45results about How to "Effective decision-making" patented technology

Methods, apparatuses and systems facilitating the management of wireless computer network environments and the detection of rogue and other devices that may affect the performance and / or security of the wireless computer network. The present invention enables accurate and cost effective WLAN airspace mapping. In one embodiment, the present invention allows any conforming access point the ability to routinely scan its airspace, collect data on all operating frequencies and report this information back to a management platform. In one embodiment, the management and reporting functionality described herein uses a standards-based vehicle, such as Simple Network Management Protocol (SNMP). In one embodiment, the present invention allows for detection of all wireless traffic within or affecting an enterprise's computer network environment, picking up all active access points (Ad Hoc or Infrastructure) and all wireless clients data regardless of SSID, channel, or security settings. The management platform, according to an embodiment of the present invention, analyzes information received from the access points under management to detect and report the state of the computer network environment. In one embodiment, the present invention facilitates isolation of rogue wireless devices affecting the computer network environment and effective decision-making as to management of the detected device. The present invention also allows network administrators to optimize the configuration of the wireless network environment for performance and security.

The invention relates to the field of wisdom traffic information management and provides a 3DGIS+BIM-based road network operation comprehensive monitoring management platform and method. The platform comprises a 3DGIS+BIM fusion interactive application module, and a server module, a cloud service module, a video and event monitoring module, an electromechanical device module, a VR interactive module, a communication module, an emergency plan response module and a management and maintenance data analysis prediction module connected with the 3DGIS+BIM fusion interactive application module; the platform further comprises a data collection and transmission module and a sensor module; and the video and event monitoring module, the electromechanical device module and the sensor module are all connected with the server module through the data collection and transmission module. According to the platform and the method, comprehensive mastering of operation dynamic information can be effectively guaranteed; an emergency event can be timely discovered, quickly responded and effectively linked and handled, so that the management efficiency is greatly improved, the energy is saved, and the operation security is ensured; and in combination with the electromechanical device and control modules, operation management is orderly carried out, and intelligent and efficient operation management is achieved.

The invention provides a method for controlling the reporting of a plurality of measured results in measurement, which comprises the following steps: a terminal measures a measured target according to measured configuration information sent by a network side; if a measured result of an event meets the reported condition, the measured result is stored; judging whether a delay timer is started or not, if not, starting the delay timer; after the stop of the delay timer, the terminal reports the stored measured result. The invention also provides a terminal for realizing the method. When a plurality of events are triggered, the terminal can effectively report a measured report, reduce a load brought to a network due to excessive measured reports and lead the network to make a more effective policy on mobile management.

A repair system for flat panel display (FPD) substrates performs a number of operations, such as automatic image capture and processing, automatic defect classification, automatic repair classification, and repair macro (instruction) generation software. Defect classification, repair classification, and repair macro generation are based on an open architecture and can address any number of use-cases through the use of multi-tiered classifiers, and thus a wide variety of panel designs may be repaired within a single repair tool. The multi-tiered set of classifiers, e.g., defect classifier, repair classifier, enables an efficient decision-making repair process with capability for customization. The multi-tiered classifiers are optionally extended to support statistical learning (both online & batch) and active learning, in the context of a supporting database of defects and associated tools. The classifiers and recipe rules may be automatically or semi-automatically improved over time, incorporating lessons learned by operators while judging defect or repair needs.

A computer-based system for requesting, assigning, monitoring, updating, and reporting on the status of the collateral recovery process for all of the participants includes a communications methodology for maintaining a series of remote databases and synchronizing the remote databases with a master database via a synchronization server. Additionally, a lien holder can access the computer-based system via a global computer network such as the Internet and request collateral repossession services and then track the request during the process. This includes the ability to monitor the date of recovery, the condition of the collateral upon recovery, and the ultimate disposition of the collateral after recovery. Similarly, the repossession agent can more quickly and efficiently receive recovery requests and provide updates to the lien holder without undue delay. Finally, the computer-based system preferably provides a series of web-based reports that allow all of the participants in the collateral recovery process full and complete access to various performance criteria and measurements. By tracking the performance of the various parties involved in the collateral recovery process, the best service providers can be identified, thereby enhancing the prospect for efficient collateral recovery and providing for more effective decision-making.

The invention discloses an RFID asset supervision system based on the internet of things. The RFID asset supervision system comprises a fixed asset core database, a fixed asset management platform, an RFID reader-writer and an electronic tag. The fixed asset core database and the fixed asset management platform are connected through mutual communication. The fixed asset management system comprises an article information initialization module, an inventory management module, an asset depreciation management module, a monthly and annular asset report module, an asset situation inquiring function module, a warehouse security management module, an article consuming and returning module, a relevant law and regulation performance module and an asset manager management module. The acquisition mode of asset inspection data is changed so that inspection efficiency is greatly increased. Meanwhile, asset form management is also additionally arranged so that omnibearing, reliable and high-efficiency dynamic data and decision basis can be provided for asset management work of enterprises and public institutions, the problem of asset management of the enterprises can be effectively solved and thus the enterprises are enabled to perform asset management more easily and effectively.

The invention relates to the communication field, and provides a cluster communication terminal track real time anomaly detection method and system based on hybrid grid hierarchical clustering. The method comprises the steps: the step 1: constructing a track based on grids, and determining the size of the optimal grid; the step 2: calculating a Hausdroff distance matrix, utilizing a Hausdroff distance formula to calculate the distance between all the tracks based on the tracks of the grids, and generating a distance matrix of a track set; the step 3: hierarchical clustering, that is, based on the Hausdroff distance matrix of the track set, applying an agglomerate hierarchical clustering algorithm from bottom to top to realize classification of normal and abnormal tracks of a large scale of tracks; and the step 4: anomaly detection method evaluation and feedback: utilizing the above method to perform anomaly track detection on the track set which has a track classification identifier to obtain an anomaly classification result, and evaluating whether a model parameter is reasonable after comparison and making a feedback. The cluster communication terminal track real time anomaly detection method based on hybrid grid hierarchical clustering can realize on-line real time detection of an anomalous event, and can improve the upper layer dispatching efficiency of a cluster communication system.

The invention discloses an intelligent vehicle speed decision-making method based on a deep reinforcement learning method. The method comprises the steps of constructing a state space S, an action space A and an instant rewarding space R of a Markov decision-making model of an intelligent vehicle passing through an intersection; initializing a neural network, and constructing an experience pool; performing action selection by adopting an epsilon-greed algorithm, and filling the experience into the experience pool constructed in the step 2; randomly selecting a part of experience from the experience pool, and training a neural network by adopting a stochastic gradient descent method; completing the speed decision of the intelligent vehicle at the current moment according to the latest neural network, adding the experience to an experience pool, randomly selecting a part of experience, and carrying out the training of a new round of neural network. The invention further discloses a simulation method of the intelligent vehicle speed decision-making method based on deep reinforcement learning. The method is advantaged in that simulation experiments are carried out based on a deep reinforcement learning simulation system established by a matlab automatic driving toolbox.

A management of wireless and wired computer network environments in which rogue and other devices that may affect the performance and / or security of the wireless computer network can be detected. Specifically, the present invention discloses a method and system of detecting all interfaces, Media Access Control (MAC) addresses and radio MAC addresses (BSSIDs) affiliated with a rogue device and compiling this information into a database. As a result, the present invention reduces the number of alerts that one rogue device can generate and increases the accuracy and speed of locating the rogue device within a network.

The invention discloses a fire-extinguishing practice commanding application method, and the method comprises the steps: carrying out the data overlapping of fire information data, and forming an intelligent information network map service layer; carrying out the data modeling of the fire information data, and forming fire spreading trend information; carrying out the assessment of the fire spreading trend information according to a fire-fighting information level assessment standard; drawing the fire-extinguishing rescue disaster level information and rescue decision data through a three-dimensional map according to the fire-extinguishing rescue disaster level information; carrying out the overlapping of the intelligent information network map service layer and a commanding scheduling application layer as the fire-extinguishing practice commanding basis. The method achieves the systematic improvement of the cooperative combat capability of each participating department through the effect assessment in a simulation environment and practice application scenes for many times. The method enables a decision-making capability of a commander to be more precise and effective, and fire fighters can obtain the data information with the big-data analysis and support function. The method enables the fire extinguishing to be more reasonable, and can reduce the injuries.

The invention discloses a smart firefighting management system. The system comprises a front-end collector, a sensor module, a video monitoring module and a background server, wherein the sensor module and the video monitoring module are both electrically connected with the front-end collector to be used for collecting fire signals, and the front-end collector is in communicating connection with the background server. The system is characterized by further comprising a BIM building information service platform, a firefighting big data platform and an alarm used for being worn on a trapped person, wherein the alarm comprises a master control module, a GPS module, a speed sensor and a sound production module with adjustable frequency and volume. Through the smart firefighting management system, the trapped person can perform effective self-rescue along a shortest escape path in an optimal escape time before a rescuer arrives. Besides, the invention furthermore provides a control method applied to the smart firefighting management system.

The invention provides a regional wind power prediction method and system based on space-time quantile regression. The method comprises the following steps: collecting the operation and numerical weather prediction data of a plurality of wind power plants in a preset time period, converting the collected data into a feature map, and building a training set, a verification set and a test set; establishing a space-time quantile regression model, and training and optimizing the model by utilizing the training set, the training set, the verification set and the test set; acquiring operation data and environment data of each wind power plant in real time, and predicting regional wind power generation in a certain time period in the future according to the optimized space-time quantile regression model. According to the invention, short-term non-parameterized probability prediction is carried out on regional wind power through the space-time quantile regression model; the selection problem of explanatory variables in regional wind power prediction with large input information is solved, the prediction accuracy and reliability are greatly improved, and a specific solution is provided forregional wind power generation probability prediction with big data.

The invention discloses a planning method for determining first-aid repair paths, which comprises the following steps of: (1) defining three-dimensional geographic information of each road junction in a factory and calculating the corresponding relationship between equipment and the road junctions in the factory first; (2) if the malfunction of the equipment at the position of the factory occurs, calculating the optimum route from a rescue starting point to accident site by using a path optimization algorithm; and (3) calculating the rotating direction of each road junction on the optimum route, and presenting the process how breakdown lorries pass through from the starting point to the destination. The planning method has the advantages that: 1) any equipment can be set to generate malfunction in the factory, and any rescue starting point and the actual traffic volumes of different roads after the malfunction occurs can be set, and the optimum rescue route is calculated by utilizing the path optimization algorithm, which is favorable for the auxiliary decision after similar conditions occur in the reality; and (2) the sense of reality is increased by seeking the rotating directions of the breakdown lorries automatically and utilizing phenomena of firing and water spray, and operators obtain the real experience through the movement of the breakdown lorries in three-dimensional environment of virtual reality so as to contribute to the rescue command of the real conditions.

The invention provides a BIM standardized modeling method for a high-speed railway swivel bridge. The BIM standardized modeling method comprises the steps of data preparation, reasonable selection ofsoftware, creation of a bridge cast-in-place structural member, creation of a spherical hinge prefabricated member, creation of a site temporary facility, creation of a site layout model, fine correction, model space integration and the like. According to the method, BIM (Building Information Modeling) software is adopted, multi-source information of the swivel bridge component is integrated and recorded into a standardized component, so that various models on site are established, and the method is suitable for high-speed railway swivel bridges and other railway and highway swivel bridges andcan be used for visually guiding swivel bridge spherical hinge installation, bridge construction procedures and the like.

Systems and process for performing analytical processes on the health-related data for a person include components and steps for processing system multiple files from multiple sources containing health-related data for numerous individual. Such processing may include: staging health-related data; matching pieces of staged data to a person using one or more matching rules; compressing the matched staged data for the person into a compressed file through assignment of a universal identifier which is associated with the person; providing the compressed file to an analytics engine; and decompressing the at least one analytics results file using universal identifier to access the analytics results for the person. Additionally, the analytics results for the person may be provided to a user for intervention into the health of the person.

The invention discloses a coal mining subsidence water area calculation method, and relates to the field of surveying and mapping science and technology, and the method comprises the steps: carrying out aerial photography above the coal mining subsidence water area by using an unmanned aerial vehicle, and sequentially carrying out image distortion correction, cloud light processing and aerial triangulation encryption on an image to obtain a coal mining area ortho-image map; importing an orthographic image of a coal mining area into ArcGIS software, creating a new Shapefile file in Catalog of the ArcGIS software, carrying out surface editing, collecting water area boundary feature point data by using a visual interpretation method, and calculating a subsidence water area based on the boundary feature point data. The method solves the problems that the extraction of the subsidence water area is difficult due to the irregular subsidence water area terrain and the special humanistic environment of the coal mining area, and finally the calculation precision of the coal mining subsidence water area is low. A more effective decision is made for accounting the water resource quantity of the mining area and planning the application of the subsidence water area.

The invention discloses a knowledge-driven war game deduction intelligent decision-making method, and the method comprises the following steps: deducing an environment interval simulation step length to transmit situation information to an intelligent decision-making system, the situation information comprising a direct situation and an integrated situation; fusing the direct situation and the integrated situation by the intelligent decision-making system; determining a core target of an adversarial entity according to the scenario task, and dividing stage tasks of the adversarial entity according to the core target; performing entity control in combination with battlefield knowledge and intelligent decision by the confrontation entity; and distributing the priority of each instruction action under different scenario tasks. The task is divided into a plurality of core modules, battlefield knowledge is combined, and multiple intelligent algorithms are combined, so that the efficiency of the intelligent agent under the specified task is quickly improved.

The invention discloses a self-learning event extraction method and application thereof. The event extraction method comprises the steps that candidate words are subjected to self-learning screening through sentence vectors of event information and candidate word role mapping contained in each sentence vector, and a trigger word set is obtained; according to the invention, industrial production abnormal logs and other information can be quickly and accurately interpreted, and an appropriate decision is further made.

The invention discloses a shoe type recommendation system based on user foot features, and the system comprises a user foot three-dimensional scanner, a cloud server and a user mobile terminal, and totally comprises nine modules: a laser scanning module, a scene simulation module, a quick charging data communication module, an image processing module, a data storage module, a three-dimensional modeling module, an AR shoe trying module, and a shoe type recommendation module. According to the invention, the foot data of the user is obtained through the foot three-dimensional scanner of the user;the foot data of the user is processed and stored; and finally, a user foot three-dimensional model is constructed according to the obtained data. In addition, the AR shoe trying-on and shoe type recommendation functions are provided, the problems that the offline shoe trying-on process of a user is tedious, the user cannot find needed shoes smoothly online, and shoes selected online are inappropriate are solved; the user can check the footwear footwear effect without going out, meanwhile, a decision is effectively provided for the user, and therefore the online shoe purchasing process is completed smoothly.

The invention provides a commodity sales prediction method, a server and a storage medium. The commodity sales prediction method comprises the steps of extracting historical data of commodities purchased by an enterprise and to-be-predicted enterprise data; Training each prediction model in a historical data training model set according to the historical data; And predicting the to-be-predicted enterprise data by using the trained prediction models to obtain the sum of commodities purchased by each enterprise and the total sales sum of the commodities. According to the method, prediction results of multiple models are integrated to obtain a final prediction result, so that the prediction accuracy of employee welfare commodities is improved; According to the method, the sum of commodities purchased by each enterprise can be predicted; By means of the method, the platform where the employee welfare commodities are located can make more effective decisions when the enterprise is developed, the total sales sum of the employee welfare commodities can be predicted, and the platform where the employee welfare commodities are located makes more effective decisions for commodity operation and the like.

The invention discloses a planning method for determining first-aid repair paths, which comprises the following steps of: (1) defining three-dimensional geographic information of each road junction in a factory and calculating the corresponding relationship between equipment and the road junctions in the factory first; (2) if the malfunction of the equipment at the position of the factory occurs,calculating the optimum route from a rescue starting point to accident site by using a path optimization algorithm; and (3) calculating the rotating direction of each road junction on the optimum route, and presenting the process how breakdown lorries pass through from the starting point to the destination. The planning method has the advantages that: 1) any equipment can be set to generate malfunction in the factory, and any rescue starting point and the actual traffic volumes of different roads after the malfunction occurs can be set, and the optimum rescue route is calculated by utilizing the path optimization algorithm, which is favorable for the auxiliary decision after similar conditions occur in the reality; and (2) the sense of reality is increased by seeking the rotating directions of the breakdown lorries automatically and utilizing phenomena of firing and water spray, and operators obtain the real experience through the movement of the breakdown lorries in three-dimensionalenvironment of virtual reality so as to contribute to the rescue command of the real conditions.

The invention discloses a multi-peak value judgment-based dim small target tracking loss redetection method. The method comprises the steps of selecting a search domain of target redetection in a to-be-detected image after a tracked target is lost; calculating a grayscale Gaussian distribution feature F of a frame image before the tracked target is lost, performing frequency domain response valueanalysis on the grayscale Gaussian distribution feature F in the search domain to obtain a frequency domain response graph, taking the size of the tracked target as a boundary, extracting 4-7 regionscomprising local peak values in sequence from the frequency domain response graph and recording peak value information of the regions; replacing tracked target image information in the frame image before loss to the central position of the search domain, and calculating the grayscale Gaussian distribution feature F of the tracked target and a response value delta of the central position of the search domain after replacement; comparing difference values between the 4-7 peak value information with the response value delta, and searching for a peak value position with the minimum difference value and a difference value ratio less than 20% to serve as position information of tracked target redetection. The method can quickly and effectively determine the position information of the lost tracked target.

The invention discloses a consciousness and subconsciousness-based parallel decision-making system and method. An L-Y parallel decision-making model is longitudinally divided into two parallel decision-making parts representing consciousness and subconsciousness; wherein the representative consciousness comprises a viewpoint set, a willingness set and a target set, input information generates viewpoints, and different information generates a viewpoint set after being catalyzed; the subconsciousness comprises a potential viewpoint set, a potential intention set and a potential target set; the viewpoint set with a large proportion of influence on events is a viewpoint set, and the viewpoint set with a low proportion is a potential viewpoint set; wherein the willingness set and the target setare the same; the l-Y parallel decision-making model transversely comprises a viewpoint set and a decision-making set, and the decision-making set is composed of a willingness set and a target set and is output through a constraint set through dynamic balance. According to the dynamic balance process, the subconsciousness and the representative consciousness can be accurately reflected in a target result to be output, and an effective decision is formed.

The invention discloses an urban dynamic and static intelligent traffic management platform, which belongs to the field of intelligent traffic and aims to provide an intelligent traffic management platform for improving the operation efficiency of urban traffic. , a traffic guidance system, a public traffic monitoring system, and a traffic data collection system, which are used to collect static traffic information and dynamic traffic information in real time and send them to the big data management system; the big data management system is used to collect static traffic information and dynamic traffic information The information is statistically analyzed and processed to generate dynamic traffic information, static parking space information, dynamic preferred routes and static preferred parking spots; the traffic guidance system is used for static traffic guidance and dynamic traffic guidance; the public traffic monitoring system is used for overview Traffic overview, overall management. Create an "integrated management service platform for urban dynamic and static smart traffic" based on Internet+, Internet of Things, and cloud platforms.

The embodiment of the invention provides a game decision-making method and system. The game decision-making method comprises the steps that a server side predicts data of an unknown state of an imperfect information environment according to data of the known state of the imperfect information environment based on a pre-trained environment prediction model, and an effective prediction result of thedata of the unknown state of the imperfect information environment is obtained; and the server makes an effective decision according to the effective prediction result of the data of the known stateof the imperfect information environment and the data of the unknown state of the imperfect information environment based on a reinforcement learning model. The game decision-making method can predictthe data of the unknown state of the imperfect information environment according to the data of the known state of the imperfect information environment so as to make an effective decision.