Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

1270 results about "Decision model" patented technology

A decision method is a formal (axiomatic) system, starting with a decision model, that contains at least one action axiom. An action is of the form "IF <this> is true, THEN do <that>". An action axiom tests a condition (antecedent) and, if the condition has been met, then (consequent) it suggests (mandates) an action: from knowledge to action. A decision model may also be a network of connected decisions, information and knowledge that represents a decision-making approach that can be used repeatedly (such as one developed using the Decision Model and Notation standard).

Representation, decision models, and user interface for encoding managing preferences, and performing automated decision making about the timing and modalities of interpersonal communications

InactiveUS7330895B1Increase and decrease likelihoodIncreasing and decreasing effectInterconnection arrangementsSpecial service for subscribersPersonalizationDiagnostic Radiology Modality
The present invention relates to a system and methodology providing a user interface that can be employed by contactors and contactees in conjunction with a communications architecture for identifying and establishing an optimal communication based on preferences, capabilities, contexts and goals of the parties to engage in the communication. The user interface can include a graphical display having a plurality of display objects and associated input fields operable by one or more parties to a communication in order to facilitate convenient access, control, personalization and communications via the communications architecture. For example, configuration capabilities are provided in the user interface to enable operational adjustments to one or more operating parameters, communications groupings, policies and/or context preferences relating to a preferred modality of communication and to potential parties of communication between the contactors and contactees. User interface controls are also provided for defining deterministic policies and for encoding preferences for cost-benefit analyses.

Method for comprehensively evaluating electric energy quality

The invention discloses a method for comprehensively evaluating the electric energy quality by applying a TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) of a grey correlation coefficient matrix, which comprises the following steps of: taking electric energy quality data at all time intervals and standard data at all grades as an original decision matrix; determining subjective weights through an improved AHP (Analytic Hierarchy Process); determining objective weights through an entropy method; establishing a least square method decision model to obtain a comprehensive weight, so that the deviation of decision results under the subjective weights and the objective weights of all indexes is the least; carrying out standardization and weighted standardization on the decision matrix and obtaining the grey correction coefficient matrix by utilizing the grey theory; taking the grey correction coefficient matrix as a decision matrix of the TOPSIS to obtain the distance between positive ideal solutions and negative ideal solutions of all schemes and the relative closeness of the positive ideal solutions and the negative ideal solutions; and comparing the electric energy quality closeness at all the time intervals with the standard closeness at all the electric energy quality grades to finally obtain the electric energy quality grades at all the time intervals. With the adoption of the method, the electric energy quality evaluation result can be objectively and reasonably obtained under the situation of poor information, so that the practicability and the feasibility are stronger.

Aggregation air conditioning load scheduling method based on temperature set value adjustment

The invention discloses an aggregation air conditioning load scheduling method based on temperature set value adjustment. The method comprises the following steps: (1) acquiring the temperature set value and outdoor temperature prediction value of each air conditioner aggregation group through a bilateral information channel; (2) adjusting and estimating the load increase/decrease scheme of each air conditioner aggregation group based on the temperature set values; (3) acquiring a load increase/decrease target issued by a superior scheduling department; (4) establishing an aggregation air conditioner scheduling decision model, and solving; (5) issuing an air conditioner control command through the bilateral information channel. By adopting the aggregation air conditioning load scheduling method, load increase/decrease service can be provided for electric power system scheduling on the premise of not influencing the user comfort by using air conditioning equipment of a user, so that the user turns from an electric energy user to a participant of an electric power system and participates in running of the electric power system; meanwhile, by using the method, technical guidance can be provided for the innovation of the scheduling mode of a power grid scheduling department.

Multi-source data fusion method in clustering wireless sensor network

The invention discloses a multi-source data fusion method in a clustering wireless sensor network, which comprises the following specific contents: a distributive data fusion structure is adopted; at all cluster-head nodes, an evidence set is preprocessed according to reliability degree of the member nodes in the cluster; based on the consistent intensity and the value of primitive supporting degree of the evidence, the evidence conflicts are distributed, the evidence combination sequence is optimized, the rules of conflicting evidence combination are established to synthesize all evidences; in connection with the evidence combination results, the value of the fine confidence interval of the primitive proposition is obtained by utilizing the uncertainty measure and the property supporting degree of the set; and then an evidence decision model is constructed based on the priority sequence of the fine confidence interval, and the final diagnosis is made. The method can improve the identifying accuracy ratio of the detected goal by the clustering wireless sensor network, and simultaneously and effectively reduce the transmitting volume of redundant data in the network and satisfy the application demands of the clustering wireless sensor network in the fields such as pipe leakage diagnosis, target tracking, environment detecting and the like.

Question-answering system combining emotion recognition and output

The invention provides a question-answering system combining emotion recognition and output. The question-answering system comprises an input module, a denoising module, an emotion analysis module, an emotion decision module and an output module. The input module is used for inputting user questioning information and user parameter information and converting the user questioning information and the user parameter information into standard text formatting information. The denoising module is used for carrying out denoising and module structuralization processing on the text formatting information. The emotion analysis module is used for building an emotion feature point model and extracting emotion feature points from the user questioning information through the emotion feature point model. The emotion decision module is used for building an emotion decision model and judging the current emotion of a user and the current circumstance where the user is located based on the emotion feature points of the user through combinatorial computing by combining the records and habits of the user. The output module is used for outputting a corresponding result according to the current emotion of the user. The emotion information of the user is combined, the user intention is speculated more accurately, intimate answers are given according to the actual situation of the user, and user experience is greatly promoted.

Automatic detection confirmations method for urban traffic incident

The invention relates to an automatic detection identification method of city traffic accidents and reaches the object that rapid disposal capacity of the city traffic accidents is improved through the comprehensive application of the traffic accident automatic detection technique and the non-automatic detection technique and the casualties and property loss caused by the city traffic accidents is reduced through the comprehensive application of traffic accident automatic detection technique and non-automatic detection technique. The concrete method is that traffic accident influent length L=(V<up-Vdown)l/n is identified through the method that data are read and is transmitted to traffic comprehensive information platform; accident site image information collected by city traffic monitoring system is read; whether the traffic accident happens or not is judged by the video mode recognition technique; traffic accident special database transmits the index information and accident detection signals such as rank valuation, accident hazard degree, traffic disposal demand and accident rescue demand to traffic comprehensive information platform to be processed according to the relational traffic accident data and the indexes such as phrase vague decision model, generation traffic accident class, accident hazard degree, traffic disposal demand and accident rescue demand.

Method for constructing three-dimensional map by mobile robot in unknown environment

The invention discloses a method for constructing a three-dimensional (3D) map by a mobile robot in an unknown environment, and proposes a multi-exploration strategy method combining information gainguided local exploration strategy and global boundary exploration strategy for a problem of constructing a map of an indoor unknown 3D environment. The method comprises the following steps: firstly, constructing an autonomous exploration and 3D map construction system framework of the mobile robot, which comprises a map construction module and an exploration decision planning control module; secondly, establishing an information gain guided decision model based on a Shannon information theory and designing an information gain objective function calculation applied to multi-step exploration action evaluation; and finally, constructing a local exploration strategy by using an offline local motion trajectory, realizing a multi-strategy exploration method by combining with the information gainguided global boundary exploration strategy, and dynamically switching the two strategies during exploration according to real-time construction situations of the 3D map. Experimental results show that the method provided by the invention ensures integrity of map construction while rapidly constructing the 3D map.

Method for planning paths of unmanned aerial vehicles on basis of Q(lambda) algorithms

ActiveCN109655066AGive full play to the flying abilitySolve the shortcomings of the lack of basis in the discretization processNavigational calculation instrumentsPosition/course control in three dimensionsDecision modelEnvironmental modelling
The invention provides a method for planning tasks of unmanned aerial vehicles on the basis of Q(lambda) algorithms. The method includes a step of carrying out environment modeling, a step of initializing Markov decision process models, a step of carrying out Q(lambda) algorithm iterative computation and a step of computing the optimal paths according to state value functions. The method particularly includes initializing grid spaces according to the minimum flight path section lengths of the unmanned aerial vehicles, mapping coordinates of the grid spaces to obtain airway points and representing circular and polygonal threat regions; building Markov decision models, to be more specific, representing flight action spaces of the unmanned aerial vehicles, designing state transition probability and constructing reward functions; carrying out iterative computation on the basis of constructed models by the aid of the Q(lambda) algorithms; computing each optimal path of the corresponding unmanned aerial vehicle according to the ultimate convergent state value functions. The unmanned aerial vehicles can safely avoid the threat regions via the optimal paths computed according to the ultimate convergent state value functions. The method has the advantages that the traditional Q learning algorithms and effectiveness tracking are combined with one another, accordingly, the value functionconvergence speeds can be increased, the value function convergence precision can be enhanced, and the unmanned aerial vehicles can be guided to avoid the threat regions and autonomously plan paths.

Automatic driving overtaking decision-making method based on reinforcement learning under opposite double lanes

The invention discloses an automatic driving overtaking decision-making method based on reinforcement learning under opposite double lanes. The method comprises the following steps of collecting the traffic state of an automatic driving vehicle through a sensor; inputting the collected traffic state into a trained decision model; enabling the decision model to select a corresponding driving actioninstruction from the action space according to the input information and output the driving action instruction, and driving the vehicle automatically to form a new traffic state after the driving action; calculating a reward value of the driving action through a reward function, and storing the original traffic state, the driving action, the reward value and the new traffic state into an experience playback pool as transfer samples; calculating a loss function value of the decision model, and optimizing parameters of the decision model according to the transfer sample and the loss function value; and repeating the steps until the automatic driving is finished. The safety and comfort of the overtaking decision-making process of the automatic driving vehicle are ensured, and the humanization and robustness of decision-making are improved through a reinforcement learning decision-making method.

Multi-time scale coordinated control method for independent microgrid with hybrid energy storage

The invention discloses an improved multi-time scale coordinated control method for independent microgrid containing hybrid energy storage, this method is based on the day-ahead planning decision model, The intra-day rolling optimization model based on model predictive control, the quasi-real-time coordinated control model based on comprehensive criteria and the real-time coordinated control modelare constructed. Firstly, the day-ahead planning decision-making model takes the operation economy as the optimization objective, the operation restriction of distributed generation and the safety and stability of the system as the constraint conditions. Then the controllable unit start-stop plan deviation and load switching plan deviation are introduced into the rolling optimization model as soft constraints, which allow to revise the unit start-stop plan and load switching plan before the day. Secondly, a comprehensive criterion is introduced into the quasi-real-time coordinated control todecide the priority of distributed generation. Finally, in the real-time coordinated control, the hybrid energy storage system adopts the improved first-order low-pass filter algorithm to compensate the second-order unbalanced power adaptively.

Unmanned logistics vehicle based on depth learning

The invention relates to an unmanned logistics vehicle based on depth learning. The unmanned logistics vehicle comprises a logistics vehicle body, an ultrasonic obstacle avoidance module, a binocular stereo vision obstacle avoidance module, a motor driving module, an embedded system, a power supply module, and a visual navigation processing system. The binocular stereo vision obstacle avoidance module is used for detecting a distant obstacle in a road scene. The ultrasonic obstacle avoidance module is used for detecting a near distance obstacle, and distance information of the obstacles obtained by the two modules are called obstacle avoidance information. According to the visual navigation processing system, a depth learning model trained by the sample set is used to process collected road image data, and control command information is outputted. Finally, a decision model integrates control instruction information and the obstacle avoidance information to control the motor driving module so as to realize the unmanned driving function of a logistics vehicle. According to the unmanned logistics vehicle, the installation of auxiliary equipment is not needed, the depth learning model can sense and understand a road surrounding environment through a learning sample set, and the unmanned driving function of the logistics vehicle is realized.
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products