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

712 results about "Database retrieval" patented technology

Systems and methods for tokenization

Computer-implemented systems and methods for tokenization. The system includes a network, at least one token database coupled to the network, and a batch tokenization server coupled to the at least one token database via the network, the server having a token table. The server is configured to receive at least one batch request comprising a delta table. In response to the batch request, the server retrieves a plurality of recent tokens from the at least one token database and updates the token table with the plurality of recent tokens. The server determines whether at least one payload to be tokenized from the delta table has a respective at least one corresponding entry in the token table. For each of the at least one corresponding entry that is not found in the token table, the server generates a new token and updates the at least one token database.
Owner:THE TORONTO DOMINION BANK

IoT security knowledge-based chatbot system

A stateful chatbot system leverages generative AI to provide an interface by which users can retrieve information from backend IoT databases of a security provider via natural language queries. Upon receiving a natural language query that corresponds to a request for information from the database, the chatbot generates a corresponding database query having a format compatible with the database. The chatbot comprises a generative model adapted to generate database queries based on natural language queries via prompt engineering using natural language and database query pairs. The chatbot queries the database with the generated database query, retrieves results comprising data / metadata that satisfy the query, and generates a summary of the results, both of which it presents as a response to the user's query. The chatbot also has access to a vulnerability database from which it can obtain information about known vulnerabilities documented therein to respond to user queries.
Owner:PALO ALTO NETWORKS INC

Multi-round dialogue interaction method and system based on context reconstruction and multi-library retrieval

The invention provides a multi-round dialogue interaction method and system based on context reconstruction and multi-library retrieval, and the method comprises the steps: firstly obtaining a multi-round dialogue data set of a target user, which comprises a plurality of dialogue round sequences composed of user input statements and system response statements; performing context reconstruction processing on the multi-round dialogue data set to generate context reconstruction characteristics of each dialogue round sequence, covering current round semantic focus offset and historical round semantic dependence intensity, and retrieving a matched multi-database retrieval result from a preset heterogeneous database based on a dynamic context window, a candidate response statement set and confidence are included. Performing multi-strategy matching on context reconstruction features and retrieval results, generating a response generation strategy to adjust candidate response semantic priorities and confidence thresholds, and finally feeding back the response generation strategy to a dialogue service system to trigger response optimization operation, and updating heterogeneous database retrieval weights and context window dynamic adjustment parameters.
Owner:JIEHELIX (SHANGHAI) MEDICAL TECH CO LTD

Knowledge database retrieval method based on feature extraction

The invention relates to the technical field of database retrieval, in particular to a knowledge database retrieval method based on feature extraction. The method comprises the following steps of obtaining a document to be retrieved, performing local hash de-duplication processing and extracting multi-modal features, performing feature spectrum clustering processing and associated entity analysis on the extracted features, generating a feature associated entity structure, performing document topic modeling and semantic direction positioning, and extracting a semantic topic of the document. The method comprises the following steps: performing word vector retrieval on a to-be-retrieved document and a knowledge database by utilizing a document semantic topic, generating word vector retrieval data, performing sentence vector retrieval, generating a final document retrieval result, integrating word vectors and the document retrieval result, and executing feature retrieval of the knowledge database through an intelligent retrieval engine, thereby realizing efficient knowledge query. The knowledge database retrieval method is more intelligent and more accurate.
Owner:GUANGZHOU XIAOHU QIANCHUAN CULTURAL COMMUNICATION CO LTD

A vector database retrieval method and system

The present invention proposes a vector database retrieval method and system, which relates to the technical field of big data processing and intelligent information retrieval. The method includes preprocessing high-dimensional multimodal data to obtain a dimension reduction feature vector; constructing a cluster center based on the dimension reduction feature vector; establishing an inverted file and an intra-cluster plane index based on the cluster center, compressing the inverted file and the intra-cluster plane index to obtain a compressed inverted file and an intra-cluster plane index; obtaining a user's query vector, using the inverted file to screen candidate clusters for the query vector, introducing a hierarchical navigable small-world graph in the intra-cluster plane index, performing an intra-cluster search on the cluster cluster, and obtaining a vector database retrieval result. The present invention effectively takes into account the efficiency and accuracy of high-dimensional data retrieval, and improves the retrieval efficiency and accuracy.
Owner:GUANGZHOU FANGHE DATA SERVICE CO LTD

Vertical large language model training method and system in carbon neutralization field

The invention discloses a vertical large language model training method and system in the carbon neutralization field, and the method comprises the following steps: collecting data of the carbon neutralization field, carrying out the data preprocessing, constructing a carbon neutralization field knowledge base, and updating the carbon neutralization field knowledge base through a dynamic updating mechanism; performing dynamic semantic partitioning and vectorization coding on the text of the carbon neutralization domain knowledge base, and storing the text into a vector database; performing staged fine tuning on the pre-trained large language model based on a low-rank adaptation technology, wherein the fine tuning comprises general instruction fine tuning and carbon neutralization field professional fine tuning; a retrieval enhancement generation mechanism is adopted, knowledge fragments related to user query are retrieved through a vector database, and a large language model is input to generate answers. Compared with the prior art, the method has the advantages that the answer reliability is improved through conflict detection and source tracing, so that the large language model can more accurately adapt to knowledge requirements in the carbon neutralization field.
Owner:SUN YAT SEN UNIV

Text-to-structured query language conversion method based on large language model

A text-to-structured query language conversion method based on a large language model comprises the steps that database outline information is cut, and tables and columns needed by query of a non-target structured query language SQL are eliminated through correlation scoring and Steiner tree problem solving; screening context samples, predicting a similarity score from a text to a structured query language Text-to-SQL by using a cross encoder language model, and selecting a sample most related to a query problem; and injecting the cut database table and column information and the screened context sample into a cue word template, and generating an SQL query statement by using a large language model. The method can be used for optimizing the automatic conversion process from the natural language to the SQL and improving the conversion accuracy, and is used for providing a quick and convenient database retrieval mechanism for a non-SQL user and providing applications such as a data access mode in a wider form for mechanisms such as big language model retrieval enhancement generation RAG and the like.
Owner:TSINGHUA SHENZHEN INTERNATIONAL GRADUATE SCHOOL

Method and system for generating document, computing device, and medium

Embodiments of the present disclosure provide a method and system for generating a document, a computing device, and a medium. The method comprises: receiving a prompt input by a user; obtaining a first keyword from the prompt; using a vector representation of the prompt, retrieving, from a vector index database, enhancement information associated with the prompt and a second keyword associated with the enhancement information; on the basis of comparison of the first keyword and the second keyword, using the enhancement information to generate an enhanced prompt; and providing the enhanced prompt to a language model to generate a document.
Owner:BEIJING ZITIAO NETWORK TECH CO LTD +1

Large medical model intelligent inquiry reasoning method and system

The invention provides a medical large model intelligent inquiry reasoning method and system, and the method comprises the steps: obtaining the input information of a user, and carrying out the processing of the input information, including intention recognition, entity recognition and historical information summarization; sequentially performing pre-retrieval, multi-modal database retrieval and knowledge reordering according to the information obtained after processing; generating an inquiry strategy according to the information obtained after knowledge reordering, and performing information retrieval enhancement generation on the medical large model according to the information obtained after knowledge reordering and the inquiry strategy; and generating content according to the generated medical large model. According to the method, reasoning and replying of symptom description and health problems input by the user are achieved through the generative medical large model and multi-modal data retrieval, the method is suitable for intelligent health management and medical consultation in the medical field, and the intelligent level of medical services and the user experience are effectively improved.
Owner:TAISHI (HUBEI) SMART TECHNOLOGY CO LTD

Automatic control code generation and verification method and device, equipment and storage medium

The invention discloses an automatic control code generation and verification method and device, equipment and a storage medium, and relates to the technical field of automatic control, the method is applied to a large language model, and a natural language command is received; performing matching retrieval on the vector database according to the natural language command to obtain an example code snippet; obtaining API structured information corresponding to the example code snippets from a knowledge graph database; generating an initial control code based on the example code snippet and the API structured information; and performing multi-stage virtual operation verification on the initial control code in the software motion control system, and generating a target control code according to a multi-stage verification result confirmed by a user for multiple times and the initial control code. According to the method, the initial control code is automatically generated through double-database retrieval based on the large language model, then multi-stage code verification is performed through the software motion control system, the target control code is generated in combination with verification results confirmed by a user for multiple times, and the code generation speed and reliability are improved.
Owner:HONG KONG UNIV OF SCI & TECH (GUANGZHOU) +1

Computer Code Generator

Disclosed herein is a system and method for generating computer code for a plurality of components of a software development project. An artificial intelligence code generator can generate computer code in response to a natural language text input describing a component of the software development project. A first database can store natural language text describing components of the software development project. A second database can store computer code generated at least partially by the artificial intelligence code generator and defining components of the software development project and corresponding to the natural language text stored in the first database. Using a pre-trained language model, the system can generate a natural language summary text based on the code intent of the first component, the identified characteristics of the objects, and the natural language text retrieved from the first database.
Owner:ACCENTURE GLOBAL SOLUTIONS LTD

Systems and methods for retrieving telematics data

The present disclosure relates to systems and methods for retrieving telematics data as well as for training machine learning models. A method for retrieving telematics data may comprise operating at least one processor to: provide a plurality of databases, each database storing at least telematics data originating from a plurality of telematics devices installed in a plurality of vehicles; receive a natural language request from a user, the natural language request comprising at least one textual question relating to the telematics data stored within one of the plurality of databases; generate, using a large language model (LLM) that does not have access to the plurality of databases, an executable query for retrieving a portion of the telematics data that is responsive to the natural language request from the database by inputting into the LLM at least: a contextual prompt, the contextual prompt providing to the LLM at least one or more features of the database, an expected structure of the executable query, and one or more example natural language requests and corresponding executable query outputs, and the natural language request; execute the executable query for retrieving the portion of the telematics data from the database; and return at least the portion of the telematics data to the user, whereby the natural language request is responded to without providing the LLM with access to the telematics data stored on the plurality of databases.
Owner:GEOTAB INC

Hardware-backed password security for cloud systems

A method of data processing is described. The method includes receiving, at a server host, a login request that includes a clear text password for an account. The method further includes retrieving, from a database, a payload stored in association with the account. The payload may indicate a hash value of a user configured password for the account, a hashing algorithm used for generation of the hash value, an initialization vector, and a key agreement public key associated with the account. The payload may be encrypted using a secret key derived from the key agreement public key and a private key provisioned to a key protection component of the server host. The method further includes transmitting a request that includes the payload and the clear text password. The method further includes receiving a response that indicates whether the clear text password corresponds to the user configured password.
Owner:SALESFORCE INC

Search engine integrated with a large language model

PCT designated stage expiredWO2024264056A1Web data queryingLinguistic modelEngineering
A search system may receive a search query for documents stored in a database associated with an organization. A search system may retrieve, from the database, search results (including responsive documents) that are responsive to the search query. A search system may initiate display of the search results on the user interface. A search system may transmit a prompt to a large language model, where the prompt includes the search query and information from at least a portion of the responsive documents. A search system may receive a model response with textual data that responds to the search query, where the textual data is generated by the large language model using at least the portion of the responsive documents. A search system may initiate display of the model response in a user interface.
Owner:ELASTICSEARCH INC

Academic paper retrieval method and device based on large language model driving and medium

The invention discloses an academic paper retrieval method and device based on large language model driving, and a medium, and the method comprises the steps: obtaining a preliminary academic paper retrieval result through retrieval of a plurality of academic paper databases according to an input retrieval request; combining the preliminary academic paper retrieval results, and performing weighted sorting processing according to correlation, popularity and time; inputting the sorted preliminary academic paper retrieval results into a pre-trained first large language model to obtain article abstracts of academic papers and comparative analysis results of similar academic papers; wherein the training process of the first large language model comprises the steps of constructing diversified task samples including abstract generation, question and answer, keyword extraction, logical reasoning, information extraction and literature review generation, and constructing a total loss function so as to train the first large language model; the total loss function is the weighted sum of abstract generation, question and answer, keyword extraction, logical reasoning, information extraction and literature review loss functions.
Owner:ZHEJIANG LAB

Transferring blockchain-based tokens representing biospecimens

A method, a system, and computer program product for managing tokenized biospecimen transfers are provided. A file including private data associated with one or more donors is retrieved by a biobank node connected to a blockchain network and from a database of a data provider. The file is processed to generate tokens corresponding to the private data, each token representing a biospecimen and being assigned to a respective donor. An inventory is updated by adding identifiers of the plurality of tokens to the inventory. A request to transfer one or more tokens corresponding to a portion of the private data is received. An authorization to transfer the one or more tokens to a target entity is received. The token is transferred to the target entity with a consent to perform one or more operations using the token.
Owner:AMINOCHAIN INC

Large language model assisted semantic web knowledge base

A system and method for accessing drilling records. A semantic web for drilling records is built, wherein building includes converting drilling records retrieved from a database into a Resource Description Framework (RDF) format and storing the RDF formatted drilling records in the semantic web. Transfer learning is applied to drilling domain knowledge to obtain a large language model (LLM) with drilling domain knowledge. A schema is applied to unstructured records to extract information from unstructured records and the extracted information is then stored in RDF format to the semantic web. The LLM is configured to query the semantic web and to manipulate RDF formatted data within the semantic web.
Owner:HALLIBURTON ENERGY SERVICES INC

Document auditing method, device and equipment based on large model and storage medium

The invention discloses a document auditing method, device and equipment based on a large model and a storage medium, and relates to the technical field of deep learning, and the method comprises the following steps: obtaining document auditing data from a plurality of preset data sources, and analyzing the document auditing data; the document auditing data comprises an auditing material for representing a document auditing rule, a historical document auditing case and a standard document; constructing a document auditing database based on the analyzed document auditing data, and constructing a large model fine tuning data set based on the document auditing database; performing fine tuning on a preset document auditing large model by utilizing the large model fine tuning data set to obtain a target document auditing large model; and determining a current document auditing task, and auditing a to-be-audited document of the document auditing task by using the target document auditing large model to generate an auditing report. Automation, high efficiency and accuracy of document auditing are achieved through intelligent document analysis, auditing database retrieval and compliance judgment of a fine adjustment large model.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Root cause analysis method and device based on large language model, equipment and medium

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.
Owner:BEIJING YOUTEJIE INFORMATION TECH

Policy and regulation intelligent question and answer method and system based on large language model

The invention relates to the technical field of artificial intelligence, and particularly discloses a policy and regulation intelligent question answering method and system based on a large language model, and the method comprises the steps: segmenting a policy and regulation text into text blocks through a recursive character text segmentation method, and constructing a knowledge base in combination with expert labeling and automatic information extraction; performing semantic embedding on the text block by utilizing a pre-trained Transform model, generating a high-dimensional vector representation, and storing the high-dimensional vector representation in a Chroma database; the user question is converted into an embedded vector, relevant laws and regulations are retrieved through a Chroma database, a large language model and a knowledge fusion attention generation module are combined, and text embedding and knowledge graph information are fused to generate an answer; and the user obtains answers through the intelligent question-answer interaction interface and can view the original texts and explanations of laws and regulations. The system comprises a data acquisition and preprocessing module, a semantic embedding and storage module, a retrieval and generation module and a user interaction module. According to the method, large-size regulation texts are effectively processed, and the retrieval efficiency and the answer quality are improved.
Owner:SHANDONG HUAKE RENJIE INFORMATION CONSULTING CO LTD

Intelligent agent optimization method, device and system based on reinforcement learning, and storage medium

The invention discloses an agent optimization method, device and system based on reinforcement learning, and a storage medium. The method comprises the steps of obtaining an initial task instruction input by a user; performing instruction deepening and expansion on the initial task instruction; optimizing and adjusting a task instruction and a data collection strategy by using a reinforcement learning algorithm; the task instruction is converted into a specific execution plan, and data collection, data cleaning and analysis, API calling, database retrieval and exception handling tasks are executed; evaluating whether the data collected by the intelligent agent is enough to support the analysis requirement of the current task; and generating an industry analysis result based on optimization data obtained by instruction deepening and expansion, and by adopting the technical scheme of the invention, the intelligent agent can adaptively generate, adjust and optimize the task instruction in a complex task environment, so that the intelligence, flexibility and efficiency of task processing are improved.
Owner:胡奇

Computer code generator

Disclosed herein is a system and method for generating computer code for a plurality of components of a software development project. An artificial intelligence code generator can generate computer code in response to a natural language text input describing a component of the software development project. A first database can store natural language text describing components of the software development project. A second database can store computer code generated at least partially by the artificial intelligence code generator and defining components of the software development project and corresponding to the natural language text stored in the first database. Using a pre-trained language model, the system can generate a natural language summary text based on the code intent of the first component, the identified characteristics of the objects, and the natural language text retrieved from the first database.
Owner:ACCENTURE GLOBAL SOLUTIONS LTD

Mass spectrum structure analysis method and device, storage medium and program product

The invention provides a mass spectrum structure analysis method and device, a storage medium and a program product, and relates to the technical field of bioinformatics, and the method comprises the steps: calculating the similarity between each reference mass spectrum in a reference database and a to-be-analyzed target mass spectrum, screening at least one similar reference mass spectrum from the reference mass spectrums according to the calculated similarity; the reference database comprises a plurality of reference mass spectra and corresponding reference molecular structures; according to a preset mass spectrum structure analysis task instruction, the target mass spectrum, the similar reference mass spectrums and the corresponding reference molecular structures, generating prompt information; and inputting the prompt information into the large language model to determine a target molecular structure corresponding to the target mass spectrum. Therefore, a relatively good mass spectrum structure analysis effect is realized by combining the advantages of database retrieval and deep learning by utilizing the few-sample learning capability of the large language model.
Owner:SHANGHAI JIAOTONG UNIV

Retrieval and push method based on fine art image tag, and use thereof

The present disclosure provides a retrieval and push method based on a fine art image tag, including the following steps: establishing a tag model database: training different tag contents with training samples of different subjects and different categories, and categorizing the training samples in the database according to knowledge point tags to obtain the tag model database; retrieval and push: uploading fine art work image samples to the trained tag model database, then extracting knowledge point tags of the fine art work image samples, retrieving associated fine art works, and then pushing the associated fine art works; real-time updating: recording knowledge point tags of input fine art work image samples by the tag model database in real time, and establishing a common tag and a model, and subsequently increasingly pushing contents relevant to the common tag; and generating a user portrait.
Owner:GUANGDONG UNIV OF TECH

Soil organic pollutant identification method and system based on combination of AI and high-throughput screening

The invention discloses a soil organic pollutant identification method and system based on combination of AI and high-throughput screening, and relates to the technical field of pollutant screening, and the method comprises the following steps: extracting a substance peak from high-resolution mass spectrum data of a soil sample; the method comprises the following steps: establishing an organic pollutant mass spectrum database, extracting spectrogram characteristics and structural characteristics of compounds in the organic pollutant mass spectrum database, establishing a molecular fingerprint prediction model, and establishing a mapping relation from a spectrogram to a structure; constructing a spectrogram vector prediction molecular fingerprint according to the extracted substance peaks, and retrieving by using an organic pollutant mass spectrum database to obtain candidate chemical structures; scoring the candidate chemical structures by predicting the molecular fingerprints, selecting the chemical structures meeting a preset standard, constructing a recognition basis according to the selected chemical structures, and obtaining an organic pollutant recognition result of the soil sample. According to the method, non-targeted intelligent analysis is carried out through cross fusion of artificial intelligence and mass spectrometry, and rapid and accurate identification of soil organic pollutants is realized.
Owner:BCEG ENVIRONMENTAL REMEDIATION CO LTD

User Interface workflow for natural language querying

Systems and methods are provided for creating a User Interface (UI) that allows a user to perform a search query. According to one implementation, a method includes a step of displaying a UI having a search request section and a dashboard section. The search request section is configured to allow an admin associated with an enterprise to enter a search query using natural language. The dashboard section is configured to display results of the search query. Upon receiving a search query from the admin via the search request section, the method further includes a step of retrieving log data from a private database associated with the enterprise according to search parameters parsed from the search query. Also, the method includes a step of displaying the log data in the dashboard section of the UI according to a display format parsed from the search query.
Owner:ZSCALER INC

Methods and Systems for Micro Edge Self Provisioning

A method for automated device provisioning and management in an edge computing system includes retrieving self-provisioning parameters and device credentials from a database using a processor. The method involves adding a new device, determining if the allowed device limit for a group is exceeded, removing devices if necessary, and adding devices through a top-off process if the limit is not exceeded. It forms trusted and self-service device groups, monitors and manages devices based on policies, changes services or applications, dynamically changes device group associations, and assigns virtual pre-shared keys (vPSKs) to private LANs. The method also includes creating private LANs and virtual private clouds (vPCs), sharing device credentials with upstream services, and generating and using virtual networks (vNets) for device provisioning and management.
Owner:VEEA INC

Multi-source heterogeneous data multi-mode mixed retrieval method and system based on large model reasoning

The invention belongs to the technical field of data processing. According to the multi-source heterogeneous data multi-mode mixed retrieval method and system based on large model reasoning, in the reasoning process of each step, a large language model determines sub-query questions of different retrieval modes and corresponding sub-query answers according to an initial query question; according to the sub-query question and the sub-query answer corresponding to the query mode of each inference process, adaptively determining an optimal retrieval path by taking the maximum reward function as a target, and determining a final answer corresponding to the initial query question according to the optimal retrieval path; wherein the optimal retrieval path comprises an optimal answer of each retrieval mode and a retrieval sequence of each retrieval mode, and the retrieval modes comprise database retrieval, semantic retrieval and atlas retrieval; according to the method, multi-hop reasoning of complex query is supported while the retrieval efficiency is ensured, dynamic fusion of multiple types of retrieval modes is realized, and the retrieval efficiency and the retrieval precision are greatly improved.
Owner:INSPUR GENERSOFT CO LTD

Behavior scheme determination method and device based on large model, electronic equipment and medium

The invention provides a behavior scheme determination method based on a large model, and relates to the technical field of artificial intelligence, in particular to the technical fields of computer vision, deep learning, large models and the like. According to the specific implementation scheme, a hybrid expert model is called based on features of multi-modal data, the hybrid expert model comprises a plurality of first large models for processing different modal data, and the features represent search words for performing in-library search on the first large models; inputting the multi-modal data into a hybrid expert model, and performing information extraction on each modal data to obtain text data, the text data including behavior information; inputting the text data into a second large model to obtain behavior content, and selecting and calling the second large model based on the category of the behavior information; and determining a behavior scheme by using the behavior content. The invention further provides a behavior scheme determination device based on the large model, electronic equipment and a storage medium.
Owner:BAIDU COM TIMES TECH (BEIJING) CO LTD

Natural language interface for querying cloud security logs

Systems and methods for processing search queries are provided. A method, according to one implementation, includes a step of receiving a search request from an authorized user associated with an enterprise, wherein the search request includes natural language and is received via a query field of a User Interface (UI). The method also includes a step of parsing the search request to convert the natural language into one or more search parameters and a display format. Also, the method includes a step of retrieving log data from a private database associated with the enterprise, wherein the log data is retrieved in accordance with the one or more search parameters and is related to network activities associated with the enterprise. Furthermore, the method includes a step of displaying the log data on the UI in accordance with the display format.
Owner:ZSCALER INC