610 results about "Automaton" patented technology

The invention provides a multi-round automatic machine learning agent system based on reinforcement learning optimization. Comprising a task analysis module used for generating an initial prompt for an MLE agent to call; the MLE agent module is used for generating an executable code; the code executor is used for generating an execution result; the evaluator is used for outputting a normalized value of each index and a code correctness identifier; the reward construction module is used for generating a reward value; the reinforcement learning optimizer is used for calculating group average return and candidate advantages and updating strategy parameters of the MLE intelligent agent module based on the candidate advantages; and the multi-round interaction control module is used for feeding back the execution result of the previous round and the reward value to the MLE agent module in the multi-round interaction process, and controlling code generation of the next round until a preset termination condition is met. According to the invention, strategy adaptive evolution, reinforcement learning optimization of fine-grained credit distribution and multi-round closed-loop automatic process improvement can be realized.

Technology is described for determining a task plan that is usable by a robotic device in a workspace. The method can include converting instructions received for the robotic device into temporal logic (TL) statements and to a non-deterministic Buchi Automaton. A task probabilistic machine learning model can be generated with feasible task plans using the non-deterministic Buchi Automaton. A plurality of task plans can also be created or generated using the task probabilistic machine learning model. A sensor probabilistic machine learning model of the workspace can be constructed using information from sensors of the robotic device. The task plans from the task probabilistic machine learning model can be compared with the sensor probabilistic machine learning model to select the task plan with a high probability of correlation to the workspace.

The invention discloses a low-altitude airway flow field sensitive area dynamic identification optimization method based on set simulation, and the method comprises the steps: building a low-altitude flow field preprocessing data base with consistent time and space based on Beidou subdivision grids and multi-source heterogeneous data fusion; constructing a low-altitude airspace digital twinning environment based on the data; based on the low-altitude airspace digital twin environment and the cellular automaton-fluid coupling model, generating a diversified flow field evolution scene covering extreme weather and equipment faults; based on a set simulation result, extracting a high-conflict probability region through a spatio-temporal clustering algorithm and quantifying region risk features; generating an air route planning scheme meeting security constraints through a multi-objective evolutionary algorithm based on the quantitative regional risk features; on the basis of a low-altitude airspace digital twin environment and an air route planning scheme, verifying the feasibility of the air route planning scheme through historical data playback and virtual-real fusion test; and according to a verification feedback result, carrying out dynamic feedback optimization on the low-altitude air route flow field sensitive area identification and air route planning scheme.

The invention relates to an AI-based planned land site selection multi-objective optimization method and system. The method comprises the following steps: constructing a city data cube; constructing a cellular automaton model and generating a land utilization potential map; constructing a game decision model, and generating a preliminary site selection scheme set; inputting the preliminary site selection scheme set into a cellular automaton model to generate an evolution simulation data set; constructing a multi-target evaluation model, and calculating the relative closeness between each scheme in the preliminary site selection scheme set and an ideal solution; generating a site selection decision report according to the relative close degree; in conclusion, the urban data cube is constructed by integrating multi-source real-time and historical data, the dynamic land potential map is generated by applying the cellular automaton model, and the multi-target scientific balance is realized by introducing the multi-agent game decision. Automatic processing and consistency guarantee of planning rules are realized, a scientific quantitative tradeoff mechanism in a multi-target conflict scene is provided, and the method has the effect of improving data timeliness and dynamic response capability of site selection decision.

The invention relates to the technical field of power system scheduling, and discloses an intra-day look-ahead scheduling rapid solving method considering large-scale new energy cluster power generation volatility. Comprising the following steps of S1, new energy cluster space-time fluctuation scene generation based on a neuron cellular automaton, S2, power grid dynamic security domain definition and simplification based on a physical information neural network, S3, scheduling rapid optimization solution based on model prediction path integration, and S4, scheduling scheme dynamic elasticity and stability evaluation based on a Kupman operator theory. The new energy cluster space-time fluctuation scene generation method based on the neuron cell automaton can effectively generate a space-time scene reflecting large-scale new energy cluster power generation volatility, supports uncertainty analysis, has the advantages of being high in calculation efficiency and scene authenticity, and is suitable for large-scale new energy cluster power generation. The problem that scene generation is inaccurate due to the fact that a traditional statistical model ignores space-time coupling is solved.

According to the automatic software development method and device and the computer program, intelligent demand analysis is achieved through a natural language processing technology, dynamic task arrangement is conducted through a finite state automaton, collaborative development is completed by means of a multi-specialized role agent, intelligent verification is implemented based on a template matching mechanism, and the development efficiency is improved. And a complete automatic closed loop from demand to delivery is constructed. According to the scheme, full-process automation is realized, manual intervention is greatly reduced, and the development efficiency is remarkably improved; through division and cooperation of multiple agents, the professionality and decision-making quality of each link are ensured, and the capability limitation of a single agent is overcome; flexible and reliable process control is provided based on state machine management, and development state changes are dynamically adapted; and the standard consistency of the delivery result is ensured by combining template verification. According to the method, the problems of long development period, large quality fluctuation and the like caused by chain splitting, low intelligent level and excessive dependence on manpower of an existing development tool are effectively solved, and a feasible path is provided for comprehensive intelligence of software development.

The disclosed methods and systems automate the process of building machine learning models. A user interface receives a selection of a dataset for a machine learning experiment. An execution plan for the experiment is determined based on the selected dataset. The experiment is executed according to the execution plan to generate a plurality of machine learning models. The performance of the generated models is evaluated based on one or more performance metrics. A model is selected from the generated models based on the evaluation of the performance metrics. The selected model may be stored for future use.

The invention discloses a bridge safety early warning method and system, and the method comprises the steps: collecting bridge structure response and environment parameter data, and carrying out the preprocessing of the data, and obtaining a distributed multi-source sensing information matrix; constructing a distributed neuron cell automaton network, interacting state information through unit local communication, operating a lightweight feature extraction algorithm, and generating a multi-dimensional feature vector; carrying out distributed modeling by utilizing a pre-trained distributed LSTM-Transform hybrid model, and carrying out parallel calculation on a local prediction result by each unit to obtain a global health state evaluation result; a local gradient change anomaly detection mechanism is established, data anomaly is identified by comparing prediction results of adjacent units, and a potential risk area is positioned by combining a related algorithm; and constructing a hierarchical early warning threshold system, activating a corresponding early warning response by means of local decision logic, executing an alarm operation, generating recovery guidance information and monitoring uploaded data. According to the invention, two types of network models are combined, so that the system reliability and early warning accuracy can be remarkably improved.

The invention provides a dynamic planning method for a fire evacuation path of a deep subway station based on a cellular automaton, and the method comprises the steps: building a subway space topology through employing the cellular automaton, simulating a fire environment through employing an FDS tool, and obtaining environment data; constructing a multi-field model based on subway space topology and environment data; based on the multi-field model, the pedestrian transition probability is calculated, then the pedestrian transition probability is corrected in combination with the deep subway facility characteristics and the pedestrian consensus behaviors, and finally the corrected pedestrian transition probability is output; and optimizing a cost function of an A star algorithm based on the corrected pedestrian transition probability to obtain a dynamic cost function, further obtaining an improved A star algorithm, planning an initial path based on the improved A star algorithm, formulating a path updating rule, and implementing a smooth transition strategy to realize dynamic path planning. According to the invention, the evacuation safety and the scheduling efficiency under the fire situation can be improved.

The invention discloses an encrypted communication system and method based on cognitive multi-carrier spread spectrum, and belongs to the field of covert communication. The encryption communication system comprises a transmitting device and a receiving device. The transmitting device comprises a data encryption module, a constellation encryption modulation module, a multi-carrier spread spectrum module, a frequency hopping module and a cognitive power distribution module. The receiving device comprises a band-pass filtering module, a de-hopping frequency module, a de-spreading module, a constellation decryption demodulation module, a data decryption module and a coherent combination module. The data encryption module is divided into an interleaving coding unit and a double-rule reversible cellular automaton encryption unit. The cognitive power distribution module continuously scans a wireless electromagnetic environment and carries out real-time spectrum analysis to give power spectrum density results sensed under all frequency hopping frequency sets. According to the invention, continuous detection and dynamic response to the spatial frequency spectrum state can be realized, and the communication concealment, the anti-interference performance and the resource utilization efficiency in a complex electromagnetic environment are remarkably improved by utilizing the frequency spectrum hole.

The invention discloses a ship knowledge graph construction method based on a large model and a graph neural network, and the method comprises the steps: carrying out the format conversion and protection type partitioning processing of a professional document, and completing the recursive segmentation through a placeholder protection formula, a table and other structures according to the semantic hierarchy, and obtaining a text block suitable for the extraction of an entity and a relation; extracting domain entities by utilizing a large language model containing thinking chain cues, and positioning candidate entities in combination with an AC automaton so as to improve the coverage rate and accuracy of relation triple extraction; performing new entity backfilling and relation standardization on an extraction result, and constructing an initial knowledge graph with a consistent structure; and inputting the initial knowledge graph into a graph neural network model with directional expansion and a multi-scale decoder, and complementing a missing relationship through link prediction, so that node distribution and a relationship structure of the graph are more complete. According to the method, a continuous processing chain from text preprocessing, knowledge extraction to graph completion is formed.

The invention provides a cable path intelligent optimization method fusing a cellular automaton and an ant colony algorithm, and the method comprises the steps: obtaining a three-dimensional boundary range of a target region, constructing a three-dimensional underground space voxel model, and dividing the target region into voxel units containing five-dimensional attribute tensors; constructing and inputting the five-dimensional attribute tensor into a physical constructable potential field model, and generating a corresponding three-dimensional physical constructable potential field; performing construction scoring according to the three-dimensional physical constructable potential field and the five-dimensional attribute tensor; constructing a composite cost function in combination with the three-dimensional physical constructable potential field and the construction score, generating a composite passing cost of each voxel, and generating an optimal cable path in combination with a path search algorithm which takes an improved ant colony algorithm as a control mechanism and introduces a rule of a cellular automaton on a path state propagation structure; and performing three-dimensional geographic mapping, structure reconstruction and geometric fairing on the optimal cable path, and outputting a standardized path result.

The invention belongs to a specification mining technology of software engineering, and relates to a construction method of an approximate specification mining model and a software behavior verification system. The construction method comprises the following steps: generating a group of linear temporal logic LTL formulas for describing positive example time sequence attributes according to a positive example set; using an LTL formula to generate a potential negative example for evaluation and training; designing and constructing a neural network for analyzing the finite state automaton from the parameter assignment so as to simulate an acceptance behavior of the finite state automaton; and iteratively searching the neural network through a gradient descent algorithm until the maximum number of iterations is reached, and mining to obtain the finite state automaton. The neural network can simulate acceptance of the finite state automaton in the reasoning process, the finite state automaton can be explained at low cost, and the problem of search space explosion is solved.

The invention provides a rural sewage treatment simulation optimization method based on a cellular automaton, which comprises the following steps of: establishing a cellular grid, and defining basic attributes of cells according to space coordinates, terrain types, population density and sewage treatment capacity; according to the sewage treatment scene, respectively establishing a cellular state evolution rule base; the sewage treatment scene comprises a pipe network collection type, an ecological wetland type and a decentralized recycling type; acquiring environmental parameters and pollutant parameters of a target area to be subjected to sewage treatment; selecting a cellular state evolution rule base according to input environmental parameters and pollutant parameters of a target area to be subjected to sewage treatment; and performing sewage treatment simulation, optimizing the sewage treatment simulation process by the cellular state evolution rule base, and outputting a sewage treatment facility layout scheme and a dynamic control strategy. The sewage treatment scheme can be quickly generated, the optimal sewage treatment scene model is automatically selected according to actual conditions, and accurate customization of the sewage treatment scheme is realized.

The invention provides a chaos enhanced credible authentication method based on a vehicle-mounted gateway, and relates to the technical field of credible authentication, and the method comprises the following steps: generating a chaos sequence by using improved Tent chaos mapping; dynamically disturbing a round constant CK of an SM4 encryption algorithm by using the chaos sequence to generate a confused round key; synchronously updating a session key between the vehicle-mounted gateway and the ECU based on a cellular automaton and a chaotic mapping mechanism; identity authentication is executed through a bidirectional challenge-response mechanism; the vehicle-mounted gateway sends an encrypted challenge frame containing a random number R1 to the ECU; after decryption, the ECU generates a response frame by using a SipHash function and returns the response frame, and meanwhile, sends a reverse challenge frame containing a random number R2; and the vehicle-mounted gateway verifies the response frame and then generates a reverse response frame, and the two parties update the session key after the ECU passes the verification. According to the method, the anti-attack capability can be remarkably improved, the method can efficiently adapt to an embedded environment, and meanwhile the system reliability can be effectively enhanced.

The invention discloses a multi-modal fusion short message compliance and security dual auditing method and system, and the method comprises the steps: encrypting account information through employing an irreversible algorithm based on SHA256 and a random salt value, and decomposing the content of a short message into a text stream, a link stream and a symbol stream through employing a regular expression; traversing each character in the short message content by adopting a prefix mode based on a Trie tree in combination with an AC automaton algorithm to detect sensitive words; performing symbol semantic classification mapping and analysis on the special symbol feature data extracted from the symbol stream; carrying out sending behavior analysis on the text feature data extracted from the text stream; performing special detection on link feature data extracted from the link stream; based on the factors corresponding to the sensitive words, the semantics, the behaviors and the links and the weights of the factors, a multi-modal feature fusion decision risk assessment algorithm is adopted to output a risk score value and a risk decision rule of the risk score value so as to execute short message interception operation or short message release operation. According to the invention, full-dimension perception and dynamic defense of risks can be realized.

The invention discloses a wind power plant voltage and frequency cooperative tuning control method, and relates to the technical field of tuning control, and the method comprises the steps: obtaining the real-time operation data of a wind power plant, carrying out the preprocessing of the real-time operation data of the wind power plant, carrying out the voltage fluctuation and frequency disturbance prediction through a cellular automaton model in combination with the pre-obtained power grid data, and carrying out the voltage fluctuation and frequency disturbance prediction. Obtaining a prediction state matrix; carrying out multi-objective optimization solution in combination with a pre-constructed multi-objective optimization problem and constraint conditions, and obtaining an optimal droop coefficient vector in combination with a preset rule; and the optimal droop coefficient vector is used as a control reference, and voltage and frequency cooperative tuning is carried out in combination with grid-connected point voltage and frequency obtained in real time and communication network topology data. According to the method, prediction is carried out through the cellular automaton model, the rapid and cooperative regulation capability of the voltage and the frequency of the wind power plant is improved, and therefore the urgent demand of a power system for rapid, accurate and cooperative control under the access of high-proportion new energy is better met.

Techniques for generating a layout for computing equipment in a data center are disclosed. The system represents a physical environment as a layout polygon and obstacles within the physical environment as obstacle polygons. The system represents groupings of racks as pod polygons. The system executes a positioning algorithm to place pod polygons in the layout polygon. The initial layout is optimized according to layout criteria. The system determines if any of the pod polygons in the initial layout collide with an obstacle polygon. The system attempts to resolve the collision by moving the colliding pod polygons or removing racks from a pod polygon. The system generates a basket tray path that minimizes the length of the basket tray path while avoiding obstacles in the path.

The invention relates to the technical field of intelligent training and data analysis, in particular to an intelligent model construction method and system for student training data analysis. Comprising the following steps: constructing an SOP time sequence knowledge graph, obtaining a standard operation specification document and expert-level operation demonstration data, and constructing the SOP time sequence knowledge graph; real-time feature extraction: capturing a multi-modal data stream, and generating a real-time behavior feature vector; state recognition and path deduction: inputting the real-time behavior characteristics into an event classifier to recognize a key event, performing path deduction based on deterministic finite state automaton logic in an SOP time sequence knowledge graph, and determining and outputting a current state pointer; deviation analysis and judgment: extracting a compliance mask based on a current state, and injecting the compliance mask into a decoding process of the attention network; and performing feedback and adjustment to generate a corresponding deviation event signal. Through deep analysis, feedback is more targeted, and the accuracy and fineness of training evaluation are remarkably improved.

The embodiment of the invention provides a chip packaging defect diagnosis method and system based on computer vision, and belongs to the technical field of computer vision, and the method comprises the steps: firstly, collecting a dynamic multi-source image sequence of chip packaging in key processes of soldering tin melting, packaging glue curing and pin shaping; and performing defect feature cellular coding processing on the dynamic multi-source image sequence to form a defect feature cellular coding set. And then, constructing a cellular automaton evolution model based on the defect feature cellular coding set, then, executing multi-source association verification processing on the cellular automaton evolution model, and matching an evolution trajectory of a cellular with a defect evolution rule base to generate a verification result. And finally, analyzing the verification result to reconstruct a complete evolution path and a source association chain of the defect cell, thereby accurately determining the type, the specific occurrence process and the position of the defect, and outputting a comprehensive diagnosis result. According to the method, cross-process and multi-source fusion accurate traceability and diagnosis of the dynamic evolution process of the packaging defect are realized.

The invention discloses a flexible resource adjustment capability assessment method and system based on labels and risk analysis, and relates to the technical field of power system demand side management. The method comprises the following steps: acquiring real-time operation parameters of load side flexibility resources, and generating a multi-dimensional capability envelope of individual resources based on a multi-state finite automaton model; constructing a multi-dimensional value label, clustering and grouping the flexible resources in combination with a multi-dimensional capability envelope, and constructing a virtual polymer; quantizing the aggregation adjustment capability of the virtual aggregate by adopting an opportunity constraint robust aggregation method to generate a multi-dimensional vector; and fusing the multi-dimensional vector with geographic information, realizing visualization through a thermodynamic diagram and an interactive interface, and generating a system-level capability map. According to the method, the full-dimensional capability evaluation of the flexible resources from individuals to aggregation is realized, the value attributes and the operation risk are considered, and a visual and reliable decision support is provided for power grid dispatching.

A system and method are described for updating Machine Learning (ML) models in an electronic warfare (EW) environment. The ML models are updated automatically post mission using threat data of emitters in the EW environment and then deployed to hardware in an aircraft. The updated ML models are used during a subsequent mission and include an unsupervised ML model to deinterleave waveforms received from the emitters and a supervised ML model for emitter identification, waveform tracking, and anomaly detection based on the deinterleaved waveforms. The ML models are updated by augmenting templates that indicate the behavior of the emitters and training the ML models using many plausible superpositions of the augmented templates. The ML models are updated by selecting and applying non-linear augmentations of at least one of the templates and new templates randomly using a Monte Carlo approach.

The invention discloses a user credit risk assessment method, system, equipment and medium based on multi-industry federated learning in order to improve data security of federated learning, and belongs to the technical field of information. The method comprises the following steps: extracting operator data and bank financial data, and performing encryption preprocessing through a Hash mechanism; performing federated learning on the operator data and the bank financial data after encryption preprocessing, accessing a PSI module as a plug-in to an FATE core, converting RSA of an FATE algorithm into an elliptic curve, and performing secret sharing through a hexagonal grid cellular automaton to obtain a trained federated model; and evaluating the credit risk of the user by using the trained federal model. According to the method, the requirement of hiding a keyword of a queried object or a client ID is met, the hidden query service provides a matched query result, calculation can be carried out without going out data of both parties, and the method follows the data authentication and access process of multi-party security calculation and the overall business process. Data barriers among different industries are broken through, and deep data cooperation of multiple industries is realized.

A processing system including at least one processor may obtain description information of a first machine learning model, obtain a set of interpretation criteria for the first machine learning model, and generate, via a second machine learning model, an explanation text providing an interpretation of the first machine learning model in accordance with the set of interpretation criteria and the description information of the first machine learning model.

The invention relates to the field of distributed storage, and discloses a distributed storage system, method and equipment for wind power plant data and a medium, which are used for realizing flexible adjustment of a storage strategy and meeting the storage requirement of dynamic change of a wind power plant data value. Comprising the following steps: collecting SCADA system data at edge nodes of a wind power plant, inputting an information entropy module and an access heat analysis module in parallel, fusing to generate a data value evaluation result, inputting the evaluation result into a cellular automaton engine, outputting a cellular state change instruction, summarizing collaborative strategy requests of at least two edge nodes to a regional center node, and carrying out collaborative strategy analysis on the regional center node. And a fair resource allocation scheme is output through the Sharpley value calculation module. And each edge node synchronously receives the scheme, the time sequence database controller generates a final storage instruction, and data distributed persistent storage is completed. According to the method, on the basis of the correlation between the long-term data value evaluation result and the actual use value, the entropy value and the popularity weight coefficient are optimized, and self-adaptive optimization of the system is achieved.

The invention relates to the technical field of quantum reinforcement learning, in particular to a reinforcement learning method and system for quantum gate regulation, and the method sequentially comprises the steps: carrying out the normalization of an offline sample, carrying out the principal component analysis, and then preparing a prior quantum state; performing wavelet scattering and persistent coherence on the quantum pulses to extract topological features, and mapping the topological features into a non-Abell geometric gate rotation angle to generate an action probability; constructing a sparse high-dimensional vector, selecting a target super vector through Grover amplification, writing the target super vector into the silicon carbide memristor array, and retrieving an action vector according to a conduction function determined by the topological feature vector; the motion vector drives the Heisenberg cellular automaton to predict the environment, the local error triggers the fine tuning of the rotation angle and the conduction value, and the global distance triggers the topology recompilation and the quantum natural gradient. According to the method, decision making within 250 microseconds, low-energy-consumption retrieval and steady-state self-healing are achieved.

The present disclosure provide techniques for automated machine learning (ML) training based on updating training data based on model performance. A system can determine a sample pattern from input data to be used for training a model. The system determines a training dataset and a test dataset including multiple samples corresponding to the sample pattern. After training a model using the training dataset, the system tests the model using the test dataset. The system determines that the trained model's performance with respect to a sample pattern is unsatisfactory, and retrains the model using an updated training dataset that includes additional samples corresponding to the sample pattern.

The invention discloses a hierarchical layout and wiring method and system based on a quantum cellular automaton circuit, and the method comprises the steps: obtaining an original logic netlist which comprises a first logic sequence among a plurality of nodes, the first fan-in and fan-out information of each node, and a first hierarchy; preprocessing the original logic netlist to obtain a first logic netlist layered according to logic depth; according to a preset layout strategy, inter-layer long lines which do not conform to global clock synchronization are eliminated, and cross lines are optimized, so that a second logic netlist is obtained, and the second logic netlist comprises a second logic sequence among the multiple nodes, second fan-in and fan-out information of all the nodes and a second level; and dynamically wiring the plurality of nodes in the second logic netlist according to a preset wiring strategy, and distributing clock signals. According to the method and the system, the layout and wiring quality and reliability of a quantum cellular automaton (QCA) circuit are remarkably improved.

The invention relates to the technical field of land data planning, and discloses a reasonable land planning system based on machine learning carbon storage, and the system comprises a multi-source data fusion module, a carbon storage prediction module, a three-generation coordination discrimination module, a land use intelligent optimization module, a scene interaction deduction module, and a planning result generation module. By integrating data such as standardized land utilization and carbon density, a machine learning model is utilized to predict the dynamic state of the carbon density in real time, and the functional coordination degree of the three plants is quantitatively evaluated; and then, by taking the improvement of the carbon reserves and the coordination of the three plants as targets, carrying out spatial simulation and iterative optimization in combination with multi-objective optimization and a cellular automaton, comparing different policy carbon sink effects through scene deduction, and finally outputting an optimization scheme, thereby realizing the real-time closed loop of evaluation and optimization, and synergistically improving the carbon sink benefits and the three-plant function.

The invention relates to the technical field of robot positioning, in particular to an automatic robot positioning method based on vision assistance, which comprises a vision acquisition module (1), a multi-modal data fusion module (2), a deep learning feature extraction module (3), a self-adaptive positioning optimization module (4) and an execution control module (5). The visual collection module (1) collects multi-source data through the camera (11), the infrared sensor (12) and the laser radar (13), after the multi-mode data fusion module (2) integrates the multi-source data, key features are extracted through the deep learning feature extraction module (3), then the self-adaptive positioning optimization module (4) dynamically adjusts weights and corrects errors, and finally accurate positioning and navigation are achieved through the execution control module (5). According to the invention, through the adaptive weight adjustment system (24), the adaptive feature enhancement system (34) and the dynamic error compensation system (44), the positioning precision and robustness in a complex environment are significantly improved, and meanwhile, the intelligent obstacle avoidance system (53) ensures safe operation. According to the invention, the problems of insufficient complex environment adaptability, limited positioning precision and low algorithm efficiency in the prior art can be effectively solved.