20results about How to "Improve decision speed" patented technology

The invention relates to a critical disease inter-hospital referral patient scoring and resource allocation method, system and device, and a medium. The method comprises the following steps: determining referral demands of patients; constructing a resource matching model in combination with the illness state and the geographic position of the patient and the medical specialist information of the hospital to generate a recommended hospital list, and determining a transfer-in hospital and a referral time window; calculating an optimal referral path and the shortest time required by referral in the referral time window according to the transfer-in hospital and the referral time window in combination with the geographic information and the real-time road condition data; and allocating the ambulances to the patients within the available range of the ambulances based on the globally optimized resource allocation model. The advanced scoring rule and the resource allocation algorithm are introduced, the treatment efficiency of critical patients is improved, more scientific and objective decision support is provided, and unnecessary referral treatment and repeated examination are reduced, so that the medical cost is effectively reduced, medical errors are reduced, and the satisfaction degree of the patients is greatly improved.

The invention provides a building robot obstacle avoidance path planning method and related equipment, and the method comprises the steps: fusing the state information of a target building robot with environment data through Bayesian filtering, and obtaining an occupied grid map; inputting the occupied grid map into the trained lightweight convolutional neural network for feature extraction, and generating environment feature data; the environment feature data and the current state of the target building robot are input into a trained decision model for decision making, an action instruction is obtained, the target building robot reaches the target position within the shortest time based on the action instruction, and the path from the target building robot to the target position is the obstacle avoidance path of the target building robot; by improving the accuracy and robustness of environment perception, efficient obstacle avoidance and path planning in a complex environment are realized.

The invention relates to the field of artificial intelligence, in particular to a rocket trajectory optimization and real-time adjustment system based on artificial intelligence, which comprises a trajectory prediction module, a real-time adjustment control module and an intelligent monitoring module, and is characterized in that a jumping mechanism is introduced into the trajectory prediction module, so that interference of an intermediate state is effectively reduced, and key time steps are directly concerned; a forward diffusion and inverse process denoising mechanism is introduced, so that the sensitivity of the model to noise is effectively reduced; in the real-time adjustment control module, the attitude and thrust of the rocket are automatically adjusted based on model predictive control, the solving process is more efficient, the calculation complexity is reduced, the decision-making speed is increased by optimizing a target function to minimize state deviation and adopting a constrained quadratic programming problem, the trajectory optimization and real-time adjustment capability of the rocket is remarkably improved, and the real-time adjustment of the rocket is realized. And powerful support is provided for realizing complex aerospace tasks.

The invention discloses a multi-satellite collaborative observation method and device, and the method comprises the steps: obtaining a training data set, task information and time window information; performing fusion processing on the training data set, the task information and the time window information to obtain to-be-processed collaborative observation information; and analyzing and calculating the task information, the time window information and the to-be-processed collaborative observation information to obtain target collaborative observation information. Therefore, according to the method, the decision speed of multi-satellite collaborative observation can be accelerated, so that the searching and optimizing difficulty and time consumption of satellite task planning are reduced.

The invention relates to the field of commodity information management of supply chains, in particular to a commodity information management method based on a supply chain, and the method comprises the steps: generating a bar code for the information of each produced commodity through commodity production management, carrying out the traceability of the commodity through the bar code, carrying out the inventory information analysis of a user, obtaining the information of each inventory in real time, and analyzing the inventory turnover rate; the sales information feedback is used for analyzing the collected sales parameters of the commodities and feeding back analysis results; according to the received signals, early warning processing is carried out on the received signals; according to commodity safety monitoring, a high-definition camera is used for monitoring commodities in real time in the transportation process, the safety state of the commodities is judged, smooth operation of a supply chain is effectively ensured, and the customer satisfaction degree is effectively improved.

The invention relates to a design method and a control system and method of an unmanned aerial vehicle command and control large model, and belongs to the technical field of command and control. In order to solve the problem that an existing command and control system depends on a traditional rule-based or manual programming method and is limited when processing complex tasks, the method for controlling the unmanned aerial vehicle through the unmanned aerial vehicle command and control system comprises the following steps that task texts are input into an unmanned aerial vehicle command and control large model, and a MavLink format instruction is generated; according to the method, unsafe instructions are corrected, executable unmanned aerial vehicle tasks are planned into a behavior tree, flight and task execution of the unmanned aerial vehicle are controlled, the powerful language understanding and generation capability of LLama3 is utilized, the intelligent level and performance of an unmanned aerial vehicle command and control system are improved, and the task execution efficiency and success rate of the unmanned aerial vehicle are improved.

The invention relates to the technical field of grid map construction, and discloses a visual robot grid map construction method comprising the following steps: 1, grid granularity size selection; step 2, grid order marking; step 3, obstacle grid adjustment; step 4, establishing a grid map; in the third step, feature extraction is carried out on obstacles, images and videos in the surrounding environment are obtained through a visual sensor assembly, and then the images and the videos are processed and analyzed to extract useful information, so that information of the obstacles in the grids can be sensed. According to the method, in the grid map construction process, the particle sizes of a plurality of grids are set to be large, for example, when obstacles exist in part of grids and the particle sizes of the grids are adjusted, the grids with the obstacles are subdivided into a plurality of 10 * 10 small grids, so that grid map construction can be carried out more accurately; and the subsequent decision-making speed is improved while the information storage amount of grid map construction is reduced.

The application provides an electronic chart system, method and equipment with water depth change prediction capability, relates to the technical field of marine electronic information technology and marine geographic information, and the system comprises a data acquisition module, a water depth change analysis and prediction module and a risk visualization module. The application superimposes and displays predictive water depth risk information in a standard ECDIS interface through the fusion of official electronic chart data and a dynamic water depth model, so that the existing operation process of the driver can be changed, and enhanced navigation support reflecting the recent seabed change trend can be provided in the case that the chart updating cycle is long.

This invention relates to the field of robot control technology, specifically to an end-to-end closed-loop control method and system for robots based on multimodal perception fusion. It includes: a perception access layer for standardized access to data from multiple sensor types; a fusion processing layer for spatiotemporal alignment and multimodal fusion processing of the standardized access data; a decision control layer for generating execution instructions based on the fusion processing results; and an execution feedback layer for feeding back the execution status to the fusion processing layer to form closed-loop control. This technical solution can solve the problems of standardized access and real-time fusion of multi-source heterogeneous data, and construct a closed-loop control architecture with high fault tolerance and low latency.

The invention provides an event assessment and auxiliary decision-making method and system for an offshore operation platform, and the method comprises the steps: taking platform data in different complex operation scenes as input, employing different key data preprocessing methods, and obtaining event assessment key factors and relationships of the whole offshore platform; an evaluation analysis model is established to analyze and evaluate the whole platform event space, auxiliary decision support data is improved, visual display is carried out with different granularities or different abstract levels, and the function of accurately evaluating and deciding platform events is achieved. According to the method, the decision-making speed is increased by analyzing, concluding and integrating complicated data accumulated by subsystem equipment of the maritime satellite launching and recycling platform and carrying out classified analysis on evaluation data by utilizing an intelligent optimization genetic algorithm; an event evaluation model constructed based on a fusion algorithm is applied to assist the platform and personnel in performing remote diagnosis and decision-making on the operation of the offshore operation platform, so that risk threats caused by emergencies are reduced, and the operation efficiency of the platform is improved.

The invention relates to the technical field of MOS transistor monitoring, and discloses a high-power MOS transistor monitoring method and system and a storage medium, and the method comprises the steps: S1, collecting key parameter data in a working process of a high-power MOS transistor; s2, performing gradient calculation on all parameter data in the key parameter data to obtain a parameter gradient feature set; s3, performing abnormal behavior analysis on each parameter gradient feature in the parameter gradient feature set to obtain abnormal behavior data, constructing a behavior analysis rule, and inputting the behavior data into the behavior analysis rule to obtain a risk behavior mode of the abnormal behavior data; s4, performing behavior score calculation based on the risk behavior mode to obtain a behavior score, and judging whether the behavior score is smaller than a set state intervention threshold value or not; by calculating the behavior score of each segment and comparing the behavior score with the threshold value, the behavior abnormity of the MOS transistor can be detected in the early stage, so that measures can be taken in time to avoid potential problems.

The present invention discloses an intelligent resource allocation method for 6G based on partially observable active reasoning, including: calculating channel power gain, transmission rate of SU and PU, constructing state information variables, reward function, parameter initialization, obtaining sub-band allocation action and drone flight direction action, obtaining instant reward of the network, completing single environmental interaction, switching to the state at the next moment, calculating variational free energy and value network loss, minimizing variational free energy and value network loss to update network parameters until the optimization is completed, obtaining an optimized algorithm model for intelligent resource allocation, and calculating the system transmission rate at this time. The present invention can enable the spectrum sharing system to obtain the maximum resource allocation efficiency and rate, and accelerate the convergence speed of the network, with stronger real-time performance, and the framework has strong generalization ability and can be extended to various wireless communication scenarios, which enables the invention to be better applied in practice.

The invention discloses an automatic decision-making method and system based on rule driving, and relates to the technical field of business decision-making automation, and the method comprises the steps: recording original decision-making data in a real decision-making scene, and extracting causal elements in the original decision-making data; creating a rule base based on causal elements of the original decision data; adding a factor element matching algorithm for the rule base, querying a rule graph corresponding to the input data based on the factor element matching algorithm, and outputting the rule graph; manual intervention is introduced to optimize the rule base, and it is ensured that each rule graph is put into a production environment after the accuracy of each rule graph reaches the standard; and the production environment outputs a final decision based on the optimized rule base. The decision-making efficiency can be improved, manual intervention is reduced through automatic processing, and the decision-making speed is increased; the interpretability and transparency are improved, the decision-making process is traceable, and audit and interpretation are facilitated; and the method is flexible and configurable, supports dynamic regulation and expansion of rules, and adapts to business change requirements.

The embodiment of the invention provides a large model application method and device based on an automatic driving scene, equipment and a medium. The method comprises the following steps: acquiring a to-be-recognized image from current automatic driving data; performing feature extraction on the to-be-recognized image according to a visual backbone network of a target visual model obtained by pre-training, and inputting the extracted features into a sensing head of the target visual model to obtain first to-be-recognized features; performing stochastic gradient descent processing on the first to-be-recognized feature through a posterior optimization trajectory generator in the target vision model to obtain a second to-be-recognized feature for indicating a subsequent reasoning direction of the target vision model; and performing semantic recognition on a target to-be-recognized feature obtained by fusing the first to-be-recognized feature and the second to-be-recognized feature through a target visual model to obtain an image recognition result of the to-be-recognized image. Therefore, the image recognition efficiency can be improved, and the image recognition accuracy of the model can be improved.

E-commerce has become a mainstream lifestyle. Users primarily rely on platform-provided content recommendation algorithms to find the goods or services they need. Recommendations are generated based on VR / AR data (CN118552273A) using virtual digital avatars, and inferred from user social connections (CN118411232A). Existing recommendation algorithms lack personalization, over-rely on user behavior and sales data, and are susceptible to data pollution from fraudulent activities like fake orders, leading to results that don't meet user expectations, causing confusion, and ultimately affecting user decision-making and purchasing decisions. To address these issues, this application provides an intelligent method for recommending goods and services. It innovatively modifies existing recommendation algorithms by introducing advanced technologies such as large-scale artificial intelligence models and computer image recognition algorithms. This method effectively improves the personalization of user search results, creating scenario-specific, personalized search results. This allows search results to help users make faster decisions and increase their willingness to purchase products and services.

The embodiments of the present application provide a large model application method, device, equipment and medium based on an autonomous driving scenario. The method includes: obtaining an image to be recognized from the current autonomous driving data; extracting features of the image to be recognized based on the visual backbone network of the pre-trained target visual model, and inputting the extracted features into the perception head of the target visual model to obtain a first feature to be recognized; performing random gradient descent processing on the first feature to be recognized through the posterior optimization trajectory generator in the target visual model to obtain a second feature to be recognized for indicating the subsequent reasoning direction of the target visual model; performing semantic recognition on the target feature to be recognized obtained by fusing the first feature to be recognized and the second feature to be recognized through the target visual model to obtain an image recognition result of the image to be recognized. In this way, the accuracy of image recognition by the model can be improved while improving the recognition efficiency of image recognition.

The application provides an emergency demand response load side flexibility resource scheduling optimization method and system, and the method comprises the following steps: constructing a resource scheduling control architecture based on regional flexibility resource adjustment capacity; the resource scheduling control architecture comprises a cloud server, a control terminal and a regional control unit (RCU) which is respectively in communication connection with the cloud server and the control terminal; an emergency demand response scheduling model is established by comprehensively considering timeliness, economic benefits and user satisfaction; and an emergency demand response scheduling decision under the resource scheduling control architecture is calculated by using a RAFT distributed algorithm based on the emergency demand response scheduling model. Through the application, an emergency demand response architecture and a scheduling decision optimization method based on a distributed algorithm are provided, rapid decision and optimal benefits are considered, the dynamic change of flexible resources is adapted, various complex power grid operation environments can be coped with, and dynamic evaluation and optimal distribution of flexible resource adjustment potential are realized.

The invention discloses a rule-based scene library setting automatic driving decision-making system and method and a vehicle, and belongs to the technical field of automatic driving, and the system comprises a sensor module which is used for collecting environment information around the vehicle; the data processing module is connected with the sensor module, and the data processing module is used for processing and analyzing the environment information collected by the sensor module so as to identify an obstacle and extract feature information of the obstacle; the decision module is used for making an avoidance decision according to the feature information extracted by the data processing module on the basis of a predetermined rule; and the execution module is used for controlling the vehicle to execute the avoidance decision generated by the decision module. According to the invention, various obstacles and moving states thereof can be accurately identified in a complex urban traffic scene, sudden occurrence of the obstacles can be rapidly judged and processed, and decision rules are continuously optimized through real-time learning and experience accumulation so as to adapt to different urban environments and obstacle arrangement.

The application relates to a daily regulation type hydropower station economic operation model and an optimization method and system based on a proximal policy optimization algorithm, wherein the method comprises the following steps: obtaining unit parameters and hydrological parameters of a daily regulation type hydropower station to determine a target function, decision variables and constraint conditions, and establishing an optimization operation model of the daily regulation type hydropower station; collecting load instruction data of the daily regulation type hydropower station at each period, monitoring reservoir inflow, an upstream water level and a unit operation state to obtain operation data of the daily regulation type hydropower station; inputting the operation data into the optimization operation model, and solving the optimization operation model based on the proximal policy optimization algorithm to convert the optimization operation model into a Markov decision process, and outputting a daily load distribution scheme. Therefore, the problems in the related art that, due to the fact that the calculation time of a dynamic programming algorithm is multiplied by the scale, and the performance of deep reinforcement learning is greatly different under different conditions, it is difficult to obtain a reliable daily regulation type hydropower station optimization operation scheme are solved.

The invention provides a group delivery method and computing equipment, and the method comprises the steps: constructing a label vector knowledge base which is used for carrying out the vectorization storage of the labels of commodity groups; obtaining a natural language question which is input by a user and is used for article selection; processing the natural language question to obtain a question vector; according to the problem vector, performing preliminary screening matching in the label vector knowledge base to obtain a preliminarily screened label list; generating a tag combination result from the natural language question and the tag list through a large language model; and putting the pallets according to the label combination result. According to the technical scheme of the invention, the work difficulty related to commodity labels can be reduced, the efficiency of a commodity selection process is improved, the complexity of commodity distribution is reduced, and commodity assembly and delivery can be better carried out.