110 results about "Dynamic decision-making" patented technology

An active collaboration technology in an open architectural framework that delivers information and decision support tools in a timely, contextual and role sensitive manner to present a collaborative dynamic decision making capability to a community of role players within a supply chain process. Such a comprehensive collaborative dynamic decision making capability is made possible through the integration of the business process, the organization of role players and relevant business applications.

Biopotential waveforms such as ERPs, EEGs, ECGs, or EMGs are classified accurately by dynamically fusing classification information from multiple electrodes, tests, or other data sources. These different data sources or “channels” are ranked at different time instants according to their respective univariate classification accuracies. Channel rankings are determined during training phase in which classification accuracy of each channel at each time-instant is determined. Classifiers are simple univariate classifiers which only require univariate parameter estimation. Using classification information, a rule is formulated to dynamically select different channels at different time-instants during the testing phase. Independent decisions of selected channels at different time instants are fused into a decision fusion vector. The resulting decision fusion vector is optimally classified using a discrete Bayes classifier. Finally, the dynamic decision fusion system provides high classification accuracies, is quite flexible in operation, and overcomes major limitations of classifiers applied currently in biopotential waveform studies and clinical applications.

The present invention relates to utilizing identity and context-sensitive decision-making for handling communications, including, channel selection, routing, and rescheduling operations. The systems and methods provide a service that allows users to assess preferences regarding real-time call handling and performs dynamic decision-making about the best timing and channel for interpersonal communication. This service can be based on various cost-benefit analyses (e.g., basic and extended) that consider cost of interruption and preferences of contactors and contactees to guide communications, and / or on decision-making under uncertainty. Statistical models that are learned from data are joined with user preferences to generate expected costs of interruption for office activity and over time, based on a user's activities, locations, calendar information and preference assessments. In addition, statistical forecasting provides presence and availability predictions. The foregoing can provide an enhanced interpersonal communication system that can maximize the value and minimize the cost of communication among people.

The invention relates to a majority consistent escape error processing device based on mimicry security defense zero-day attack and a method thereof. The method comprises: a heterogeneous executive in a dynamic online executive assembly independently operating an input request; performing multimode adjudication on an operation result, if an adjudication result meets a consistency requirement, outputting the adjudication result, if not, feeding back the adjudication result to a dynamic decision dispatching module; comparing new online executive operation output with online original majority consistent executive operation output, respectively feeding back results to the dynamic decision dispatching module and a responding module; the responding module processing the response according to feedback, and feeding back abnormal output executive to the dynamic decision dispatching module; and the dynamic decision dispatching module selecting new executive to be online from an executive resource pool, and cleaning and resetting offline executives. The method is used to provide means of detection and response when majority of mimicry defense online executives are attacked, and solves security threat a mimicry defense system faces, so as to enhance robustness of the mimicry system.

A dynamic diagnostic plan generator arranges diagnostic test procedures related to a vehicle symptom or operational problem in a sequence based on a probabilistic Failure Mode and Effects Analysis (FMEA). The diagnostic plan generator also tracks a vehicle state, and provides instructions for test preparation steps and instructions for performing the diagnostic test procedures. The plan generator further generates schematic illustrations of the diagnostic test procedures, and creates a diagnostic data structure containing information related to the diagnostic test procedures. In addition, the diagnostic plan generator sends and receives information regarding actual failure mode occurrences, for example, to and from a central database. Furthermore, the diagnostic plan generator facilitates the creation of failure mode tests by an expert diagnostics author.

The invention discloses a no-signal intersection vehicle intelligent cooperative passage method based on a CPS (Cyber-Physical System), aiming to overcome the shortcomings of green light zero passage and low passage efficiency caused by fixed traffic light time control, and lack of information interaction among vehicles in the intersection passage management of prior art. Based on the deep fusion of the 3C (computing, communication and control) technology in a CPS, and supported by the GPS technology, vehicle-vehicle communication technology and speed intelligent control technology, the method is provided and comprises three steps of vehicle passage data acquisition, information processing and communication, and decision control; vehicles close to an intersection continuously obtain the passage information of local vehicles, and perform communication interaction with vehicles in other directions so as to percept surrounding environments in real time, and on the basis, the method performs dynamic decision making and control, i.e., the method analyzes whether the local vehicles and other vehicles exist potential bump risks according to the passage information of surrounding vehicles, cuts the risks, considers vehicle passage priorities, controls speeds and ensures vehicle safe and efficient passage.

The invention discloses a multipath parallel transmission dynamic decision-making method based on path quality. In consideration of the influence on the whole network transmission performance by the path quality difference, the method comprises the following steps: firstly sending a detection data packet to measure four parameters for deciding the path quality in real time: delay, jittering, packet loss probability and cache occupation rate, feeding back the measured data to a sending end, and processing the measured data through a TOPSIS method in a sending end cache area, selecting out the most appropriate path combination for data transmission, and then sending the to-be-transmitted data packet, when the data packet arrives the receiving end, sending the selected path with the minimum delay to a feedback ACK to a receiving end. The design disclosed by the invention sufficiently gives full play to the advantage of the dynamic decision-making path, the network throughput out is improved, and the efficient data transmission is realized.

The invention relates to the technical field of artificial intelligence, and provides a ten-thousand-level intention classification method and device, a storage medium and electronic equipment. The ten-thousand-level intention classification method comprises the steps of obtaining a dialogue statement of at least one round of dialogue with a user; performing context analysis on the dialogue statement to complement the context information of the dialogue; performing semantic analysis on the dialogue statement to obtain a plurality of candidate intentions of the user; and based on the pluralityof candidate intentions and the complemented dialogue context information, determining a real intention of the user by utilizing an intention decision model constructed based on a reinforcement learning algorithm. The method is realized based on a brand-new three-layer man-machine conversation technology framework. According to the method, the plurality of candidate intentions are obtained throughsemantic analysis on a semantic understanding layer, complemented context information is obtained through context analysis on a logical reasoning layer, dynamic decision making is conducted on a decision judgment layer through an intention decision making model according to the candidate intentions and the complemented context information, and the accuracy of intention classification through themethod is high.

The invention discloses a security policy dynamic acquisition method of a process control system based on an attack-defense game. The method comprises an offline process and an online process; the method comprises the following steps: firstly, analyzing the process control system and establishing a Bayesian network; secondly, building a defense strategy model; thirdly, screening a potential attack strategy set and a potential defense strategy set; fourthly, quantizing an attack-defense payoff matrix; and finally, according to the attack-defense payoff matrix, establishing an equation solution and acquiring an optimal security strategy. The method of the invention comprehensively considers various consequences caused by the attack-defense strategy, and performs uniform scale quantization; an idea of an attack-defense game theory is introduced to a solving process of the optimal security strategy, so that the problems that the traditional dynamic strategy decision is excessive responsive, and the response mode of a dynamic decision response method is fixed and easily exploited by attackers are solved; and besides, the Bayesian network and the attack-defense strategy model are used for screening the potential attack-defense strategy, so that the number of alternative attack-defense strategies can be greatly reduced, thereby reducing the computing time of cost-benefit quantification of the attack-defense strategies, and improving the real-time performance of a dynamic decision.

A method of updating prices, includes automatically and continually adjusting prices of goods and services provided by a company through local outlets located across a geographic area, including activating trigger sources, the trigger sources including static and dynamic causes, inputting additional parameters, the parameters including a competitor's name, location, price of an item, a time and date, and an observed popularity of an item, storing the additional parameters in a historical database, making dynamic decisions for adjusting the prices across the local outlets based on the trigger sources and the additional parameters, the making dynamic decisions being based on the trigger sources, the additional parameters, and company selected criteria, which includes revenue targets, market conditions, market forecasts, and historical data, automatically adjusting a price of goods and services provided by the company.

The invention discloses a robot soccer dynamic decision-making device and method based on an ant colony algorithm, and belongs to the technical field of artificial intelligence. The robot soccer dynamic decision-making device comprises an information monitoring and extracting module, a situation assessment module, a motion decision-making module and an effect assessment and feedback module. The robot soccer dynamic decision-making method is based on the device and comprises the steps that the information of an opposite side, the own side and a soccer on a ball park are acquired through the information monitoring and extracting module; the situation assessment module is used for accessing the situation of the ball park; the motion decision-making module is used for selecting the next motion scheme to be executed; the effect assessment and feedback module is used for comparing an expected result with an actual execution result, and the priority of the motion scheme is updated. According to the device and method, the defect that a current robot is poor in dynamic adaptability in a soccer game is overcome, the decision-making success rate is high, the tactic strategy of the own side can be modified dynamically, and tactic effectiveness and the whole offensive and defensive ability of a team are improved.

The invention discloses a method for dynamically deciding a block generation strategy and an MEC calculation unloading strategy by utilizing a deep reinforcement learning (DRL) algorithm in a block chain technology collaborative energization Internet of Things scene based on mobile edge calculation (MEC) and a DPoS consensus mechanism so as to realize expandability optimization. The invention discloses a method for realizing distributed storage of application data in an Internet of Things scene by utilizing a block chain technology based on a DPoS consensus mechanism, so as to obtain higher data storage robustness and security. The invention discloses an edge resource collaboration mechanism for enabling Internet of Things nodes to strategically unload computing tasks to an MEC server through a base station based on an MEC technology. A deep deterministic strategy gradient (DDPG) algorithm based on distributed training enables Internet of Things nodes to adaptively and dynamically decide an optimal block generation strategy and an MEC calculation unloading strategy so as to jointly improve the expandability of the whole system.

The invention provides a power distribution network state estimation method based on a firefly algorithm. The method comprises steps as follows: Step 1, generating a power distribution network node admittance matrix; Step 2, initializing fluorescein and dynamic decision domains of fireflies; Step 3, updating the fluorescein of the fireflies; Step 4, calculating the distance between the fireflies to acquire neighborhoods; Step 5, calculating the movement probability of the fireflies; Step 6, updating positions of the fireflies; Step 7, updating the dynamic decision domains of the fireflies; Step 8, judging whether a convergence condition is satisfied or not, if the convergence condition is satisfied, ending the process, executing Step 9, and otherwise, executing Step 3; Step 9, outputting an optimal solution. According to the method, node voltage is used as a state variable, the node injection power is calculated, an objective function value of the least square method is taken as a firefly fitness function value and converted into the fluorescein of the fireflies, the state variable is updated continuously, and the firefly position with the highest fluorescein is taken as the optimal state estimation result. Experiments indicate that the method has good accuracy and adaptability.

Processing provides a high level of automated decision support using COTS computing software and hardware. By combining information gathered from multiple structured and unstructured data sources and converting to a common protocol shared with the conditional decision logic, the operator is freed from the task of continually monitoring the situation for compliance with pre-established rules. By organizing the conditional and simulation logic of the system in a hierarchical manner, rules are applied to data-based entities, their interactions, and the overall operational situation, and then to established procedures. The hierarchical organization of the conditional logic permits a high level of control over aggregated complex rule-based processing, and provides dynamic behavior, allowing modifications of the entire system processing to be based on the simplest human interaction or a single change in the state of one data item gathered by the system.

The invention relates to a method for dynamically updating a rule set during a changing process of an attribute set in a rough set. According to the method provided by the invention, a dynamic change rule of a decision rule set is discussed in the aspect of dynamic change of an approximation set, simultaneously a change rule for the decision rule set when a conditional attribute set and a decision attribute set are simultaneously changed is provided, and a method for dynamically updating increment of the decision rule set when a conditional attribution is increased or deleted is provided. The technical scheme is as follows: when the attribute set in a dynamic decision information system changes, a change trend of the dynamic rule is analyzed, a dynamic rule updating algorithm while changing the attribute set is provided, and the correctness of the dynamic rule updating algorithm is verified by virtue of examples. Subsequent main work comprises testing performance of a rule increment updating algorithm by virtue of experiment and simulation, analyzing and expanding dynamic change of the rule set while changing the attribute set in a rough set model, and updating rule increment as well as assisting in making a better decision in each application field.

A dynamic diagnostic plan generator arranges diagnostic test procedures related to a vehicle / power tool / patient symptom or operational problem in a sequence based on a probabilistic Failure Mode and Effects Analysis (FMEA). The diagnostic plan generator also tracks a vehicle / power tool / patient state, and provides instructions for test preparation steps and instructions for performing the diagnostic test procedures. The plan generator further generates schematic illustrations of the diagnostic test procedures, and creates a diagnostic data structure containing information related to the diagnostic test procedures. In addition, the diagnostic plan generator sends and receives information regarding actual failure mode occurrences, for example, to and from a central database. Furthermore, the diagnostic plan generator facilitates the creation of failure mode tests by an expert diagnostics author.

The invention provides a backward learning-based dynamic multi-attribute service selecting method. The method comprises the following steps: 1, user preferential learning based on backward learning: initializing a service set, a user set, a service evaluation level set and a user non-functional attribute evaluation link (UQEL) table; calling service several times and giving evaluation by a user, mapping the user evaluation on service to evaluation on corresponding non-function attribute, adding to the UQEL table of the user to acquire a user preferential table finally; and 2, weight-based dynamic multi-attribute service selection: generating a candidate service set according to user requirement to acquire a user preferential set, calculating the weight of each non-functional attribute to generate a dynamic decision matrix sequence, calculating weight included angle cosine of a user preferential vector and a candidate non-functional attribute vector, the weight of each observation time, and the weight cosine sum of each candidate service in all observation times, and recommending the service with the maximum weight sum to the user. The method is used for realizing adaptive service selection without more participation of users, is convenient to use, and has good service selection adaptability.

The invention relates to a method and a system for predicting a state of charge of a power battery of a pure electric vehicle. The method for predicting the state of charge comprises the following steps of S1, acquiring external characteristic parameters of the power battery; S2, performing data mining on the external characteristic parameters; and S3, establishing a multi-input parameter combination type multiple dynamic decision tree model to obtain a predicted value of the state of charge. According to the method and the system for predicting the state of charge of the battery, the external characteristic parameters are mined by adopting the multiple dynamic decision tree model to obtain effective data, and useless data is removed, so that data redundancy is avoided and the prediction time is shortened; and especially under the condition of considering energy feedback of the battery and continuously changed working condition, the value of the state of charge of the battery still can be predicted accurately in real time, so that the practicality and validity are high.

The invention provides a reinforcement learning training method and a decision-making method based on reinforcement learning, and the method comprises the following steps: obtaining a plurality of groups of historical state data; inputting each group of historical state data into a reinforcement learning model to obtain preliminary decision data; inputting each group of historical state data and the preliminary decision data into a pre-established Bayesian neural network model to obtain a state variable quantity and a reward value, the state variable quantity being a difference value between current state data and next state data; and updating model parameters of the reinforcement learning model according to each group of historical state data, the corresponding preliminary decision data,the state variation and the reward value. By implementing the method, the training sample size of the reinforcement learning model can be increased, the reinforcement learning effect is improved, andthe accuracy of a dynamic decision planning result is improved.

The invention discloses a naval vessel formation dynamic air defense threat estimation method based on intuitionistic fuzzy TOPSIS, and relates to the field of naval vessel formation air defense decision. The method comprises the following steps of firstly standardizing different types of target information, and establishing an intuitionistic fuzzy decision matrix; secondly obtaining an initial weight of an evaluation index by using an intuitionistic fuzzy entropy weight method, and fusing subjective preference information of a commander to solve an index weight optimization model, so that a weight result better meets the requirements of a battlefield; then, determining a dynamic decision matrix by adopting intuitionistic fuzzy cross entropy and relative closeness, processing the multi-moment information by adopting a normal distribution method, establishing a weighted dynamic decision matrix to present the air defense threat situation dynamically; and finally obtaining a threat degreesorting result of the incoming targets by using a TOPSIS method. The method can be applied to the dynamic air defense threat estimation of a naval vessel formation in an uncertain sea battlefield environment.

The invention discloses a layered cooperative control and dynamic decision-making method for large-scale power transmission network frame restoration. The method comprises steps as follows: step one, a power transmission network frame is divided into a main network frame layer and a regional layer which are connected through power receiving points, and the power receiving points have attributes of load and a power supply in the main network frame layer and the regional layer respectively; step two, index values of the power receiving points are determined; step three, a commitment and agreement based restoration cooperative mechanism is established, and commitment values of the power receiving points are updated according to system state change; step four, the restoration optimization of the main network frame layer and the regional layer is taken as a lower-level problem, optimization of the commitment values of the power receiving points is taken as an upper-level problem, a bi-level planning power transmission network frame restoration decision-making model is established and solved, and an integral decision-making method is obtained. The problem about coordination and cooperation of all-level and all-region scheduling in response to layered and divisional multi-process restoration is solved, independent parallel restoration of subprocesses can be realized, the operation safety is guaranteed, and the restoration efficiency is improved.

The invention provides a virtual machine migration decision method and device. The method comprises the following steps: acquiring network traffic statistics information of a physical node and network traffic occupation information of virtual machines in the physical node; judging whether the network traffic statistics information of the physical node satisfies threshold information or not, wherein the threshold information is traffic information of the physical node under normal work; if the network traffic statistics information of the physical node does not satisfy the threshold information, determining difference values between the network traffic occupation information and traffic occupation information of the virtual machines respectively according to preset traffic occupation information of the virtual machines; and migrating the virtual machines according to the difference values. Through the technical scheme, the problems that network congestion occurs and a dynamic decision cannot be made due to virtual machine migration in an existing scheme are solved. Whether the virtual machines need to be migrated or not is judged according to the network traffic statistics information of the physical node and the network traffic occupation information of the virtual machines in the physical node; migration of the virtual machines is decided dynamically; and the human participation degree of system maintenance is lowered.

Method includes executing a dynamic decision-making process that includes (a) receiving environmental data and (b) determining a fused ensemble based on the environmental data and a state parameters of a current state of a machine assembly. The fused ensemble includes communications from a system interface to the operator for the state parameters. The communications inform an operator about the state parameters and includes at least one of a visual signal, an audible signal, or a tactile signal from the system interface. The decision-making process also includes (c) communicating the fused ensemble to the operator through the system interface and (d) repeating (a)-(c) while the machine assembly is in the current state. The fused ensemble is configured to change based on changes in the environmental data.

The invention discloses a vehicle parking time calculation method based on number plate data. The signal cycle program of an intersection, the parking times of effective vehicles, the parking times of other vehicles and the average parking times of vehicles are calculated by combining urban road travel time characteristics based on the number plate data. The method provided by the invention provides a solid foundation for urban traffic control and can also provide dynamic decision-making basis for traffic participants. Meanwhile, the travel time data characteristics are fully utilized by the method, the parameter calculation does not rely on artificial selection, and the project is easily realized.

The invention discloses a dynamic decision-making method and device for ozone pollution prevention and control. According to the method and the device, an ozone pollution prevention and control dynamic decision-making technical route of monitoring and early warning, ozone source analysis, decision-making evaluation and standard reaching and performance is realized. And establishing a measure library according to the emission list, and continuously evaluating and optimizing the measure library through the effect of scene simulation. The local list and the regional list are fused to realize refined and quick source tracing of ozone and precursors thereof; multi-dimensional comprehensive source analysis of models, observations and lists is realized, and key emission areas and key pollution industries are accurately judged; and quick evaluation and dynamic optimization of ozone pollution standard reaching planning are realized. By means of three-dimensional monitoring, emission lists, numerical simulation, emergency emission reduction technologies and the like, ozone pollution sources are subjected to multi-dimensional analysis, source contributions of local areas, surrounding areas and pollution industries are quantitatively analyzed, and key causes of urban ozone pollution are recognized.

The invention discloses a decision-making method based on deep reinforcement learning. The method comprises the steps that an intelligent agent makes a decision according to environment information and selects a decided action; the intelligent agent compares the decided action with a knowledge base, and decides to execute the decided action or replace the decided action based on a preset rule setin the knowledge base; the intelligent agent executes the decided action or the replaced action in the environment, obtains rewards and new environment information from the environment, combines the old environment information, the action, the rewards and the new environment information into experience information, and stores the experience information into an experience playback pool; and a preset amount of experience information is randomly selected from the experience playback pool to update the deep reinforcement learning model so as to guide the next iteration. By utilizing the method, the training time can be shortened, disastrous decisions can be avoided, and the method can be widely applied to the field of dynamic decisions.

A system and method are disclosed for utilizing a Z slope test to select polygons that may be candidates for multiple storage methods. The method may calculate the absolute Z slope from vertex data and compare the calculated value with a specified threshold value. In some embodiments, for polygons that have an absolute Z slope less than the threshold value, parameter values may be rendered for only one sample position of multiple neighboring sample positions. The parameter values rendered for the one sample position may then be stored in multiple memory locations that correspond to the multiple neighboring sample positions. In some embodiments, storing parameter values in multiple memory locations may be achieved in a single write transaction. In some embodiments, utilization of the Z slope test method may be subject to user input and in other embodiments may be a dynamic decision controlled by the graphics system.