to obtain a data value list, and rendering to generate a visual report snapshot; for each metadata identifier, extracting the metadata identifier of each metadata which directly depends on and indirectly depends on the metadata identifier from the task detail information associated with the metadata identifier, and obtaining a single metadata tree based on the hierarchical dependency relationship among the metadata; rendering and generating N metadata tree snapshots based on the N metadata trees; and displaying the metadata circulation process corresponding to the abnormal data value by skipping to display the metadata tree snapshot of the metadata identifier corresponding to the report data column where the abnormal data value is located.

The invention discloses a knowledge question-answering method and system based on a large language model and a semantic abstract. The system comprises a tree structure abstract generation subsystem which comprises a knowledge base configuration module, a file management module, a document analysis module and a knowledge block management module and is used for automatically generating tree structure hierarchical knowledge blocks for large manual documents or multi-chapter manual documents; the dual-channel retrieval engine subsystem comprises a question rewriting module, a semantic abstract retrieval module, a detail knowledge block retrieval module, a father-son retrieval module and a prompt word construction module, and all the modules work cooperatively to ensure that semantic abstract knowledge blocks and detail knowledge blocks related to the question of the user are retrieved. According to the method, by introducing the semantic abstract based on the tree structure and the two-channel retrieval, perception of global knowledge and accurate extraction of local fine-grained knowledge can be achieved at the same time, and then the ability of a knowledge base question-answering system in processing the general and inductive problems is improved.

The invention discloses an agent training data set construction method and system combined with cross-modal learning, and relates to the technical field of agent training, and the method comprises the steps: obtaining multi-modal intelligence data from a multi-source database, extracting feature information, and projecting the feature information to a preset semantic space to obtain cross-modal alignment features; constructing an agent function call syntax tree based on cross-modal alignment features, analyzing the syntax tree into an instruction sequence, constructing an analysis reasoning chain, and generating a sample label and an interaction track; constructing a task dependency graph by using the sample labels and the interaction tracks, decomposing the task dependency graph into a plurality of parallel decision branches, and dynamically adjusting a processing strategy to form a training data set; mapping the training data set to an agent target space, optimizing and analyzing an inference chain through a training feedback channel, and outputting a standardized sample library; and finally inputting to-be-analyzed data into the trained agent, and generating an intelligence analysis report according to the analysis reasoning chain.

The invention discloses a large language model reasoning acceleration method and device based on two-stage speculative decoding and a storage medium, and the method comprises the steps: constructing and initializing a Trie tree, and inserting a historical corpus, and phrase sequences in a document library or a code library into the Trie tree one by one; in the reasoning process, longest prefix matching is carried out based on a Trie tree, and a candidate draft sequence is generated by adopting branch backtracking and recursive search; performing confidence evaluation on the candidate draft sequence, calculating a joint confidence score of the sequence through probability multiplication and a Top-K screening mechanism, and judging whether the joint confidence score reaches a confidence threshold; if the accumulated confidence of the candidate sequence reaches a threshold value, skipping a small model generation stage, and directly entering large model verification; otherwise, entering a small model draft completion stage; and the final large model takes the replaced and updated draft sequence as final output. According to the method, adaptive acceleration of the decoding process can be realized, and the long text reasoning delay of the large language model is remarkably reduced while the generation quality is ensured.

A three-stage pipeline is used to create a data structure for efficiently producing grounded recommendations that guarantee that the recommended items are part of a set, D. In the first stage, each item in D is converted into a vector representation. In the second stage, a hierarchical clustering method is used to build a tree based on the vector representations. Each item is a leaf node of the tree. Each non-leaf node represents a group of items or a group of groups of items, and so on. In the third stage, an LLM is used to generate text that encapsulates the information of the group (or groups) of items represented by each node. The generated tree is recursively traversed to generate recommendations.

A system can be used to generate interactive data visualizations and textual content. The system receives a layout of a content item. The content item can be a data visualization dashboard or an article. The system can generate a content structure tree based on the layout. The content structure tree represents hierarchical and semantic relationships between sections of the content item. The system can receive input adding content elements, such as data visualizations or textual paragraphs, to sections within the content item. The system can identify text roles for different sections based on the content structure tree and the content elements. The system can generate text suggestions for the content item based on the text roles. The system can also generate text content for a text suggestion using a large language model, display the generated text content within the content item, and iteratively refine the content item.

The invention discloses a verifiable retrieval method and device, equipment, a medium and a product, and relates to the technical field of block chains. Obtaining a query request; performing data positioning from a retrieval algorithm tree based on the query request to obtain at least one target leaf node and a data index set corresponding to the target leaf node; generating a target node proof and a path proof based on the retrieval algorithm tree, the target leaf node and the data index set; and verifying the target node proof and the path proof based on the retrieval algorithm tree. By the adoption of the technical scheme, under-chain retrieval and verification are carried out through the retrieval algorithm tree, on-chain and off-chain cooperation of query verification is achieved, it is ensured that the certification size is small, verification calculation complexity is lowered, on-chain storage overhead is reduced, and the problems that at present, request query certification is large in size and low in verification efficiency are solved.

The invention provides a large model context processing method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of obtaining a new action step request, updating a context view tree and a source interaction data tree based on the new action step request, and determining a pressure coefficient according to the updated context view tree; according to the pressure coefficient, determining whether a to-be-compressed node exists in the updated context view tree or not; if the to-be-compressed node exists, combining the updated source interaction data tree and the updated context view tree to perform back-to-source compression on the to-be-compressed node so as to update the updated context view tree and the updated source interaction data tree, and returning to the step of determining the pressure coefficient according to the updated context view tree until the to-be-compressed node does not exist; and based on the updated context view tree, expanding the context view tree into context content and inputting the context content into the large language model. By adopting the method, the large language model can accurately understand and respond to the new action step request.

The invention relates to the field of power transmission line operation and maintenance, in particular to a power transmission line tree obstacle intelligent supervision system and method based on the Internet of Things, and the system comprises an intelligent sensing module, a data cloud transmission module, a fusion prediction module, an analysis decision module and a linkage execution module. According to the coupling prediction, historical data are processed through an algorithm model, future tree growth and conductor wind deviation are predicted, and the scientificity and accuracy of prediction are ensured through cooperation of a state space model and a Kalman filtering algorithm, so that the prediction accuracy is improved through a sensor deployed at the front end and an intelligent algorithm at the cloud end. The device can continuously and automatically monitor for 7 * 24 hours, not only measures the current static distance, but also predicts the future growth trend of the tree based on historical data, and calculates the dynamic windage yaw of the lead by combining the real-time wind speed and wind direction, thereby being convenient to give out early warning before the tree actually approaches the safe distance, realizing the process from post-event disposal to pre-event prediction, and improving the working efficiency. And the preventive safety level of the power grid is improved.

The invention discloses a marketing activity-associated batch digital certificate generation and distribution method and system, and relates to the technical field of digital certificate generation, and the method comprises the steps: receiving a marketing activity arrangement rule, and screening a target user identifier list from a user database according to the marketing activity arrangement rule; based on the target user identifier list, generating a digital certificate record for each target user, constructing a lightweight Merkel tree based on target data of the digital certificate records, and performing calculation to obtain Merkel tree root hash; submitting the Merkel tree root hash to a block chain network for evidence storage, and obtaining an evidence storage transaction hash which is hash with the Merkel tree root; and distributing the digital certificate records to the users in the target user identifier list. According to the method, the zero-knowledge proof with hidden detail information is generated based on the certificate record and the Merkel path proof during verification, and the verification operation is executed to update the state after verification is passed, so that efficient generation, credible distribution and privacy protection verification of batch certificates are realized.

The invention discloses a differential chlorophyll fluorescence inversion method, system and device and a storage medium, and is applied to the field of vegetation remote sensing and physiological ecological monitoring, and the method comprises the steps: obtaining vegetation state monitoring data of a target region; on the basis of vegetation state monitoring data, asynchronous leaf-changing type evergreen arbors and synchronous deciduous type arbors are identified; carrying out SIF simulation on the asynchronous leaf-changing type evergreen arbors and the synchronous deciduous type arbors by adopting corresponding models respectively; according to the phenological phase function and the stress response function, generating correction factors corresponding to the asynchronous leaf-changing evergreen arbors and the synchronous deciduous arbors; the obtained initial SIF value is optimized through a corresponding correction factor; fusing the optimized SIF values to generate an SIF time sequence product; according to the method, differential model configuration and physical mechanism driven online correction are coupled, so that the problems of model mismatching and physiological mechanism deficiency in heterogeneous vegetation SIF inversion are solved, and an SIF time sequence product which is high in precision and clear in physiological and ecological significance is generated.

The invention discloses a book-based subject knowledge system construction method and device, and the method comprises the steps: representing a directory as a directed tree, and dividing the directed tree into a skeleton module and a plurality of chapter modules; carrying out the association and expansion of a title through a large language model, and generating an abstract; knowledge concepts, subject terms and structural relations in titles in all the modules are extracted and subjected to double correction to obtain a plurality of knowledge system trees, and then a mother tree obtained after the skeleton module is processed and a sub-tree obtained by the chapter module are spliced; and finally, giving a plurality of knowledge trees obtained according to a plurality of groups of book directories in the same subject field, and combining the knowledge trees into a unified knowledge system tree based on a finite-state machine principle. According to the method, the knowledge system is constructed and decoupled into an extraction stage and a fusion stage based on LLM, the problem of a pain point of drifting between knowledge concepts and attributes when a simple chapter title is faced is solved, and strict control on semantic consistency and hierarchical rationality in a path merging process is ensured based on a state machine.

The invention relates to the technical field of information processing, in particular to a full-automatic work order processing information generating and pushing method based on a fault knowledge base. The method comprises the following steps: acquiring an initial decision tree; identifying a core fault work order in a plurality of fault work orders corresponding to the target fault type; pruning the initial decision-making tree based on the core fault work order to obtain a target decision-making tree, the number of nodes of the target decision-making tree being smaller than the number of nodes of the initial decision-making tree; and processing a plurality of fault work orders corresponding to the target fault type according to the target decision tree to obtain work order processing information of each fault work order. According to the technical scheme of the invention, a lighter target decision tree is obtained through decision tree pruning, and batch processing is carried out on the plurality of fault work orders corresponding to the target fault type, so that the overall time consumption of the plurality of fault work orders corresponding to the target fault type during processing is reduced, and the overall response efficiency of a large batch of fault work orders is improved.

The invention discloses a multi-modal fusion short message compliance and security dual auditing method and system, and the method comprises the steps: encrypting account information through employing an irreversible algorithm based on SHA256 and a random salt value, and decomposing the content of a short message into a text stream, a link stream and a symbol stream through employing a regular expression; traversing each character in the short message content by adopting a prefix mode based on a Trie tree in combination with an AC automaton algorithm to detect sensitive words; performing symbol semantic classification mapping and analysis on the special symbol feature data extracted from the symbol stream; carrying out sending behavior analysis on the text feature data extracted from the text stream; performing special detection on link feature data extracted from the link stream; based on the factors corresponding to the sensitive words, the semantics, the behaviors and the links and the weights of the factors, a multi-modal feature fusion decision risk assessment algorithm is adopted to output a risk score value and a risk decision rule of the risk score value so as to execute short message interception operation or short message release operation. According to the invention, full-dimension perception and dynamic defense of risks can be realized.

The present disclosure relates to predicting genomic instability status in biological samples using machine learning techniques with comprehensive genomic and immune profiling (CGIP) data. Particularly, aspects are directed towards performing a genomic instability test on a biological sample. Then, multi-omics data for the subject are obtained by DNA sequencing and RNA sequencing assays, including genomic alteration data for a first set of genes and expression data for a second set of immune genes. The multi-omics data are input into a machine learning model having a tree-based architecture, which is configured to analyze features by traversing paths from root nodes to terminal nodes in each tree based on values generated from the data. The model predicts a genomic instability status, which is then provided via a user interface notification or as part of a testing report.

A method of retrieval-augmented text generation is provided to generate a response to by an artificial intelligence (AI) agent. The method incudes constructing an indexing tree reflecting sematic relationship among textual contexts of one or more documents. The indexing tree includes at least a first level of nodes representing a plurality of propositions indicating facts about at least one entity from the documents, a second level of nodes representing a plurality of proposition aggregates that aggregate one or more first-level propositions mentioning a same entity, and a third level of nodes representing a plurality of summaries that summarize one or more second-level proposition aggregates. The method also includes receiving the user query; retrieving, from the indexing tree, one or more nodes across multiple levels based on similarity comparison with the user query based at least on a similarity between embeddings of the nodes and an embedding of the user query.

The invention provides a cross-platform session context synchronization method and system based on browser request interception, and is applied to the technical field of browser extension and network data interaction. The method comprises the steps of loading site strategy configuration to define a data mapping and input container positioning rule, injecting proxy codes to monitor a page request state, locking a target input container in a DOM tree based on a multi-dimensional score, intercepting a session submission request and analyzing an original load, retrieving a historical context and converting the historical context into an implicit data segment according to a mapping relation, combining the data to an original load to generate a recombination request and then sending the recombination request; according to the scheme, session context non-inductive synchronization of cross-heterogeneous platforms can be realized on the premise of not depending on a fixed selector and not changing a page UI (User Interface), the continuity of user memory by different platforms is kept, the robustness of element positioning and the accuracy of an operation time sequence are improved, and the user experience is improved. The problem of data islands is effectively solved, and man-machine interaction continuity is enhanced.

The invention relates to a model reasoning acceleration method and device, computer equipment and a readable storage medium. The method comprises the steps of inputting obtained initial text data into a target reasoning model for reasoning, scheduling and executing draft token generation, context token retrieval and probability calculation prediction distribution of an initial text in parallel through an asynchronous execution engine, and sequentially obtaining a draft token set, a retrieval token set and probability distribution of tokens; integrating the draft token set and the retrieval token set to generate a target draft tree; and based on a tree attention mechanism, performing recursive verification on the target grassy tree according to the probability distribution, determining an effective token sequence from the target grassy tree, updating the initial text data according to effective tokens, and executing the step of inputting the initial text data into the target reasoning model for reasoning until a preset ending condition is met. By adopting the method, the hardware resource utilization rate and the model reasoning speed can be improved on the basis of not sacrificing accuracy.

The invention discloses a photovoltaic array multi-working-condition mode recognition method based on Stacking and interpretability analysis. The method comprises the following steps: constructing a multi-dimensional photovoltaic array operation characteristic matrix; constructing a multi-dimensional photovoltaic array operation characteristic matrix and carrying out normalization processing; performing data set division on the normalized feature matrix and the corresponding tag set; the method comprises the following steps: constructing a Stacking learning framework based on a K-fold cross validation mechanism, selecting LightGBM, RF and XGBoost as base learners and LR as a meta learner, and constructing a multi-working-condition mode recognition model; and on the basis of the constructed multi-working-condition mode recognition model, taking F1 score maximization as an optimization target, and adopting an Optuna Bayesian search algorithm to carry out joint optimization on key hyper-parameters and fusion layer weights of all base learners. According to the method, deep derivation is carried out on the original monitoring quantity on the feature engineering level, a tree model-based Stacking architecture is constructed, and global and local interpretation mechanisms are introduced, so that the influence of environmental fluctuation and sample imbalance on an identification result is weakened, and the accuracy and reliability of photovoltaic array working condition identification are improved.

The invention provides a finite-state machine extraction method and device for logic system design and a storage medium, and the method comprises the steps: determining a signal node based on a condition trigger signal and an assignment signal of a process block in a compiling partition, so as to construct a first finite-state machine tree; associating a condition assignment statement for assigning the condition trigger signal to the corresponding signal node in the first finite-state machine tree to obtain a second finite-state machine tree; determining a signal value of the signal node based on a conditional statement corresponding to the conditional trigger signal and the conditional assignment statement, and updating the second finite-state machine tree based on the signal value to obtain a third finite-state machine tree; updating corresponding state transition information between the signal values of the signal nodes in the third finite-state machine tree to obtain a fourth finite-state machine tree; and combining the fourth finite-state machine trees to obtain a global finite-state machine result.

The present disclosure relates to driving decision-making methods, apparatuses, and chips. One example method includes constructing a Monte Carlo tree based on a current driving environment state, where the Monte Carlo tree includes a root node and N−1 non-root nodes, each node represents one driving environment state, and a driving environment state represented by any non-root node is predicted by a stochastic model of driving environments. Based on at least a value function of each node in the Monte Carlo tree, a node sequence that starts from the root node and ends at a leaf node is determined. A driving action sequence is determined based on a driving action corresponding to each node in the node sequence.

Disclosed are methods and apparatuses for image data encoding / decoding. A method of decoding an image includes receiving a bitstream in which the image is encoded; obtaining index information for specifying a block division type of a current block in the image; and determining the block division type of the current block from a candidate group pre-defined in the decoding apparatus. The candidate group includes a plurality of candidate division types, including at least one of a non-division, a first quad-division, a second quad-division, a binary-division or a triple-division. The method also includes dividing the current block into a plurality of sub-blocks; and decoding each of the sub-blocks with reference to syntax information obtained from the bitstream.

The invention relates to a case-related property query method and system based on a natural language processing technology, and belongs to the technical field of informatization data management.The query method comprises the steps that a natural language query text input by a user is received, word segmentation processing enhanced in the legal field is carried out, and a structured query object is recognized and extracted; inputting into a legal field word vector encoder to generate an entity vector group and an intention vector; calculating the weighted cosine similarity between the entity vector group and each field vector in the database vector index, and matching a target field according to a preset similarity threshold and generating a table connection path; generating an SQL statement according to the target field, the table connection path and the operation intention; executing the SQL statement to obtain an original data set, and constructing a case series tree based on the original data set; and integrating the case-related property state change records along the time axis of the case series tree, generating an enhanced property view, and generating a natural language report and block chain evidence storage data at the same time. The query efficiency and accuracy of the property involved in the case can be improved.

The invention provides a laser engraving path planning method, system and device and a medium, and relates to the technical field of laser engraving, the method comprises the steps that a preset format file is obtained, and the preset format file comprises a three-dimensional model of a to-be-machined part; performing cross cutting on the three-dimensional model to obtain a plurality of intersection points and a plurality of intersection lines; performing contour reconstruction on the three-dimensional model based on each intersection point and each intersection line to obtain at least one closed region segmentation curve; based on each region segmentation curve, determining an inclusion relation among the region segmentation curves by adopting a Vatti polygon cutting algorithm; establishing a topological relation tree based on inclusion relations among the region segmentation curves; performing region division based on the topological relation tree to obtain a plurality of different processing regions; and for each machining area, a preset filling method is adopted to generate a corresponding carving tool path. According to the method, the machining precision is guaranteed through local intersection point and intersection line processing while the machining area is accurately and rapidly divided to generate the carving tool path.

Disclosed are methods and apparatuses for image data encoding / decoding. A method of decoding an image includes receiving a bitstream in which the image is encoded; obtaining index information for specifying a block division type of a current block in the image; and determining the block division type of the current block from a candidate group pre-defined in the decoding apparatus. The candidate group includes a plurality of candidate division types, including at least one of a non-division, a first quad-division, a second quad-division, a binary-division or a triple-division. The method also includes dividing the current block into a plurality of sub-blocks; and decoding each of the sub-blocks with reference to syntax information obtained from the bitstream.

A database system is operable to generating a query operator execution flow that includes an optimized join tree implementing a plurality of join operations applied to a plurality of input row sets based on: identifying a set of filter predicates indicated by the query expression and generating, based on the plurality of input row sets and the set of filter predicates, cardinality data for each of the plurality of input row sets. The optimized join tree is generated based on generating the optimized join tree based on selecting an ordering for applying the plurality of join operations to the plurality of input row sets based on the cardinality data for the each of the plurality of input row sets. The query operator execution flow is executed in conjunction with executing the query expression based on executing the plurality of join operators of the optimized join tree.