107 results about "Logical rules" patented technology

The invention discloses a power transmission line fault positioning method and system, and relates to the technical field of power transmission lines. The method comprises the following steps: dividing a power transmission line into a plurality of logic sections, and setting a basic logic rule; performing coarse-grained threshold judgment and fine-grained logic check on the real-time monitoring parameters of each logic section, and screening out candidate fault logic sections; establishing a node logic link, detecting a breakpoint node of the node logic link, comparing the breakpoint node in a previous time period and a later time period, judging whether the breakpoint node is a persistent fault or not, and obtaining a breakpoint judgment result; performing logic consistency check on breakpoint judgment results of different monitoring points and different parameter types, and when conflicts occur, making decisions according to priorities to generate a unified judgment result; and synthesizing the candidate fault logic sections and the unified judgment result to generate a final fault positioning result of the power transmission line. According to the invention, high-precision, reliable and intelligent positioning of power transmission line faults is realized.

One method includes extracting word-elements, each corresponding to a respective element of a ground truth cell-item array from an annotated document, applying logic rules to the extracted word-elements so that the applicability, or not, of each logic rule to each element of the ground truth cell-item array is determined. Based on the applying of the logic rules, metrics are obtained that indicate, for each word-element of the annotated document, the applicability of the logic rules, and the frequency with which applicable logic rules is satisfied. A first aggregation process is performed that aggregates the metrics across a group of unstructured, and annotated, documents, and a second aggregation process is performed that aggregates the metrics regarding a model-generated cell item array that was created based on the group of annotated documents. Finally, respective outcomes of the first and second aggregation processes are compared so as to identify logic rules of interest.

The invention discloses a reciprocal calculation instruction sequence generation method oriented to a heterogeneous processor, and belongs to the field of compilation optimization and code generation. Aiming at the problems of instruction redundancy, weak precision control, poor hardware adaptation and high manual dependence of an existing method in a heterogeneous environment, characteristics of a reciprocal instruction and an operand are accurately identified by linearly scanning heterogeneous object codes (including vectorization, scalar and complex instruction sequences); in combination with hardware characteristics of RISC / SIMD / VLIW / DSP and the like, a multi-round iteration precision improvement and temporary register optimization allocation strategy is adopted, differential generation logic is formulated, and a high-precision low-redundancy instruction sequence is generated. The method comprises linear code scanning classification, reciprocal instruction and operand identification, cross-architecture generation logic rule formulation, instruction sequence generation and legality verification. Full-process automation is achieved, manual intervention is reduced, the execution efficiency and precision of reciprocal calculation of the heterogeneous processor are improved, and the method is suitable for embedded systems, high-performance calculation and other scenes.

The invention discloses a transformer substation anti-error logic verification method, system and device and a storage medium. The method comprises the following steps: configuring secondary locking primary logic for primary equipment; only secondary locking secondary logic needs to be configured for the protection pressing plate, and primary locking secondary logic does not need to be configured; when the primary equipment is operated, secondary locking primary logic is verified; when the protection pressing plate is operated, the secondary locking secondary logic is verified, and meanwhile, the secondary locking primary logic is verified based on the expected state of the simulation pressing plate, so that primary locking secondary verification is achieved. According to the method, the problem that secondary anti-error configuration of an existing transformer substation is complex can be solved, the engineering configuration efficiency is greatly improved, the logic rule acceptance time is shortened, the configuration error risk caused by human errors is reduced, the system reliability is remarkably improved, and the practical level of secondary anti-error configuration of the transformer substation is improved.

The invention provides an industrial cognitive base system based on multi-modal comparative learning and an execution method, and the industrial cognitive base system based on multi-modal comparative learning is characterized in that a system architecture comprising a knowledge graph management module and a cross-modal coding fusion module is constructed; industrial field knowledge is dynamically injected into a multi-modal feature learning process in the form of a structured sub-graph, and a comparative learning mechanism introducing industrial semantic constraints is combined, so that a model obtained by final training can realize semantic alignment of multi-modal data; it can be ensured that generated unified semantic representation and reasoning results strictly conform to predefined industrial logic rules, and therefore the defect that in the prior art, a pure data driving method may generate results violating industrial common knowledge is effectively overcome; and the output reliability, the decision credibility and the practical application value of the industrial cognitive system in key tasks such as fault diagnosis and state monitoring are remarkably improved.

The invention discloses an AI model manual annotation method with associated logic, relates to the technical field of artificial intelligence and optical character recognition (OCR), and aims to solve the problems that the existing OCR recognition technology is low in accuracy and lacks an effective content verification and correction mechanism when processing complex certificates. The method comprises the following steps of: firstly, extracting a driving license, a driving license, an electronic license and text contents of various certificates through OCR (Optical Character Recognition) scanning equipment; constructing an association logic AI model for storing certificate information association logic rules; performing structured labeling processing on an OCR recognition result to realize document information classification and regularization; performing logic verification on the annotated content by utilizing an association logic AI model, marking problems and proposing a modification scheme; and finally, corrected data is fed back to the model to complete optimization iteration. According to the method, the logic contradiction can be accurately found and corrected, the identification accuracy of the AI model on multiple types of certificates is remarkably improved, the manual labeling error is reduced, and the certificate information extraction efficiency and reliability are improved.

The embodiment of the invention provides a verification code file generation method and device, equipment, a medium and a program product, and the verification code file generation method comprises the steps that an editing interface is displayed, in response to a configuration operation for the editing interface, domain knowledge of a target domain is obtained, the editing interface comprises a configuration area and guide information, and the domain knowledge is stored in the target domain; the guide information is used for guiding the front end to input domain knowledge in the configuration area, and the domain knowledge is used for representing a logic rule of a verification task in the target domain; based on the domain knowledge, verification guiding prompt information is constructed, and the verification guiding prompt information is used for guiding generation of a verification code file according to a logic rule; and calling a code generation model, generating a verification code file containing verification logic based on the prompt information, and deploying the verification code file to the target verification platform. Structured domain knowledge is collected through a guide type interface, accurate prompt information is automatically constructed, a verification code file conforming to a domain rule is generated, and the generation accuracy and efficiency are improved.

The invention relates to the technical field of pump system monitoring and diagnosis, and discloses a pump system performance monitoring and fault diagnosis method and system based on digital twinning, and the method comprises the steps: carrying out the topological correlation analysis of target pump equipment, and obtaining a working logic rule and component relation; performing digital three-dimensional mapping on the target pump equipment to construct a digital twin frame; performing operation simulation deduction on the digital twin frame to obtain simulation operation data; performing synchronous deviation analysis on the simulation operation data and the actual operation data, and performing evolution trend fitting on the analyzed deviation data in combination with historical operation data to obtain a degradation track; performing fault risk study and judgment on the degradation track to obtain a fault symptom category and a fault severity level; performing health state evaluation on the target pump equipment to generate a diagnosis report; according to the invention, the efficiency of performance monitoring and fault diagnosis of the pump system based on digital twinning can be improved.

The invention discloses a script generation method and device, equipment, a storage medium and a product, which are applied to the technical field of computer data processing, and the method comprises the following steps: obtaining business demand information corresponding to a target business function; semantic analysis is conducted on the service demand information, a template configuration file is generated, and the template configuration file at least comprises service parameters needed for achieving the target service function, attribute information of the service parameters and logic rules corresponding to the service parameters; analyzing the logic rule to generate an abstract syntax tree corresponding to the target service function; and performing data integration on the service parameters, the attribute information of the service parameters and the abstract syntax tree to generate an executable script for realizing a target service function. According to the scheme, manual code writing and manual template configuration are not needed, and the script generation efficiency is improved.

The embodiment of the invention provides an operator network selection method, terminal equipment, a readable storage medium and a program product, and relates to the technical field of mobile communication, the method comprises the following steps: receiving update information of a policy rule file issued by a server; the strategy rule file comprises an acquisition triggering rule and an operator switching rule, the acquisition triggering rule defines a condition for triggering acquisition of a network environment state, and the operator switching rule defines a logic rule for deciding whether to switch an operator network according to the network environment state; according to the updating information of the strategy rule file, updating the strategy rule file locally stored in the terminal equipment; when a condition meeting the definition of the acquisition triggering rule is monitored, acquiring the current network environment state of the terminal equipment; and based on an operator switching rule, according to the current network environment state, deciding whether to switch the currently used operator configuration file. According to the embodiment of the invention, the flexibility of switching the operator network is improved.

Various embodiments are directed to verifying outputs of large language models ("LLMs") using logical reasoning. Various embodiments can obtain raw data from a datastore which can be presumed as true. Various embodiments can then factorize the raw data into factorized data points using a large language model ("LLM"). The large language model can then be used to analyze, categorize, and summarize the factorized data points to generate an insight summary. Various embodiments can then validate the insight summary by identifying a chain of logic between the raw data and the insight summary, such that each statement can be proven using logical reasoning (e.g., deductive reasoning, temporal logic, syllogisms, etc.).

The invention is suitable for the technical field of artificial intelligence and multi-modal reasoning, and provides a neural symbol reasoning method and system for multi-modal information processing, and the method comprises the following steps: obtaining multi-modal input data; respectively extracting semantic attribute representations of the image data and the text data on a predefined attribute set to obtain a multi-modal semantic attribute representation; mapping the multi-modal semantic attribute representation into a predicate in a first-order logic form, and constructing a symbolized multi-modal attribute fact set; inputting the multi-modal attribute fact set and a logic rule in a pre-constructed first-order logic knowledge base into a Markov logic network for reasoning to obtain a reasoning result; and integrating the reasoning results, and generating an interpretable decision result and a reasoning logic link. According to the method, multi-modal shared attribute symbols are taken as bridges, information fusion, conflict resolution and high-level consistency constraint among multiple modals are realized, and a reasoning result with interpretability, high robustness and strong generalization ability can be obtained.

The invention relates to the field of big language model reasoning, in particular to an intelligent reasoning method based on big language model chain reasoning and a self-verification mechanism. The scheme comprises the steps of performing semantic analysis on a text input by a user, and extracting a problem structure and a reasoning intention; the problem is disassembled into a plurality of sub-problems, and a reasoning chain is constructed for reasoning; verification is performed after reasoning is completed; the verification result is judged, if verification passes, the reasoning result is reserved, and if verification of the reasoning result fails, the reasoning path is automatically optimized. Through a chain structure and a self-verification mechanism, the inference error rate is remarkably reduced, an inference path, a verification score and a logic basis are provided, and the user trust is improved. And multi-mode and multi-field tasks, such as knowledge questions and answers, logical reasoning and task decomposition, are supported. When verification fails, a reasoning path is automatically optimized, reasoning efficiency is improved, various large language models, knowledge bases and logic rule bases can be accessed, collaborative reasoning is achieved, and the method is suitable for multi-modal and multi-field intelligent reasoning tasks.

The invention discloses a data quality evaluation and restoration method and system based on machine learning. The method comprises the following steps: firstly, preprocessing data, and constructing a structured generator network containing a parameterized adjacent matrix; in the training stage, the network outputs preliminary reconstruction data, and manifold constraint projection is utilized to find a logic correction target matrix meeting domain constraints; and constructing a potential consistency loop through gradient blocking, and calculating a consistency loss to drive the network to approach a compliance manifold. Meanwhile, an overall target integrating reconstruction errors, logic consistency and acyclic constraints is constructed, and an augmented Lagrangian method and a double-layer circulation strategy are adopted to jointly optimize parameters. And after the double convergence judgment is met, final inference is executed based on mask synthesis. According to the method, the logic rule is internalized into the generation capability, and the sparse causal structure is mined synchronously, so that high-quality data recovery with logic compliance, distribution consistency and interpretability is realized.

The invention belongs to the field of three-dimensional digitization, and particularly relates to a three-dimensional design system for a large transformer oil tank, which comprises an oil tank service rule table, a three-dimensional design table, a three-dimensional design table and a three-dimensional design table, wherein the oil tank service rule table is used for expressing execution logic rules and assembly information logic rules of oil tank services in a file form; the parameterization design module is used for inputting calculation order data to the parameterization design module by a user, calculating the data input by the user by inheriting the calculation order data in combination with an execution logic rule, and matching a rule of an oil tank business rule table with an assembly information logic rule; and calling the parameterized template library according to the assembly information logic rule of the fuel tank service rule table, matching the parameters in the fuel tank service rule table with the parameters defined by the matched model, and generating a fuel tank three-dimensional model through three-dimensional modeling to realize regular assembly or interactive assembly of the transformer fuel tank. According to the method, standardization, normalization and unification of design input are achieved, and human errors caused in the manual calculation and model creation process are reduced.

A search and retrieval data processing system for retrieving classified data for execution against a cyber-security logic rules includes one or more hardware processors and memory, networked to communicably couple through a secure connection to a classified data database, the classified data database including an aggregated plurality of classified data records captured from a plurality of classified data sources; and the memory in communication with the processor, the memory storing an execution environment and the execution environment including an input port for receiving, from an entity, data associated with requested operations; a search engine for searching the classified data records of the classified database; and a logic execution module. The logic execution module is operable for executing a set of cyber-security logic rules against the received data and classified data records; and based on a positive comparison between the received data to the classified data records, writing to memory one or more instructions for initiation of one or more termination actions of the one or more requested operations.

The application discloses a kind of hierarchical formalization modeling and safety verification methods for automatic driving emergency brake logic, electronic equipment, computer readable storage medium and program, including obtaining and abstracting the environment perception information related to automatic driving emergency brake, vehicle operating state parameter, emergency brake trigger condition and brake control constraint, to form the basic formalization element of emergency brake logic;Then according to the processing flow of emergency brake logic, the emergency brake logic is divided into multiple functional levels, and each level is respectively formalized modeling, including describing the constraint relationship between each logic rule in the same level and the data transmission relationship between different functional levels, state evolution relationship and timing constraint relationship, define system safety attribute, input formalization verification platform to execute safety verification.The application reduces the overall modeling complexity and improves the verification efficiency.

A machine learning method for learning and applying a rule set from relational data includes receiving a graph representing relational data, wherein nodes represent elements of the graph, and edges represent relationships between nodes, and generating an intermediate representation of the graph by mapping features of the nodes and edges of the graph to an intermediate vector representation. Optimized logical rules that define the nodes and edges of the graph based on the intermediate vector representation are learned by: defining a maximum satisfiability (MAX-SAT) problem for the graph; and estimating a gradient around a solution of the MAX-SAT problem to produce the optimized logical rules, which are applied to a new graph. The data can be medical data and the graph can be used in a machine-learning task, such as using the medical data for disease prediction, for optimization of the machine-learning task and / or to support decision-making.

The invention relates to the technical field of industrial internet-of-things automatic control, and discloses an actuator internet-of-things multi-protocol adaptation system and method.The method comprises the steps that a protocol module constructs a state machine model for each protocol adapter, cross-protocol state collaboration and abnormal event release are achieved through tense logic rule verification, and a resource module receives abnormal events and sends the abnormal events to a server; the method comprises the following steps: dynamically updating a global resource constraint graph, analyzing an optimal resource reallocation scheme and an atomic task sequence, deconstructing the task sequence into a pi-calculation concurrent process network by applying a reconstruction module, recombining the process network and mapping the recombined process network into a cross-protocol instruction set to drive an executor, and finally, executing the Pi-calculation concurrent process network. Full-link adaptation from protocol layer state consistency guarantee and resource layer dynamic optimization scheduling to application layer process flexible reconstruction is realized, and the reliability and response efficiency of a multi-protocol actuator system in a complex industrial environment are improved.

A method for training a machine learning model, a method for generating an output based on a natural language and a corresponding machine learning model, a data processing device and a computer program are disclosed. A training method may include providing at least one training data sample and adjusting a parameter set of a machine learning model based on the at least one training data sample. The training data samples may include natural language-based input tokens, sign annotations of the natural language-based input tokens, natural language-based target tokens, and sign annotations of the natural language-based target tokens, where the sign annotations may be used to validate an output of the machine learning model by means of logical rules.

This invention discloses a method for counting sports events based on a deep learning network, comprising the following steps: Step 1, data annotation; Step 2, training data preparation; Step 3, training data preprocessing; Step 4, model building; Step 5, model training; Step 6, model inference. This invention uses a deep learning network structure to replace logical rules for counting sports events. Users only need to use annotation tools to quickly and easily annotate the data, and then feed the annotated data into the network to train the model to achieve sports event counting. Furthermore, this solution is simple to iterate later; only new data needs to be added and the model continued to be trained to adapt to new rules, resulting in a short development cycle and low cost.

This invention discloses a three-color probability assessment method and system based on high-precision clause mapping, comprising the following steps: Step S1: Receive text input containing facts to be assessed, and perform structured preprocessing to extract core entities, time elements, and request types to generate a structured case representation; Step S2: Based on the structured case representation, plan a mapping path from the starting point of the case to potentially relevant clauses in a preset clause knowledge network. The mapping path consists of multiple sequentially connected nodes and directed edges, where each node corresponds to a clause to be assessed, and each directed edge corresponds to a verification operation based on logical rules. This invention, through high-precision clause mapping, probability calibration, versioned threshold management, and structured report generation, overcomes the shortcomings of existing technologies and achieves standardization, traceability, and efficiency throughout the entire assessment process.

The invention discloses an AI-based aviation luggage compliance intelligent consultation method, system and device and a storage medium, and the method comprises the steps: S1, constructing and maintaining an aviation regulation knowledge base which is used for storing luggage transportation and dangerous goods regulation terms from a plurality of official or industrial standard aviation regulations; s2, natural language segment query of a user is received, and query information used for compliance judgment is obtained through semantic understanding; s3, retrieving at least one associated target clause from the aviation regulation knowledge base based on query information, and performing compliance judgment reasoning on the target clause in combination with the query information based on a preset logic rule to generate a judgment result; and S4, outputting a consultation result, wherein the consultation result at least comprises a conclusion and rules and regulations based on the conclusion. The method has the advantages of being high in accuracy and authority, high in efficiency and instantaneity, good in user experience, high in interpretability and credibility and the like.

A system and method for analyzing data transfers using pattern mining, including: categorizing sequences of events into categories based on an order of the events in the sequences; identifying, for one or more sequences in a given category, subsequences of events in a dataset of event data using one or more data mining algorithms; and accepting or denying a data transfer based on applying logical rules to the data transfer, where the rules may be determined using the identified subsequences. In some embodiments, event sequence categories may include an order sensitive category and an order insensitive category, and identifying one or more subsequences of events may include applying a first data mining algorithm to order sensitive sequences, and applying a second data mining algorithm to order insensitive sequences; rules may be determined based on calculating metrics for identified subsequences, describing occurrences of the subsequences in the dataset of event data.

The invention belongs to the technical field of software testing, and relates to an NLP-based test case generation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a demand document, and carrying out intelligent analysis and structural processing on the demand document; performing test element and logic rule extraction on the demand document subjected to intelligent analysis and structured processing; constructing a test model based on the demand document after the test elements and the logic rules are extracted; generating test data and a test path based on the test model; based on the test data and the test path, automatically synthesizing diversified test scripts; and closed-loop feedback and model iterative optimization are carried out. The method can ensure that the test method is always synchronous with the business demand, and finally realizes the dual improvement of the test quality and efficiency.

This invention discloses a sequence recommendation method based on the fusion of positive and negative feedback and logical rules, comprising: dividing user behavior into positive and negative feedback; constructing a feedback sequence, including positive and negative feedback sequences, based on user behavior and time sequence; processing the features of the user behavior sequence and the feedback sequence to obtain corresponding embedded features; using the self-attention mechanism of a deep learning model to process the input embedded features, capturing the internal dependency features of the original user behavior sequence; and using a cross-attention mechanism to cross-associate the feedback sequence and the input user behavior sequence to capture the dynamic relationship between user behavior and feedback; and through an output layer, mapping the model's intermediate features to user preference ratings for target items, outputting a rating list for recommendation ranking. This invention significantly improves the performance, interpretability, and adaptability of recommendation systems by combining positive and negative feedback information from user behavior with logical rules.

The invention discloses a rewinding order allocation method and device and a medium, and the method comprises the steps: obtaining the order information of a rewinding order, and determining the information type of the order information; at least one corresponding distribution model is determined based on the information type, a target unit is determined based on the unit information and the order information through the at least one distribution model, the at least one distribution model comprises at least one of a filtering distribution model and an understanding distribution model, the filtering distribution model is used for screening a rewinding unit based on a logic rule, and the understanding distribution model is used for understanding the rewinding unit; the understanding distribution model is used for screening rewinding units based on semantic understanding, and the unit information is used for indicating the unit specification of each rewinding unit; and distributing the rewinding order to the target unit. Through the technical scheme provided by the invention, the distribution efficiency of the rewinding order can be improved.

The application provides a data query method and system based on text recognition, and relates to the technical field of database query. The method comprises the following steps: constructing a knowledge base for storing power field database metadata; using a pre-trained vector embedding model to convert data table names, field names and Chinese descriptions into high-dimensional vectors and storing the association relationship between the high-dimensional vectors and the metadata; after obtaining a query request, using the pre-trained vector embedding model to convert the query request into a query vector, and obtaining a target field and a target description according to the query vector; combining a preset business logic rule to construct a dynamic prompt word; inputting the dynamic prompt word and the query request into a large language model to generate a thinking chain reasoning process and a target SQL statement; and finally executing a query task. The application improves the query efficiency.

The application discloses a three-component proportional controller parameterization modeling method, and belongs to the technical field of controller parameterization modeling. The method realizes the collaborative driving design of the overall structure by establishing a parameterization system of active size, associated logic rule and passive size. Specifically, the parameterization modeling of six parts, i.e. a shell, a displacement rotor, a resistance and leakage rotor, a matching level, a transmission gear and a sliding bearing, is included. By defining a few core active sizes such as rotor radius, hub thickness and blade thickness, and based on geometric relationship and physical constraint, all passive sizes such as center distance, rotation chamber angle, gear tooth number, shell height ratio and the like are automatically calculated. The application overcomes the disadvantages of the traditional trial and error design method, can automatically update all models by modifying a small number of parameters, greatly improves the design efficiency and accuracy, guarantees the rotor matching precision and proportional control performance, and is convenient for realizing the rapid optimization and serialization of products.

The embodiment of the application provides a product recommendation method, device, equipment, medium and program product based on a large model, and relates to the technical field of data processing. The method comprises the following steps: obtaining product recommendation basic information of a target user; obtaining current product recommendation prompt information; using a pre-trained product recommendation large model to perform reasoning based on the product recommendation basic information and the product recommendation prompt information, and obtaining a recommendation bank result of a next dialogue round. Through the steps of obtaining a current recommendation bank, historical dialogue records and a recommendation priority order list, and using a large model to combine a recommendation task target and a logical rule to perform reasoning, the embodiment of the application can dynamically generate a product recommendation result of a next round, thereby effectively improving the flexibility and accuracy of product recommendation, and effectively reducing the maintenance cost of a recommendation system.