Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

30results about How to "Improve decision speed" patented technology

Platform for management of Internet based public communications and public comment

An Internet-based integrated technology platform that simultaneously supports the management of Public Information Sites—Web sites used to both (1) inform the public; and (2) capture and manage public comment (including submission of images)—while at the same time providing support for electronic communication for project teams that manage public involvement projects. The support includes sharing of graphic, text and collaborative tasks. The system and method allow revisions to comments and dynamic feedback in agency decision making based on comments with greater responsiveness. The system is also suited for implementing charettes with a large number of participants.
Owner:INGAGE NETWORKS

Dynamic behavior decision-making method for autonomous vehicle in networked environment

The invention discloses a dynamic behavior decision-making method for an autonomous vehicle in a networked environment. The method includes: step one, acquiring ambient environment information by a surrounding road user in a V2X network connection environment of an own vehicle; with the center of mass of the own vehicle as the center, carrying out regional division at different radiuses and predicting a risk area; step two, carrying out first-stage behavior decision making based on the ambient environment information of the surrounding road user and the predicted risk area, and determining anavailable feasible action set for ensuring the own vehicle driving safety; and S3, carrying out second-stage behavior decision making; to be specific, selecting a finally performed action preferably from the available feasible action set with consideration of the non-safety constraint conditions, and carrying out driving behavior decision making.
Owner:TSINGHUA UNIV

Evidence-based medical data base establishment method and related evidence-based medical disease diagnostic method

The invention relates to an evidence-based medicine database establishment method and an evidence-based medicine disease diagnosing method to solve the problem that the traditional medicine database cannot be applied to evidence-based medicine decision making. For the invention, diagnostic elements of each disease are grouped and the elements provided with the identical internal-weight value and parallel value are grouped into the same group to form a diagnostic element group and then the diagnostic element groups are adopted to form the corresponding diagnostic template which is adopted to establish the database used for evidence-based medicine disease diagnosis. Based on the database, the evidence-based medicine disease diagnosing method can be established; wherein, the corresponding diagnostic element group can be searched out according to the diagnostic elements inputted by users and then the decision probability to the relevant one or a plurality of diseases against the received diagnostic elements is figured out according to the corresponding parallel value S, internal-weight value P and external-weight value R in the diagnostic element group and the number of the diagnostic elements actually meeting the diagnostic element group and is also sorted and displayed to the user so as to realize the purpose of intelligent diagnosis under the evidence-based medicine theory.
Owner:CLINIXOFT MEDICINAL SOFTWARE SHENZHEN

Task unloading intelligent decision-making method based on unmanned aerial vehicle group in edge computing environment

The invention discloses a task unloading intelligent decision-making method based on an unmanned aerial vehicle group in an edge computing environment. The method comprises the following steps that (1) environment information is acquired; (2) meta-learning is carried out, and if it is found that the environment of an edge server or a cloud center changes, initial parameters of the model are modified; (3) a retrieval mechanism and reinforcement learning are carried out, the retrieval mechanism is responsible for retrieving whether similar tasks exist before or not, and if yes, a decision resultis directly output; and if not, reinforcement learning is carried out, the reinforcement learning is responsible for training and judging the whole reinforcement learning system, two used modules arenetwork freezing and experience playback, and the action with the maximum value function after judgment is taken as a decision result to be output. According to the scheme, the meta-learning model isadopted to quickly adapt to the environment, and when the environment of the decision-making system is changed, the scheme can be quickly adjusted and a reasonable result can be quickly given. For the similar tasks of the unmanned aerial vehicle group, a memory function is introduced in the scheme, and rapid decisions can be made for the similar tasks.
Owner:TIANJIN UNIV

Platform for management of internet based public communications and public comment

An Internet-based integrated technology platform that simultaneously supports the management of Public Information Sites—Web sites used to both (1) inform the public; and (2) capture and manage public comment (including submission of images—while at the same time providing support for electronic communication for project teams that manage public involvement projects. The support includes sharing of graphic, text and collaborative tasks. The system and method allow revisions to comments and dynamic feedback in agency decision making based on comments with greater responsiveness. The system is also suited for implementing charettes with a large number of participants.
Owner:NEIGHBORHOOD AMERICA

Decision assisting method, device and equipment, storage medium and system

The invention discloses a decision assisting method, device and equipment, a storage medium and a system. The method comprises the following steps: state information of aircrafts is obtained, whereinthe state information comprises environment information, pose information and system information; the state information is input into decision assisting models stored in onboard terminal equipment toobtain target operations needing to be implemented by pilots of the aircrafts in present flight phases, wherein the decision assisting models are obtained by training through ground terminal equipmentand uploaded to the onboard terminal equipment; and the pilots are guided to implement the target operations. Through the technical scheme, the method can assist the pilots to make decisions to reduce the accident rate of the aircrafts.
Owner:BEIJING AERONAUTIC SCI & TECH RES INST OF COMAC +1

Service flow analysis method based on fuzzy logic Petri network

The invention discloses a service flow analysis method based on a fuzzy logic Petri network, which belongs to the field of service flow analysis of the fuzzy logic Petri network and comprises the following steps of firstly proposing a fuzzy logic Petri network theory; secondly, modeling the order processing problem of the merchant; according to the reachable graph generation algorithm, making a reachable identification graph of the order processing model based on the fuzzy logic Petri network; and finally, through a forward reasoning algorithm, reasoning to obtain the credibility of each decision of the order processing model based on the fuzzy logic Petri network, obtaining the possibility that the merchant delivers the order, further obtaining the optimal decision of the merchant for processing the order, and achieving the goal of process optimization. The fuzzy logic Petri network not only can perform fuzzy reasoning, but also has the characteristics of batch processing and value transmission uncertainty, and Tokine is used for corresponding to propositions in the modeling process, so that the Petri network has the stronger expressive force, and the complexity of the model is simplified.
Owner:SHANDONG UNIV OF SCI & TECH

Parameter adjusting method and device and storage medium

The invention discloses a parameter adjusting method and device and a storage medium. The method comprises the following steps of: carrying out convolutional neural network model-based iterative training on a value of a hyper parameter; determining a hyper parameter value of the value of the hyper parameter during the iterative training at each time; and taking the value corresponding to the maximum hyper parameter value in the hyper parameter values obtained via n iterative trainings as an optimum value of the hyper parameter. According to the method, the speed of deciding the optimum hyper parameter in the convolutional neural network model is effectively improved.
Owner:ZTE CORP

Method, system and device for constructing few-sample industrial image defect detection model

PendingCN114782391AImprove detection accuracy and speedCategory performance is goodImage enhancementImage analysisImage contrastClassification result
The invention discloses a few-sample industrial image defect detection model construction method, system and device. The method comprises the following steps: dividing an industrial image data set into a training set and a test set; preprocessing the training set and the test set to enhance the image contrast; performing random vertical overturning and horizontal overturning on the preprocessed training set to obtain training sample data; inputting training sample data into the segmentation network for training, and completing first-step construction of a detection model; correcting the mask image to obtain an industrial image defect area, and completing second-step construction of the detection model; splicing the mask pattern and the industrial image defect area to obtain a dual-channel feature pattern, and inputting the dual-channel feature pattern into a decision network for training to complete third-step construction of a detection model; and evaluating the detection model according to the defect classification result of the industrial images of different defect types in the test set. According to the invention, the detection precision and speed of the defect image can be improved, and the constructed model is evaluated.
Owner:GUANGZHOU UNIVERSITY

Autonomous lane changing method and system fused with deep reinforcement learning

The invention discloses an autonomous lane changing method and system fused with deep reinforcement learning. The method comprises the steps: training a deep reinforcement learning model in a training environment, and obtaining and storing training parameters; in the training environment, information of a target vehicle driving according to a rule-based automatic driving strategy is added; formulating an evaluation function according to the training environment and the rule-based automatic driving strategy; judging whether the information of the target vehicle meets an arbitration condition or not according to the evaluation function; if yes, the training parameters are fused into information of the target vehicle, and the target vehicle is controlled to run; and if not, the target vehicle is still controlled to run according to the rule-based automatic driving strategy. According to the method, deep reinforcement learning and a rule-based automatic driving strategy are fused, a large amount of work of traversing a lane changing scene for modeling is omitted in an unmodeled environment, and applicability, decision accuracy, decision efficiency and driving safety are improved.
Owner:中汽创智科技有限公司

Decision modeling and cooperative control method and system for multi-robot system based on human-in-the-loop

The invention relates to a decision modeling and cooperative control method and system for a multi-robot system based on a human-in-loop, and the method comprises the steps: obtaining an output information value after a robot carries out a task, and selecting robot position deviation information as the decision information of a person; using the drift diffusion model of the person as a modeling method, and modeling the decision behavior of the person according to the decision information of the person; and designing a man-made decision task, and when the robot cannot depend on an autonomous control system to complete the task, executing the man-made decision task to help the robot smoothly complete the task. The drifting diffusion model is combined with the behavior control method based onthe null space, the drifting diffusion model of the person is provided, the corresponding decision threshold formula is obtained through the speed-accuracy criterion, and the decision accuracy of theperson can be improved through adoption of the method.
Owner:FUZHOU UNIV

Robot system-oriented human-in-loop decision modeling and control method

The invention provides a robot system-oriented human-in-the-loop decision modeling and control method. The method comprises the steps of robot task design, human decision information selection, human decision behavior modeling, human decision task design and fixed time sliding mode adaptive behavior controller design. The method comprises the steps: firstly acquiring an output information value after a robot executes a task, then selecting robot position deviation information and speed deviation information as decision information of a person, using a human decision drift diffusion model as a modeling method, modeling decision behaviors of the person according to the decision information of the person, after a decision threshold value is reached, selecting to execute a human intervention behavior, designing a human decision task, finally designing an adaptive behavior controller based on a fixed time sliding mode control method, and when the robot cannot autonomously control to complete the task, executing the human decision task to complete the work task in finite time, According to the method, the man-machine composite task can be completed within limited time, and man-machine task co-fusion is realized.
Owner:FUZHOU UNIV

Intelligent shop order routing decision platform based on LBS height configuration

The invention relates to an intelligent shop order routing decision platform based on LBS height configuration. The decision platform is provided with an online shop module, a decision module and an offline shop module, wherein the decision module is provided with a first storage module and a second storage module, the first storage module is used for storing offline shop data, and the second storage module is used for storing decision condition combinations. The decision platform is advantaged in that the decision platform is suitable for various types of shop platforms, and seamless butt joint is realized; all the decision condition combinations can be acquired through utilizing an enumeration method and are stored, platform computational complexity is reduced, and a decision speed is improved; different decision condition combinations can be configured according to different users, when the combinations are changed, adding and deleting operation can be carried out according to demands, operation is simple and convenient, user operation maintenance cost is low, and user experience is good.
Owner:上海宝尊电子商务有限公司

Diagnostic device and method for ascertaining an effect of an additive addition on a drive train of a motor vehicle

A diagnostic device for ascertaining an effect of an additive addition on a motor vehicle drive train, having a control device to control an internal combustion engine thereof during the additive addition, based on a control unit parameter(s); a detection device to detect at least one process parameter of the additive addition and at least one operating parameter of the drive train during the additive addition; a comparison device coupled to the detection device to compare the at least one detected process parameter and the at least one detected operating parameter to parameter values stored in a memory device and based thereon to ascertain at least one comparison result; and an evaluation device, coupled to the comparison and control devices, to ascertain the effect of the additive addition on the drive train based on the at least one ascertained comparison result and the at least one control unit parameter.
Owner:ROBERT BOSCH GMBH

Prediction mode selection method and device, video coding equipment and storage medium

The invention discloses a prediction mode selection method and device, video coding equipment and a storage medium, and belongs to the technical field of video coding. The method comprises the following steps: obtaining a pre-analysis motion vector of a down-sampling unit corresponding to a to-be-coded unit, wherein the down-sampling unit is obtained by performing down-sampling and division on a current coding frame where the to-be-coded unit is located; determining M candidate motion vectors according to motion vectors respectively corresponding to at least two coded units adjacent to the to-be-coded unit in the current coding frame; determining a target motion vector from the M candidate motion vectors according to a current to-be-selected target prediction mode; and when the pre-analysis motion vector and the target motion vector meet a preset condition, determining the target prediction mode as a prediction mode for coding the to-be-coded unit. In combination with the motion information of the pre-analysis stage and the motion features inherited from the adjacent coded units, the prediction mode can be quickly judged, the decision time of the prediction mode is shortened, and the decision efficiency of the prediction mode is improved.
Owner:TENCENT TECH (SHENZHEN) CO LTD

Comment information display method and device, comment information generation method and device and electronic equipment

The invention relates to a comment information display method and device, a comment information generation method and device and electronic equipment, and the comment information display method comprises the steps: responding to a live broadcast page display request of a target live broadcast room, and obtaining historical business comment information of a target user account corresponding to the target live broadcast room; the target user account has a service interaction relationship with a historical recommendation object of a target anchor corresponding to the target live broadcast room; the historical business comment information is business comment information of the target user account on the target anchor; and displaying a live broadcast page of the target live broadcast room, and displaying the historical business comment information in a first area of the live broadcast page. According to the embodiment of the invention, other users can be helped to better understand the execution condition of the target anchor service, the service decision-making speed of the users is improved, the object recommendation effect and the processing efficiency of the object recommendation service in the live broadcast process can be improved, and the resource waste of a live broadcast platform system is effectively reduced.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

Business service request processing method and device

The invention discloses a business service request processing method and device. The business service request processing method includes: receiving a business service request, wherein the business service request comprises a plurality of business characteristic items; if the business characteristic item which is matched with a characteristic index in a service decision set is existed in the business characteristic items, calling a sub-service decision set corresponding to the characteristic index in the service decision set or a service plug-in to process the business service request. Through carrying out hierarchical classification on the business characteristic items and leading in the characteristic items in the service decision process to serve as the decision index, the original total characteristic matching is changed into characteristic matching in hierarchical range, and accordingly the decision speed is improved, and the system efficiency is improved; the decision result precision is reinforced, and the business requirement satisfaction degree of the system is improved; through distributing index rules to the referenced sub-sets when constructing the service decision, the service plug-in can be used repeatedly in different scenarios, and accordingly the reuse rate of the system components is improved.
Owner:HUAWEI SOFTWARE TECH

Electric power system source-load look-ahead scheduling method and device based on deep reinforcement learning

The invention provides an electric power system source-load look-ahead scheduling method and device based on deep reinforcement learning. The method comprises the following steps: obtaining the economic operation basic data of an electric power system, constructing an electric power system source-load look-ahead scheduling model according to the economic operation basic data of the electric power system, and constructing an electric power system look-ahead scheduling model containing demand side response; designing a state space, an action space and a reward function based on the prospective scheduling model of the power system so as to design a time sequence decision-making mechanism of the economic scheduling problem of the power system; and according to the time sequence decision mechanism, applying a deep reinforcement learning algorithm to the electric power system look-ahead scheduling model, and improving and applying the deep reinforcement learning algorithm to obtain a look-ahead scheduling strategy based on deep reinforcement learning. A solution is provided for intelligent power grid economic optimization dispatching with sufficient supply and demand interaction, participation of a large number of subjects and uncertainty improvement, and the decision-making speed, the reliability and the automation and intelligence level of power system dispatching are improved.
Owner:TSINGHUA UNIV +3

Emergency capacity allocation plan deduction method and system

The invention relates to an emergency capacity allocation plan deduction method and system. The method comprises the following steps: constructing corresponding emergency production event meta-models for different types of events in an emergency state; matching the capacity allocation demand with the emergency production event meta-model to obtain the information description of the actual capacity allocation demand and the information description of the plan optimization constraint condition; constructing a productivity allocation plan library; calculating the global similarity between the capacity allocation demand and the existing cases in the capacity allocation plan library, and outputting an optimal matching plan according to the similarity; and accessing the knowledge base to call stored expert knowledge and rules according to actual requirements of capacity allocation, correcting the capacity allocation plan in the optimal matching plan, and outputting the corrected capacity allocation plan to decision makers. According to the method, the capacity allocation auxiliary decision-making plan in the emergency state can be generated, multi-element global similarity analysis of capacity allocation in the emergency state is achieved, and capacity demand description and intelligent allocation of manufacturing resources are achieved.
Owner:北京航天智造科技发展有限公司

Projection and support vector machine-based multiclass classification method

The invention discloses a projection and support vector machine-based multiclass classification method. The method comprises the following steps of: voting to-be-classified samples on the basis of one-to-one support vector machine classifiers, and determining the type of the to-be-classified sample when the highest vote number type is unique; when and only when the highest vote type number is equal to a vote participation type number, calculating projections from vectors between the to-be-classified sample and the center of a support vector machine to vectors between the to-be-classified sample and the center of the type, eliminating a highest vote number type, the projection of which is maximum, and reducing a data recognition area; tracing among the residual highest vote number types by adoption of a one-to-one classifier voting and discriminating mechanism, and recognizing the type of the to-be-classified sample until a decision blind area disappears; and when the highest vote type number is smaller than the vote participation type number, continuing to trace among the residual highest vote number types by adoption of the one-to-one classifier voting and discriminating mechanism. According to the method disclosed by the invention, the sample classification correctness is improved, the decision time of the classifiers is shortened and the decision blind area can be completely eliminated.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Bridge mechanics real-time analysis method based on finite variables

The invention discloses a bridge mechanics real-time analysis method based on finite variables. The method is based on the design of a bridge. Variable parameters influencing the stress of the bridgeare variables such as an invariable load, an automobile load, forced displacement, a temperature gradient and the like; characteristics of various variables are studied; data tables are designed for different variables respectively to form a database; under vehicle load variables, an influence surface of a bridge is established, a numerical value of the influence surface is stored in a table, whena vehicle load changes, a bridge effect under the action of a load is analyzed through the influence surface under the action of a unit load, effect values are analyzed under different current loadsone by one, and finally calculating is carried out to obtain a mechanical effect of the bridge through an effect superposition principle. The mechanical effect of the bridge can be analyzed in real time, and the situation that the real-time effect of the bridge cannot be obtained in time in the construction and maintenance stages and the safety of the bridge structure cannot be evaluated is avoided.
Owner:JIANGSU PROVINCIAL COMM PLANNING & DESIGN INST +1

Commitment process to generate jointly supported decisions

ActiveUS20190205836A1Easy to identifyReduce controlOffice automationDecision-making softwareDecision taking
The invention relates to a commitment process for efficiently generating a jointly supported decision. The commitment process comprises the following steps: Generating requirements for the commitment process, at least including a decision whether a quality of a call of decision is sufficient; when the call of decision quality criteria is met, deciding about a comprehension in the commitment process; when a common comprehension on the commitment is agreed, deciding about a first commitment; when no commitment is achieved: discovering objections concerning the first commitment; transforming the discovered objections into measures; deciding about the first commitment including the transformed measures; if no commitment is achieved, decide whether a commitment can be achieved at all and, if the commitment cannot be achieved, abort the commitment processed; or in all other cases repeat the steps of discovering, transforming and deciding about the commitment including the transformed measures; if a commitment is achieved, generate the jointly supported decision. A decision making software application for leading the Commitment-Process, designing and generating questions, collecting and protocolling each answer from each participant as a cloud based service is also provided herewith.
Owner:GRAF RICHARD

Robot motion decision-making method, system, and device introducing emotion regulation mechanism

The invention belongs to the field of intelligent robots, and specifically relates to a robot motion decision-making method, system, and device introducing an emotion regulation mechanism, aiming at solving the problems of robot decision-making speed and learning efficiency. The system method includes using the environmental perception model to generate the predicted state value at the next moment according to the current action variable and state value; based on the action variable, state value, and immediate reward, update the state-action value function network; obtain the predicted trajectory based on the environmental perception model , calculate the local optimal solution of the predicted trajectory, and perform differential dynamic programming to obtain the optimal decision based on the model; according to the current state and strategy, minimize the state-action value function to obtain a model-free decision; based on the state prediction error and reward prediction error And the average reward value, the emotional response signal is generated through the computational model of emotional processing, and the path decision is selected according to the threshold of the signal. The present invention gradually improves the decision-making speed while ensuring the learning efficiency.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products