2216 results about "List" patented technology

The invention relates to the technical field of data processing, in particular to a method and system for processing data based on a large language model.The method comprises the following steps that based on inter-sentence punctuation positioning and part-of-speech tagging, sentence blocks are divided to generate functional partitions, themes and relational words are extracted to judge semantic chain starting points, a trigger index sequence is constructed, and logic jump points and breakpoint positions are recognized; and mapping the label structure to the language model output analysis deviation, and generating a label mapping combination list. According to the method, semantic turning nodes can be captured by analyzing the semantic direction change trend, the relation between the semantic turning nodes and verb and noun combinations is judged, the position of a trigger point of an actual information transfer effect is extracted, and the break point area of a semantic path is recognized through the positioning of key word starting and stopping blocks and the logical judgment of noun group cross combination; the path integrity has a clear fracture identifier, a traceable semantic mapping structure path is established in a language model, and the accuracy, coherence and hierarchy clearness of semantic reconstruction are enhanced.

The invention relates to the technical field of data asset sharing, in particular to a data asset sharing method and system based on square and circular clouds, and the method comprises the following steps: obtaining data structure information and establishing a standardized list, counting field matching and jumping conditions to construct a remapping list, extracting an idle path aggregation path group to generate a candidate list, and judging priority conflicts to generate a shunting mapping result, and performing sharing operation on the combined fields and the paths in a butt joint manner. According to the invention, through combination of field name coding and type expression, the unified field identification capability is enhanced, coding difference and type vector difference are adopted to synthesize a score and screen a remapping field pair, the field matching precision is improved, and a path state, service attribution and priority elements are fused to construct a path group; the alternative number and the distribution identifier are configured under the path conflict, and the field and the path number are combined and butted, so that the granularity collaborative sharing is realized, the correspondence between the data channel structure and the access control is enhanced, and the stability of data sharing under multiple environments is improved.

The invention provides a cross-domain book recommendation method and system based on a neural network, and relates to the technical field of intelligent book recommendation, and the method comprises the steps: obtaining first information containing user reading history, retrieval behaviors, research directions and paper information, and converting the first information into an initial interest topological structure and an evolution trend of a user; then, a cross-domain interest migration graph of the user is obtained through Markov clustering; and inputting the interest migration graph and the structured book text information into an extended probability latent variable semantic model to obtain a semantic embedding expression fusing user interests. Potential association scores between the user and the books are calculated through association analysis of the expression and the interest migration graph, a cross-domain recommendation list is generated according to sorting, and personalized and structured book recommendation is achieved. According to the method, deep alignment of the interest migration structure and the semantic space is realized, and the accuracy and practicability of cross-domain recommendation are remarkably improved.

The invention discloses an intelligent document analysis method and system, the method is executed by the intelligent document analysis system, and the method comprises the following steps: carrying out layout analysis on a PDF page by adopting a deep learning model; merging the block list from bottom to top by adopting a recursive algorithm; carrying out balance optimization on the binary tree structure; and outputting a result of the processed binary tree structure by adopting a preorder traversal mode. Layout analysis is carried out by adopting a deep learning model, various complex typesetting formats such as multi-column layout, image-text mixed typesetting, tables, lists and the like can be effectively identified and processed, and semantically continuous text blocks are ensured to keep continuity in a tree structure through a tree structure optimization module; a global semantic error correction module is added to carry out global document semantic representation learning and carry out adaptive adjustment and error correction on a preliminary structure, so that deep ambiguity is eliminated, logic errors are repaired, and the consistency of a final analysis result and human reading logic on the semantic level is maximized.

The invention relates to the technical field of knowledge graph question answering, and discloses a knowledge graph retrieval reasoning method and system based on big language model enhancement, and the method comprises the steps: carrying out the entity extraction of a user question through a big language model, and generating a candidate entity list; retrieving entity nodes corresponding to the candidate entity list in a knowledge graph database through a mixed retrieval method of fuzzy matching and vector retrieval; re-screening the entity nodes by using a large language model to generate a starting node list; performing width-first traversal on each node in the starting node list in an edge-in direction and an edge-out direction, and retrieving a reasoning path in the knowledge graph; constructing the reasoning path into a prompt template, and inputting the prompt template into a large language model to generate an answer to the user question; according to the method, the big language model is utilized to analyze questions and query the knowledge graph in the knowledge graph question-answering scene, question-answering is performed based on the knowledge graph path, and the effectiveness and accuracy of user knowledge graph question-answering are improved.

The invention discloses an enterprise scientific and technological achievement adaptation method based on big data accurate retrieval and query, and relates to the technical field of big data processing and knowledge maps, and the method comprises the steps: constructing an enterprise technical field knowledge map based on a standardized multi-modal feature matrix, receiving incremental technical data in real time by adopting an Apache Flink streaming processing framework, and carrying out the real-time retrieval and query of the enterprise technical field knowledge map. Dynamically updating a graph node relationship, removing expired nodes through a pruning algorithm, and outputting a dynamic knowledge graph with a timestamp; and receiving a query request of a user, extracting a query vector by utilizing the cross-modal embedding model, retrieving a Top-N candidate node list through a dynamic knowledge graph, calculating a comprehensive similarity score in combination with a graph relation weight, and outputting a sorted technical achievement list. Multi-source heterogeneous data is mapped to a unified semantic space through a cross-modal embedding model, and the intelligent level and the actual application effect of scientific and technological achievement adaptation are comprehensively improved in combination with construction and updating of a dynamic knowledge graph.

The present disclosure pertains to natural language techniques for querying data stored in feature stores using zero shot learning. In a particular aspect, a computer-implemented method includes receiving a natural language query for retrieving features from a feature store, generating an input prompt by appending a script to the natural language query, and then using a large language model to determine tables or databases from the feature store that are relevant to the natural language query, retrieve metadata for the tables or databases from the feature store, determine feature groups comprising features relevant to the natural language query, and generate a programming language query based on the input prompt, the metadata, and the groups. A list of features within the feature groups that are accessible within the feature store may then be retrieved by executing the programming language query on the feature store.

The invention discloses a literature semantic search method and system based on elastic search, and relates to data retrieval. The literature semantic search method comprises the steps that vectorization processing is conducted on a noun phrase list by means of a text2vec-based-multilingual model trained based on a CoSENT method; according to the semantic vector, performing approximate nearest neighbor search in a second retrieval module to obtain first candidate data; inputting the query text data into a first retrieval module, and performing keyword matching through a BM25 algorithm to obtain second candidate data; fusing the first candidate data and the second candidate data to obtain third candidate data; a Sequence Matcher algorithm is adopted to calculate character string similarity between expansion words in the third candidate data, a similarity threshold value is set based on the length of the longest common subsequence, duplicate removal is carried out, and fourth candidate data is obtained; and performing weight distribution based on positions and similarity scores on the fourth candidate data, and enhancing the distinction degree of the extension words by expanding a score interval to obtain extension word recommendation list data. According to the method, the accuracy of document retrieval is remarkably improved.

The invention discloses an intelligent bid invitation file generation method and system based on text automation, and relates to the technical field of artificial intelligence and data processing, and the method comprises the steps: carrying out the semantic analysis of a bid invitation demand text through a project type recognition model, and extracting a feature vector and a keyword set of a project; based on the feature vector, a cosine similarity algorithm is adopted to retrieve a matching template in a preset bid invitation file template library, a candidate template list is generated, and label classification and parameterization setting are carried out on templates of the candidate template list; based on the keyword set, carrying out content adaptation on templates of the candidate template list, and generating an initial bid invitation file; and performing segmented auditing on the initial bid invitation file, adjusting the keyword set in combination with auditing opinions, and synchronously updating the keyword set to the parameterized database through the mapping relationship to generate the bid invitation file. According to the invention, closed loop from demand to achievement is realized, labor cost of bid invitation file compiling is reduced, and bid invitation file quality and generation efficiency are improved.

The invention provides an abnormal behavior recognition method and system based on multi-dimensional data analysis, and the method comprises the steps: carrying out the cleaning and standardization processing of structured data and unstructured data, obtaining a data set in a unified format, employing a natural language processing technology, processing the document text in the data set, extracting the entity, relation and behavior information, and carrying out the recognition of abnormal behaviors. Generating a structured feature vector; constructing behavior statistics, time sequence and association features by using the feature vectors and the structured data, selecting a feature combination by adopting a sampling algorithm, establishing an entity relation graph according to association data in a constructed multi-dimensional feature set, calculating association strength among entities, and optimizing the entity relation graph according to the association strength to establish a network structure model; a feature weight system is set according to the model and a multi-dimensional feature set, a multi-dimensional abnormal score is calculated by using a pruning tensor structure measurement method, an abnormal score is comprehensively calculated by using a low-rank tensor recovery technology, and an early warning list is output, so that the recognition accuracy and efficiency can be improved.

The invention relates to the technical field of metadata generation, and discloses a data platform metadata automatic generation method based on a large model, which comprises the following steps of: firstly, performing unified standardization and preliminary grammatical analysis on an original SQL (Structured Query Language) code to obtain a structured intermediate representation; on the basis, preliminary blood relationship analysis based on rules is carried out, and simple column references are quickly identified and processed. For complex expressions which are difficult to accurately analyze by a traditional method, code snippets and context information of the complex expressions are accurately extracted and submitted to a large language model for deep semantic understanding and complex blood relationship analysis. And finally, integrating the complex consanguinity analyzed by the large model with the initial consanguinity list to form a comprehensive and accurate field-level consanguinity, and further generating complete data platform metadata. In this way, the defect that a traditional analysis tool understands complex semantics is effectively overcome, and the accuracy and integrity of metadata generation are remarkably improved.

The invention provides a cross-frame code migration method and system, electronic equipment and a storage medium, and the code migration method comprises the steps: carrying out the frame-level conversion of a first frame code, and generating a target engineering skeleton adaptive to a second frame protocol; analyzing the construction configuration and the entry file, determining an entry point and a compiling rule of code migration, analyzing the first frame code through an abstract syntax tree, and generating a target code range list needing to be migrated; and according to the target code range list and the dependency item list, applying a preset conversion rule to the first framework code, and generating a second framework code adaptive to a second framework protocol. Through automatic framework-level conversion and dynamic rule adaptation, rapid migration from the first framework code to the second framework code is realized, a multi-terminal code library is unified, the manpower development cost is reduced, synchronous operation of business iteration and migration is supported, and the development efficiency is improved.

The invention discloses a root cause analysis method and device based on a large language model, equipment and a medium. The method comprises the steps that a target entity and a topological relation are extracted in response to a root cause analysis request; searching matched historical root cause cases in a vector database, inputting the topological relation, the historical root cause cases and cue words into a large language model to generate a doubtful point list, and extracting downstream entities in the doubtful point list; calling a detection tool to collect entity diagnosis data and identify abnormal downstream entities; returning to execute the operation of retrieving the historical root cause case until a preset iteration ending condition is met; and inputting the final doubtful point list, the abnormal diagnosis data, the topological relation and the historical root cause case into the large language model again to obtain a root cause reasoning result and generate a root cause report. According to the embodiment of the invention, through the full-chain design of natural language understanding, topological constraint, historical cases, dynamic detection and iterative reasoning, the fault positioning efficiency and the root cause accuracy are improved, and the operation and maintenance labor cost and the service fault time consumption are remarkably reduced.

The invention relates to the technical field of language data processing, in particular to a language data processing method and system, terminal equipment and a storage medium. The method comprises the following steps: acquiring current round dialogue data of a user; performing dialogue language text processing according to the current round dialogue data of the user to obtain current round dialogue language feature data; carrying out anonym detection on the current round dialogue language feature data, and carrying out dynamic historical anchor point screening to obtain cross-round screening anchor point list data; performing multi-round dialogue intention evolution reasoning according to cross-round screening anchor point list data to obtain an interaction adjustment intention representation strategy; and according to the interaction adjustment intention representation strategy, carrying out current round dialogue language key referring word determination so as to realize cross-round dialogue type language referring word identification. According to the method, the cross-round dialogue type language anonyms are accurately recognized through multi-round dialogue situation and multi-modal clue language data processing.

Embodiments described herein provide a large language model (LLM) based AI agent that adopts Monte-Carlo Tree Search (MCTS) to execute a task. The LLM is prompted with a task description and it responds with its first attempted list of actions. Based on the success or failure of the first attempt, the LLM is prompted with an updated prompt which includes feedback from the first attempt based on a determined reward. The prompt may include a relative “score” for each action taken at each step. A numeric score may be mapped to a set of pre-defined text labels, such as “high” or “low” value putting the score in a form more suited for an LLM prompt. In this way, the LLM is iteratively given prompts which are updated with the scores from each action taken at each previous iterations so that it traverses different paths on the tree in each iteration.

The invention discloses a supply chain production scheduling optimization method and system based on multi-source data. According to the method, supplier purchase data is extracted through a data crawler, raw material sharing is analyzed in combination with a knowledge graph, and a raw material sharing list is generated; on the basis of delivery records and product attributes, a quality stable value is predicted through linear regression, process similarity is calculated through a text similarity algorithm, and a process similarity matrix is constructed; in combination with historical sales data, a market demand prediction model is constructed by applying multiple linear regression and time sequence analysis. A complex relation among raw material sharing, process similarity and market demands is described through a graph neural network, a product association network graph is generated, an optimal balance point is found between delivery time and a resource utilization rate through Pareto optimization, and a production scheduling scheme is formed; and finally, integrating the performance score, the quality stable value, the raw material sharing list and the production scheduling scheme through an integer programming algorithm, and optimizing a supplier combination. According to the invention, the production scheduling efficiency and precision are improved, and complex business requirements are met.

The invention discloses a multi-dimensional natural resource intelligent monitoring method and system based on big data analysis, and relates to the technical field of resource monitoring, and the method comprises the steps: calculating the information sharing degree between different data streams, constructing an abnormal feature credibility distribution map, and carrying out the calculation of the abnormal feature credibility distribution map; and inputting the abnormal feature credibility distribution graph and the multi-source auxiliary information into an integrated classifier, carrying out joint analysis and comprehensive research and judgment on multi-dimensional information to output a target list, constructing an event response relation graph reflecting a monitoring task priority and an execution logic relation according to the attribute features of each element in the target list, and carrying out event response analysis on the monitoring task priority and the execution logic relation. Wherein each node represents a to-be-monitored target, an edge represents a dependency relationship between tasks, and an optimal monitoring execution path is planned for various intelligent monitoring carriers by using an improved A algorithm integrated with a multi-factor cost function. Through natural resource monitoring of multi-modal data interference correction, intelligent classification and path optimization and dynamic response, the monitoring quality and the execution efficiency are effectively improved.

The invention discloses an information retrieval system and method based on semantic normalization, and relates to the technical field of artificial intelligence information, and the method comprises the steps: collecting a semantic query record input by a user, carrying out the preliminary semantic analysis, and generating structured data; on the basis of the structured data, entity disambiguation is carried out by utilizing a knowledge graph, abstract classes are generated through a neural network, calibration and dynamic weight adjustment are carried out, and high-confidence entity abstract classes and confidence scores are generated; entity abstract classes and confidence scores are combined with user contexts, an action-value function is calculated through a value network, and an optimal action is selected by utilizing a-greedy algorithm; executing semantic normalization mapping according to the optimal action, and obtaining an intermediate expression by using a meta-symbol dynamic generator; and performing index retrieval and multi-dimensional sorting based on the intermediate expression to generate a sorted retrieval result list. According to the method, the semantic fragmentation problem of multi-modal query is solved, and deep semantic alignment and dynamic weight calibration of heterogeneous data are realized.

The invention discloses a structured data retrieval system and method based on semantic matching and hierarchical indexing, and the related retrieval system comprises a first construction module which is used for extracting slice data in a preset vector library and meta-information corresponding to the slice data, and constructing a text node object containing an id; the second construction module is used for traversing a text node object to obtain meta-information subjected to hierarchical structure processing, and constructing a nested index tree; the directory decomposition module is used for receiving an input text, performing decomposition based on a hierarchical structure and generating a corresponding query vector; the retrieval module is used for performing semantic retrieval and hierarchical retrieval on the text in sequence to obtain a retrieval result; the grouping and sorting module is used for grouping the retrieval results according to the hit hierarchy, sorting the retrieval results in each group according to a descending order, and combining all groups to obtain a final retrieval result list; and the data backtracking module is used for acquiring an original text field from the vector database according to the id corresponding to the retrieval result.

A method develops a programming language model for machine learning tasks. The method includes adjusting a token list to include a language token used by a tokenizer for a pretrained language model. The pretrained language model includes a set of layers. The set of layers includes a set of initial layers, an embedding layer, and an output layer. The method further includes performing an output layer modification of the output layer to replace the output vector with the embedding vector. The method further includes freezing the set of initial layers to generate a set of frozen layers of the pretrained language model that do not update during training. The method further includes training the pretrained language model using the language token, the output layer modification, and the set of frozen layers to form a fine-tuned model from the pretrained language model.

The present invention provides a method for training a complex machine learning model based on a dataset that comprises datapoints and ground truth labels for at least some of the datapoints of the dataset, wherein the datapoints comprise images, the method comprising:using a reduced-complexity machine learning model to predict pseudo labels for the dataset, andtraining the complex machine learning model using an extended dataset that comprises the ground truth labels and the pseudo labels as output.

The invention relates to the technical field of text inspection and analysis, in particular to a localized bidding document error inspection method based on a large language model, which comprises the following steps of: constructing a bidding requirement knowledge graph which comprises a plurality of requirement item nodes, the requirement item node attribute comprises requirement content, a chapter to which the requirement item node attribute belongs and an importance level; establishing a preliminary mapping relationship between the requirement item node and the text content set, and generating a structured bidding file parse body; and carrying out double-round model analysis and error checking, generating an error record for the items judged to be not satisfied, and outputting a structured error list comprising the non-satisfied items and reasons of the non-satisfied items. The method improves the accuracy and coverage of error checking, and is especially suitable for checking scenes of bidding and tendering documents with numerous and jumbled contents and various formats.

Certain aspects and features of the present disclosure relate to providing contextually grounded recommendations using a large language model. For example, a method involves receiving domain specific data for a simulation and transforming the domain specific data into a labeled, natural language description of the domain specific data. The method also involves providing the labeled, natural language description and a classification task prompt with interaction history to a large language model (LLM) to generate a contextually enhanced LLM configured to produce context-aware output. The method further involves outputting, using the contextually enhanced LLM, an interactive list of scored actions corresponding to the simulation. The interactive list can be used to produce a sequence of actions to direct a process or control a machine.

An embodiment detects by a Clustering Component of a Recommendation System, a candidate content based on a user query, responsive to the detected candidate content, executes a clustering algorithm on the detected candidate content to output a cluster and a cluster result. The embodiment decides, by a Recommendation Clarification Component of the Recommendation System, to recommend a clarification based on the cluster result, comprising computing a distance between a cluster and a response of a large language model to the user query where an option list is updated with the clarification where the clarification is based on the cluster and the distance. The embodiment also detects by the Recommendation System a selection in the option list, responsive to the detected selection, generates a prompt based on the selection where the prompt is inputted into the Recommendation System and the large language model.

The invention provides a file uploading attack interception method based on semantic entropy enhancement, and aims at overcoming the defects of an existing file uploading security protection technology in the face of complex attacks. The method specifically comprises the steps that S1, file format analysis and content extraction are conducted, hidden scripts are mined through nested content recognition, and intermediate representation is generated through grammar cleaning and coding specifications; s2, constructing an abstract syntax tree and semantic entropy calculation, tracking a pollution chain, analyzing a high-risk function, identifying a high-entropy character string, modeling and controlling flow complexity, and generating a semantic entropy vector; s3, dynamic scoring and decision making are carried out, and accurate judgment is carried out in combination with white list perception, feature comparison, multi-modal model scoring, adaptive threshold and sandbox observation; and S4, carrying out real-time interception and feature synchronization, blocking malicious file landing, generating an attack log and synchronizing an attack fingerprint. The method takes the semantic entropy vector as a core, breaks through the limitation of static features, remarkably improves the recognition rate of complex attacks, reduces missed judgment, and guarantees the safety of Web applications.

The invention relates to a data cleaning method based on rule data driving and a data cleaning engine, and belongs to the technical field of data processing. The data cleaning method comprises the following steps: receiving original data streams of a plurality of heterogeneous service systems; extracting a multi-source data feature and a cross-system field association feature, and constructing to obtain a data feature fingerprint; similarity matching is carried out on the data feature fingerprints, rules with the matching degree higher than a preset threshold value are screened, and a candidate rule set is obtained; converting the candidate rule set into a directed acyclic graph; marking conflict rule pairs to obtain a conflict early warning list; a virtual isolation layer is inserted into the directed acyclic graph, and a path identification table is generated; performing topological sorting according to the directed acyclic graph, generating a rule execution sequence, and performing cleaning processing on the original data stream; distributing a data execution channel according to the path identification table; and outputting the cleaned clean data stream and the cleaning log containing the rule execution path. According to the invention, data from different business systems can be efficiently and accurately processed.

The invention discloses a dynamic field verification method and system based on user-defined annotations, belongs to the technical field of computer software, and aims to solve the technical problem of how to realize flexible and efficient parameter verification, improve development efficiency and reduce duplicated codes. The technical scheme adopted by the invention comprises the following steps: creating a user-defined annotation: defining a user-defined annotation (at) ValidateFields, and setting up a ValidateFields set in the ValidateFields set in the ValidateFields set in the ValidateFields set in the ValidateFields set in the ValidateFields set; the parameter name list receiving module is used for being marked on an input parameter of a Controller layer and receiving a character string array as a parameter name list; a field verification annotation is created, wherein an annotation (at) ValidateField used for being labeled on an entity class field is defined; creating a verification tool class: creating a verification tool class Validation Util, reading the annotation by using a reflection mechanism, and executing verification logic; and automatic logic verification: using Spring AOP to realize automatic logic verification, intercepting a method of adding (at) Validate Fields annotations in parameters, performing parameter verification through a verification tool class, executing a target method if the verification passes, and returning failure information if the verification fails without manually calling the verification tool class.

The invention relates to the technical field of information retrieval, and provides a multi-dimensional heterogeneous knowledge recall enhanced hybrid retrieval method and system.The method comprises the steps that texts recalled through keyword retrieval, sparse vector retrieval and dense vector retrieval are screened through a reciprocal sorting fusion algorithm, and a text type candidate knowledge list is obtained; based on user query, generating and checking a query statement through a large language model, and retrieving an entity-relationship-attribute triple from the knowledge graph library; based on user query, generating enhanced knowledge through a knowledge graph enhanced retrieval method fusing keyword retrieval, vector retrieval and community retrieval; and carrying out format alignment and duplicate removal on the text type candidate knowledge list, the triple result and the enhanced knowledge to form a multi-modal candidate pool, and carrying out reordering score calculation and ordering on each piece of recall knowledge in the multi-modal candidate pool through a reordering model and a business rule to obtain a final retrieval result. And the coverage blind area of single retrieval on heterogeneous knowledge is solved.

The invention belongs to the technical field of database management, and particularly relates to a knowledge base intelligent management system and method based on a large model, and the system collects question and answer texts and index information of different target subjects through a data collection module, and generates a first text hierarchical sequence and a directed index graph through word segmentation preprocessing and directed graph neural network mapping; the feature extraction module extracts text and index embedding representation in combination with a feature distillation model, and obtains similar overlapping degrees of different target main bodies through a three-dimensional overlapping degree model; the conflict simulation module constructs an initial knowledge base based on a tree database, detects index conflicts in target subjects and among the subjects by using a Bayesian simulation algorithm, and generates a conflict risk list; the conflict resolution module outputs a resolution strategy in combination with a conflict resolution confrontation model, and the feedback adjustment module iteratively optimizes the knowledge base until a conflict threshold and a user demand are met; according to the method, intelligent management of cross-subject question and answer indexes is realized, and knowledge base conflict resolution efficiency and cross-subject query accuracy are improved.

The invention provides a standardized data processing method based on a large model, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: generating a standard field semantic vector through large model coding field name character string input, a field value sample list and context structure information of a field; calculating a semantic offset degree between the semantic vector of the field to be standardized and the semantic vector of the standardized field, and generating a successfully matched field pair set and a normalized failed field set; obtaining a historical standard version, and generating an optimal field and maximum score version mapping set; semantic positioning is carried out in the maximum score version according to the optimal field, and a matching field is calculated; and obtaining standard mapping field information under the current version based on the mapping rule table of the matching field, and outputting the standard mapping field information. The problem that a traditional rule system depends on a fixed field and is not sensitive to version change is solved.