33 results about "Decision quality" patented technology

Load shedding schemes for mining data streams. A scoring function is used to rank the importance of stream elements, and those elements with high importance are investigated. In the context of not knowing the exact feature values of a data stream, the use of a Markov model is proposed herein for predicting the feature distribution of a data stream. Based on the predicted feature distribution, one can make classification decisions to maximize the expected benefits. In addition, there is proposed herein the employment of a quality of decision (QoD) metric to measure the level of uncertainty in decisions and to guide load shedding. A load shedding scheme such as presented herein assigns available resources to multiple data streams to maximize the quality of classification decisions. Furthermore, such a load shedding scheme is able to learn and adapt to changing data characteristics in the data streams.

A robust process for automating the tuning and maintenance of decision-making systems is described. A configurable multi-stage mutation-based evolutionary algorithm optimally tunes the decision thresholds and internal parameters of fuzzy rule-based and case-based systems that decide the risk categories of insurance applications. The tunable parameters have a critical impact on the coverage and accuracy of decision-making, and a reliable method to optimally tune these parameters is critical to the quality of decision-making and maintainability of these systems.

The invention discloses a production concentrating operation system of a provincial power metering center. A visual emulation mode is used for managing a storeroom, work is finished by a task establishing mode, and a statistic outcome is presented in a mode of imaging and report forms by analyzing progress data, thus facilitating the control and checking of a user on loops; the flow managing in the metering operating progress is informationized, distributed service processing of the system is realized by the modern network and a data storing technology, and service is finished by merging the sharing data of intelligent equipment and an external system, so the production concentrating operation system of the provincial power metering center has the advantages of optimizing the producing service flow, ensuring the efficient operating of the metering work, reducing the managing and operating cost, alleviating the work load of staff, improving the refining level and the decision quality of managing and realizing a better application prospect.

The invention discloses a building information integration platform based on a BIM technology. A construction process can be simulated before construction, so that the building condition is predictedin advance, the design quality is improved, the construction process is simulated, and the construction scheme is optimized; in the construction process, the construction quality is monitored throughthe BIM technology, quality related problems are found and solved in time, and the building quality is effectively improved; visualization of the construction progress and visualization of the investment cost are achieved through the BIM, timely and accurate investment data are obtained timely and rapidly, the manufacturing cost is effectively controlled, and the investment risk is reduced; a BIMthree-dimensional visual model is used as a carrier of all information of a building, the communication efficiency and decision quality among all units are effectively improved, and after completion,the BIM three-dimensional visual model is used as important basic data of a subsequent owner operation and maintenance stage to realize traceability of information and responsibility.

The invention provides a track traffic network dynamic security risk evaluation method. Firstly, a track traffic network dynamic security risk evaluation dynamic index system is determined, then all dynamic index values are calculated according to data collected by road network equipment in real time, and finally a track traffic network operating security risk is dynamically evaluated based on a new method with the interval type-2 fuzzy number and the TOPSIS combined. Technical supports are provided for precisely mastering the real-time security state of track traffic network operating and provided for decision making of related management personnel, and the quite important practical significance in improving decision making quality is achieved.

The invention discloses a comprehensive administrative decision support and administrative behavior management information platform, which comprises a dynamic management information system, an enterprise information base and a dynamic management technology supporting platform. The dynamic management information system provides an enterprise service space, establishing a "one number for one internet" service mechanism for an enterprise, realizing the access of various government services, enabling the real-time collection and exchange of the enterprise production and operation information to adynamic management information system, and providing the identification service and policy cashing service for the enterprise. The enterprise information base and the dynamic management technology supporting platform provide an extensible technical platform for the application of the cloud PAAS technology, ensure the access convenience of applications and the sustainable development of the construction. According to the invention, through the development and management of information resources required by the government and owned by the government, the strict institutional design and the efficient workflow management are conducted. The normalization, the pertinency and the effectiveness of the government economic management work are enhanced. The working efficiency, the decision quality, the regulation and control capability and the standardization degree of the government are improved. The current problems of government management fragmentation, information islanding phenomenon, passive services and the like are solved.

The invention discloses a method and a system for realizing comprehensive factor comparison of e-questionnaires. The method comprises: generating a factor importance e-questionnaire according to all factors which are listed and need comparing, obtaining factor importance evaluation information, filling the factor importance evaluation information in a factor comparison e-questionnaire, generating the factor comparison e-questionnaire, and obtaining comprehensive factor comparison information. The system comprises a network, a plurality of e-questionnaire terminals which are linked with the network through a TCP/IP adapter and are used to receive the e-questionnaires and to send a questionnaire filling result to an e-questionnaire server, and the e-questionnaire server which is linked with the network through the TCP/IP adapter and is used to generate and send the e-questionnaires and to automatically gather, state and calculate questionnaire results. The invention is realized through using electronic conferences and e-questionnaire facilities, the processing ability of the e-questionnaires on complex decision making problems is extended, and the method provides users with the practical electronic conference function and effectively increases the conference efficiency and the decision making quality.

The invention discloses a networked multi-robot system. The system comprises: embedded visual nodes, a console and a multi-robot group. The embedded visual nodes are used to collect and process visual information and send processing results of the visual information to the console and the multi-robot group. The console, combining the visual information processing results of the embedded visual nodes and position and state information of the multi-robot group, is used to provide instruction information and environment information for the multi-robot group. The multi-robot group is used to send the position and state information of the multi-robot group itself to the console, receive the processing results of the embedded visual nodes to the visual information and the instruction information and the environment information of the console, combine perception of the multi-robot group itself and carry out a movement decision. In the invention, a plurality of the embedded visual nodes independently collect and process the visual information so that distributed parallel processing can be realized. The information can be timely provided for the multi-robot system. Decision quality and efficiency can be increased.

The invention relates to a security investment decision-making method and device based on a neural network and machine learning. The method comprises the steps of collecting the transaction related data of a security market; preprocessing and normalizing the data; building a plurality of neural network models; training and screening out a high-quality model; enabling the plurality of models independently to make an investment decision and vote to obtain a final investment decision; adjusting the voting right of each model according to the decision quality of each model; and continuously carrying out supplementary training on each model by utilizing the new data so as to adapt to the subsequent decision-making requirements. The invention further provides a computing device for executing theabove method. According to the invention, the neural network and the machine learning technology are utilized to realize the artificial intelligence of the security investment field, investors do notneed to have any mathematical knowledge or economic finance knowledge, any investment experience is not needed, and the decision-making process can completely realize the black box operation on the investors.

The invention discloses a shopping center site selection device and method based on big data and expert experience, and the device comprises four modules: a basic data comprehensive processing module,an expert scoring module based on site selection big data, a weight learning module of each influence factor, and an intelligent site selection sub-module for calculating an alternative land parcel.According to the method, the data of each dimension of the alternative land parcel can be quickly known and evaluated, the site selection efficiency is greatly improved, the expert experience is digitized, the deviation caused by expert personal judgment is eliminated, more objective evaluation is given, the intelligent site selection score gives a single number to evaluate the alternative land parcel, the data analysis efficiency is greatly improved, the decision quality is improved, and continuous optimization can be realized in the future.

The invention relates to an index comprehensive display method. The method comprises the following steps of I, applying an index and power network information visual display technology; II, applying a massive data mining and drilling analysis technology; and III, applying a typical business topic analysis technology. According to the comprehensive analysis method provided by the invention, logic, interconnected and interactive visual display of power network operation information and various decision-making assistant information is effectively realized in combination with power network regulation business data characteristics and power network operation analysis results; complete information and technical support are provided for timely mastering overall conditions and real and accurate field conditions of power network production and carrying out scientific decision-making; and the data mining technology is introduced for analyzing and processing power network data, and system data is converted into valuable knowledge to assist decision-making and management personnel to perform data analysis and decision making, so that the decision-making quality is improved and the potential value of the power network data is fully mined.

The invention discloses a facility site selection method based on a graph convolutional neural network. The method comprises the steps: carrying out the prediction and evaluation of all candidate position points through an inputted to-be-selected facility type, the spatial layout of built-up facilities in a current target range, and observable human activity intensity information, and selecting anoptimal position as a site selection result for output. Technically, modeling is carried out on the position relationship and the environmental characteristics of urban facilities through a model with strong spatial relationship depicting capability, namely a graph convolutional neural network, and objective and accurate urban facility candidate position prediction and evaluation are realized ina data driving manner by taking observed urban human activity data as a training basis of the model. The defects that target constraints are too subjective and the computing power is insufficient in the urban facility site selection problem are overcome, and the decision quality is improved. And an intelligent and objective facility site selection solution can be provided for a high-density and multi-attribute-dimension urban space.

The invention relates to the technical field of air traffic management, and provides an airspace network capacity prediction method in severe weather. The method comprises the following steps: dividing an airport terminal area into a plurality of sub-airspaces according to a historical track, constructing a space-time diagram convolutional neural network diagram structure data set based on an attention mechanism according to a severe weather time list and a set number of node features, and designing and training the space-time diagram convolutional neural network based on the attention mechanism, the method comprises the following steps: acquiring a neural network parameter mapped by a weather-to-capacity influence mechanism, inputting graph structure feature data by using a trained time-space graph convolutional neural network based on an attention mechanism, and carrying out capacity prediction on each sub-airspace of an airspace network. According to the method, the airspace network capacity is predicted more accurately, the decision quality and the refinement degree are improved, meanwhile, the interpretability of the model is improved, the model is closer to the manual control judgment effect of a controller, and the control pressure of an air traffic control department is effectively relieved.

The invention discloses an emergency treatment technology identification method for sudden watershed water pollution accidents and an emergency decision-making system. According to the method, firstly, a decision weight calculation method for identifying indexes is provided, an evidence theory synthesis rule is applied to introduce similarity coefficients among index evidences, n groups of weightscores given by n experts for different identifying indexes are fused into one group of decision weight scores, and the technical problem of weight conflicts among different expert scores is solved. According to the emergency treatment technology identification method for the sudden drainage basin water pollution accident, the decision weight calculation method is introduced, and the optimal decision quality is improved. According to the two-stage identification method optimized by the method, the calculation amount can be reduced, and the emergency decision making time can be saved. Accordingto the emergency decision-making system for the sudden drainage basin water pollution accident, the emergency response is divided into the daily work part and the optimal decision-making part, the emergency response time can be shortened on the premise that subjective opinion conflicts of experts are reduced, and real emergency decision-making is achieved.

The invention discloses a software quality evaluation method based on product line development. The software quality evaluation method is specifically implemented according to the following steps: step 1, determining quality evaluation factors of each stage of a development process; step 2, pre-processing A decision quality evaluation factor; step 3, determining the weight of each decision quality evaluation factor; and step 4, calculating a comprehensive evaluation value of the software quality. According to the software quality evaluation method based on product line development, the quality evaluation factors of all development stages can be calculated for software products based on product line development, and the weights of all the quality evaluation factors are distributed according to software characteristics to complete software comprehensive quality quantitative evaluation.

The invention discloses a dynamic service deployment method, system and device of the Internet of Vehicles and a storage medium. According to the method, a service request and environment data are obtained, a service deployment decision is generated through a strategy function according to the service request and the environment data, then a decision action and a decision response are obtained according to the service deployment decision, and then the service deployment is completed according to the decision action and the decision response. And generating a decision quality value of the service deployment decision through a value function, then determining a target service deployment decision from the service deployment decisions according to the decision quality value, and then performing service deployment on the service according to the target service deployment decision. The method is more in line with the actual dynamic scene, the response time of the service can be effectively shortened, and the resource balance of the edge server is kept, so that the emergency situation is effectively handled. The method can be widely applied to the technical field of the edge computing technology of the Internet of Vehicles.

The invention discloses a knowledge graph construction method and a device, a computer storage medium and a terminal. The method comprises the steps of obtaining event related data; analyzing the obtained event related data to obtain decision behavior information and decision influence information of each event; constructing a knowledge graph according to the obtained decision behavior informationand decision influence information of each event; wherein the event related data comprises one or any combination of event processing data, enterprise internal process data, sales analysis data, public opinion analysis data and other unclassified associated data. According to the method of the invention, the knowledge graph is constructed based on the decision behavior information and the decision influence information of the event, the application efficiency of enterprise internal data is improved, and information support is provided for improving the enterprise decision quality.

The invention relates to an boring enterprise product market strategy decision-making method and system based on product involving degree, and the method comprises the steps: S1, updating consumer involving degree information through market information, and constructing a market strategy through employing a market positioning rule, and the market strategy comprises a separation balance strategy and a hybrid balance strategy; respectively establishing profit functions of corresponding boring enterprises based on a separation equalization strategy and a hybrid equalization strategy; s2, on the basis of different market strategies, derivation is carried out on the profit function about the product quality and the advertisement input amount, and then a corresponding optimal price decision, a quality decision and an advertisement decision are obtained; and S3, bringing the optimal price, the optimal quality decision and the optimal advertisement decision into the corresponding market strategies to obtain the balanced profit of the boring enterprise, and taking the market strategy with the maximum balanced profit as the optimal boring enterprise product market strategy. The method provided by the invention has few solving steps, is easy to operate, and can quickly obtain the optimal product market strategy.