10results about How to "Guarantee service continuity" patented technology

The embodiment of the invention provides a 5G-Advanced sensing communication collaborative resource scheduling method and system for a smart substation, and belongs to the technical field of power system operation and maintenance. The method comprises the steps that a 5G-Advanced cellular-free unmanned aerial vehicle communication and sensing integrated network architecture is constructed, the network architecture comprises a passive sensing layer, an air-ground cooperative access layer and a centralized processing layer, and deep integration of sensing, energy supply and communication functions is achieved; establishing a system model based on the network architecture, wherein the system model comprises a network topology model, a communication and inductance integrated transmission model and a constraint optimization problem model; a cross-CPU dynamic resource scheduling algorithm based on MADDPG is designed, and joint optimization of user association, power distribution and load balancing is achieved through a centralized training-distributed execution mechanism; based on a scheduling algorithm and a system model, substation global real-time sensing, data transmission and operation and maintenance performance collaborative guarantee are achieved. The sensing fusion and coverage capability is greatly improved, the dynamic scene adaptability is better, and the sensing-operation and maintenance collaboration value is higher.

The invention relates to the technical field of artificial intelligence security and cloud computing resource management, and discloses an AI reasoning service elastic scaling method and system for an edge cluster, and the method comprises the steps: constructing a dynamic risk file for each hardware computing unit in a computing cluster; distributing the reasoning service request to a target hardware calculation unit of which the risk state is matched with the security demand level; instantiating an independent logic calculation container for each allocated reasoning service request, and destroying the logic calculation container after the reasoning task is executed; and monitoring the resource configuration change of the computing cluster, and updating the risk state of the computing cluster in the dynamic risk file. According to the method, a mixed protection mechanism with logic isolation as a main part and physical reset as an auxiliary part is adopted, and hardware-level state pollution attacks triggered by antagonistic input are effectively defended in a dynamic elastic edge AI reasoning scene on the premise that the elastic scalability is not obviously sacrificed.

The embodiment of the invention provides a message processing method, computing equipment, a storage medium and a program product. The method comprises the following steps: detecting a session request sent by a first user side; wherein the session request is generated according to a session starting operation triggered by the first user for the second user; performing multiple rounds of sessions with the first user side by using the intelligent session robot, and detecting whether the first user meets a first quality requirement or not according to at least one session message sent by the first user side; obtaining a first detection result; and when the first detection result is yes, sending the historical message record generated by the multi-round session and the session message currently sent by the first user side to the second user side. According to the technical scheme provided by the embodiment of the invention, the session quality is improved.

The invention relates to the technical field of cloud computing and data center operation and maintenance, and provides a data center resource scheduling optimization method based on artificial intelligence, and the method comprises the following steps: collecting multi-dimensional data; preprocessing the data; constructing and training a hybrid intelligent scheduling model; and real-time scheduling decision generation, scheduling execution and closed-loop optimization are carried out. According to the artificial intelligence-based hybrid intelligent model-driven data center resource scheduling optimization method provided by the invention, through multi-dimensional data acquisition, feature engineering optimization, hybrid intelligent model construction and closed-loop iterative optimization, multi-target collaborative optimization of a resource utilization rate, an SLA standard-reaching rate and energy consumption is realized; and the intelligent level and the dynamic adaptability of resource scheduling of the data center are improved.

The invention discloses a cloud computing resource configuration and management method and system, and the method comprises the steps: collecting service flow data, resource consumption data and external influence data in a historical state, carrying out the integration through combining with data obtained by a data collection unit, and calculating a resource prediction demand index Xy through combining with a formula; monitoring the use condition of the current cloud resource, obtaining current resource utilization data, and calculating a current resource demand index Xs based on the resource utilization data; and comparing the resource prediction demand index Xy with the current resource demand index Xs, and calculating a resource prediction coincidence index Fh to implement an elastic scaling strategy. According to the system, the unification of resource configuration flexibility and efficiency is realized, and the double troubles of cost and performance are solved.

This invention proposes a hierarchical task offloading and resource allocation method for large-scale model tasks in the Industrial Internet, belonging to the technical fields of Industrial Internet and mobile edge computing. The invention includes: establishing a cloud-edge-device collaborative reasoning architecture for large-scale models in Industrial Internet scenarios, and modeling the large language model reasoning task as a phased resource consumption model including a pre-filling stage and a decoding stage; modeling the large-scale model task offloading and resource allocation problem as a hierarchical Markov decision process, constructing a composite reward function; and utilizing the proposed hierarchical multi-agent large-scale model task offloading and resource allocation algorithm based on deep reinforcement learning, adopting a two-layer collaborative architecture of distributed offloading at the bottom layer and centralized allocation at the top layer to achieve task offloading and resource allocation. This invention significantly improves memory security and service stability during the large-scale model reasoning process; greatly reduces the action space dimension, and achieves rapid convergence and efficient decision-making in large-scale scenarios.

This invention relates to an automatic software update method based on an in-vehicle embedded operating system, belonging to the field of computer software technology. It solves the problem that existing methods cannot simultaneously achieve reliable system startup and flexible, secure automatic software updates. The method includes: partitioning the physical disk into a system root partition, a user data partition, and an OverlayFS working partition; automatically entering safe mode by detecting kernel boot parameters, mounting the system root partition as read-only, and mounting specified directories as read-write overlays based on the OverlayFS file system and whitelist configuration files; dynamically switching the safe mode on and off via system services and command lines; upon detecting an external update device, entering maintenance mode, performing security verification on the update package from the external update device, and then performing an atomic update operation on the user data partition. This achieves both reliable operating system startup and flexible automatic software updates.

The application relates to a bank intelligent customer service response method, equipment and medium, a bank intelligent customer service response method comprises the following steps: collecting interactive service data in multiple interactive channels, preprocessing the interactive service data to generate corresponding feature vectors, performing clustering calculation on the interactive service data to generate corresponding customer behavior characteristics, inputting the feature vectors and customer portrait information into a response process to generate corresponding response content; obtaining customer feedback data of the response content, selecting corresponding target models in each decision model according to the customer feedback data and the customer portrait information, and training the target models according to training samples. By constructing a full-process closed-loop path of collection-understanding-generation-feedback-retraining, the system can continuously optimize the response strategy in a real scene, continuously improve the response accuracy, customer satisfaction and adaptability, and meet the efficient, accurate and evolvable requirements of bank intelligent service.

The invention provides a lightweight non-intrusive micro-service non-stop version upgrading method, and relates to the technical field of service operation and maintenance under a micro-service architecture, and the method comprises the following steps: S1, deploying a new-version back-end service, and registering meta information; through a lightweight architecture, only depending on a basic load balancer and a configuration center and without containerization transformation, the version raising cost of a traditional virtual machine / physical machine architecture is remarkably reduced, and through a dynamic flow routing strategy, service zero-code transformation is achieved, second-level strategy updating is supported, service continuity is guaranteed, and non-intrusive control is achieved. A bypass Nginx mirror image verification mechanism and user-level gray level control are provided, a real production scene is covered by 100%, production-level accurate verification is achieved, smooth upgrading without perception of a user is achieved through a dynamic flow routing and version decoupling mechanism, service continuity is guaranteed, meanwhile, accurate verification of a production environment is supported, and service risks caused by version defects are reduced from the source.

The invention discloses a GPU (Graphics Processing Unit) intensive service lateral extension system and method based on container network sharing, and aims to solve the problems of code invasiveness and performance bottleneck during existing containerization service extension. The system comprises at least two processing unit containers running in a custom service network; a load balancing unit container connected to the network; and a client unit container. Wherein the client unit container is configured to share the same network namespace with the load balancing unit container. The client application sends a request by accessing a local loopback address, and the load balancing unit container directly receives the request through the shared namespace and transparently forwards the request to the processing unit container through the custom service network. According to the method, a network namespace sharing mechanism is utilized, transverse extension of zero code intrusion of the client is realized, and the method has the advantages of high availability, fault tolerance, high-performance linear extension and the like.