833 results about "Service networks" patented technology

Apparatus and methods are disclosed for implementing a copilot as a network of microservices including specialized large language models (LLMs) or other trained machine learning (ML) tools. The microservice network architecture supports flexible, customizable, or dynamically determinable dataflow. Compared to much larger competing LLMs, comparable or superior performance is achieved for certain tasks, while significantly reducing hardware requirements and computation time. Disclosed examples incorporate microservices for expansion, retrieval, embedding, and evaluation, in addition to one or more core microservices. Optionally, intermodal I / O, multiple data repositories, competency qualification, or human feedback can be supported. Multiple core microservices can support varying client authorizations or cognitive functions. The disclosed architecture supports any major LLM use case and can be deployed on a single compute node with a single GPU. Techniques are disclosed for multi-recursive retrieval, expansion ML tool training, input / output translation at data producers, and qualification of input / output data against copilot competency.

Apparatus and methods are disclosed for implementing a copilot as a network of microservices including specialized large language models (LLMs) or other trained machine learning (ML) tools. This architecture supports flexible, customizable, or dynamically determinable dataflow. Compared to much larger competing LLMs, comparable or superior performance is achieved for certain tasks, while significantly reducing computation time and hardware requirements, even to a single compute node with a single GPU. An expansion microservice converts client input tokens into associated tokens to diversify targeted tasks presented to a core microservice. An ML tool in the expansion microservice is pretrained in multiple stages for varying tasks using varying general and target-specific corpora. Synthesized training data derived from a knowledge graph can also be used. The expansion ML tool is subsequently fine-tuned in one or multiple stages. Variations and additional techniques are disclosed.

In a technique for directing network traffic to distribute client service requests among a set of service clusters of a service network, capacity and performance information is regularly obtained for the service clusters and provided to a trained reinforcement-learning (RL) model that integrates learned request-distribution and reward information for the service network. The RL model is operated to regularly update recommendation values for directing the client service requests to the service clusters, and updated recommendation values are regularly provided to a traffic director which directs network traffic at least partly based on the regularly provided updated recommendation values. The traffic director may be realized by a Domain Name System (DNS) server, having an ability to select among candidate service clusters based on weight values reported by the RL model.

An apparatus, method, and computer program for a serving network access node that causes the serving network access node to: provide a first user equipment with access to a network; signal, to a first network access node, a request for a first indication that indicates how at least one load-related parameter of the first network access node would likely be affected if the first network access node were to serve the first user equipment; receive, from the first network access node, the first indication; and make at least one load-related decision for the first user equipment in dependence on the received first indication.

A method for screening inter-PLMN messages at a SEPP to implement roaming agreements includes storing an originating and target network mapping database containing records including mappings between originating network identifiers and target network identifiers. The method further includes receiving, at the SEPP, an inter-PLMN SBI request message originating from an NF in a network served by the SEPP. The method further includes determining originating and target network identifiers from the message, locating a matching record in the database, and determining, from the record, whether the message should be allowed to flow from the originating network to the target network. The method further includes forwarding the message to the target network or preventing the forwarding of the message to the target network based on results of the determining.

Apparatus and methods are disclosed for implementing a copilot as a network of microservices including specialized large language models (LLMs) or other trained machine learning (ML) tools. This architecture supports flexible, customizable, or dynamically determinable dataflow. Compared to much larger competing LLMs, comparable or superior performance is achieved, while significantly reducing computation time and hardware requirements, even to a single compute node with a single GPU. Examples incorporate a retrieval microservice, as least one data producer, and a core microservice. Based on client input, the retrieval microservice can perform multiple iterations of retrieval augmented generation (RAG). At each iteration, output (based on any preceding iterations' results or the client input) is transmitted to a data producer, and results received therefrom. Eventually, based on these results, an output is transmitted toward the core microservice for generation of a response to the client input. Variations and additional techniques are disclosed.

An X-centric network architecture and associated methods are provided. The network architecture provides comprehensive control and processing functions that support heterogenous XaaS services. For different XaaS services, the network architecture supports the activation / selection of different functions / interfaces. The network architecture has a control / management (C / M) plane that includes a mission manager (MM) that manages a mission comprising tasks associated with heterogenous services. The network architecture also has a mission data plane (MDP) coupled to the C / M plane. The MDP plane includes processing functions (PFs) required for the tasks and also includes data plane functions (DPFs) that are configured to interface a PF of a XaaS service to a PF of a different XaaS service. The network architecture also has one or multiple XaaS module(s) which may be provided by third parties as plug-in module(s). Each XaaS module is associated with a XaaS service, one of multiple XaaS service controller(s) (XC), and one or multiple PF(s) / DPF(s) conducting corresponding tasks. Detail procedures, interfaces, and signals for mission execution and device accessing a mission (mission access) are described in the associated methods.

Various aspects of the present disclosure relate to methods, apparatuses, and systems that support service monitoring in wireless networks. For instance, when a service request from a UE to a visited serving network is rejected, rejection reports can be generated and validated using secure techniques, such as via a blockchain and / or a permissioned distributed ledger (PDL). The information can then be maintained and communicated in a trusted and secure manner, such as to a home serving network and / or service providers that provide network services.

The invention discloses a multi-mode fusion time service method and system based on dynamic calibration of DCP equipment. The method comprises the following steps: completing initial time reference data acquisition based on a multi-mode satellite signal; meanwhile, time data of a ground time service network are collected, and motion parameters of DCP equipment are monitored in real time through an inertial navigation unit; establishing a correlation model of the motion parameter and the time service error; quantitative analysis of error sources is completed based on the correlation model; fusing the multi-source time data; dynamically adjusting the fusion weight of each data source according to the real-time motion state of the DCP equipment; redundant time slots are automatically distributed to high-error equipment; outputting the calibrated time signal to DCP equipment through an interface to complete clock synchronization; and continuously monitoring the time deviation of the DCP equipment, and dynamically updating the calibration parameters to form closed-loop optimization. And the environmental adaptability and the precision stability of the timing system are improved.

The invention discloses an information communication network technology, a method and equipment. The information communication network comprises a service network and a bearing network, the service network is used for generating, organizing, managing and controlling services and applications on the information communication network, the bearing network is used for transmitting data packets generated by the service network, the access capability of the bearing network is the same as that of a traditional internet, and the bearing network can provide end-to-end credibility, safety, certainty and other capabilities for the service network. The information communication network can support services (namely OTT services) which can be supported by the traditional internet and are completely decoupled by a service network and a bearer network, and can also support services (namely non-OTT services) which cannot be supported by the traditional internet and have collaborative management and control requirements on the service network and the bearer network. A traditional internet is a network which takes a service network as the center and takes a bearing network as the best effort for transmission. The information communication network is centered on the bearer network, and the service network can obtain support of credibility, security, certainty and other capabilities provided by the bearer network.

Various solutions for improvement of network energy saving with user equipment assistive waking-up are described. An apparatus may receive a system information (SI) from a serving network node of a wireless network. The SI indicates a sequence information. The apparatus may transmit a sequence to wake up an energy-saving network node based on the sequence information. The sequence information includes a mapping information for a measured reference signal (RS) and a measured power level.

A network device may receive one or more first user inputs in a security gateway creation user interface (UI) provided by a controller. A network device may query, by the controller, the CSP using Application Programming Interfaces (APIs) to retrieve information about applications within the at least one virtualized network environment including any services deployed within the at least one virtualized network environment. A network device may present a security status user interface that identifies the at least one virtualized network environment applications configured in the CSP account and a respective status indicating whether the at least one virtualized network environment is protected by the security gateway. A network device may receive a second user input within the security status user interface, the second user input is effective to enable protection of the at least one virtualized network environment by the security gateway.

Recorded sessions of skilled personnel at work are used to train a first machine learning (ML) tool to extract workflow maps. These maps are used to train a second ML tool to emulate at least one workflow. The first ML tool is trained to predict an annotator's output. Either ML tool can be a copilot having a microservice network architecture. Further, complex sets of workflows can be subdivided for efficient support with small ML tools for (1) workflow map extraction and (2) emulation. Based on segment demarcation accompanying a recording, segments are assigned to specialized ML extraction tools for workflow map extraction. Extracted workflow maps are used to train workflow emulator(s). Similarly, specialized ML emulation tools can emulate respective tasks. A distribution microservice can identify a task to be emulated and can invoke the appropriate specialized ML tool. Similar microservice network architectures support both applications.

The invention discloses a cloud service providing method and device, and belongs to the technical field of cloud services. The method comprises the following steps: a cloud platform provides a network configuration interface for a user, the network configuration interface prompts the user to input network feature information, and the network feature information indicates a cloud service network required for realizing a target cloud service; the cloud platform provides a network association interface for a user, the network association interface prompts the user to input association information, the association information indicates a plurality of service nodes associated with a cloud service network, the service nodes are used for deploying application programs of the user, and the application programs are used for realizing a target cloud service; the plurality of service nodes are obtained based on resource deployment in one or more resource deployment areas; and the cloud platform establishes an association relationship among the plurality of service nodes based on the network feature information and the association information to obtain a cloud service network. According to the invention, the performance of the cloud service provided by the cloud service network is improved.

A communication method and a communication device, the method comprising: a first network element receiving a registration request message from a second network element for requesting registration of the second network element as a service network element of a terminal device to the first network element, the registration request message comprising a first uniform resource identifier; and under the condition that the first uniform resource identifier is the same as the uniform resource identifier stored in the first network element, the first network element sends a message used for indicating registration failure to the second network element. Based on the method, the malicious network element can be prevented from registering to the first network element by using the uniform resource identifier of the network element actually providing service for the terminal equipment, and the network security can be improved.

A first communication apparatus determines a first transmission delay indicating a transmission delay of a fine granularity service in the first communication apparatus; and the first communication apparatus sends the first transmission delay to a second communication apparatus. A service bit flow sent by a sink node meets a delay compensation requirement to ensure that a network transmission delay from a source node to the sink node and a network transmission delay from the sink node to the source node in a fine granularity service network are equal or meet an expected error range, or that the network transmission delay from the source node to the sink node and the network transmission delay from the sink node to the source node are adjusted to an expected value to meet a service requirement.

The invention discloses a method for measuring the toughness of a high-speed railway transportation network, and relates to the technical field of railway transportation networks. Comprising the following steps: respectively establishing a high-speed railway tense service network in a normal state and a high-speed railway tense service network under interference, and determining the instantaneous performance of the high-speed railway transportation network in the normal state and the instantaneous performance of the high-speed railway transportation network in the interference state; and determining the optimal network toughness of the high-speed railway transportation network according to the instantaneous performance in the normal state and the instantaneous performance in the interference state. According to the method, the instantaneous performance is measured and calculated on the smaller time granularity, the change rule of the instantaneous performance along with time can be effectively observed, the measurement and calculation precision of the network toughness is improved, and the method has more guiding significance for formulating a recovery strategy.

A wireless device (12) performs authentication (14) with a home network (10H) of the wireless device (12). The wireless device (12) encrypts a network slice identifier (24) with cryptographic key material (22) that is available from the authentication (14) with the home network (10H) and that is shared between the wireless device (12) and the home network (10H). The wireless device (12) transmits a message (20) that includes the encrypted network slice identifier (26). In some embodiments, a network node in a serving network (10S) of the wireless device (12) receives the message (20) and decrypts, or requests decryption of, the encrypted network slice identifier (26) using cryptographic key material (22) that is available to the wireless device (12) from authentication (14) of the wireless device (12) with the home network (10H) and that is shared between the wireless device (12) and the home network (10H).

A communication method and apparatus are provided. The method includes: A first control plane network element receives call signaling related to a call service, sends network element requirement information and preferred network element information to a network function repository network element based on the call signaling, and receives information about a target media plane network element configured to provide a second media plane service. The call signaling includes information about a first media plane network element configured to provide a first media plane service associated with the call service. The network element requirement information indicates to provide information about a media plane network element that can provide the second media plane service associated with the call service. The preferred network element information indicates that the first media plane network element is a preferred media plane network element. According to the method, failures of the second media plane service are reduced.

The invention relates to the technical field of wireless communication, and particularly discloses a spectrum sensing method and device for a cooperative frequency switching network and a communication system, and the method comprises the steps: generating a service network air interface frequency utilization situation table according to a network-level cooperative frequency control instruction transmitted by a guard network; a frequency spectrum sensing control instruction is generated according to the service network air interface frequency use situation table, the frequency spectrum sensing control instruction is diffused through a guard network, and the service terminal guard module can sense and monitor a service network air interface according to the frequency spectrum sensing control instruction and a to-be-sensed frequency set; and sensing and monitoring a service network air interface according to the to-be-sensed frequency set. The spectrum sensing method of the cooperative frequency switching network provided by the invention can assist in improving the anti-interference capability of the cellular network.

The invention relates to the technical field of architecture optimization, in particular to a communication network architecture optimization method, device and system, and the method comprises the following steps: based on edge access equipment, extracting and classifying data packet length and protocol port parameters, forming sequence clustering features, analyzing protocol and length pairing changes, and summarizing abnormal distribution signals; and combining node response characteristics to evaluate a health state, screening available paths, dynamically adjusting a data flow channel, and outputting a switching opportunity discrimination signal. According to the method, by dynamically collecting network multi-dimensional data and utilizing data flow feature classification, protocol pairing grading and node health association judgment, potential abnormal flow direction and node fluctuation are quickly found, resource redistribution and flow direction adjustment are actively guided, the phenomenon of uneven resource occupation caused by burst flow is effectively reduced, the path switching response period is shortened, and the network switching efficiency is improved. And the forwarding continuity of the high-priority task is improved, and self-adaptive flow control and task guarantee oriented to a multi-service network scene are realized.

Embodiments of the application may provide a decentralized wireless cloud service system including a distributed ledger database, a consensus algorithm, an exchange wallet, a platform, a distributed cloud, software configured to integrate the exchange wallet, the platform, and even the distributed cloud into a distributed ledger database to create a decentralized wireless cloud system, resource nodes in a decentralized wireless cloud system configured to provide a resource on a decentralized wireless cloud system, wherein a resource may include a network resource from at least some of the resource nodes; and perhaps even a reward system to owners of said resource nodes for a resource.

Apparatus and methods are disclosed for retrieving data, responsive to received input, at a microservice supporting an application programming interface (API). A score is generated, indicating likeness of semantic content, between each of multiple candidate API-conforming queries and the received input. Queries are selected based on their scores, and executed on a live repository. Based on retrieved data, a response to the input is formulated and transmitted. Disclosed techniques are suitable for a data producer front end in a copilot having a microservice network architecture. Compared to much larger competing LLMs, comparable or superior performance is achieved for certain tasks, while computation time and hardware requirements are significantly reduced, even to a single compute node with a single GPU. One or more data producers can provide a retrieval microservice with access to various databases having respective APIs, to extend the copilot's reach. Variations and additional techniques are disclosed.

The invention relates to an artificial intelligence model service discovery method and device, equipment and a storage medium. The method comprises the steps that the iNB sends artificial intelligence model service network element information to an intelligent wireless terminal iWT, and the artificial intelligence model service network element information comprises an identifier of an artificial intelligence model service network element capable of communicating with the iNB and / or artificial intelligence model service capability information; the artificial intelligence model service network element is a network element capable of providing an artificial intelligence model in the intelligent wireless access network, and the artificial intelligence model service capability information is used for indicating the iWT to obtain a limiting condition of the artificial intelligence model from the iNB; and the iNB receives a model request sent by the iWT based on the artificial intelligence model service network element information. According to the method, a novel artificial intelligence model service discovery process design is provided for endogenous intelligence characteristics of a smart wireless access network.

Recorded sessions of skilled personnel at work are used to train a first machine learning (ML) tool to extract workflow maps. These maps are used to train a second ML tool to emulate at least one workflow. The first ML tool is trained to predict an annotator's output. Either ML tool can be a copilot having a microservice network architecture. Further, complex sets of workflows can be subdivided for efficient support with small ML tools for (1) workflow map extraction and (2) emulation. Based on segment demarcation accompanying a recording, segments are assigned to specialized ML extraction tools for workflow map extraction. Extracted workflow maps are used to train workflow emulator(s). Similarly, specialized ML emulation tools can emulate respective tasks. A distribution microservice can identify a task to be emulated and can invoke the appropriate specialized ML tool. Similar microservice network architectures support both applications.

A method performed by a communication device (12) is disclosed. The communication device (12) stores, at the communication device (12), a self-organizing network, SON, report (16) associated with a non-public network, NPN, including storing the SON report (16) in association with an NPN identifier of the NPN with which the SON report (16) is associated. The communication device (12) also transmits a message to the serving network indicating that the SON report (16) is available at the communication device (12), if a serving network of the communication device (12) is an NPN identified by an NPN identifier which matches the NPN identifier associated with the SON report (16).

A disclosed method of operating an emergency data management system includes: obtaining emergency data related to an emergency call to an emergency communication center (ECC) by a cloud server of the emergency data management system independent from the ECC; obtaining an address for the emergency call via a connectivity device located at the ECC, where the connectivity device is operatively coupled to the cloud server; matching the address to an ECC computer-aided-dispatch (CAD) system incident record address; and sending the emergency data to the ECC CAD system incident record corresponding to the matched CAD system incident record address.

The invention relates to a household equipment intelligent fault early warning and after-sales optimization system based on multi-sensor fusion and wireless transmission, which comprises a sensing layer, a transmission layer, a cloud intelligent layer and an application layer, and is characterized in that the sensing layer comprises a heterogeneous sensor cluster and an edge computing node, and the heterogeneous sensor cluster deploys a multi-dimensional sensor; and mechanical, electrical and environmental parameters are covered. Through a physical model and data-driven double-engine architecture, a flexible sensing technology and a decentralized service network, full-chain intelligent reconstruction from fault early warning to after-sales service is realized, and analyzed data is timely and stably transmitted back to an after-sales service center or a specified monitoring platform. Through deep analysis and processing of the sensor data, a scientific fault prediction model can be established, and the model can be utilized to accurately predict possible faults of the equipment and perform early warning before the faults occur, so that a user can know potential problems of the equipment in advance and take corresponding measures in time.

The invention belongs to the technical field of network communication, and discloses a service network message cross-domain transmission method and system based on SRv6SID function extension. According to the method, a service network identifier is embedded in an Args field of the SRv6SID, the service network identifier comprises a service network type (TYPE) and a service virtual group tag (VGT), and service awareness transmission of a cross-domain network is realized in combination with an intelligent routing decision driven by deep reinforcement learning. Compared with the prior art, the protocol compatibility can be ensured, the transmission delay and the protocol overhead can be remarkably reduced, the transmission flexibility, the high efficiency and the customizability of the service network message among different network domains can be improved, and the method and the device are suitable for scenes such as 5G, industrial internet and the like.

According to the energy storage system battery full life cycle state perception and value circulation method and system, digital twin bodies of all battery modules are generated according to battery static information, and life cycle stage identifiers are set in the digital twin bodies; training is carried out based on a federated task scheduling contract, an edge calculation unit of each energy storage power station enters a corresponding federated collaborative clustering group through dynamic matching according to the life cycle stage identifier, and a corresponding stage global sensing model and model parameters thereof are obtained; updating the corresponding stage global perception model parameters by using the global model parameter update quantity obtained by decryption; the under-chain service network writes a state evaluation result and an evaluation timestamp into a digital twinborn body of each battery module according to the updated parameters of the stage global perception model and the real-time operation data of each battery module; and monitoring the SOH of each battery module in real time to update the life cycle stage identifier, performing training based on a federated task scheduling contract, and constructing a full life cycle data file.