Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

469 results about "Named entity" patented technology

In information extraction, a named entity is a real-world object, such as persons, locations, organizations, products, etc., that can be denoted with a proper name. It can be abstract or have a physical existence. Examples of named entities include Barack Obama, New York City, Volkswagen Golf, or anything else that can be named. Named entities can simply be viewed as entity instances (e.g., New York City is an instance of a city).

Method for constructing knowledge graph based on large language model and vector library

The invention discloses a method for constructing a knowledge graph based on a large language model and a vector library, and relates to the technical field of knowledge graphs, and the method comprises the following steps: carrying out word segmentation, part-of-speech tagging and semantic analysis processing on a collected natural language text by using a pre-trained RoBERTa model to obtain a semantic representation vector of the natural language text; through a Seq2Seq framework and an attention mechanism, obtaining association between the semantic representation vector and the corresponding named entity, and obtaining the named entity through the obtained association; constructing a knowledge graph; fusing the constructed knowledge graph with a relational database of a preset field to generate a fused knowledge graph; named entities and corresponding attributes are obtained through dependency syntax analysis, the entity relation of the named entities is obtained, and a structured triple fusing the named entities, the attributes and the entity relation of the knowledge graph is constructed. In order to solve the problem of high entity linking difficulty in the prior art, the knowledge graph is converted into low-dimensional dense vector representation, and an inverted index database and the like are constructed, so that the difficulty is reduced.
Owner:北京长河数智科技有限责任公司 +1

Processing Natural Language Network Queries

A method of operating a network is provided that includes receiving a query, using a first language model to determine an intent or purpose of the query, using a second language model to extract a named entity from the query, and obtaining search results by searching for the extracted named entity on a named entity list corresponding to a particular tenant. The method can further include generating a response based on the search results. The query can be a natural language query, and the first language model can be a natural language model. The second language model for extracting the named entity can be a network-related language model that is trained on network records associated with a plurality of tenants. The network records associated with the plurality of tenants can be stored on a multi-tenant database.
Owner:ARISTA NETWORKS INC

Geological domain named entity recognition and classification method based on thinking chain and hybrid experts

The invention discloses a geological domain named entity accurate recognition and classification method based on thinking chain enhancement and hybrid expert architecture, which is characterized by comprising the following steps: firstly, extracting geological document text data through an OCR (Optical Character Recognition) technology, and extracting structured entity data by utilizing a locally deployed large language model; then calling a local large model to generate a diversified sentence pattern template according to language styles in the geological field, filling the template with the extracted professional entities, and constructing an instruction fine tuning data set; further constructing a thinking chain (CoT) enhanced data set on the basis, and explicitly simulating an expert reasoning process; efficient fine tuning is carried out on the large model by innovatively combining a low-rank adaptation (DoRA) technology and a hybrid expert (MoE) architecture, the DoRA technology carries out dimension reduction decomposition and orthogonal transformation on weight matrixes of a decoder layer and a multi-layer perceptron, and the MoE architecture constructs a plurality of special sub-networks to enhance the multi-task processing capability; and finally, performing entity extraction on the geological document by using the fine-tuned model, outputting an identification result containing a reasoning process, and filtering and perfecting the result through a rule matching mechanism. According to the method, the problems of fuzzy boundary, indefinite semantics, difficulty in classification and the like of the named entities in the geological field are effectively solved, the recognition and classification accuracy of the named entities in the geological field is remarkably improved, and key technical support is provided for downstream applications such as geological resource exploration and mineral evaluation.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Multi-modal power knowledge base construction method and retrieval method based on AI large language model

The invention belongs to the technical field of power system informatization, and provides a multi-modal power knowledge base construction method and retrieval method based on an AI large language model.The method comprises the following steps that S1, classification and named entity extraction are conducted on an original database, and a data set and an entity set are obtained; s2, aligning the data set and the entity set based on an AI large language model; s3, extracting and complementing entity relationships, and constructing an electric power diagram database; s4, performing joint embedding on the entities and the associated data, mapping the entities and the associated data to the same vector space, constructing a multi-modal power knowledge base, and generating a data index; and performing retrieval by using the constructed multi-modal power knowledge base, and performing source file backtracking through a data index. According to the method, multi-modal data are fused, the constructed multi-modal electric power knowledge base is rich and accurate, and source file backtracking can be carried out.
Owner:STONE TECH CO LTD

Named entity recognition method and equipment based on large language model

The invention aims to provide a named entity recognition method and device based on a large language model, and the method comprises the steps: carrying out the data cleaning of a to-be-trained text, carrying out the data enhancement of the cleaned data, and obtaining target data; the lora structure is fused into a large language model LLaMA model, and a new large language model is obtained; training the new large language model by using target data to obtain a target model; and extracting a target entity from the text by using the target model to complete identification of the named entity. Therefore, the problem of insufficient effect caused by less parameter quantity and knowledge in the traditional method is solved, the training data is increased, the effect of the model is improved, the training speed of the model is improved by adopting lora, and the problem of insufficient training resources is solved.
Owner:上海蜜度蜜巢智能科技有限公司

Network security named entity recognition model construction method based on prompt learning thought, electronic equipment and storage medium

The invention discloses a network security named entity recognition model construction method based on a prompt learning thought, electronic equipment and a storage medium, and belongs to the technical field of network security named entity recognition. In order to solve the problem that extracted information is directly applied when facing a specific network security entity identification task, the method comprises the following steps: collecting network security data, obtaining a network space security data sequence, setting a labeling set based on a labeling rule, and generating a labeling sequence; the annotation rule comprises the entity type of the annotated data and the fact that the annotated data does not belong to any entity; based on an annotation rule, segmenting the cyberspace security data sequence, then correspondingly generating annotation subsequences, and obtaining processed cyberspace security data; defining a data augmentation rule, and carrying out data augmentation on the processed cyberspace security data to obtain a cyberspace security data set with data augmentation; and continuing pre-training and fine tuning operation in the pre-training model to obtain the network security named entity identification data extraction model.
Owner:HARBIN INST OF TECH

Conversational agnostic matchmaking model architecture

A system for matchmaking using a conversational agnostic matchmaking model is described. The system can receive a first query indicating a request for document objects and including criteria for selection of the document objects. The system can identify named entities from portions of the first query. The system can generate a second query to obtain the document objects, in response to the named entities being indicative of a context for the first query. The system can obtain the document objects according to the second query. The system can generate a reply to the first query including a description object and the documents, the description object based on the first query. The system can cause a user interface to present the reply to the first query and the description object.
Owner:ADP INC

Entity standardization method and model based on large language model retrieval enhancement

The invention discloses an entity standardization method based on big language model retrieval enhancement, and provides a biomedical entity standardization model generated based on big language model retrieval enhancement. The model converts a named entity standardization task into a question and answer task by constructing a prompt template, and the prompt template is a query about entity mention and comprises the entity mention, context and a candidate entity list. According to the method, the interaction between the entity mention and the standard entity, the interaction between the entity mention and the context information and the interaction between the candidate entities can be effectively simulated. In addition, in order to ensure the consistency of the entity mention and the context information of the candidate entity, the entity description information of the candidate entity is added into the prompt template.
Owner:BEIJING ANDING HOSPITAL CAPITAL MEDICAL UNIV +2

Geographic name entity identification method based on spatial relation perception, medium and equipment

The invention relates to the technical field of natural language processing, in particular to a place name entity recognition method based on spatial relation perception, a medium and equipment, and the method comprises the following steps: constructing a corpus through natural language sentences of place name entities in a network and pseudo sentences constructed by processing a geographic data set, and utilizing the pseudo sentences and the natural language sentences, and further training a natural language model by adopting comparative learning and mask language modeling learning. According to the method, a Chinese named entity recognition model is built based on a natural language model, character-level feature representation is learned through word vector conversion, word-level feature representation is learned through the natural language model, and new feature representation is generated by integrating the character-level feature representation and the word-level feature representation through a fusion embedding layer. And text context semantic features are extracted through a bidirectional long short-term memory network, a global optimal tag sequence is obtained through a conditional random field, and place name entity recognition is realized. According to the method, the overall performance of the place name entity recognition model is improved.
Owner:CENT SOUTH UNIV

Entity information extraction method and device and electronic equipment

The invention relates to an entity information extraction method and device and electronic equipment, and relates to the technical field of cloud computing, and the method comprises the steps: obtaining named entity representative words and corresponding entity information of to-be-labeled network alarm information and historical network alarm information, and the entity information comprises coarse-grained entity information and fine-grained entity information; extracting seed named entities of the network alarm information corpus according to the coarse-grained entity information and the fine-grained entity information, and identifying target related lexical items to expand named entity representative words; performing entity labeling on the target related lexical item by utilizing the expanded named entity representative word to obtain entity information; and performing model training on the entity information extraction model by using the historical network alarm information and the entity information, and performing entity extraction on the network alarm information to be labeled by using the entity information extraction model to obtain the entity information corresponding to the network alarm information to be labeled. And the accuracy of tasks such as entity extraction is improved.
Owner:CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1

Nested named entity recognition

Named Entity Recognition is the identification and classification of named entities within a document. Nested NEs occur when an NE is contained within another NE. The disclosed invention leverages the CapsNet architecture for improved nested NE identification and classification. This includes deriving the features of an input text. The derived features are used to identify and classify any named entities in the text. The system is further configured to identify named entities in the text and perform clustering to group named entities. The disclosed CapsNet considers the context of the whole text to activate higher capsule layers in order to identify the named entities and classify them. The teachings of this invention are applicable to other NER models to improve nested NE identification and classification.
Owner:COGNIZER INC

Identification method and system for complex named entity of natural language text

The invention provides a method and system for recognizing complex named entities of natural language texts, and relates to the technical field of natural language processing, an input and output template containing position information and category information is introduced to guide a candidate entity generation module, and a candidate entity screening module based on a feature enhancement network and a multi-layer perceptron is adopted to recognize the complex named entities of the natural language texts. Therefore, the accuracy and recall rate of entity recognition are improved. According to the method, template guidance, feature enhancement and category information are comprehensively utilized, the invalid output probability is effectively reduced, accurate and comprehensive candidate entities are generated, and accurate and efficient entity recognition is achieved.
Owner:INSTITUTE OF INFORMATION ENGINEERING CHINESE ACADEMY OF SCIENCES

Data processing method and device, medium and program product

The invention relates to the field of computer data processing, in particular to a user generated content-based data processing method, which comprises the following steps of: identifying, namely identifying named entities in notes, and acquiring category words of the named entities; an extraction step: determining a context corresponding to the category word in the note based on the category word; a recall step: performing first recall and / or second recall on predetermined commodity categories based on the category words to select candidate items; and a sorting step: calculating the confidence of the candidate items based on the context, and determining a target commodity category associated with the user generated content from the candidate items based on the confidence. The invention also relates to a user-generated content-based data processing device, a medium and a program product. According to the method, the recall robustness can be improved, and the cost of manually annotating data can be reduced.
Owner:XIAOHONGSHU TECH CO LTD

Geological text translation method based on large language model and retrieval enhancement generation

The invention discloses a geological text translation method based on a large language model and retrieval enhancement generation, and aims to identify a geological text named entity as a keyword and retrieve and query a professional dictionary database to perform enhancement translation. According to the method, when entity recognition is carried out on a fine tuning large language model, a syntax-aware entity pruning (SAEP) method is provided for data enhancement, controllable noise is introduced, and the named entity recognition effect of the large language model is improved. When a vector database is constructed and retrieved, geological classification labels are added to data information based on a data level, and a data similarity query threshold value is set, so that the accuracy of information retrieval is improved, and the illusion problem of a general large language model caused by the lack of professional domain knowledge of training data is effectively reduced.
Owner:SUN YAT SEN UNIV

Generic contextual named entity recognition

Improved systems and methods for named entity recognition (NER) are disclosed and can include attaching domain-specific context to extracted data. In a particular example implementation, the techniques can include an artificial intelligence (AI) based entity extraction and labeling process using unstructured data as input. The generated labels can include automatically determined entity types. The techniques can further include a domain-aware entity resolution process. First, applying a reverse question-and-answer (Q&A) technique to the output of the entity extraction and labeling process can generate a set of predicted entity keys (e.g., predicted metadata identifiers, such as likely database column references) for the extracted entities and entity types. Second, entity alignment operations can enable determining domain-specific entity keys for the predicted entity keys. In some implementations, the techniques can be utilized to identify named entities in an electronic conversation, such as a chat session.
Owner:EXLSERVICE HLDG

Relationship enhanced named entity recognition method and device, medium and program product

The invention discloses a relation enhancement type named entity recognition method and device, a medium and a program product, and relates to the field of data processing. The method comprises the following steps: performing feature extraction on text data through a BERT model to obtain a plurality of tokens and semantic feature vector sequences; performing different-scale convolution operations by using a convolutional neural network to obtain local character combination features, and fusing the local character combination features with the semantic feature vector sequence to form a feature enhanced semantic feature vector sequence; the Transform model determines a long-distance dependency relationship of semantic feature vectors in the sequence by using an attention mechanism; generating a long entity structure model based on the long-distance dependency relationship, and then determining an enhanced semantic feature vector sequence; and performing tag sequence optimization processing on the named entity through a conditional random field layer, determining sequence labeling loss, boundary detection loss and relation prediction loss, determining total loss, and adjusting a tag sequence so as to determine the named entity. According to the method, the accuracy and integrity of named entity recognition can be effectively improved.
Owner:QIZHI TECH CO LTD

Techniques for classifying data using large language models

A system and method for classification. A method includes identifying candidate entities among text data by applying at least one entity identification rule to the text data. Inputs are constructed based on the identified candidate entities, where each input includes a first portion of text indicating a candidate entity and at least one second portion of text and where the at least one second portion of text of each input is adjacent to the first portion of text of the input. Multiple language models are applied to the inputs, where each language model is trained to identify a respective set of entities and where outputs of the language models include at least one portion of entity-indicating text for each input. Based on the outputs of the language models, at least one named entity in the text data is determined.
Owner:CYERA LTD

Generative span-based named entity identification method in big data

The invention relates to a generation type span-based named entity recognition method in big data, which comprises the following steps of: inputting a text sentence into a trained named entity recognition model, and outputting an entity and an entity category in the text sentence; wherein the named entity recognition model comprises a feature extraction module, a candidate span generation module and a candidate span classification module; the feature extraction module is used for performing feature extraction on input text sentences to obtain feature vectors of each word in the text sentences; the candidate span generation module is used for taking the word meeting a preset condition in the text sentence as a span seed according to the feature vector of each word, and generating a candidate span entity according to the span seed; the candidate span classification module is used for classifying the candidate span entities according to a preset template to obtain the categories of the entities, flat entities and nested entities can be recognized at the same time, the calculation amount is reduced, and the recognition efficiency and accuracy are improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Entity identification method, system and equipment for operator business performance index based on large model, and medium

The invention discloses an entity identification method, system and equipment for operator business performance indexes based on a large model, and a medium, belongs to the technical field of artificial intelligence, and aims to solve the technical problems of inaccurate identification, frequent ambiguity, high efficiency and the like generally existing in the existing entity identification technology. According to the technical scheme, efficient, accurate and comprehensive named entities and conversion services are provided by combining a large model, AC keyword matching, similarity search and a natural language processing technology; the method specifically comprises the following steps: constructing an entity library and a vector library; constructing an entity identification fine tuning data set; finely adjusting the large model; identifying a large model entity; performing AC accurate retrieval; performing vector similarity retrieval; operator entity conversion; outputting an index list; and integration: sorting AC accurate retrieval results, vector similarity retrieval results, operator entity conversion results and index list output results according to similarity relevancy from high to low, integrating the results into a unified JSON format and outputting the unified JSON format, and providing standardized data for service calling.
Owner:INSPUR TIANYUAN COMM INFORMATION SYST CO LTD

Supply chain material data management method and system

The present invention discloses a supply chain material data management method and system, the method comprising receiving material data of upstream and downstream enterprises in the supply chain; performing named entity recognition for each material data, and analyzing the semantic dependency of attributes using dependency analysis technology; mapping different entities to corresponding concept nodes in an ontology, and establishing associations between entities and concepts; using a constructed material ontology, performing semantic standardized representation of entities, mapping entities to corresponding concept nodes in the ontology, and replacing them with standardized concept names or identifiers to form a standard material attribute feature library. The present invention realizes the collection and standardized processing of material data of upstream and downstream enterprises in the supply chain and the precise association of upstream and downstream material data.
Owner:ANHUI HIGH QUALITY MINING TECH DEV CO LTD

Determination of data-source influence on data manifestations

Disclosed are methods and system for predicting data-source influences on one or more data manifestations of a named entity. The method includes receiving an inheritance dataset of the named entity. The method determines first and second portions of the inheritance dataset of the named entity. The method determines an aggregated data-bit association score for the named entity based on the inheritance dataset at an identified subset of the data-bit regions. The method determines aggregated data-bit association scores associated with the first and second data source based on the first and second portions of the inheritance dataset at the identified subset of the data-bit regions. The method selects one of the first and second data sources as having a measure of influence on a data manifestation of the named entity corresponding to the identified subset of the data-bit regions.
Owner:ANCESTRY COM DNA LLC

Generating weighted contextual themes to guide unsupervised keyphrase relevance models

The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize intelligent contextual bias weights for informing keyphrase relevance models to extract keyphrases. For example, the disclosed systems generate a graph from a digital document by mapping words from the digital document to nodes of the graph. In addition, the disclosed systems determine named entity bias weights for the nodes of the graph utilizing frequencies with which the words corresponding to the nodes appear within named entities identified from the digital document. Moreover, the disclosed systems generate a keyphrase summary for the digital document utilizing the graph and a machine learning model biased according to the named entity bias weights for the nodes of the graph.
Owner:ADOBE INC

Maintenance conflict processing method and system based on large language model

The invention relates to a maintenance conflict processing method and system based on a large language model. The method comprises the following steps that power grid maintenance documents are collected to construct a word list, and a prompt word template is set; converting the segmented document into a high-dimensional semantic vector to construct a vector database; matching contents in a database, adding a cue word template, generating a named entity extraction result by using a plurality of large language models, replacing a document entity with an entity type to construct a predicate proximity graph, and aligning predicates by comparing a relation semantic type; generating entity vector representation by using a TransE method, aligning different map entities and judging a corresponding relation; based on the cue word template and the domain word list, the power grid maintenance document entity is identified, the conflict information is extracted, the conflict information is integrated in combination with a multi-model mechanism, conflict identification and mediation between maintenance tasks are achieved, and the power grid maintenance efficiency and safety are improved.
Owner:ANHUI JIYUAN SOFTWARE CO LTD +2

Method for processing insulation status data of power equipment

The present application relates to a method for processing insulation status data of electric equipment. The method comprises: obtaining text data of insulation status of electric equipment, and identifying and extracting named entities of the text data of insulation status of electric equipment to obtain entity vocabulary; performing co-reference resolution processing on the entity vocabulary to determine the final entity library; classifying the association relationship between entity vocabulary in the final entity library to obtain classified data; normalizing the classified data, and outputting normalized data for importing into a graph database. The use of this method can reduce the manual workload of the data processing process, has good applicability, and greatly increases the processing efficiency of insulation status data of electric equipment.
Owner:GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

General named entity recognition method based on continuous learning and prompt template

The technical scheme of the invention provides a general named entity identification method based on continuous learning and a prompt template. The method is characterized in that: 1, the method only needs a small amount of annotation samples of past entities; 2, a neural network layer does not need to be expanded, and a new encoder layer does not need to be copied every time to construct a new model; according to the method, training is always carried out on the same model, so that waste of a storage space can be avoided, and an output layer of the model does not need to be dynamically adjusted and retrained each time; and 3, a representative difficulty-based sample playback method and an EWC-based regularization method are innovatively combined, so that the problem that the performance of the NER model in continuous learning is rapidly reduced due to a catastrophic forgetting problem is greatly relieved. According to the method, developers can be guided to better complete a named entity recognition task under class increment setting, and the named entities in the unstructured text are quickly and accurately positioned and classified into predefined types.
Owner:NANJING UNIV

Intelligent equipment fault information extraction method based on multi-semantic knowledge interaction and dynamic pruning

The invention discloses an intelligent equipment fault relation extraction method based on multi-semantic knowledge interaction and dynamic pruning. Performing word segmentation and sentence segmentation on the original equipment fault text to obtain a statement set; obtaining a character-level word embedding representation set of the text by using a pre-training language model; extracting fault entity representations, obtaining fault type representations based on the constructed fault type knowledge base, constructing semantic association between the fault type representations, and generating a context feature representation sequence; calculating a correlation score between the enhanced semantic representation and an original text statement based on a dot product attention mechanism, dynamically selecting a core statement set, focusing the core statement, updating the semantic representation, and inputting the semantic representation into a relationship classification module to predict a relationship type between the entity pairs; and finally, outputting a named entity boundary and a relation label based on conditional random field decoding to obtain a final relation extraction result. According to the method, the ability of understanding the context is enhanced, and the fault relation extraction task under the complex context can be better processed.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY

Transforming natural language to structured query language based on scalable search and content-based schema linking

Techniques for preprocessing data assets to be used in a natural language to logical form model based on scalable search and content-based schema linking. In one particular aspect, a method includes accessing an utterance, classifying named entities within the utterance into predefined classes, searching value lists within the database schema using tokens from the utterance to identify and output value matches including: (i) any value within the value lists that matches a token from the utterance and (ii) any attribute associated with a matching value, generating a data structure by organizing and storing: (i) each of the named entities and an assigned class for each of the named entities, (ii) each of the value matches and the token matching each of the value matches, and (iii) the utterance, in a predefined format for the data structure, and outputting the data structure.
Owner:ORACLE INT CORP

Named entity recognition method and apparatus, terminal device, and storage medium

ActiveCN111339775BNatural language data processingMatrix additionAlgorithm
The application is suitable for the technical field of computers, and provides a named entity recognition method, including: acquiring a to-be-recognized text, and converting the to-be-recognized text into a first matrix of n*k dimensions; performing multi-layer convolution layer convolution on the first matrix, wherein the last convolution layer of a convolution kernel in the multi-layer convolution layer has a channel number of m, four convolution operations are performed on the last convolution layer, and four parallel second matrices of n*m dimensions are obtained; performing attention weight self-adaption on three second matrices of the four second matrices to obtain a third matrix of n*m dimensions, performing matrix addition on the third matrix and the remaining one second matrix, and outputting a fourth matrix of n*m dimensions; performing classification on the fourth matrix, and outputting an entity label corresponding to the to-be-recognized text; and outputting a named entity corresponding to the to-be-recognized text according to the entity label. By introducing an attention mechanism in the convolution layer, data redundancy is effectively reduced, the number of model parameters is reduced, and the recognition speed of the named entity recognition model is accelerated.
Owner:PING AN TECH (SHENZHEN) CO LTD

Border event aggregation classification algorithm based on space-time correlation analysis

The invention discloses a boundary event aggregation classification algorithm based on space-time correlation analysis. The algorithm comprises the following steps: constructing event classification and a named entity model; calculating association rules between border events based on the historical event topic collection data; constructing a affair graph based on association rules; performing event classification and named entity identification on the border events based on event classification and a named entity model; and based on the event classification and the named entities, classifying and sorting the border events through the event atlas to obtain a border event aggregation result. Aiming at the characteristics of border event data, the invention provides an incidence relation mining algorithm based on the border events, the event atlas of the border events is obtained and is used for incidence aggregation of the events, the border event rules can be effectively extracted, and the events are collected according to themes.
Owner:NO 15 INST OF CHINA ELECTRONICS TECH GRP

Named entity identification method and device, computer equipment and storage medium

The invention provides a named entity recognition method and device, computer equipment and a storage medium. The method comprises the steps of obtaining an initial text to be subjected to entity recognition processing; obtaining first feature information and second feature information of the initial text based on the initial text and the part-of-speech information of each word in the initial text; and determining the named entity in the initial text according to the first feature information and the second feature information. According to the named entity recognition method provided by the embodiment of the invention, the recognition efficiency of the named entity is improved without depending on prompt construction information input by a user in an auxiliary manner, and the accuracy of obtaining the named entity by subsequent decoding is also ensured by fusing the part-of-speech information of the words in the encoding process.
Owner:TCL TECHNOLOGY GROUP CORPORATION