178 results about "Fusion system" patented technology

The present invention relates to pattern recognition and classification, more particularly, to a system and method for meta-recognition which can to predict success / failure for a variety of different recognition and classification applications. In the present invention, we define a new approach based on statistical extreme value theory and show its theoretical basis for predicting success / failure based on recognition or similarity scores. By fitting the tails of similarity or distance scores to an extreme value distribution, we are able to build a predictor that significantly outperforms random chance. The proposed system is effective for a variety of different recognition applications, including, but not limited to, face recognition, fingerprint recognition, object categorization and recognition, and content-based image retrieval system. One embodiment includes adapting machine learning approach to address meta-recognition based fusion at multiple levels, and provide an empirical justification for the advantages of these fusion element. This invention provides a new score normalization that is suitable for multi-algorithm fusion for recognition and classification enhancement.

The invention discloses an infrared and visible light image real-time fusion system based on a heterogeneous multi-core architecture. The system uses a heterogeneous multi-core processor, with an ARM core and a DSP core as cores, to take charge of the control flow and the data sending and receiving and processing logic of the whole system, complete video data collection and real-time enhancing and fusion of infrared and visible light images, and display and output the video data after fusion. The ARM core is responsible for real-time data collection of both infrared light and visible light video data and real-time transmission of compressed data after image fusion. The DSP core is responsible for registration preprocessing and image enhancement preprocessing of the infrared light input image, real-time fusion of the infrared light and visible light video data, and real-time encoding compression of the video data after fusion. A three-layer Laplacian pyramid structure is used for the real-time fusion. The system is high in computation efficiency, good in compatibility, high in extensibility and adaptability, and convenient and highly efficient in software developing.

The invention discloses a management scheduling technology based on a hyper-converged framework. The method comprises a hyper-converged system architecture design, resource integrated management basedon a hyper-converged architecture, unified computing virtualization oriented to a domestic heterogeneous platform, storage virtualization based on distributed storage, network virtualization based onsoftware definition and a container dynamic scheduling management technology oriented to a high-mobility environment. According to the management scheduling technology based on the hyper-converged framework provided by the invention, the virtualization capability and the management capability of the tactical cloud platform are improved; a key technical support is provided for constructing army maneuvering tactical cloud full-link ecology; an on-demand flexible virtualized computing storage resource pool is provided, heterogeneous fusion computing virtualization is achieved, meanwhile, a distributed storage technology is used for constructing a storage resource pool, a software definition technology is used for constructing a virtual network, a super-fusion resource pool is formed, localization data and network access of application services are achieved, the I / O bottleneck problem of a traditional virtualization deployment mode is solved, and the service response performance is improved.

The invention provides a hyper-converged system for providing service for edge computing. Aiming at the special requirements of an edge computing scene on artificial intelligence computing, information security, storage capacity and application software deployment, a high-performance computing platform which is high in performance, low in power consumption and capable of effectively using space isrealized through software and hardware integration. Edge calculation relates to a large amount of data acquisition and data processing (machine learning model reasoning operation), and the deploymentis close to an application place, so that strict requirements on space and power consumption are met. For the diversity of applications, sufficient flexibility needs to be provided in the aspect of deployment of software systems and software applications. According to the invention, a special computing platform for effectively solving technical challenges faced by edge computing equipment is designed; a safe and convenient means is provided for integrating various special hardware acceleration devices to construct an edge computing application through a container virtualization software technology, and various edge computing scenes with extreme requirements on computing and data capacity can be effectively adapted.

The invention provides a cloud native development component system, which comprises a micro-service architecture system used for constructing a micro-service architecture of a platform in a cloud native technology; a fusion system which is used for combining a plurality of development tools and fusing the development tools into the micro-service architecture system; a development platform which isused for obtaining a cloud native development component based on the micro-service architecture system and the fusion system, and multiplexing the application or the cloud native development component; a support platform which is used for deploying the cloud native development component; and a component market which is used for publishing the information of the cloud native development componentand carrying out authorization distribution on the component according to a user request. The method is used for helping a user to quickly develop or deploy related application software and componentsbased on the Kubernetes cloud environment, and meanwhile, a construction market for application and component authorization distribution in the cloud native environment is provided.

The invention discloses a statement sorting method and system applied to an answer fusion system. The method comprises the following steps that: preprocessing input target data to obtain a statement pair of an index form, wherein the statement pair is a candidate answer; carrying out feature extraction on the statement pair to obtain the relationship probability of every two adjacent sentences inthe statement pair; according to the relationship probability and a solution space retrieval algorithm, obtaining a sorting result, wherein a target function solved by the retrieval algorithm is Score(s,o)= [Sigma]<k>i=1[Sigma]<k>j=i+1 score (s,o,i,j); and according to the sorting result, obtaining a target answer. The step of carrying out feature extraction on the statement pair to obtain the relationship probability of every two adjacent sentences in the statement pair comprises the following steps that: judging whether sentences in the statement pair are in a sequential order relationshipor not, utilizing a seq2seq model based on an attention mechanism to carry out feature extraction on the statement pair, and inputting an extracted feature into a feedforward neural network to obtaina sentence sequential order probability. By use of the method, sentences extracted from different answers can be sorted, so that the obtained target answer is smooth, is favorable for understanding and is high in readability, and user experience is improved.

The invention discloses a heterogeneous storage and calculation fusion system and method supporting deep neural network reasoning acceleration, and the system comprises a host processor which is usedfor controlling and managing the whole heterogeneous storage and calculation fusion system; a nonvolatile memory module which is connected with the host processor and used for neural network processing; a 3D stacked memory module which is connected with the host processor and used for neural network processing; a network module which is connected with the host processor and used for being connected with an external host; a configuration circuit which is connected with the host processor, and is used for receiving a configuration command of the host processor and controlling a voltage generator, and is also used for receiving the configuration command of the host processor and configuring a 3D stacked memory module; and a voltage generator which is respectively connected with the nonvolatile memory module and the configuration circuit and is used for receiving the control command of the configuration circuit, applying external excitation to the nonvolatile memory module and adjusting the conductivity state of the nonvolatile memory module.

There are disclosed techniques for performing data fusion. In one embodiment, the technique comprises: (a) receiving an input; (b) processing the input in accordance with parameters of a stochastic model to derive a state of a stochastic process of the stochastic model, the parameters of the stochastic model previously established during a training period; (c) obtaining a predicted next state of the stochastic process; (d) receiving a next input and processing the next input in accordance with the parameters of the stochastic model to derive a next state of the stochastic process; (e) comparing either (i) the next state and the predicted next state, or (ii) the next input and a predicted next input corresponding to the predicted next state; and (f) if there is a discrepancy between that compared in (e), then using the next input to modify the parameters of the stochastic model.

The invention discloses a fusion system for infrared images and low-illumination images. The fusion system comprises a low-illumination optical lens group, an infrared optical lens group, a synchronous focus control device, a low-illumination image sensor, an infrared image sensor, a low-illumination image sensor driving module, an infrared image sensor driving module, an image sensor simulation front end, a low-illumination image signal processor, an infrared image signal processor, a synchronous signal generator, a synchronous image collection module, a digital image processing module, an image display control module, a microdisplay, a display magnifying lens group, a power supply module, a processor peripheral circuit and a display switching key. According to the fusion system, two-way synchronous focus control of an infrared and low-illumination video is realized optically, and complexity of a back-end registration algorithm is reduced; with the adoption of an embedded type multicore heterogeneous processor, performance of image collection control and real-time algorithm treatment is guaranteed; three-type display switching of infrared, low-illumination and pseudo-color fusion video can be realized.

The invention relates to the field of intelligent power grids, in particular to a multi-station fusion system operation situation anomaly monitoring and alarm merging method, which comprises the stepsof training an anomaly detection model based on historical data of a power multi-station fusion system, and determining an abnormal value threshold; obtaining time sequence data of the operation situation of the power multi-station fusion system in real time, inputting the processed time sequence data into a trained anomaly detection model to obtain an anomaly score of the data, comparing the anomaly score with an anomaly value threshold, and determining anomaly information; based on the historical alarm data information, mining the correlation between the alarm information, and determining an association rule; and determining the category and the emergency degree of the anomaly information, generating corresponding alarm information, and completing combination and output of the alarm information based on the association rule. According to the invention, combination and output of alarm information are realized, and effective detection of anomaly data in time series data in operation and maintenance of the power multi-station fusion system is realized.

The invention divides a microgrid control structure into a communication system and a physical system based on the concept of an information physical fusion system, and a novel distributed control strategy is proposed on this structure to improve a control effect of voltage and angular frequency by traditional droop control. Firstly, a microgrid communication system model is proposed based on graph theory knowledge, and communication structures of a plurality of single distributed power supplies form an integral communication system; secondly, in the communication system, a method combining areverse neural network and prediction control is proposed to solve the problem of communication time lag; a novel consistency protocol with a virtual navigator is proposed to solve the problem of packet loss; thirdly, in the physical system, P-omega / Q-U droop control is used as primary control of voltage and angular frequency; and finally, voltage and angular frequency data in the communication system and the proposed novel consistency protocol are utilized to complete secondary control of voltage and angular frequency output by droop control in the physical system, and the control strategy has a distributed cooperative characteristic.

A converged system and migration method capable of preventing system performance degradation with respect to data transfer is proposed. A first calculation node continues executing I / O processing in response to an I / O request from an application; and, upon execution of the I / O processing, the first calculation node issues an I / O processing event notice indicating a transfer status of data on which the I / O processing has been executed. When receiving a migration command from a migration management unit, a second calculation node judges whether or not data stored in a first I / O node is data which should be transferred, based on the I / O processing event notice; and then transfers the data, which should be transferred, to a third calculation node.

The invention discloses a BI system multi-source database cross-source cross-database fusion system and a fusion method. The system comprises an external service database, a data processing engine anda data storage module. The data storage module includes a traditional relational database and a big data database. The external business database connects the traditional relational database and thebig data database through the data processing engine. The data processing engine reads the external data stored in the external business database, then encapsulates the external data into the fusion data set through the data fusion component, and finally inserts the fusion data set into the data storage module through the extraction component. The system of the invention realizes the fast cross-source and cross-database data fusion on a BI system, does not need to use a third-party ETL tool and does not need to write a complex script language, supports large data warehousing based on Hadoop, and adopts a bottom-level distributed computing framework to realize the data processing and fusion of the data of TB and PB-levels.

The invention discloses a cyber-physical fusion-oriented building information model (BIM) expansion method. The method is used for building construction and operation and maintenance process measurement and control based on a BIM, construction of application software platforms of augmented-reality human-machine interaction and the like and the like, and realizes coupling, linking and state consistency between BIM entities in virtual space and physical building entities in real space. According to the method, a BIM framework based on an IFC (Industrial Foundation Class) is expanded on the basis of conception and thinking of cyber-physical systems (CPS), four new object entities are defined inside the traditional BIM framework, the four objects are associated with other building objects (such as doors) in the BIM framework through related connection mechanisms, the virtual building objects are enabled to have perception, decision-making, control and animation ability, and dynamic interaction to physical building objects is realized. The method accords with application requirements of BIM technology for future dynamic interaction processes, and is compatible with mainstream BIM technology standards.

The invention relates to a data fusion system based on a data evaluation and system coordination module and a working method of the data fusion system. The data fusion system comprises an informationcollection module, an information processing module, an application and feedback module, the data evaluation and system coordination module, a knowledge base module and a data base module. A data analysis and algorithm selection mechanism of the data evaluation and system coordination module performs two times of analysis before and after on collected data through data itself and expert or user feedback information, so that an algorithm suitable for a current data fusion system is determined to coordinate module resources of the system. The introduction of data evaluation and system coordination enables the system to perform ''act according to actual circumstance'' on the data during answering the specific data under the premise of meeting the user requirements, a suitable processing method is selected, the selective rationality of the algorithm and the universality of the system are ensured, the whole data fusion process is more flexible and efficient, and the result is more reliable.

The invention provides a forward fusion system for advanced driving assistance. The forward fusion system comprises an automobile-mounted TBOX, a camera and a radar which are connected in sequence, wherein the TBOX receives the roadside information and transmits the roadside information, each of the camera and the radar comprises a target detection module, a fusion module and a function module, and the target detection module detects to obtain the corresponding target information, the camera and the radar fusion module respectively fuse the corresponding automobile-mounted target information and the roadside target information, and then combine the automobile-mounted target information and the roadside target information with the roadside map information or other target information, and the function modules respectively realize different ADAS functions according to the fusion information, the automobile body information and the like of the corresponding fusion modules. The invention further provides a forward fusion method. The forward fusion system for advanced driving assistance is advantaged in that the automobile-mounted information and the roadside information are fused, different strategies are adopted for fusing the automobile-mounted information and the roadside information in the radar ECU and / or the camera ECU, different ADAS functions are achieved, and the minimum time delay can be achieved.

The invention discloses an interconnection fusion method for a heterogeneous industrial network. The method comprises the following steps of: setting a general industrial field network connection fusion system, and periodically detecting and analyzing link layer data in the heterogeneous network by the general industrial field network connection fusion system; generating a network management strategy file and storing the network management strategy file in a memory of a reconfigurable control module; and loading a corresponding network management strategy file, and downloading a compiled specific configuration bit stream file to an FPGA subsystem of the reconfigurable control module to complete network reconfiguration. The invention further discloses a system for implementing the method. The system comprises the reconfigurable control module, a reconfigurable wireless module and a universal wired communication module which are connected with one another and communicated with one another. According to the invention, interconnection and intercommunication between heterogeneous devices and networking acquisition of industrial data can be realized, so that the devices have interoperability and interoperability, and flexible networking and reconstruction are easy to realize, thereby promoting the process of automatic and intelligent upgrading and reconstruction of the industrial devices.

The invention discloses a clinical research and follow-up fusion system and method. The system comprises the components of an information acquisition unit which is configured for acquiring historicalmedical record information of a patient and acquiring current health data of the patient based on follow-up information of the patient; an information extracting unit which is configured for extracting a clinical diagnosis-and-treatment plan for treating the affected disease of the patient from the historical medical record information, and extracting a current symptom of the patient from the current health data of the patient; a processing unit which is configured for determining a reoccurrence probability of the affected disease of the patient according to the current symptom of the patientand a pretrained predicting model, and in response to a fact that the reoccurrence probability is higher than a preset threshold, analyzing the clinical diagnosis-and-treatment plan for determining apotential hazard factor which causes the reoccurrence; and a pushing unit which is configured for pushing the potential hazard factor that causes the reoccurrence to a doctor client for assisting a doctor in adjusting the clinical diagnosis-and-treatment plan and pushing a further diagnosis notification to a patient terminal. The system according to the invention facilitates optimization of the diagnosis-and-treatment plan by the doctor to the patient.

The invention discloses a fusion method of multi-source heterogeneous data for an urban brain scene. The fusion method comprises the following steps: converting the multi-source heterogeneous data into multi-source data in a unified format; superposing and analyzing the multi-source data in the unified format according to the unified space reference; normalizing attributes of the multi-source datain the unified format; performing spatial position alignment on the normalized multi-source data in the unified format, and unifying a coordinate system; fusing the multi-source data in the unified format; constructing a data model by taking urban governance business as a guide. The invention further discloses a fusion system of the multi-source heterogeneous data for the urban brain scene. The multi-source heterogeneous data fusion method and system for the urban brain scene aim at solving the problem that fusion cannot be achieved due to the fact that data of all industries is not unified in urban governance.

The invention discloses an intelligent substation reliability evaluation method based on an information physical fusion model. Firstly, an information physical fusion system model capable of reflecting an electric power primary system and an information network topological structure is constructed, and then reliability indexes of all equipment nodes are obtained according to actual operation conditions for the electric power primary system side of an intelligent substation; reliability indexes of all devices and communication links are analyzed based on an analytic hierarchy process for the information network side, and then the mode and the process of the interaction effect of the electric power primary system and the information network are analyzed in detail, and a method for quantitatively analyzing the interaction effect of the electric power primary system and the information network is proposed, thereby obtaining the reliability index of the electric power primary system side ofthe intelligent substation under the interaction effect of the electric power primary system and the information network. The reliability evaluation method of the intelligent substation is provided based on a Monte Carlo simulation method accordingly. The analysis result is accurate and reliable, and the evaluation result better conforms to the actual operation condition.

The invention provides a fusion method and a fusion system for a spacecraft power supply and distribution big image and energy simulation data. The method comprises the steps of: acquiring variations of driving parameters of entity objects in the power supply and distribution big image in real time, sending the variations of the driving parameters to an energy simulation model library to carry out energy simulation, and generating the energy simulation data, wherein the driving parameters of the entity objects comprise an electrical characteristic variable, a driving parameter of a dynamic component, a driving parameter of a simulation animation flight orbit and a driving parameter of a key curve; and receiving the energy simulation data in real time and matching the energy simulation data into the power supply and distribution big image to carry out display output. According to the fusion method and the fusion system which are provided by the invention, by establishing the energy simulation model library matched and related with the driving parameters of the entity objects in the spacecraft power supply and distribution big image, acquiring the simulation data according to a single-step solution step length, carrying out automatic fusion, distinguishing and regulation and attaching the simulation data to display objects of the power supply and distribution big image, information fusion of the spacecraft power supply and distribution big image and the energy simulation data is implemented, and digital modeling, simulation, analysis and verification are implemented.

The invention discloses a method for accelerating decoding of a camera video stream through a programmable GPU in a virtual-real fusion system. The method comprises the steps of obtaining an originalYUV video; Creating a single-channel texture for the pixel flow of each frame of YUV image and transmitting the single-channel texture to the GPU; Drawing a three-dimensional virtual scene, and judging whether the current pixel belongs to a camera image or not; And mixing the RGB pixels and the three-dimensional scene to form a final virtual-real fusion image. Compared with a traditional method for decoding YUV video pixels on a CPU in a multi-thread mode, more original video pixels which do not need to be sampled can be effectively cut, and meanwhile the decoding efficiency is greatly improved on the basis of a GPU with higher parallel decoding capacity. The method is clear in algorithm and robust in result, can be applied to fusion application of a large three-dimensional virtual scene and real-time monitoring, and can be well combined with a video of a current mainstream camera manufacturer for use.

The invention discloses a traffic behavior fusion system based on multi-source heterogeneous sensor information. The traffic behavior fusion system comprises an information acquisition unit, a multi-source information database, a traffic behavior matching unit, a behavior fusion unit and a traffic behavior output unit. The invention further provides a fusion method based on the fusion system, existing various sensors are used as multi-source information acquisition equipment, detected traffic behaviors are collected to the multi-source information database, the multi-source information database carries out data space-time synchronization and redundancy processing on the acquired multi-source information, and a detection target and the traffic behaviors of the detection target are distinguished. And then behavior fusion is performed on the traffic behaviors detected by the information sources, so that the current traffic behavior is further determined, the speed and accuracy of trafficbehavior identification are improved, and the fitness of the traffic behavior identification in a bad detection environment is enhanced.

A semantic augmentation system includes a sensor with a computing system and a memory in communication with the computing system, the memory storing a plurality of endpoints. The computing system is configured to infer a first and a second semantic identity for an object, based on inputs from the sensor, project a coherent narrative and perform semantic augmentation towards a user. In further examples, the system infers a first narrative comprising two semantic identities and a second narrative wherein the system infers that a user observing view didn't infer the second semantic identity and further doesn't use the second semantic identity in the second narrative. It further, uses the corresponding narrative to remind the user to carry an item and / or credential in order to start an activity.

The invention discloses a method for carrying out modeling on an information physical fusion system by using AADL-Modelica. An information system and a physical system of the information physical fusion system are respectively modeled by using the AADL and the Modelica. Aiming at the problem that AADL cannot describe inter-state probability migration and inter-component detailed communication, a probability behavior attachment is provided. As a supplement of the AADL, the Modelica language uses a differential algebraic equation to model the continuous dynamics of the physical system. The method comprises the following steps: according to a mapping rule of AADL and Modelica; and correspondingly expanding the attribute set of the AADL, converting the model established by Modelica into an AADL model, fusing an information system and a physical system in the information physical fusion system, and analyzing the delay time in the information physical fusion system by using Osate. On the basis of Modelica and AADL modeling, Z specifications are adopted to carry out formalized constraint on a large amount of data generated in the system interaction process.

The invention belongs to the technical field of network security, and relates to a multi-protocol VPN gateway fusion system and method. The multi-protocol VPN gateway fusion system comprises a fusion server, a first VPN device and a second VPN device, wherein the first VPN equipment and the second VPN equipment are used for receiving / transmitting VPN ciphertext data packets, and the fusion server is used for performing VPN protocol conversion and / or forwarding on the VPN ciphertext data packets transmitted between the first VPN equipment and the second VPN equipment; the fusion server comprises more than one Docker container, an external VPN protocol gateway, a physical network card, a system kernel, a first virtual network card and a second virtual network card; one inner VPN protocol gateway is correspondingly arranged in each Docker container, and the outer VPN protocol gateway is arranged outside the Docker container. According to the invention, two or more VPN protocol gateways are quickly fused through the Docker container, hardware resources are saved, so that convenience and rapidness are achieved, and the serial communication requirements of various VPN protocols can be quickly met.

The invention relates to a hyper-fusion system data localization storage method based on a node evaluation function, and relates to the technical field of data storage. A centralized distributed storage system is used as a bottom storage device of the system, a mode that a local physical node and a plurality of far-end physical nodes jointly maintain data copies is adopted, a data block of a virtual machine instance in the system stores a main copy at the physical node where the data block is located, data balance distribution between the nodes is considered, the hardware performance and the relative storage utilization rate of the physical nodes are comprehensively considered, the other two far-end physical nodes are selected to store the second data copy and the third data copy, complete localization storage of virtual machine data is guaranteed, and therefore when the virtual machine reads the data, needed data can be directly read from the physical node where the virtual machine is located, the data reading I / O path of the virtual machine is shortened, cross-physical-node reading is avoided, and the data reading delay of the virtual machine is reduced.

The invention discloses a GBAS and SBAS fusion system based on a global satellite navigation system. The fusion system comprises a ground reference receiver, a ground central processing station, very high frequency equipment, an uploading injection station and a ground data link network. According to the fusion system provided by the invention, the existing GBAS and SBAS systems are subjected to ground end integration, so that GBAS and SBAS services can be provided at the same time, and the fusion system can be used for providing precise navigation positioning and integrity services of ground-based enhancement and satellite-based enhancement in a GNSS (Global Navigation Satellite System) enhancement system. The system has the following advantages that the ground end integrates the GBAS system and the SBAS system, so that the practicability is high; the cost of respectively arranging the GBAS and the SBAS is effectively reduced, and the aim of economy is fulfilled; a mode of fusing the GBAS and the SBAS at a ground end is adopted, and two alternative enhancement modes of the GBAS and the SBAS are provided for a user by using one set of equipment, so that the method is more practical.

The invention provides a fusion system for satellite network management and satellite measurement and control, and an application method and a deployment method thereof. The fusion system comprises an application service system, a satellite network management system and a satellite measurement and control system. Through the fusion system, a master station operator carries out unified management on the FDMA satellite communication network and the TDMA satellite communication network on different interfaces of one piece of software, and the purpose of convenient management is achieved. On the other hand, interaction with satellites is achieved by fusing a satellite measurement and control system, and the efficiency of managing and configuring satellite resources is further improved.

The invention discloses an optimization method for multi-station fusion site selection planning. The method comprises the following steps: A, constructing a multi-station fusion system architecture by a transformer substation, a data center, a charging station, an energy storage station and a photovoltaic power station; b, constructing different load distance cost coefficients of each single station, and establishing a multi-station fusion site selection mathematical model by taking the minimum load distance cost as a target; and C, optimizing the objective function by using a particle swarm algorithm, and selecting an optimal site. According to the invention, multi-subject planning problems are fused into unified subject planning, and a multi-target subject with unified standard measurement is constructed; when the load distance is calculated, different load distance cost coefficients are set by considering the differences of the transformer substation, the data center, the charging station and the photovoltaic power station; in addition, a particle swarm algorithm is used for calculating and analyzing multi-station site selection, and an optimal station site is selected; in practical application, the obtained optimal candidate site is compared with an existing substation, the substation most suitable for transformation is screened out, and reference opinions are provided for implementation of a multi-station fusion project.