236 results about "Smart applications" patented technology

The invention discloses an intelligent application management system of an automobile in the internet. The intelligent application management system comprises a consumption point unit, a client software unit and an internet computer management platform. The consumption point unit and the client software unit are respectively connected with the internet computer management platform network. The consumption point unit comprises geographic information, a longitude and latitude coordinate module and a vehicle information acquisition module, a vehicle identification processing module, a vehicle billing processing module and a main control module. The client software unit comprises satellite positioning longitude and latitude coordinate information, registration user information and internet payment information. The internet computer management platform comprises registration user information, registration vehicle information and internet payment information corresponding to the client software unit. According to the invention, rapid and convenient payment can be realized when the vehicle is consumed; the license plate and the fake board in the vehicle safety problem are improved when the vehicle is parked conveniently; theft and effective management can be realized, and the parking space resources can be quickly shared.

A method and an apparatus for organization and detection of homogeneous and heterogeneous swarms of devices and application of swarm intelligence using swarm intelligence framework are provided. The Swarm Intelligence Framework provides a generic platform for realizing solutions involving Swarm Intelligence Technology via flexible container-based Algorithm Plug-in Architecture which is essential to utilize Swarm Intelligence Framework for various scenarios and use cases, including dynamically loading and using the Swarm Detection Algorithm.

The invention discloses a method for deploying a cache-based deep neural network on decentralized edge equipment in a distributed manner. The method comprises the following steps: dividing a neural network; pruning is carried out on the previous layer of neural network at the division position; then, a part of the deep neural network is calculated in the task initiating device; a small number of intermediate results are transmitted to other edge equipment; and calculating the remaining portion, in addition, caching and reusing an intermediate result of the edge device neural network; differentdevices can share cache, so that the delay of an edge intelligent application is reduced, the requirement of a neural network for the performance of the edge device is reduced, and particularly, whenan intelligent task request is initiated to similar data on the edge side, the repeated calculation amount can be reduced, the performance requirement of deep learning for the device is reduced, andthe calculation resources of an edge scene are fully utilized.

A method and a system are provided of testing AI applications / systems on a System for testing one or more artificial intelligence System (STAIS) connectable to under-test AI systems (UTAIS) via the AI test connectors / interfaces through AI test platform. The method includes test modeling, data preparation, testing script generation, testing automation, and quality assurance. The system automatically identifies, analyzes, and displays all quality issues of UTAIS.

The invention provides an application management method of a smart television and the smart television. The application management method of the smart television comprises the steps of judging whether a television application belongs to traditional television applications when a command of starting any television application is received; applying to a resource management service for processing resources through a traditional application management service when the television application is judged to belong to the traditional television applications so that the television application can be processed, or else, releasing the applied processing resources through the traditional application management service, wherein the traditional application management service is used for applying for or releasing the processing resources used for processing the traditional television applications, and the resource management service is used for managing the processing resources of the smart television. According to the technical scheme, the difficulty for developing the traditional television applications can be reduced, the time for developing the traditional television applications can be shortened, and meanwhile, resource contention caused by unreasonable resource distribution between the traditional television applications and intelligent applications is avoided.

The invention discloses a method for accelerating multi-exit DNN (Deep Neural Networks) reasoning by a heterogeneous processor under edge computing, which comprises the following steps of: firstly, respectively counting the computing cost of each layer of a deep neural network on a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit) under different loads, the classification capability of each layer exiting a branch exit in advance and the intermediate data volume of each network layer; then analyzing the data to obtain an optimal parallel combination model for distributing each layer of the deep neural network to a CPU (GPU) processor under a specific load condition; and finally, the load conditions of the CPU and the GPU and the current computing power are monitored and analyzed on a terminal device on line, a deep neural network reasoning task is segmented with the purpose of minimizing reasoning time delay, task blocks are distributed to the GPU and the CPU respectively, and finally a reasoning acceleration framework based on a heterogeneous processor is formed. According to the method, the reasoning flexibility can be improved, the accuracy is ensured, the reasoning total time delay is reduced, and the real-time and high-precision requirements of edge intelligent application are met.

Systems and methods for implementing an application programming interface (API) that controls operations of a machine learning tuning service for tuning a machine learning model for improved accuracy and computational performance includes an API that is in control communication the tuning service that: executes a first API call function that includes an optimization work request that sets tuning parameters for tuning hyperparameters of a machine learning model; and initializes an operation of distinct tuning worker instances of the service that each execute distinct tuning tasks for tuning the hyperparameters; executes a second API call function that identifies raw values for the hyperparameters; and generates suggestions comprising proposed hyperparameter values selected from the plurality of raw values for each of the hyperparameters; and executes a third API call function that returns performance metrics relating to a real-world performance of the subscriber machine learning model executed with the proposed hyperparameter values.

The invention relates to a heat supply network real-time data warehouse system. The system comprises a data access module, a real-time calculation module, a big data storage subsystem and a data application module; the data access module is used for carrying out partition storage on acquired data in a standard format; the real-time calculation module is used for carrying out detail summarization and application processing according to the acquired data and outputting a summarization result and an application processing result to the big data storage subsystem, the detail summary is a process of associating the unit real-time data with the related dimension data, and the application processing is a process of performing data processing according to business requirements; the big data storage subsystem is used for storing the data output by the real-time calculation module by adopting a data model; and the data application module is used for carrying out multi-dimensional analysis, artificial intelligence application or business intelligence application on the data stored in the big data storage subsystem. Integration of heat supply network data can be realized, and standardized multi-dimensional analysis of the data is realized.

The invention discloses a distributed artificial intelligence application development system and method. The system comprises a feature engineering module which is used for processing the preprocesseddata through feature data conversion; a machine learning module which is used for receiving the data processed by the feature engineering module, and analyzing and processing the model by using machine learning, and comprises a model training module, a model prediction module and a model evaluation module, wherein the model training module is used for checking the quasi-removability of the original data through the training of the model, and determining the data source and the use model for the model prediction; the model prediction module, which is used for predicting the test data by the trained model; the model evaluation module is used for evaluating the model effect by using the test data through the model generated by the training set. The invention not only realizes the data acquisition across databases and platforms, but also interacts with the Hadoop cluster on the Web control table of the browser end to analyze and process the data.