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

2804 results about "Template based" patented technology

Hallucination prevention for natural language insights

Methods and systems are provided for hallucination prevention for natural language insights. In embodiments described herein, a template-based insight with a set of facts is generated by a template-based insights engine. The set of facts are generated from a set of data and the template-based insight is generated based on a text template. A natural language insight is generated from the template-based insight through a language model. If a threshold number of facts of the template-based insight are missing from the natural language insight as determined by a hallucination gatekeeper engine then a new natural language insight is generated from the template-based insight through the language model.
Owner:ADOBE INC

Determining critical logs for network applications

Techniques are described for a computing system configured to obtain a plurality of candidate logs for a plurality of layers of a computing infrastructure. The computing system may, for each candidate log of the plurality of candidate logs, map the candidate log to a log template of a plurality of log templates, wherein each log template to which a candidate log is mapped is a mapped log template. The computing system may rank mapped log templates based on properties of the mapped log templates. The computing system may select, based on the ranking, one or more candidate logs as critical logs. The computing system may output at least one of (1) an indication of the critical logs to determine a potential root cause associated with a performance issue of a network application or (2) an indication of the potential root cause associated with the performance issue of the network application.
Owner:JUNIPER NETWORKS INC

Data extraction, verification, and field population

A method can include receiving a document associated with a checklist item. A method can include identifying a template associated with the document. A method can include identifying an area of the document associated with a value of a key-value pair based at least in part on the template. A method can include extracting, using a first optical character recognition process, the value from the area. A method may cause display of the value. A method can include receiving a corrected value from the user. A method may include extracting, using a second optical character recognition process, full text of the document. A method may include determining a location of the corrected value in the document. A method may include updating the first optical character recognition process, wherein updating the first optical character recognition process causes the first optical character recognition to extract the value from the location.
Owner:SIDE INC

Cross-border e-commerce compliance intelligent auditing platform and multi-language contract analysis method

The invention discloses a cross-border e-commerce compliance intelligent auditing platform and a multi-language contract analysis method, and relates to the field of cross-border contract compliance auditing. In the multi-modal data access step, customs codes, laws and regulations and other multi-source data are collected, and 18 kinds of language contract texts are analyzed; in the cross-language semantic alignment step, a knowledge graph is constructed, and multi-language legal concept mapping is achieved; in the compliance risk reasoning step, a rule engine and an agent cooperatively check a contract, and the compliance conclusion confidence is calculated; the dynamic risk assessment step adopts an LSTM network to analyze historical data and predict a risk trend; in the multi-language report generation step, a multi-format bilingual or multilingual report is generated based on a template engine, encrypted and archived. According to the invention, cross-border contracts are audited efficiently and intelligently, dynamic adaptation laws and regulations are analyzed in multiple languages, compliance risks are identified accurately, and a multi-language report is generated quickly; therefore, the checking efficiency is improved, the manual workload is reduced, the compliance risk is reduced, and the enterprise cross-border business competitiveness and the risk response capability are enhanced.
Owner:GUOSHU INTELLIGENCE (CHANGZHOU) DIGITAL TECHNOLOGY CO LTD

Jenkins continuous integration method and system based on Kubernetes

The invention relates to the technical field of continuous integration and continuous delivery, and discloses a Jenkins continuous integration method based on Kubernetes. According to the method, a Jenkins server is deployed in a Kubernetes cluster to serve as a control plane, a construction environment is created through a preset multi-container Pod template, and a Pod containing a plurality of containers is dynamically created based on the Pod template, so that each container executes different construction tasks. Containers in the Pod realize collaboration through sharing a network namespace and a storage volume, and a Jenkins server monitors task execution states of the containers in the Pod and performs dynamic scheduling according to task priorities and cluster load states. And after the task is completed, automatically destroying the Pod and releasing cluster resources. According to the method and the device, dynamic expansion and contraction of a construction environment and efficient parallel execution of tasks are realized, the problem that a traditional Jenkins static resource pool is difficult to deal with load changes is solved, the resource utilization rate is improved, the expandability of the system is enhanced, and an efficient and reliable solution is provided for an enterprise-level continuous integration system.
Owner:BEIMI TECHNOLOGY (ZHUHAI) CO LTD

Text classification method and device, computer equipment and storage medium

The invention belongs to the field of artificial intelligence and finance, and relates to a text classification method, which comprises the following steps: preprocessing an original text data set, labeling classification labels to obtain a labeled text data set, inputting a training set into a large language model for keyword extraction to obtain a candidate keyword set, cleaning the candidate keyword set to obtain a classification keyword set, constructing an instruction template based on the classification keyword set, and inputting the training set and the instruction template into a large language model to obtain a prediction classification result; and based on a prediction classification result and a loss function between the classification labels, performing fine tuning on the large language model to obtain a fine tuning model, evaluating that the fine tuning model is qualified to obtain a text classification model, and inputting the to-be-classified text into the text classification model for classification. The invention further provides a text classification device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the tagged text data set can be stored in a block chain. According to the method, the text classification accuracy and stability can be improved.
Owner:CHINA PING AN LIFE INSURANCE CO LTD

Systems and methods for generalized multi-hypothesis prediction for video coding

Systems and methods are described for video coding using generalized bi-prediction. In an exemplary embodiment, to code a current block of a video in a bitstream, a first reference block is selected from a first reference picture and a second reference block is selected from a second reference picture. Each reference block is associated with a weight, where the weight may be an arbitrary weight ranging, e.g., between 0 and 1. The current block is predicted using a weighted sum of the reference blocks. The weights may be selected from among a plurality of candidate weights. Candidate weights may be signaled in the bitstream or may be derived implicitly based on a template. Candidate weights may be pruned to avoid out-of-range or substantially duplicate candidate weights. Generalized bi-prediction may additionally be used in frame rate up conversion.
Owner:INTERDIGITAL VC HOLDINGS INC

Generating and deploying phishing templates

In some implementations, a phishing test engine may receive a set of email messages that are associated with a set of users and with an indication of legitimacy. The phishing test engine may perform clustering on the set of email messages to identify a subset of similar email messages and a subset of users. The phishing test engine may generate an email template based on the subset of similar email messages and including an indicator of phishing. The phishing test engine may generate, from the email template, a test email message addressed to a user in the subset of users and may transmit the test email message to the user. The phishing test engine may receive an indication of an interaction with the test email message and may update a policy associated with the set of users based on the indication of the one or more interactions.
Owner:CAPITAL ONE SERVICES LLC

Derived intra prediction modes and most probable modes in video coding

A method of encoding or decoding video data comprises: for each respective intra prediction mode of a plurality of intra prediction modes in a most-probable mode (MPM) list: generating, based on reference samples for a template region and using the respective intra prediction mode, prediction samples for the template region; and determining a cost for the respective intra prediction mode; determining a first intra prediction mode and a second intra prediction mode in the MPM list having lowest costs; determining a preliminary prediction block for the first intra prediction mode and a preliminary prediction block for the second intra prediction mode; generating a prediction block based on a fusion of the preliminary prediction blocks weighted according to a weight for the first intra prediction mode and a weight for the second intra prediction mode.
Owner:QUALCOMM INC

Access control strategy construction method and device, electronic equipment and storage medium

The embodiment of the invention provides an access control strategy construction method and device, electronic equipment and a storage medium. The access control strategy construction method comprises the following steps: determining access control elements and attributes thereof of an application based on an acquired resource access scene; based on the access control elements and the attributes thereof, an access control strategy template is created according to different access control scenes, and the access control strategy template comprises preset access control elements and attributes; selecting the access strategy template based on a service demand and assigning a value to the attribute to create a corresponding access control strategy; and performing matching calculation on the access control strategy and the intercepted resource access request based on a strategy calculation engine, and if matching succeeds, executing a corresponding strategy action. Through the steps, access control configuration is more convenient and easier to understand, and access control is more flexible.
Owner:CHINA PETROLEUM & CHEMICAL CORP +1

Transpiler to extract and use intermediate representations of a code base

Provided is a process including: obtaining, with a computer system, access to a code base; decomposing, with the computer system, the code base into parts; classifying, with the computer system, the parts according to content type; selecting, with the computer system, processing templates based on the content types, with at least some different content types having different selected processing templates; and generating natural language documentation for the parts, with one or more generative language models, using the processing templates selected for the parts.
Owner:DRIVER AI INC

Target tracking method and system based on grouping attention feature extraction network

The invention provides a target tracking method and system based on a grouped attention feature extraction network, and the method comprises the steps: obtaining a template and search features based on a template and a search image through employing the grouped attention feature extraction network; learning local areas of the template target image features and the search image features, and aggregating to obtain target information; splicing the template with the search features to obtain the input of the self-attention encoder in the asynchronous interaction stage; the fused features are combined with a prediction head for calculation, a classification regression result is obtained, and a target is predicted according to the classification regression result; training the target tracking model in combination with the large-scale data set to obtain a trained target tracking model, and performing accurate target tracking on the target by using the trained target tracking model; according to the multi-scale feature extraction network based on Transform, sequential local and global information interaction in the windows and between the windows is promoted, and the optimal balance between performance and speed is achieved.
Owner:NANCHANG INST OF TECH

Chip verification method, test equipment and chip verification system

The invention relates to the technical field of chip verification, and discloses a chip verification method, test equipment and a chip verification system.The method comprises the steps that a template file is built, a verification environment and a test case are generated based on the template file, a configuration file is obtained, and parameters in the verification environment and the test case are updated through parameters in the configuration file; according to the method, the verification environment and the test case are updated, the updated verification environment and the updated test case are obtained, regression testing is carried out on the chip on the basis of the updated verification environment and the updated test case, the test result is obtained, the verification environment can be rapidly generated on the basis of the template file, parameters can be rapidly replaced, and the chip testing efficiency is improved.
Owner:CHONGQING LANSHAN AUTOMOTIVE ELECTRONICS CO LTD

Decoding method, encoding method, and storage medium

Embodiments of the present disclosure provide a decoding method, an encoding method, and a storage medium. In the decoding method provided in embodiments of the present disclosure, first transform is performed on first transform coefficients of a current block based on a transform set corresponding to a first intra prediction mode, and the first intra prediction mode is designed to be any one of: an intra prediction mode derived from a decoder side intra mode derivation (DIMD) mode for a prediction block of the current block, an intra prediction mode derived from the DIMD mode for an output vector of an optimal matrix based intra prediction (MIP) mode for predicting the current block, an intra prediction mode derived from the DIMD mode for reconstructed samples in a first template region adjacent to the current block, and an intra prediction mode derived from a template based intra mode derivation (TIMD) mode.
Owner:GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD

Conversational enterprise knowledge question answering method and device, storage medium and electronic equipment

The invention discloses a dialogue type enterprise knowledge question answering method and device, a storage medium and electronic equipment, and relates to the technical field of data analysis, and the method comprises the steps: obtaining user request information; obtaining a corresponding channel; reconstructing the question content to obtain the reconstructed question content; performing vectorization processing on the reconstructed question content to obtain vectorization information of the reconstructed question content; obtaining a plurality of first FAQ knowledge and second FAQ knowledge; obtaining a plurality of pieces of first document block knowledge and second document block knowledge, and obtaining documents corresponding to a plurality of document blocks; obtaining a corresponding prompt word template based on the dialogue intention and the channel; and constructing a large language model, and sorting to obtain corresponding answer information. Based on the question content of the user, the dialogue intention is obtained through analysis, the knowledge base is matched, the answer information is obtained through arrangement, the user question is automatically answered, and the method has the advantages of being simple, efficient and high in real-time performance.
Owner:XINIU MEDICAL TECH (ZHEJIANG) CO LTD

Systems and methods for templating of executable graph-based models

A method discloses obtaining a node template comprising a predetermined node structure and rules governing generation of node instances based on the node template. Data elements are received. A run-time node is generated in response to the reception of the data elements. The run-time node comprises the node template and a node instance. The node instance comprises the data elements mapped to the node template based on the rules of the node template. A run-time overlay comprising an overlay template and an overlay instance comprising processing logic implementing at least one generic rule of the overlay template are obtained. The executable run-time node is generated. It comprises a composition of the run-time node and the run-time overlay such that the processing logic of the run-time overlay is operable to interact with the run time node during execution of the executable run-time node.
Owner:INFOSYS LTD +1

Electrical work ticket intelligent generation method and device, medium and equipment

The invention discloses an electrical work ticket intelligent generation method and device, a medium and equipment in the technical field of power systems, and aims to solve the problems of serious module decoupling, dependence on manual connection and insufficient intelligent generation capability in the prior art. The method comprises the following steps: generating a required digital knowledge base and an electrical work task description generation work ticket based on a pre-constructed work ticket by utilizing a multi-model collaborative generation architecture; the multi-model collaborative generation architecture comprises a rule driving module used for calling a corresponding template based on task element matching; the task execution unit is used for executing a specific subtask according to a pre-deployed lightweight model or rule engine; and the large language model is used for performing semantic understanding and reasoning according to the electrical work task description, calling the rule driving module and the task execution unit according to a semantic understanding and reasoning result, and generating a work ticket in combination with a digital knowledge base required by work ticket generation. The method has both the accuracy of structured knowledge recognition and the flexibility of natural language generation.
Owner:HUADIAN ELECTRIC POWER SCI INST CO LTD

Environment detection method and system based on multi-modal data fusion and deep learning

The invention provides an environment detection method and system based on a sample target detection model. The method comprises the following steps: synchronously acquiring an environment image, a video stream and physical parameters by using a multi-mode sensor; decomposing the data into image features and environmental parameter components through a dual-time sequence control signal, and realizing space-time alignment by adopting a linear phase filter; constructing a foreground region template based on the depth information, and generating target recognition feature representation containing an abnormal blurred target; adversarial training is carried out on the lightweight target detection network in combination with a transfer learning strategy, the network integrates convolutional features and a Transform attention mechanism, and the weight is dynamically adjusted through environmental parameters; fusing a target result and sensor data in real-time detection, and inputting a decision tree model for risk grading; and after the early warning is triggered, reconstructing a false detection sample through an online learning mechanism and iteratively optimizing the model. The system correspondingly comprises a multi-modal data acquisition module, a data enhancement and annotation module, a model training module, a real-time detection and fusion module and an early warning and optimization module. According to the invention, through multi-source data fusion, dynamic data enhancement and an adaptive compensation mechanism, the small target detection precision, the environmental adaptability and the real-time early warning capability are significantly improved.
Owner:SHANDONG HUANFA INSPECTION & TESTING CO LTD

Method and system for generating Text2SQL (Structured Query Language) driven by large language model

The invention provides a Text2SQL generation method and system driven by a large language model, and the method comprises the steps: recognizing key entities and relationships in a natural language question through the large language model, and carrying out the construction to obtain a query graph; constructing a hierarchical graph representation model based on the database mode of the target database; searching candidate sub-image sets which have the same structure as the query graph and are in semantic association with the query graph from the constructed graph representation model; and constructing a structured Prompt template based on the candidate sub-image set and the user question, generating an initial SQL statement, and outputting a final query result after grammar and semantic detection correction. According to the method, a traditional database is converted into the graph knowledge base, so that the SQL generation accuracy and performance are improved; guiding the large model to generate an SQL (Structured Query Language) meeting business requirements through knowledge graph storage and retrieval table and column information; and the accuracy of the SQL is continuously optimized by utilizing a self-adaptive feedback mechanism, so that the method is particularly suitable for a large-scale complex query scene, and self-improvement and customization of the model are realized.
Owner:SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES

Human resource data natural language query and SQL generation method and system

The invention discloses a human resource data natural language query and SQL generation method and system, and relates to the technical field of SQL generation, and the method comprises the steps: preprocessing a natural language query text input by a user, and constructing a query semantic tree; traversing the query semantic tree to generate a candidate entity set, determining an unambiguous entity through a three-layer ambiguity resolution mechanism of semantic scoring, service verification and cross validation, identifying a composite intention, disassembling the composite intention into a sub-intention sequence, and generating an SQL operation instruction set in combination with a preset SQL operation mapping rule; based on the SQL operation instruction set and the human resource data association model, determining a data table set and an association path, generating a dynamic calculation logic and structured condition expression, and constructing a structured query skeleton; according to the method, the personalized SQL template is dynamically generated according to the query skeleton, after filling, grammar verification, strategy optimization and logic consistency verification are performed, and the optimized SQL statement is output, so that the query accuracy and performance are remarkably improved.
Owner:ZHEJIANG TOPTHINKING INFORMATION TECH +1

Intelligent Legal Document Generation and Review System with Attorney Feedback Loop

An intelligent legal document generation and review system and associated methods are disclosed. The system comprises one or more processors coupled to memory storing instructions to provide a user interface for receiving user input, execute a natural language processing subsystem to extract relevant information, access a legal rules database, store document templates, and execute an AI algorithm. The AI algorithm retrieves a relevant template based on user input and extracted information, populates the template to generate a customized legal document, and stores the document. An attorney feedback loop allows attorneys to provide feedback that the AI algorithm learns from to improve document generation. The AI algorithm collaborates with attorneys to revise and finalize documents based on the feedback. The system streamlines document preparation, automates complex tasks, and provides expert guidance to help users adhere to legal requirements across jurisdictions.
Owner:DAVIS ALEXANDER

Legal document generation method and device, electronic equipment and storage medium

The invention discloses a legal instrument generation method and device, electronic equipment and a storage medium, and relates to the technical field of legal instrument generation or other related fields, and the method comprises the steps: receiving first language case information and a legal instrument generation demand; analyzing the first language case information through a semantic analyzer corresponding to the first language to obtain case factors of the target case, and translating the first language case information through a translator to obtain second language case information; querying a target legal knowledge base based on the case factors to obtain a query result; and determining a target document template based on the legal document generation demand, and generating a target legal document based on the target document template, the second language case information, the case factors and the query result. According to the method and the device, the technical problem that the generated legal document is inaccurate and even not compliant due to the fact that professional legal terms and contexts cannot be accurately understood and converted in the cross-language generation process of the legal document in related technologies is solved.
Owner:CHINA TELECOM ARTIFICIAL INTELLIGENCE TECHNOLOGY (BEIJING) CO LTD

Systems and methods of template-based digital asset exchanges using a public key cryptography (PKC) framework

Systems, methods, and computer-readable storage media of template-based digital asset exchanges using a public key cryptography (PKC) framework. One method includes storing a plurality of exchange templates, and receiving a signed exchange request signed by a private key of a public and private key pair associated with a digital asset. The method further includes receiving an environmental dataset, and selecting, utilizing the environmental dataset, an exchange template of the plurality of exchange templates. The method further includes populating the plurality of fields of the selected exchange template based on the environmental dataset. The method further includes providing, to a plurality of user devices, a public key, updating a provider ledger, and updating a central ledger.
Owner:WELLS FARGO BANK NA

Extension of template based intra mode derivation (TIMD) with ISP mode

Template based derivation of intra sub-partitioning (ISP) mode is used to improve coding efficiency of intra predicted coded video blocks. The template is formed from surrounding reconstructed top and left samples. In one embodiment, ISP is performed independently from template based intra mode derivation (TIMD). The derivation of an intra sub-block partition mode is determined from template pixels using a current prediction mode for either an upper or left template. In another embodiment, ISP and TIMD are combined. In a further embodiment, a flag is signaled to communicate template based intra mode derivation and intra sub-block partition usage.
Owner:INTERDIGITAL CE PATENT HOLDINGS SAS

Archive knowledge management method and system based on large language model

The invention provides an archive knowledge management method and system based on a large language model in the technical field of archive knowledge management. The method comprises the steps of S1, creating an archive knowledge base, an archive knowledge extraction rule base and a problem template base; s2, acquiring a historical archive file to construct a data set; s3, creating a large language model and training the large language model; s4, identifying the to-be-managed archive file through an OCR technology to obtain the content of the to-be-managed archive, and extracting a corresponding archive knowledge extraction rule and a problem template; s5, inputting the generated knowledge extraction problem and the to-be-managed file content into a large language model to obtain file knowledge; step S6, storing the archive knowledge into a neo4j graph knowledge base and a mysql relational knowledge base; step S7, obtaining a knowledge triple from the graph knowledge base and expressing the knowledge triple in a knowledge graph mode; and step S8, performing addition, deletion, update and query management on the archive knowledge. The method has the advantage that the efficiency and quality of archive knowledge management are improved.
Owner:FUZHOU JINRUIDI SOFTWARE TECH

Interactive user interfaces for digital customer relationship management

Customizable template-based user interfaces for digital CRM tools. For instance, the CRM tools are pre-loaded with customizable templates, which are rendered as interactive user interfaces that allow customization of the templates based on user needs. This customization therefore allows a user to rapidly, visually, and easily define a customer engagement pipeline and customer segments without any specialized programming knowledge. The user interfaces may dynamically show the flow of customers between different phases and provide recommended actions to further drive customer engagement. Additionally, the CRM tools are integrated with other on-line platforms such as social media sites and e-commerce sites.
Owner:INTUIT INC

Text-to-SQL (Structured Query Language) method and device of mixed strategy, electronic equipment and storage medium

The invention discloses a mixed strategy Text-to-SQL method and device, electronic equipment and a storage medium, and relates to the technical field of natural language processing and database query, the method comprises the following steps: generating question and answer pairs based on a large language model, and constructing a vector database based on the question and answer pairs and schema information of a target database; in the vector database, performing complementary mask retrieval on the sample questions to obtain schema information to be used and question and answer pair examples; and analyzing the sample SQL statement to obtain target sc hema information. Constructing a first prompt template based on the sample problem and to-be-used schema information so as to perform fine adjustment on the data table recall model; constructing a second prompt template based on the sample question, the question and answer pair example and the target schema information so as to perform fine adjustment on the Text-to-SQL model; and based on the fine-tuned data table recall model and the Text-to-SQL model, reasoning an SQL statement of the problem to be processed. The problems of data leakage and dependence on training data are solved, and the Text-to-SQL performance is improved under the condition that the number of tokens is limited.
Owner:LANZHOU XIANGWEI YONGCHUANG INTELLIGENT TECHNOLOGY CO LTD

Template based CCLM / MMLM slope adjustment

Systems, methods, and instrumentalities are disclosed for template based cross component linear model / multimode linear model (CCLM / MMLM) adjustment. In an example, a device, such as a video decoding device, or a video encoding device, may obtain a prediction model for predicting a coding block. The device may select an adjustment model, from multiple adjustment models, for adjusting the prediction model. The device may adjust the prediction model based on the selected adjustment model. The device may process (e.g., encode and / or decode) the coding block based on the adjusted prediction model.
Owner:INTERDIGITAL CE PATENT HOLDINGS SAS

Template-based aeronautical part technological procedure reasoning method and system

The invention relates to the technical field of intelligent manufacturing of aeronautical parts, and discloses an aeronautical part technological procedure reasoning method and system based on a template, and the method comprises the steps: firstly obtaining and storing technological characteristics and geometric structure characteristics of a to-be-machined part; secondly, encoding the feature data of the to-be-processed part, the feature data of the historical processing part, the technological procedure template data and the technological knowledge data which need to be used in a One-hot mode; then, according to the process characteristics and geometric structure characteristics of the to-be-machined part, a matched process procedure template is obtained through a characteristic-based template matching algorithm, and typical process parameters related to part process procedure compilation based on the process procedure template are obtained through a typical process parameter reasoning decision algorithm; and the matched technological procedure template and the typical technological parameters obtained through calculation are fused, and a part technological procedure is formed and output. According to the method, the required part technological procedure can be quickly and intelligently generated, and the design efficiency of the technological design link in the production process is greatly improved.
Owner:CHENGDU AIRCRAFT INDUSTRY GROUP