40 results about "Human decision" patented technology

The embodiment of the invention discloses a human and AI collaborative large-scale group decision-making method and equipment based on a trusted network. The method comprises the following steps: constructing a decision-making problem; performing initial evaluation on the alternative scheme through a human decision maker set and an AI decision maker set to obtain initial evaluation information; constructing a human and AI trusted network; establishing a continuously learned human and AI consensus reaching algorithm, and dynamically updating the human and AI trust network and the initial evaluation information through the human and AI consensus reaching algorithm to obtain final evaluation information; calculating the weight of each attribute in the alternative scheme and the weight of each decision maker according to the final evaluation information; the final score of each alternative scheme is calculated, and a final decision is generated; the decision-making response speed, precision and decision-making consistency can be effectively improved, and the method is suitable for the complex decision-making field.

The invention discloses a DQN-based icing disposal decision optimization method and system, and the method comprises the steps: selecting a first task mode for a first object, and carrying out the modeling of a first task problem; and establishing a first comprehensive mathematical model and a first comprehensive function to obtain an environment suitable for the first task. And calculating and learning an optimal decision by using a first algorithm. According to the invention, systematization and intellectualization of icing decision making are realized, interference of human factors on decision making is reduced, and accuracy and real-time performance of decision making are improved. And the damage risk of extreme weather to the power transmission line is effectively reduced. A deicing decision is automatically optimized, so that risks and resource waste caused by excessive deicing or delayed deicing are reduced. Through the DQN algorithm, the decision strategy can be automatically adjusted, and the decision effect is gradually improved, so that the system can still maintain high decision accuracy when facing changeable weather and resource restrictions, errors and limitations of human decision are avoided, and the adaptive ability and generalization ability of the system are greatly improved.

Systems, methods, and other embodiments described herein relate to integrating human decision-making into a model-based system. In one embodiment, a method includes acquiring sensor data, including driver data about a driver of a vehicle and driving data about the vehicle and a surrounding environment of the vehicle. The method includes encoding, using a world encoder, the sensor data into a latent representation. The method includes determining human decision- making characteristics according to the latent representation. The method includes generating a control signal for providing shared control of the vehicle according to the human decision-making characteristics and the latent representation.

The invention discloses an environmental chemistry research automation system and method based on a large language model, and relates to the technical field of environmental chemistry automatic research. The environmental chemistry research automation system based on the large language model comprises a key information extraction module, a structure generation and optimization module, an experiment scheme generation module, an experiment management module and a visual editing module. According to the method, full-automatic workflow from experimental design to data analysis is achieved, the research efficiency and accuracy are remarkably improved, through the method, complex scientific problems can be converted into understandable input of a language model, complex analysis and reasoning processes are completed through the model, and a physical and chemical calculation tool is combined, so that the research efficiency is improved. According to the method and the system, comprehensive simulation and calculation of a research object are realized, the degree of human participation is effectively reduced, subjective deviation caused by human decision is reduced, and scientific research becomes more systematized and accurate.

This invention discloses a method, system, device, and medium for predicting human trust behavior towards artificial intelligence (AI), relating to the field of AI technology. The method includes: determining a participant's decision-making confidence based on a human decision-making confidence model; determining the participant's confidence in AI decisions based on a human confidence model for AI decisions; determining the expected utility of the participant trusting AI and the expected utility of the participant not trusting AI based on the participant's decision-making confidence and the participant's confidence in AI decisions; inputting the expected utility of the participant trusting AI and the expected utility of the participant not trusting AI into a human trust behavior prediction model for AI, and outputting a trust result; the human trust behavior prediction model for AI is trained using machine learning methods on a training set. This invention enables the prediction of human trust behavior towards AI.

The invention relates to the technical field of coal mining, in particular to an ultra-thick coal seam fully mechanized caving face mine pressure regulation and control optimization method. The method is used for solving the problems that in the mine pressure detection process, response to mine pressure fluctuation emergencies is slow, multi-dimensional data cannot be effectively combined for comprehensive analysis, and manual judgment errors are caused by excessive manual intervention. By monitoring the mine pressure of the fully mechanized caving face of the coal seam, displacement of a supporting structure and soil settlement data in real time and combining a Kalman filter and a neural network deep learning algorithm, the stability of a mine pressure system is accurately analyzed, the change trend of the mine pressure is predicted, early warning is conducted in advance, mine pressure regulation measures are optimized, and coal mine operation safety is ensured; a convolutional neural network and a recurrent neural network are adopted to process time domain and frequency domain feature data, automatic signal matching and control decision are achieved, the operation modes of a supporting structure and mechanical equipment are dynamically adjusted, the human decision complexity is reduced, and mine safety is ensured.

The invention relates to the technical field of robot intelligent control, and discloses a table tennis playing robot preset performance control method based on an optimal human decision, which comprises the following steps: reconstructing a kinetic model of a table tennis playing robot system, and obtaining servo constraints after state transformation; constructing a hierarchical hybrid controller of a robot preemption algorithm and a human decision control algorithm, integrating a human fuzzy intention with mechanical control to optimize a ball hitting strategy, and converting a decision problem into a functional optimization problem; and obtaining an analytical expression of the optimal membership function to obtain weights or priorities of human decisions in different states. According to the method, machine motion guided by a clear physical law is combined with fuzzy representation of human behaviors and intentions to form a coherent framework, optimization of system performance is achieved by integrating a preemption algorithm and a human decision algorithm, and meanwhile safety and robustness are ensured.

The invention relates to a knowledge data hybrid-driven man-machine interaction aid decision making system and method. The system comprises a man-machine interaction module, an intelligent decision algorithm training module, a virtual action support environment module, a knowledge module and an external data interface design. In the system, a human decision maker and an intelligent algorithm can work cooperatively and complement each other. A human decision maker uses own experience and intuition to guide and adjust learning of an intelligent algorithm, and the intelligent algorithm assists human in making a more accurate and scientific decision by processing and analyzing a large amount of data. Through the mode, the knowledge data hybrid-driven man-machine interaction auxiliary decision making system can effectively cope with a complex and changeable decision making environment, the decision making quality and efficiency are improved, and especially in the field of high-risk and high-uncertainty action decision making.

According to the value belief simulation agent decision-making method and system, through a big data search engine tool, various human decision-making data are collected, invalid decisions and small correlation decisions are screened and removed, and various types of values in cognition during human decision-making are automatically learned from the various human decision-making data; based on the current belief and the multi-type value, multi-type value weights during social interaction are autonomously learned, a long-term intention and a short-term intention are generated, value weight state selection is carried out, and a corresponding value item intention is obtained; performing long-term intention series actions and short-term intention series actions on the long-term intention and the short-term intention respectively to form action sets; according to social interaction process data and corresponding value item intentions, multi-type value decision guidance corresponding to diversified human personalities is counted, intelligent action decisions corresponding to the human personalities are selected from a series of action sets to be selected, and a simulation agent action decision system is constructed to simulate a human decision process and continuously learn progressive optimization.

To provide a mechanism for supporting human decision-making at a work site.SOLUTION: An information processing device includes: an acquisition unit that repeatedly acquires situation data indicating a situation at a work site in which a user participates; a storage unit that stores, for a plurality of events that can occur at the work site, an action plan selection table that defines one or more action plans that can be executed when each event occurs at the work site and one or more pieces of the situation data that are conditions for selecting the action plans so as to associate them with each other; and a control unit that controls processing for recommending the one or more action plans to be selected by the user on the basis of the situation data acquired by the acquisition unit and the table related to the event that occurs at the work site.SELECTED DRAWING: Figure 1

A method and system for analyzing and predicting human decision-making patterns is disclosed. A processor receives facial expressions of a subject while the subject interacts with displayed content. The displayed content is displayed on an interactive user interface. The captured facial expressions are processed using a computer vision algorithm to identify emotional states of the subject. Contextual data from the displayed content is extracted using a text categorization module to determine topics associated with the emotional states of the subject. The identified emotional states are correlated with the determined topics to generate an emotional response profile. The emotional response profile is analyzed using a machine learning model to identify patterns in decision-making behaviour of the subject. predictive insights regarding decision-making tendencies of the subject is generated based on the identified patterns. Further, the predictive insights are presented through the interactive user interface.

The invention discloses an intelligent enterprise energy optimization method and system based on Internet and big data analysis, relates to the technical field of intelligent energy optimization, and aims to make energy management more accurate and efficient, reduce the risk of human decision and improve the flexibility and sustainability of energy use due to the intelligentization and automation of the system. Through accurate prediction and dynamic adjustment, the enterprise can reduce the energy cost and improve the equipment reliability, and finally the improvement of the overall operation benefit is promoted. The system provides a scientific decision basis for enterprises, so that energy management is more transparent and efficient, and the enterprises are promoted to realize higher-level sustainable development. Through early warning of energy waste and dynamic optimization of an energy scheduling strategy, an enterprise can reduce environmental influence while reducing cost, and through dynamic analysis of an energy demand and an energy efficiency level, the system can reduce energy waste, optimize energy supply and consumption and reduce energy cost of the enterprise to the greatest extent.

This patent proposes a visual virtual component intelligent upgrade method based on upgrade demand priority. Its innovation points include using mesh topology to visually display the dependency relationship between virtual components, each node contains detailed component information, and the consumption of virtual components is visually displayed through a heat map. It supports time dimension data analysis and provides two upgrade modes: full automatic and manual. The full automatic mode calculates the upgrade order according to the component load and upgrade reward, while the manual mode relies on human decision-making. A detailed upgrade reward calculation formula is defined, which considers the benefits, costs and risks brought by component upgrade. A detailed upgrade process is provided, including software package upload, sending upgrade request, generating upgrade instruction, and executing upgrade. It supports upgrade success confirmation and result feedback. This method is structured and intuitive, automated and intelligent, significantly improving the efficiency and effectiveness of virtual component management.

The man-machine collaborative group decision-making method, device and equipment based on the internal self-confidence degree in the embodiment of the invention comprises the following steps: evaluating a plurality of alternative schemes to obtain probability language evaluation information corresponding to each alternative scheme; calculating the internal self-confidence degree corresponding to the probability language evaluation information of each alternative scheme; comparing the internal self-confident degree corresponding to each alternative scheme with an internal self-confident degree threshold value; if the internal self-confidence degree corresponding to a certain alternative scheme is greater than an internal self-confidence degree threshold value, the probability language evaluation information corresponding to the alternative scheme is final evaluation information; otherwise, introducing the alternative scheme into a human decision maker for re-evaluation, performing information fusion on the evaluation information of the large language model and the evaluation information of the human decision maker to obtain final evaluation information corresponding to the alternative scheme, and outputting the final evaluation information; sorting the alternative schemes according to the final evaluation information, and determining an optimal scheme; the accuracy and efficiency of decision making can be improved; the method is suitable for the intelligent decision-making field in data processing.

The present invention discloses a mixed traffic intelligent vehicle dynamic game interactive decision-making method based on subjective cognition, including: sensing, acquiring and exchanging the driving information of each vehicle in the mixed traffic; judging whether the K instantaneous game system is started according to the situation risk assessment; if started, each vehicle participating in the game first makes a decision based on its own subjective cognition until the subjective cognition of each vehicle reaches a consensus; respectively establish and optimize the personalized embedded expected utility dynamic equation of each vehicle participating in the game, output its own acceleration at the K instant based on this decision and execute it; synchronously update the driving information and characteristic quantitative index of each vehicle in the mixed traffic at the K+1 instant; repeat the above steps until the potential mixed traffic conflict is completely resolved through continuous interactive decision-making. This method fully simulates human decision-making logic, improves the intelligence, interactivity, sustainability and integrity of decision-making, and realizes personalized driving and human-like decision-making of intelligent vehicles.

The invention belongs to the technical field of artificial intelligence, and provides a man-machine hybrid crowd intelligence knowledge driven decision-making method, device and equipment and a medium, and the method comprises the steps: obtaining machine data, and processing the machine data to obtain machine decision-making attributes; expert knowledge and public knowledge are obtained and combined to obtain human decision attributes; processing according to the machine decision attribute and the human decision attribute to obtain a man-machine mixed decision attribute weight and a human crowd intelligence decision opinion; constructing a man-machine hybrid social network, and determining a man-machine hybrid crowd intelligence knowledge value measure through the man-machine hybrid social network, the information entropy and the credibility; executing multi-attribute man-machine knowledge fusion and adjustment to obtain an optimized group knowledge value and an optimized man-machine mixed decision subject weight; and constructing a man-machine mixed decision subject weight feedback optimization model, and executing decision processing through the man-machine mixed decision subject weight feedback optimization model to obtain a decision result. The method has the beneficial effect that the scientific degree and fitness of decision making are improved.

A computing device determines a relative weightage of human-in-the-loop component usage to artificial intelligence component usage in a computing process that includes human decision-making and artificial intelligence decision-making. When the relative weightage is below a given range, such that the human-in-the-loop component usage is low relative to the artificial intelligence component usage: the computing device adjusts the computing process to increase the human-in-the-loop component usage relative to the artificial intelligence component usage. When the relative weightage is above the given range, such that the human-in-the-loop component usage is high relative to the artificial intelligence component usage: the computing device adjusts the computing process to decrease the human-in-the-loop component usage relative to the artificial intelligence component usage

Various embodiments enable automation of non-production activities of a coordinate measuring machine by ascertaining, prior to executing such activities, that such activities could be safely executed in the machine's environment. Although making such a determination can be fully automated, some embodiments include a human decision-maker in the loop.

Safety reinforcement learning is widely applied to the fields of games, robot control and the like. However, the traditional method often causes efficiency and stability problems due to limitation of an optimization strategy and a projection technology. In order to solve the problems, the invention provides a new algorithm which is named as an OSAPS (One-step Anticipative Policy Selector), and the new algorithm is an OSAPS (One-step Anticipative Policy Selector). The OSAPS improves the efficiency and safety of agent behaviors through integrating strategy selection, single-step planning and a self-adaptive safety threshold mechanism. The core of policy selection is a conditional dual-path policy network architecture, which comprises a vertex policy network and a basic policy network. In addition, a single-step planning mechanism of the OSAPS enables the intelligent agent to perform prospective action adjustment in a safe range, and simulates a human decision process. The self-adaptive safety threshold mechanism further improves the balance and safety between exploration and utilization. A robot simulation experiment shows that the OSAPS improves the time efficiency by 18.52% in a Pendula environment; the performance is improved by 7.67% in a Hovertrap environment, and meanwhile, the stability and the safety are kept.

The application discloses a kind of method and system for constructing intelligent automobile class human decision model, comprising: analysis host car in current traffic environment's cognitive task, determine the key elements of host car in traffic scene and cognitive link is relevant, based on this, analysis the representation method of multi-agent safety between host car and traffic environment, construct class human understanding model;Analysis long-term safety risk represented by key elements, and according to long-term safety risk evaluation result and destination planning result, the future space-time range of traffic situation is predicted, and heuristic pre-judgment model is constructed, further combined with class human understanding model, form class human understanding and pre-judgment decision model;According to the optimization evaluation parameter except multi-agent safety, the decision result obtained by class human understanding and pre-judgment decision model is optimized.The application can make decision result keep logical continuity in space-time scale, and improve the explainability and scalability of decision model by reasonable connection between models.

A method and system for analyzing and predicting human decision-making patterns is disclosed. A processor receives facial expressions of a subject while the subject interacts with displayed content. The displayed content is displayed on an interactive user interface. The captured facial expressions are processed using a computer vision algorithm to identify emotional states of the subject. Contextual data from the displayed content is extracted using a text categorization module to determine topics associated with the emotional states of the subject. The identified emotional states are correlated with the determined topics to generate an emotional response profile. The emotional response profile is analyzed using a machine learning model to identify patterns in decision-making behaviour of the subject. predictive insights regarding decision-making tendencies of the subject is generated based on the identified patterns. Further, the predictive insights are presented through the interactive user interface.

The application provides a kind of automatic driving model verification method, device, controller, vehicle and medium, method includes: in the process of vehicle driving, make the automatic driving model to be verified based on shadow mode operation, collect first environment data and human decision planning result, obtain the risk scene and corresponding data segment of model decision deviation;Human decision planning segment is used as supervision label, and the model is incrementally trained;Control vehicle to run on open road, collect second environment data to obtain model decision planning result and driving scene;Statistical model and driver's feature parameters under each scene category;According to the comparison result of feature parameter, calculate the comprehensive confidence index of model;If the index is greater than the preset threshold, determine that the model passes the verification.Based on this, the application realizes hierarchical, closed-loop model verification method, realizes the quantitative evaluation of the uncertainty of automatic driving model, improves the pertinence and effectiveness of test verification.

The present invention discloses an end-to-end autonomous driving control system and equipment based on human preference reinforcement learning. In the pre-training stage, the data collected in the CARLA simulator is used to pre-train the neural network model of the reward function based on the yaw angular velocity and the true value of the existing reward function, providing certain prior knowledge for the reward function model, which helps to accelerate the convergence process of the model. In the reward function learning stage, human preferences are used to correct and optimize the reward function. The cross entropy loss of the reward prediction value and the actual preference is used and L2 regularization is added to the loss function to ensure that the learning behavior is closer to human decision-making and prevent reward hacking, thereby achieving the alignment of the decision-making of the autonomous driving system with human values. In the intelligent agent learning stage, the PPO algorithm and multi-channel BEV are used as environmental inputs, and real-time training is performed in combination with the vector output of the throttle opening and the steering angle to ensure the real-time responsiveness and safety of the autonomous driving system.

[Problem] To provide a mechanism capable of supporting human decision-making at a work site. [Solution] An information processing device which comprises: an acquisition unit that repeatedly acquires situation data indicating a situation at a work site in which a user participates; a definition unit that defines an action plan selection table in which an action plan that is an option of one or more operations that can be executed when an event occurs at the work site and one or more situation data that are conditions for selecting the action plan are associated with each other; a storage unit that stores the action plan selection table for a plurality of the events that can occur at the work site; and a control unit that controls processing for recommending one or more action plans to be selected by the user on the basis of the situation data acquired by the acquisition unit and the action plan selection table related to the event that occurred at the work site.

The present invention discloses a human-machine integrated intelligent agricultural machinery automatic driving formation transfer system and method. The system is installed on a pilot host and several follower slaves. The pilot host and each follower slave are equipped with the same driving status collection system. The pilot host is also provided with a formation control terminal system, a router main station and a host WiFi module connected in sequence. Each follower slave is provided with a slave WiFi module that wirelessly communicates with the host WiFi module. All collected information is transmitted to the formation control terminal system via the router main station. The on-board computer in the formation control terminal system obtains the machine adjustment decision of the follower slave. The pilot host operator transmits the human decision to the on-board computer through a human-machine interaction interface. The on-board computer integrates the human decision and the machine adjustment decision to generate a formation decision and a control instruction for the control quantity input. The present invention realizes the complementary advantages between human experience and machine decision, and improves the reliability of the multi-machine formation transfer system.

The invention relates to the field of robot control, in particular to a robot adaptive control method based on a human-in-the-loop and an asymmetric barrier, and the method comprises the following steps: obtaining a reconstructed decoupling constraint based on a U-K principle; asymmetric logarithmic barrier transformation based on a dynamic skew factor is constructed, and bounded constraints are mapped to an unbounded virtual space; an ideal constraint force without a Lagrange multiplier is constructed based on decoupling constraint and a U-K principle, and a self-adaptive robust controller and an optimal decision model based on a fuzzy theory are constructed; and constructing a dynamic adjustment mechanism of a basic weight based on a constraint following error norm and an internal force safety index, and combining a smooth regional transition mechanism with a human decision based on a fuzzy theory to synthesize final control input. By orthogonally decomposing the task space, it is ensured that the robot can independently and strictly maintain the clamping internal force between the two arms while responding to a human random motion instruction, and objects are effectively prevented from sliding off in the cooperation process.

A method includes receiving, by a processing circuit, a plurality of solutions to avoid or decrease an adverse effect caused by an event. The method also includes selecting, by the processing circuit, a selected solution from the plurality of solutions by performing a socio-technical decision process. The socio-technical decision process includes simulating a human decision using a behavior model and a goal model for each of a plurality of agents and simulating a system decision using a sequential error search method for each of a plurality of systems. The socio-technical decision process also includes generating a socio-technical decision using the human decisions and the system decisions. The socio-technical decision corresponds to the selected solution. The method further includes facilitating a performance of one or more actions to implement the socio-technical decision.

The invention discloses a mudstone stratum shield tunnel portal slope supporting mechanism and method. A hydrogeological information and supporting information acquisition module is used for acquiring the hydrogeological change conditions of a current mudstone stratum shield in different seasons in real time, generating a hydrogeological change early warning signal and transmitting the hydrogeological change early warning signal to a remote engineer data calculation center; the hydrogeological information and support information acquisition module is further used for acquiring the current mudstone stratum shield cutter torque, cutter rotating speed and propulsive force of the tunnel portal slope and a support signal of tunnel portal slope concrete. According to the supporting mechanism and method, real-time monitoring, intelligent calculation, machine learning and automatic early warning are combined, and the safety, accuracy and stability of shield tunneling in a complex mudstone stratum can be ensured. By means of a highly-automatic analysis and adjustment mechanism, the risk of human decision making is remarkably reduced, and the long-term stability of the tunnel portal slope and the engineering construction efficiency are improved.

The invention relates to the technical field of project management, in particular to a digital information management method for enterprise projects, which comprises the following steps: determining a to-be-managed project core feature set corresponding to a to-be-managed project; matching the to-be-managed project core feature set with a historical project feature library to obtain at least one feature matching result set; wherein different types of feature sets correspond to different project management types; determining a feature similarity weight between the to-be-managed project core feature set and the at least one type feature set; and screening out a target similar weight with the maximum weight value from the feature similar weights, and determining a target project management type corresponding to the target similar weight. According to the method, the core feature set of the project to be managed is matched with the historical project feature library, so that the management mode of similar projects can be quickly identified, and the most suitable project management type can be found in a short time, so that the human decision time is shortened, and the overall management efficiency is improved.

This invention discloses an improved cognitive-driven decision-making method for predicting human decisions, comprising: acquiring the current situation; based on the current situation, performing feature recognition based on a preset memory model to obtain a prototype corresponding to the current situation; based on the prototype corresponding to the current situation, performing memory retrieval to obtain memory retrieval information; based on the memory retrieval information, performing an expectation check to obtain memory retrieval information that passes the check; and based on the memory retrieval information that passes the check, performing a simulated action to obtain the final decision action. On the one hand, the preset memory model can effectively store continuous memory information and can match the corresponding prototype based on continuous information in the current situation; on the other hand, this invention uses a joint probability density function, which has the ability to simulate the uncertainty of human decision-making.