52 results about "Plan evaluation" patented technology

Agent-based models (ABMs)/multi-agent systems (MASs) are one of the most widely used modeling-simulation-analysis approaches for understanding the dynamical behavior of complex systems. These models can be often characterized by several parameters with nonlinear interactions which together determine the global system dynamics, usually measured by different conflicting criteria. One problem that can emerge is that of tuning the controllable system parameters at the local level, in order to reach some desirable global behavior. According to one exemplary embodiment t of the present invention, the tuning of an ABM for emergency response planning can be cast as a multi-objective optimization problem (MOOP). Further, the use of multi-objective evolutionary algorithms (MOEAs) and procedures for exploration and optimization of the resultant search space can be utilized. It is possible to employ conventional MOEAs, e.g., the Nondominated Sorting Genetic Algorithm II (NSGA-II) and the Pareto Archived Evolution Strategy (PAES), and their performance can be tested for different pairs of objectives for plan evaluation. In the experimental results, the approximate Pareto front of the non-dominated solutions is effectively obtained. Further, a conflict between the proposed objectives can be seen. Additional robustness analysis may be performed to assist policy-makers in selecting a plan according to higher-level information or criteria which is likely not present in the original problem description.

When evaluating the execution plan of a job executed in a computer system by using simulation, the simulation is completed and the execution plan evaluation is completed within the time desired by a user. The evaluation system includes a performance storage section for storing a performance value of a computer executing the simulation, a model database for storing a performance model used for the simulation, and a model creation section for creating a performance model from the performance model stored in the model database for use in the simulation. The model creation section modifies the method for creating the model according to the limit time input by the user and the performance value of the computer stored in the performance storage section. By using the performance model created by the model creation section, the simulation is executed and the job execution plan is evaluated.

The invention provides an underwater vehicle three-dimensional path planning method based on a Lazy Theta satellite and particle swarm hybrid algorithm. The method comprises the following steps of 1, performing navigation space modeling; 2, building a Lazy Theta satellite algorithm cost function; 3, performing two-dimensional path planning in a horizontal plane by using a z=zsafemin horizontal plane as a Lazy Theta satellite algorithm two-dimensional path plan plane, and using X-axis and Y-axis coordinates (xs, ys) of a path starting point S and X and Y-axis coordinates (xd, yd) of a path terminal point D as a starting point and a terminal point of a two-dimensional path; 4, finding a collision-free length-shortest path optimization target according to three-dimensional path planning; designing a depth plan evaluation function; 5, using a particle swarm algorithm to perform depth planning; 6, outputting an optimum three-dimensional path. Through the simplification on a three-dimensional problem, the advantages of two kinds of different algorithms are combined; the calculation complexity of the algorithm is reduced; the high speed performance and the reliability of the three-dimensional path planning are improved.

The invention belongs to the field of radiotherapy plan evaluation and discloses a machine learning-based radiotherapy plan evaluation method. With the method adopted, the problems of the non-uniformity of standards and susceptibility to subjective deviation of a conventional technology which adopts manual operation to evaluate radiotherapy plans. The method includes the following steps that: pre-processing work such as voxel selection, voxel feature extraction and voxel data annotation, is performed on the DICOM (Digital Imaging and Communication) data of high-quality radiotherapy historicalplans; voxel data are used to train a machine learning model; the model outputs predicted dose values for each voxel in a plan to be evaluated; a two-dimensional DVH prediction curve and a three-dimensional voxel dose prediction distribution map are further generated for each crisis organ; and finally physicists actually evaluate the radiotherapy plan to be evaluated with the reference of the curves and distribution maps. The present invention also discloses a corresponding evaluation system suitable for the objective and accurate evaluation of a radiotherapy plan.

The invention discloses a single-point intersection signal timing plan evaluation method in an unsaturated state and belongs to the technical field of traffic control. The method includes obtaining measured values of different evaluation indexes before and after signal timing plan optimization in the unsaturated state, wherein each evaluation index includes time headway and delay; according to the measured values of the different evaluation indexes before and after signal timing plan optimization, calculating the difference values of the indexes before and after optimization on different phases of a single-point intersection; according to the difference values of the indexes before and after optimization on the different phases of the single-point intersection, evaluating the optimization directions of the different phases in the signal timing plan. According to the invention, by taking the time headway and the delay on the different phases of an entrance way of the single-point intersection as the evaluation indexes of the signal timing plan in the unsaturated state, the optimization directions of the phases can be indicated clearly and an optimized step size is obtained, so that the signal timing plan can be optimized according to the optimization directions of the different phases and phase utilization rate can be increased.

Simulation for evaluating approval/rejection of an action plan of the type in which work breakdown struction is changed by influences of external risk factors is achieved. A simulation apparatus includes a plan/risk input portion for accepting input of action plan data and risk scenario data, a plan/risk simulation portion for conducting simulation of an action plan by using the action plan data and the risk scenario data so accepted, and a plan evaluation output portion for evaluating a simulation result. The plan/risk simulation portion simulates occurrence of a risk phenomenon by using the risk scenario data, determines influence information given by the risk phenomenon to the action plan when the risk phenomenon is simulated as occurring and conducts simulation of the action plan by reflecting the influences of the risk scenario on the action plan by using the influence information so determined.

The invention provides a multi-index based intersection signal timing plan evaluation method, which belongs to the field of traffic control technology. The method comprises the steps of collecting traffic parameters generated by running a current signal timing plan and selecting a plurality of evaluation indexes in the traffic parameters; based on a preset normalization function, subjecting the plurality of evaluation indexes to normalization to obtain corresponding evaluation index values; based on a preset evaluation index weight algorithm, calculating weight values of the plurality of evaluation indexes; and obtaining the evaluation result of the intersection signal timing plan based on the plurality of evaluation index values and the weight values of the plurality of evaluation indexes. By the use of the plurality of independent and uncrossed evaluation indexes, and by normalization of the various evaluation indexes to eliminate the problems caused by differences in the dimension, the authenticity of problems in the signal timing plan that are reflected by the various evaluation indexes is improved, and with combination of the weight value of each index, the obtained evaluation result of the signal timing plan can be very accurate.

The invention discloses a radiotherapy plan evaluation method and device, relates to the field of medical technology, and mainly aims to be able to realize automatic evaluation of a radiotherapy planso as to improve the efficiency and accuracy of the radiotherapy plan evaluation. The method includes the steps of analyzing a radiotherapy plan to be evaluated to obtain radiotherapy information andtarget area attribute information; inputting the radiotherapy information into a pre-trained deep learning model for training, the deep learning model being used for outputting the target area attribute information according to a mapping relationship between the radiotherapy information and the target area attribute information; judging whether the target area attribute information obtained from the analysis conforms to the target area attribute information output by the deep learning model; and if not, determining the radiotherapy plan to be abnormal. The radiotherapy plan evaluation method and device in the invention are suitable for the evaluation of radiotherapy plans.

The invention discloses a network planning evaluation method and device, relates to the technical field of communication, and is used for scoring and sorting grids from a plurality of evaluation dimensions and determining planning requirements of the grids according to priority sorting, so that the accuracy of determining the network planning requirements is improved, and the waste of investment is reduced. The method comprises the following steps: acquiring optical splitter information and grid information of optical splitters in a predetermined network range; establishing a corresponding relation between the optical splitter and the grid according to the latitude and longitude of the optical splitter and the position of the grid; obtaining basic data of the grid according to the opticalsplitter information corresponding to the grid; determining each evaluation dimension of the grid according to the basic data of the grid, and scoring each evaluation dimension of the grid; and obtaining the score of the grid according to the scoring result of each evaluation dimension of the grid, obtaining the priority order of each grid according to the score of each grid in a predetermined network range, and sequentially determining the planning demand of the grid according to the priority order.

The invention discloses a three-dimensional GIS electric power emergency command system. The three-dimensional GIS electric power emergency command system comprises a GPS/big dipper person position management client side for transmitting GPS/big dipper position information of a manager to a central server, a sudden event input client side for sending sudden event information to the central server, a central server for transmitting the sudden event information to a command plan input client side and a command decision-making input client side, the command plan input client side for inputting a disposal plan of a sudden event and sending the disposal plan to the central server for sending the disposal plan to the command decision-making input client side, the command decision-making input client side for making a command decision and transmitting corresponding decision-making information to the central server, and an emergency plot input client side for inputting an emergency plot and sending the emergency plot to the central server. The three-dimensional GIS electric power emergency command system can simultaneously achieve command decision-making, emergency management, plan formulation, plan evaluation, emergency plotting, three-dimensional display and other functions.

The invention discloses a shipment operational plan evaluation method for an automatic container terminal. The method is dedicated to realizing shipment operational plan evaluation of the automatic container terminal. The method is mainly characterized in that the method can be independent of equipment and dispatching of the terminal, factors which exist in a shipment operational plan and possibly influence shipment operation time are pointed out in a targeted mode, and the influence degree on the shipment operation time is evaluated according to the factors. The method is a supplement to an automatic dispatching system of the container terminal, and an evaluation system developed through the method is reference to connection of the automatic dispatching system and a TOS (Terminal Operation System). The method has important significance for automatic transformation of artificial container terminals in China.

The invention belongs to the technical fields of medical treatment and cloud service, and relates to a cloud radiation therapy plan evaluation method, equipment and a storage medium. The method comprises the steps of: inputting a radiotherapy plan data to-be-evaluated into a patient database according to a standard format; using a machine learning method to generate a standard radiotherapy plan corresponding to the radiotherapy plan to-be-evaluated; automatically comparing the radiotherapy plan to-be-evaluated with the standard radiotherapy plan for scoring; and displaying the scoring resultsobtained by the machine learning method and outputting a result report. The evaluation method provided by the invention is beneficial to collecting expert knowledge and forming an expert knowledge base, which reduces artificial subjective factors, improves objectivity and reduces errors.

A method for reviewing a treatment plan (24) for delivering radiation therapy to a patient. The treatment plan(24)includes geometric analysis data, dose distribution analysis data, dose volume histogram data, parametric analysis data or deliverability analysis data of a patient. First, for the treatment plan (24), a plurality of clinical and delivery goals are identified (20, 22).Next, goal data points are extracted (26)from the treatment plan (24). Then, data points are correlated (28) to identify deficiencies in the treatment plan (24). A report is generated (30) to display on a display (10) the correlated data points using visual markings (84) to highlight identified deficiencies. Text and audio notations can be attached to the report to explain the correlations and warn a user of plan deficiencies.

The invention discloses a differentiated evaluation method for county-area power distribution network plan, wherein the method relates to power distribution network plan evaluation. The method aims at the characteristic of a to-be-evaluated power distribution network plan area, thereby determining an evaluation index system. A total least square method is utilized for constructing a scoring function of each index. A subjective analyzing method in which a fuzzy analytical hierarchy process and a G1 method is combined is utilized for determining weight configuration of each index. According to predicated data of each year in future in planning, a total score of each year in future is generated, and evaluation is performed on the to-be-evaluated power distribution network plan according to the total score. The differentiated evaluation method is advantageous in that scientific, integrated and comprehensive evaluation can be performed on the power distribution network plan in future; differentiated evaluation can be performed on the power distribution network plan according to an actual development requirement for aiming at the characteristic of the to-be-evaluated county-area power distribution network; and relatively long years of year-by-year comparing can be performed on the power distribution network plan in future, thereby performing a guiding function in power distribution network plan improvement and promoting integral quality improvement of a power grid.

The invention relates to the field of radiotherapy plan optimization, discloses a radiotherapy plan optimization system and method based on Monte Carlo tree search, and solves the problem that a radiotherapy plan optimization scheme in the traditional technology needs to rely on a large number of iterative trial and error and senior physicist experience. The method comprises the steps of: a. selecting a set of target parameters as initial value of a radiotherapy plan optimization process, and determining plan evaluation criteria for characteristics of a disease to be treated; b. circularly performing the Monte Carlo tree search operation in conjunction with the plan evaluation criteria until a set of optimized target parameters is obtained; c. performing dose calculation on the optimization target parameters, and checking whether a calculation result meets the optimization requirements; if yes, ending the process; and if not, proceeding to a step d; and d. slightly adjusting the set ofoptimization target parameters and returning to the step b. In addition, the present invention also discloses a radiotherapy plan optimization system based on the Monte Carlo tree search, and the system is suitable for automatic optimization of a radiotherapy plan.