72 results about "Decision points" patented technology

The invention discloses an electric power information operation violation risk supervision system based on a knowledge graph, which relates to the field of violation risk supervision and comprises a dynamic graph construction module, a causal analysis module, a strategy analysis module, a strategy modeling module and a supervision decision module. The method comprises the following steps: obtaining multi-type electric power operation field sensing data and information system data, and carrying out data processing and knowledge graph dynamic construction to obtain a dynamic knowledge graph; performing risk situation quantification and risk decision point inference based on the dynamic knowledge graph to obtain a key causal decision point set; based on the key causal decision point set, through strategy logic analysis, obtaining a logic rule set which can be directly deployed and executed; according to the method, a logic rule set which can be directly deployed and executed is subjected to dynamic strategy evolution of a stochastic differential equation to obtain a dynamic strategy model, and the dynamic strategy model is subjected to decision optimal screening of measurement transformation to obtain an optimal supervision decision set, so that a risk value can be accurately calculated, and the supervision response speed can be increased.

The invention relates to the technical field of computers, and discloses a data control method and system, electronic equipment and a storage medium, and the method comprises the steps: receiving a data control strategy defined by a data owner, and the data control strategy is constructed based on a quintuple framework and comprises a subject, an object, an environment condition, an operation behavior and an effect; compiling the data control strategy into an intelligent contract code, and generating a source code based on an intelligent contract template; deploying the smart contract code to a block chain network to form a decentralized strategy decision point; intercepting the data access request, triggering the smart contract to verify the access request, and generating an access credential when the verification is passed; and allowing data access based on the access credential, and monitoring a data use behavior to ensure consistency with the data control strategy. According to the method, the fine granularity and the whole-process coverage of data control can be improved, the auditing credibility can be improved, the automation level and the efficiency of a control system can be improved, and the end-to-end safety guarantee capability is enhanced.

The invention relates to the technical field of artificial intelligence, and discloses an information security model auxiliary decision-making method and system based on an intelligent knowledge graph, and the method comprises the steps: constructing a multi-modal security data pool of a to-be-decided scene, training a joint extraction model of the to-be-decided scene, and extracting data examples and example relationships of the multi-modal security data pool; constructing a security knowledge graph of the scene to be decided; constructing an attack tactics-technology-process ontology layer of the scene to be decided to calculate a potential attack path of the scene to be decided, and calculating an attack path occurrence probability and an attack influence range of the potential attack path; marking a strategy decision point of the security knowledge graph, and analyzing a Top-K strategy of the strategy decision point by using a preset PPO algorithm; and constructing an attack chain analysis interface of the Top-K policy in the security knowledge graph to generate a policy optimization parameter of the Top-K policy, and executing the information security model aided decision of the scene to be decided based on the policy optimization parameter. According to the invention, the efficiency of security decision-making of to-be-decided scene information can be improved.

The invention provides a data processing method based on request interception, which comprises the following steps of: intercepting a calling request for marking a service method through a request interception mechanism, preposing a decision point of service logic, and selecting whether the service method is executed or not according to a request context. According to the method and the device, the business rules are stored in the configuration center, external rule configuration is performed, the business rule expressions are pre-stored in the configuration center, dynamic acquisition is performed based on the rule identifiers, decoupling of the business rules and the codes is realized, the business rules can be configured independent of the codes, and flexible business processing can be realized only by modifying the expressions of the corresponding rules in the configuration center. The problems of code expansion and difficult maintenance caused by business rule change in a multi-channel environment are effectively solved, so that the flexibility and maintainability of a business data processing system are improved. The method can be applied to a business processing system in the financial field or the medical field, so that the flexibility of the business processing system in the financial field or the medical field is improved.

The invention relates to the technical field of artificial intelligence, and discloses a military simulation agent design method based on a knowledge graph, and the method comprises the steps: taking a synchronous matrix, an execution matrix and decision support information formed in the military planning and war game deduction process as the basis, and uniformly representing units, stages, combat functions, decision points and condition elements in the knowledge graph, and a computable high-dimensional plan state expression is formed. On the basis, a plan updating model reflecting stage propulsion, function collaboration and decision point triggering relations is constructed and used for describing dynamic evolution of plan states in the simulation process. Through systematic description of a transient amplification phenomenon in a plan evolution process, clear association is established between the transient amplification phenomenon and decision points and condition elements in a knowledge graph, so that a simulation agent has stable and reproducible behavior performance in decision generation and action execution processes.

The invention discloses a distributed intelligent deduction system and method for multi-source data fusion and dynamic scheduling, and relates to the technical field of deduction simulation. The deduction preprocessing module is used for carrying out task stage division on military scenarios and setting decision points, generating branch tasks according to tactical rules and carrying out model classification; the deduction management module is used for promoting deduction from an initial state based on a simulation engine, generating branch tasks at a decision point according to a real-time state, distributing initial weight coefficients by combining historical efficiency parameters and model types, and realizing parallel deduction and dynamic model switching; the deduction optimization module continuously updates a weight coefficient through a branch efficiency parameter, screens an optimal deduction path and iterates a state snapshot in a closed loop; the resource regulation and control module collects data in real time to support efficiency evaluation, resource distribution is dynamically optimized according to task loads, the deduction efficiency and accuracy are remarkably improved, and intelligent resource scheduling and system self-adaptive optimization are achieved.

The invention discloses an LCD display screen production multi-workshop collaborative management method based on AI prediction, and particularly relates to the technical field of production management. The method is used for solving the decision difficulty that an existing production management system is difficult to quantitatively evaluate process interruption loss and order delay loss when dynamic demands change. The method comprises the following steps: acquiring production data, order information and material commitment data of each workshop, respectively predicting first loss of interrupting a current irreversible process and second loss of delaying a new order by using an AI prediction model, correcting the first loss in combination with the idle cost of downstream key resources, generating an advantage and disadvantage balancing index based on the corrected loss value, and calculating the defect of the new order according to the advantage and disadvantage balancing index. And constructing a multi-workshop topology network model to simulate disturbance propagation and identify an optimal decision point, and finally generating an adjusted production plan and outputting the adjusted production plan to a production management system to realize multi-workshop collaborative optimization management.

Intent-based automation that discovers automatable tasks and / or determines task variants in data is disclosed. Task capture data may be utilized to determine task variants in task mining data. Semantic understanding of user actions by artificial intelligence (AI) / machine learning (ML) model(s), for example, may be applied to determine the intent of the user rather than only focusing on what actions the user is performing on the computing system. Application logs and semantic understanding may be used to facilitate a more accurate determination of what the user actually intends to do. Task capture for individual user flows may be performed. Once these are captured, task capture algorithms and AI / ML models are used to determine which parts of the flows are similar and / or match and which parts are unique. The path through these flows can then be followed to build a process graph that includes decision points representing the unique flows.

The invention provides a termination strategy optimization method considering a staged task system, and relates to the field of task termination strategies. Firstly, for each stage of a staged task, it is defined that the degradation state of a system obeys a Wiener process, and the number of decision points of each stage is obtained; secondly, converting the degradation state of each stage into a discrete state model to solve the state transition probability of the system; secondly, solving the task termination cost and the task continuation cost of each decision point in different system states, and selecting a smaller value as a corresponding expected cost; and finally, selecting task termination or task continuation action based on the current decision point and the expected cost in the system state by adopting a reverse dynamic programming algorithm to obtain a task termination strategy set. According to the optimization method provided by the invention, the blank that a staged task termination strategy is not considered in related technologies is filled up, and meanwhile, the optimization problem is expressed by adopting a random dynamic programming framework, so that the cost is effectively reduced compared with a fixed threshold strategy.

The application provides a heterogeneous computing power automatic adaptation method and system for an intelligent chip, relates to the technical field of heterogeneous computing adaptation of the intelligent chip, and acquires computing graph structure and operator feature data and hardware state data of a to-be-deployed model; an execution knowledge base is constructed, a scheme list is generated in combination with real-time data and the execution knowledge base; execution code is distributed according to the decision weight of the scheme list; the current execution state is evaluated at a predefined execution decision point to determine whether to switch the adaptive path; the actual execution effect and environment data generated after each decision are summarized, execution track records are formed, and the execution knowledge base is updated to periodically optimize the basis for scheme generation. The application can realize automatic perception, decision, optimization and online learning of a computing task in a heterogeneous computing power environment for an intelligent chip, significantly reduces the adaptation cost and improves the resource utilization efficiency.

A dynamic task scheduling method for heterogeneous multi-machine systems based on multi-agent reinforcement learning includes the following steps: 1. Inputting task information and decomposing all tasks into multiple atomic tasks with different capability requirements that can be executed by a single robot; 2. Establishing an adhesion utility evaluation model and heterogeneous priorities to create a mathematical optimization model; 3. Establishing a local perception domain model and a Markov decision model based on the sequential decision-making process of scheduling decision points; 4. Building a heterogeneous multi-machine system scheduling environment and combining multiple advanced training strategies to learn a deep reinforcement learning solver for heterogeneous multi-machine task scheduling through the interaction between the environment and the agents; 5. Using the deep reinforcement learning solver, sequentially outputting actions for each scheduling decision point for the scheduling instance to obtain a dynamic scheduling solution. This method can handle the uncertainty in the task execution process by inserting dynamic scheduling decision points for dynamic events, thereby achieving fast and robust dynamic task scheduling.

The application discloses a kind of based on blockchain's pedigree data dynamic permission access control system and method, rely on attribute-based access control paradigm, and combine pedigree data access constraint to carry out dynamic access control.First, user sends access request to policy decision point;Decision point according to the policy loaded from policy management point, request relevant information to blockchain, and call user historical behavior verification module based on pedigree data, the legality of current access request is verified using dependency relationship and pedigree data graph.System administrator records access request and verification result to blockchain, to support the fast verification of same query, reduce query overhead.In addition, the system passes access information such as query user, time, result, operation content to management node, for subsequent user access tracking and management.The method uses the anonymity and non-tamperability of blockchain, provides strong evidence for user supervision, realizes efficient management and reasoning to source information.

The application discloses a task scheduling method, electronic equipment, readable storage medium and program product, and relates to the technical field of computers, which comprises the following steps: adopting non-cooperative game theory, multiple iterations of game, determining the final task scheduling strategy according to respective regret values corresponding to respective iterations, determining respective regret values of each game participant at respective decision points by sampling and simulating the game process of a task scheduling game instance based on the theory of counterfactual regret minimization, and then determining the task scheduling strategy according to respective regret values corresponding to respective iterations. The application is also applicable to new types of task scenarios, solves the technical problems of poor real-time performance of task scheduling, low accuracy of task scheduling and low system resource utilization, and achieves the technical effects of improving the real-time performance of task scheduling, improving the accuracy of task scheduling and improving the system resource utilization.

Systems and methods in which a training dataset of a trained tree-based model is embedded as an array of vectors, where each dimension represents a decision point in the model; a distance between historical sample points in a time series is defined as a cosine similarity function between two of these vectors; the array of vectors is processed through a Hierarchical Navigable Small World index, thereby producing an approximate view of similar vectors; for a new prediction, there is a search for a number of most similar vectors; and a discrete probability distribution is created.

Systems and methods for implementation of a multi-agent reinforcement learning based decision system for a materials handling system, including initializing a simulation environment comprising decision points for dispatching materials and attributes of the materials handling system, the simulation environment configured to request a decision for materials dispatch at the decision points to the multi-agent reinforcement learning based decision system; initializing the reinforcement learning agents representative of the decision points for the multi-agent reinforcement learning based decision system; initializing domain expert heuristics for the decision points for the multi-agent reinforcement learning based decision system; and iteratively training the reinforcement learning based decision system with the initialized domain expert heuristics on the simulation environment.

The application provides a man-machine cooperative cognitive decision space construction and on-the-spot decision method, that is, in the action planning process, on the basis of the main line action plan designed based on the static task purpose, a person estimates possible variables in action execution in advance, refines situation cognitive characteristics of key decision points, and proposes countermeasures, the system explores diversified possible action processes, analyzes and excavates key variables which have greater influence on action results, explores the best action options under the guidance of countermeasures and trains a dynamic planning intelligent agent, finally, the cognitive characteristics and countermeasure options, the planning intelligent agent are added to the main line action plan, and a cognitive-decision space is constructed; in the action execution process, the cognitive-decision space is used to guide the real-time monitoring of the change of situation characteristics and the dynamic triggering of key decision points, the online optimization of the best countermeasure and the dynamic generation of subsequent action planning.

The invention provides a dynamic self-adaptive DNN collaborative reasoning method supporting a backspacing mechanism, relates to the technical field of image processing, and designs an elastic two-way task flow from equipment to edge to equipment, so that the elastic two-way task flow becomes an intelligent scheduling decision point. And when the edge server is overloaded, the task can be actively returned to the source mobile equipment to be executed, so that the bottleneck of queuing delay caused by edge resource competition is fundamentally avoided. A rollback decision is introduced, so that an unloading strategy is upgraded from'static 'or'semi-static' to real'dynamic self-adaption ', the change of edge resources can be directly responded, and a decision target is expanded from optimizing a single task to optimizing a global system load. Three key dimensions, namely a backspacing decision, resource allocation and a model segmentation point, are arranged in a unified framework for joint optimization. Through an integrated reinforcement learning model, the three decisions are output at the same time, so that the three decisions can cooperate with each other and have a synergistic effect.

The embodiment of the invention discloses a quality evaluation model training method, which comprises the following steps of: dividing a thinking chain into a plurality of reasoning nodes, regarding each reasoning node as a decision point, evaluating the risk of the reasoning node by simulating the future track of the reasoning node, and quantifying the inherent potential of successful guidance of the reasoning node. And constructing a fine-grained label of the whole thinking chain according to an evaluation result of the reasoning node. A quality evaluation model is trained by utilizing thinking chain sample data with a fine-grained label, so that the quality evaluation model not only can pay attention to a final result, but also can learn the ability of deeply insight into the quality, risk and potential of a thinking chain reasoning process. The quality evaluation model training device, the quality evaluation method, the reply generation method and the reply generation device in the embodiment of the specification also have the above beneficial effects.

This invention provides an industrial control method and system based on anthropomorphic thinking chain and hybrid expert model, including: Step S1: Based on the operator's thinking decision points and decision chain when controlling the equipment, construct a decision model based on anthropomorphic thinking chain and multi-layer hybrid expert model for each process segment in the complete production chain; Step S2: Train the decision model of each process segment using historical data to obtain the trained decision model; Step S3: Use the trained decision model to obtain the control setpoint based on the real-time sensing data of the corresponding process segment.

The invention discloses an intelligent generation method and device for a fine-grained data access control strategy and a medium, and belongs to the technical field of data security and artificial intelligence. S2, data processing; s3, generating strategy parameters, acquiring an initial data set required by clustering by utilizing the stored user information and the access log, and acquiring required strategy parameters by combining a DAC (Digital-to-Analog Converter) algorithm; s4, storing strategy parameters; s5, constructing a strategy mechanism; and S6, strategy use: calling the strategy through the strategy decision point, obtaining related parameters in the knowledge graph, returning an access request result to the strategy implementation point, performing access control operation by the strategy implementation point according to the result, providing data if passing, recording an alarm log while providing data if giving an alarm, and refusing access if blocking. And generating an alarm log. According to the invention, intelligent generation of the data security access control strategy is realized.

The invention discloses a network security operation behavior knowledge graph construction method and device, and belongs to the technical field of network security education. The method comprises the following steps: defining node types including operation steps, risk behaviors, safety principles, capability dimensions and decision points; defining relationship types of inclusion, time sequence, mapping, cause and examples; independently obtaining a standard operation process from the expert knowledge base, the attack and defense drill data or the user behavior log, and extracting steps, attributes and corresponding safety principles and capability dimensions of the standard operation process; mining a risk behavior pattern from the historical user behavior data; integrating the nodes and the relationships to construct a knowledge graph and storing the knowledge graph in a graph database; and establishing a mapping interface from the behavior sequence to the map for real-time behavior matching and capability diagnosis. The invention further provides a method and a device for user evaluation, group analysis and collaborative application with the event case knowledge graph (including but not limited to prior applied patents) based on the graph. According to the method, structured modeling is carried out on fragmented operation behaviors, accurate mapping of behaviors and capabilities is established, interpretable capability diagnosis and personalized teaching support are realized, and the method can be widely applied to network security awareness training and behavior analysis systems.

The present disclosure relates to a driving planning method, device and equipment of a vehicle and a storage medium. The present disclosure obtains driving decision information of the vehicle by analyzing the action trajectory of at least one obstacle according to the obtained dynamic information of the obstacle, wherein the driving decision information at least includes at least one driving decision point and a vehicle driving strategy corresponding to each driving decision point; performs tree search on the at least one driving decision point according to the driving decision information, plans the driving acceleration of the vehicle for the at least one driving decision point, and obtains the vehicle driving strategy according to the driving acceleration, so that the obtained vehicle driving speed is more accurate. Compared with the prior art, the present embodiment avoids returning to the initial position for decision planning when there is no vehicle driving strategy for the current obstacle, saves the time for planning the vehicle speed, and improves the planning efficiency.

The application discloses a multi-source data fusion and dynamic scheduling distributed intelligent deduction system and method, and relates to the technical field of deduction simulation. A deduction preprocessing module divides a military scenario into task stages and sets decision points, generates branch tasks according to tactical rules and classifies models; a deduction management module advances deduction from an initial state based on a simulation engine, generates branch tasks according to real-time states at the decision points, combines historical performance parameters and model types to distribute initial weight coefficients, realizes parallel deduction and dynamic model switching; a deduction optimization module continuously updates weight coefficients through branch performance parameters, filters optimal deduction paths and closes loop iteration state snapshots; a resource regulation module collects data in real time to support performance evaluation, dynamically optimizes resource allocation according to task load, significantly improves deduction efficiency and accuracy, and realizes intelligent resource scheduling and system adaptive optimization.

The application discloses a high-throughput large model inference method and device based on a time separation type pipeline architecture, equipment and a storage medium, relates to the technical field of large model inference, and the high-throughput large model inference method based on the time separation type pipeline architecture comprises the following steps: when the current inference stage is a pre-filling stage, pre-filling is performed according to a client request, and the key value cache capacity of each request decision point is determined; the stage switching time is determined according to the key value cache capacity of each request decision point and a preset memory capacity; the current inference stage is switched from the pre-filling stage to a decoding stage according to the stage switching time, and the client request is processed according to a preset load balancing strategy to obtain a target load balancing result; the inference of the large model is performed according to the target load balancing result and the pipeline architecture, and the output text corresponding to the client request is obtained according to the inference result. The efficiency of the high-throughput large model inference is improved.

This invention discloses a method for calculating the takeoff trajectory of a helicopter in Category A flight. The key technical points include the following calculation steps: S1: Statistically analyze the parameters of a twin-engine helicopter and the parameters of the engines it uses; S2: Based on the statistically analyzed parameters, calculate the power required for forward flight of the twin-engine helicopter and plot N. xu -V0 curve; S3: Calculate the safe takeoff speed of the twin-engine helicopter based on the power required for forward flight and the statistical power of a single helicopter engine; S4: Calculate the lift and forward thrust provided by the helicopter rotor based on the statistical parameters; S5: Calculate the critical takeoff decision point of the twin-engine helicopter and plot the critical takeoff decision point curve; S6: Based on the calculated critical takeoff decision point of the twin-engine helicopter, calculate the takeoff trajectory of the twin-engine helicopter in Category A flight according to the location of the failure point, and plot the Category A takeoff trajectory curve of the helicopter.

This invention discloses an access control method and system based on distributed decision-making. The method includes: S1: A subject initiates an access control request to an access control enforcement point to perform a specific operation on a target object; S2: The access control enforcement point forwards the access control request to an access control decision point; S3: The access control decision point queries the access control policy corresponding to the target object; S4: A decision information point returns the required information to the access control decision point; S5: The access control decision point evaluates whether the access control request is allowed; S6: The access control enforcement point initiates a specific operation or returns an error message to the subject; S7: The target object returns the access result to the access control enforcement point; S8: The access control enforcement point returns the access result to the subject based on the decision result. This invention supports multiple access control models and comprehensive decision-making, providing efficient and secure access control capabilities for complex distributed systems.

According to a first aspect of the present invention, a computer-implemented access control method is provided, being performed by an access control system. The access control system may include at least one access decision point being configured to communicate wirelessly with a plurality of low- power access enforcement points. Each low-power access enforcement point may be configured to operate an access point, in particular by unlocking and / or locking the access point. The low-power access enforcement points may have energy harvesting means. The low-power access enforcement points may not be connected to a power grid. The method may comprise instruction-polling, by the plurality of low-power access enforcement points, wherein instruction-polling includes repeatedly sending instruction requests to the at least one access decision point in defined time intervals. The method may comprise generating, by the at least one access decision point, a respective instruction dedicated to a respective low-power access enforcement point upon receiving a respective instruction request from the respective low-power access enforcement point, wherein if the at least one access decision point detected an authentication medium, preferably a mobile device, of a user and determined an intent to unlock the respective access enforcement point, the respective instruction includes an unlock-command causing the respective low-power access enforcement point to unlock, and else, the respective instruction includes a no-action-command. The method may comprise sending, by the at least one access decision point, the respective instruction to the respective low- power access enforcement point.

[Objective] To provide a control device that can improve safety. [Means of Achieving the Goal] A control device 61 is provided in a vehicle system 2, which is logically divided into several subdivisions 64. The control device 61 comprises a semantic kernel (SK) 62, which controls communication access between two subdivisions 64 among several subdivisions 64 based on a static rule set; a rule set decision point (PDP) 66, which controls communication access between the two subdivisions 64 based on a dynamic rule set; and a rule set enforcement point (PEP) 68, which controls communication access between the two subdivisions 64 based on the control result of the PDP 66. If a predetermined condition is met, the PEP 68 forces the SK 62 to use the dynamic rule set instead of a part of the static rule set.

The invention discloses a signal induction control method, which comprises the steps of predicting an optimal decision point of each phase of a current intersection through a global induction model based on the number of parked vehicles, the number of coming vehicles and the number of departed vehicles at the current intersection; adjusting the optimal decision point based on a flow direction comparison result between a current phase of the current intersection and a lap joint phase; and phase switching is executed according to the adjusted optimal decision point, so that the problem of long-time idle release of the signal lamp is solved.

This invention provides a reinforcement learning-based intelligent adversarial system for game NPCs, belonging to the field of game adversarial systems. The system includes a data acquisition module that collects all raw interaction data from the target game engine and generates standardized trajectory data packets; a feature transformation module that uses a preset computational model for feature extraction and semantic encoding, and uses an adaptive segmentation algorithm to segment tactical fragments and mark target decision points; a causal path acquisition module that constructs a temporal causal discovery dataset, executes a preset temporal causal structure learning algorithm, generates a domain knowledge-enhanced causal graph, and acquires the target causal path; and a counterfactual inference module that proposes counterfactual intervention hypotheses, performs structured counterfactual inference using a preset inference method, and generates causal comparison training samples. This invention improves the information density of learning samples and the generalization ability of strategies, enriches game content, extends the game lifecycle, and directionally improves the intelligence level of NPCs without human intervention.