151 results about "ControlNet" patented technology

The invention provides an addressing method for a strategy control network element, an application side network element and a control plane network element, and the method comprises the steps: obtaining a device address of a strategy binding network element retrieval database network element based on the local static data configuration information of the application side network element; retrieving a device address of a database network element according to the policy binding network element, and sending the control plane network element query message to a corresponding target policy binding network element retrieval database network element, so as to query an address of a target control plane network element in the target policy binding network element retrieval database network element according to the control plane network element query information; according to the address of the target control plane network element, sending the policy control network element address query request to the target control plane network element; and receiving a query result corresponding to the policy control network element address query request sent by the target control plane network element. According to the invention, the problem that the application side network element cannot acquire the IP address of the policy control network element according to the user IP address information is avoided.

The invention provides a policy control network element addressing method, an application side network element and a control plane network element, and the method comprises the steps: obtaining the addresses of a plurality of control plane network elements based on the local static data configuration information of the application side network element according to a user terminal address and a mobile communication network access external network identifier; determining a first target control plane network element, and sending a policy control network element address query request to the first target control plane network element; if the session association information of the user terminal is not queried in the first target control plane network element, acquiring an address of a second target control plane network element sent by the first target control plane network element; sending a policy control network element address query request to the second target control plane network element according to the address of the second target control plane network element; and receiving a query result sent by the second target control plane network element. According to the invention, the problem that the application side network element cannot acquire the IP address of the policy control network element according to the user IP address information is avoided.

The invention provides a metadata processing acceleration method, electronic equipment and a storage medium, and relates to the technical field of distributed storage. According to the technical scheme, the acceleration card obtains the metadata request, the metadata is cached to the cache module of the hybrid storage architecture based on the dynamic cache management strategy, and the acceleration card directly queries the cache and controls the network card to directly construct the response packet to return when the cache is hit, so that the data processing efficiency is improved. According to the method and the device, the problems of high delay and CPU resource scrambling and the like caused by the fact that a metadata request depends on a CPU to analyze a network protocol and inquire software cache in the prior art can be solved, so that the technical effects of remarkably reducing metadata processing delay, improving metadata throughput, reducing CPU occupancy rate, optimizing hardware resource utilization rate and reducing cross-node synchronous bandwidth occupancy can be achieved.

The invention relates to the technical field of image restoration, in particular to a diffusion model image restoration method based on regional mask and dynamic exit, and mainly solves the technical problems of high calculation overhead and iteration step number redundancy of an existing diffusion model image restoration method. According to the method, on the basis of an extension architecture of encoding and decoding, a UNet denoising network and a ControlNet conditional constraint module, on the basis of retaining the core functions of an existing encoder, an existing decoder and an existing Unet denoising network, a space region mask generation sub-module, a back diffusion dynamic exit module and the ControlNet conditional constraint module are creatively integrated; and a triple optimization architecture of'constrain structure protection, space redundancy reduction and time step number reduction 'is formed, so that the structure consistency is met and efficient acceleration is realized during image restoration.

The invention provides an embedded part group precision control method for wind tunnel construction, and belongs to the technical field of wind tunnel construction, and the method comprises the steps: building an initial control network, dividing embedded part groups in a segmented manner, and determining the position of an optimal control point through an iteration experiment method and a graph theory network model; establishing an error propagation mathematical model to describe a measurement error propagation rule, performing control point position optimization calculation by applying a double-layer game optimization algorithm and a cross subwolf optimization algorithm, calculating three-dimensional coordinates of the embedded part by combining a resection method and a forward intersection method, and implementing real-time monitoring and dynamic adjustment of the laser tracker; and finally, overall precision verification is carried out through the total station and the laser scanner, and the technical problem that accumulated error propagation is difficult to effectively control in the installation process of the wind tunnel embedded part group is solved.

The invention discloses a corn leaf disease image generation method and device based on a ControlNet and LoRA enhanced Stable Diffusion model, and relates to a corn leaf disease image generation method and a corn leaf disease image generation device based on a ControlNet and LoRA enhanced Stable Diffusion model. Belongs to the technical field of image processing. According to the method, a data set covering seven types of corn leaf diseases is constructed, and a Stable Diffusion model integrating ControlNet and LoRA is trained on the basis of the data set so as to generate an image of a corresponding disease type. Afterwards, the generated image is combined with a real image to be used for training a Swin Transform model and generating a vivid corn leaf disease image, the problems of scarcity of field data and insufficient diversity are solved, and the effectiveness of the image in a disease recognition task is verified through quantitative evaluation.

The application provides a communication method and device, the method comprises: a session management function network element acquires an interface identifier; the session management function network element sends an address of a user plane function network element and the interface identifier to a first network element, the interface identifier is used for the first network element to determine an interface corresponding to the interface identifier, and the address of the user plane function network element and the interface corresponding to the interface identifier are used for the first network element to control the user plane function network element. In the communication method of the embodiment of the application, the UPF can realize that other types of control plane network elements of non-SMF type control the UPF network element, and the UPF network element can be isolated and operated based on different configurations of the SMF network element and other network elements, and the same message is processed in parallel, so that multiple types of controllers control the same UPF network element.

A slice control method and apparatus are provided. The method includes: a policy control network element receives, from a slice access control network element, slice access status information of a network slice, the slice access status information comprises information indicating a network slice traffic bandwidth of the network slice; determines, based on the current slice access status information of the network slice, that the network slice traffic bandwidth exceeds a corresponding maximum value allowed by configuration; generates, in response to the determination, first session policy control information for a first session in the network slice; and sends the first session policy control information to a session management network element corresponding to the first session, the first session policy control information being for policy control on the first session.

The invention provides an intelligent design method for a subway room layout based on Stable Diffusion. The method comprises the following steps: carrying out feature extraction on multiple types of plane drawings of actual engineering, generating a space division heat map based on a room center point by utilizing a region growing algorithm, and constructing a heat map-layout sketch pairing data set; a two-stage training strategy is adopted, a ControlNet model is firstly trained to learn a spatial constraint relation, and then LoRA is trained to carry out efficient fine tuning on parameters; room agent points are set according to design requirements, a heat map is generated through a region growing algorithm, and the trained ControlNet model is combined with LoRA to achieve accurate translation from the heat map to an arrangement diagram. According to the method, the condition control capability of the ControlNet and the parameter efficient fine tuning advantage of the LoRA are creatively fused, the generation quality is guaranteed, meanwhile, the computing resource requirement is remarkably reduced, and the design efficiency and the resource utilization rate are improved.

The invention relates to the technical field of ocean engineering large LNG module construction, in particular to an LNG module general assembly closure space precision control method. The method comprises the following steps: S1, establishing a measurement control network which comprises a plane control network and an elevation control network; s2, performing three-dimensional coordinate measurement by using a total station; s3, observing the distance from the to-be-fixed point to at least two control points by using a free station setting technology; s4, carrying out space measurement on the large steel structure; and S5, according to a measurement result, carrying out dynamic adjustment and optimization on the installation of the steel structure. The folding and butt joint precision is improved from the traditional centimeter level to the millimeter level, the situation of interface dislocation is greatly reduced, and the overall structure quality is guaranteed; one-time successful closing can be achieved, the long rework period caused by insufficient precision is omitted, the construction progress is accelerated, the project can be put into use earlier, and benefits are created; manual correction, material waste and mechanical machine-team cost are reduced, and the construction cost is reduced.

The application provides a sandwich combination structure lower hanging steel beam coordinate precision control method, and belongs to the technical field of wind tunnel construction. The application establishes an independent reference control network, sets a forced closed control point to block error linear transmission, calculates the lower hanging steel beam camber, and offsets the dead load deflection through reverse prefabricated bending processing. A buried part rigid positioning frame is installed and the position deviation is monitored. A hydraulic synchronous jacking device is used to iteratively adjust the posture of the steel beam. Pre-stressed tension is applied to realize reverse arch shaping. Finally, the least squares adjustment technology and the minimum spanning tree optimization algorithm are used to reasonably distribute the section cumulative error between the forced closed control points, thereby solving the technical problem of excessive steel beam coordinate precision caused by large-span multi-section construction cumulative error.

The application provides a method for addressing a policy control network element, an application-side network element and a control plane network element. The method comprises the following steps: obtaining the device address of a policy binding network element search database network element based on the local static data configuration information of the application-side network element; sending a control plane network element query message to a corresponding target policy binding network element search database network element according to the device address of the policy binding network element search database network element, so as to query the address of a target control plane network element in the target policy binding network element search database network element according to the control plane network element query information; sending a policy control network element address query request to the target control plane network element according to the address of the target control plane network element; and receiving the query result corresponding to the policy control network element address query request sent by the target control plane network element. The application avoids the problem that the application-side network element cannot obtain the IP address of the policy control network element according to the user IP address information.

The invention discloses a vehicle body controller, a control system, a vehicle, a control method, a device and equipment. The vehicle body controller comprises a gateway module, a plurality of control modules and a processing module. And the gateway module is used for communicating with a network outside the vehicle body controller. And the plurality of control modules are used for performing various different function control on the vehicle body. The processing module is connected with the gateway module and the control module, and is used for controlling the working states of the gateway module and the control module. Therefore, the cost of the whole vehicle can be reduced, vehicle body wiring is reduced, vehicle body weight is reduced, and stability is improved.

The invention relates to the technical field of brewing process intelligent control, and discloses an artificial intelligence-based deer wine production process optimization control method. The method comprises the following steps: configuring a multi-source sensing unit array integrated with a thermosensitive sensor, a humidity-sensitive sensor and an image collector, and synchronously collecting temperature, humidity and appearance data in a fermentation process; carrying out multi-modal feature fusion through a machine learning fusion engine, and generating a production state evaluation vector; constructing a virtual simulation platform for operating a physical mechanism model, and performing simulation deduction based on the vector to generate a simulation control signal; deploying an edge computing control grid, and generating a control strategy in real time by each node according to local data; and integrating the information through the data exchange middleware, and analyzing and optimizing the control instruction stream. According to the method, interactive optimization of digital simulation and a physical process and cooperative control of center planning and edge execution are realized, and the accuracy, the adaptability and the product stability of production process control are improved.

This invention discloses a service-oriented method, apparatus, and electronic device. The method is applied to a policy control network element and includes: sending a service registration request message, the service registration request message including configuration information of the policy control network element; and receiving a service registration response message. The policy control network element provides network function services, the network function services including at least one of home policy control service and visited policy control service, and the configuration information of the policy control network element includes relevant information of the network function service.

A policy association processing method, an access control network element, a computer-readable storage medium and an electronic device. The policy association processing method comprises: receiving capability information of a user equipment; in response to the capability information containing first indication information, establishing a subscription relationship for user subscription data with a user subscription data storage network element, wherein the first indication information indicates that the user equipment supports an access control network element in issuing a user equipment policy to the user equipment; and in response to the user subscription data sent by the user subscription data storage network element containing second indication information, not establishing policy association with a policy control network element, wherein the second indication information indicates that the access control network element is prohibited from establishing policy association with the policy control network element. The method enables more flexible and efficient processing of policy association, so as to adapt to network environments and user requirements, thereby providing better network service experience for users.

The invention relates to the technical field of man-machine interaction, and discloses a multi-modal AI and emotional intention recognition three-dimensional content real-time generation method, which integrates a multi-modal AI collaborative generation module, a dynamic emotional intention recognition module, a three-dimensional content real-time generation module and a holographic software and hardware collaborative module, the method comprises the following steps: realizing an immersive holographic interaction and multi-modal AI collaborative generation module, constructing a unified semantic space by adopting CLIP + VATT, analyzing an instruction by adopting LLM to generate parameters, generating 2D content by adopting Diffusion, converting NeRF into a textured 3D model in real time, and realizing sketch / semantic driven parameterization generation by combining ControlNet and LoRA. According to the scheme of the invention, the breakthrough efficiency can be improved, and the AI driven automatic generation technology is realized; a traditional 3D content production process which needs to be completed in several days can be compressed to be completed in several minutes by means of collaborative optimization of models such as Point-E, NeRF and Diffusion and combining ControlNet structured control and LoRA low-rank fine tuning, and the modeling efficiency is integrally improved.

The application provides a prism remote control system and method, a user terminal sends a control command to a server, a control terminal obtains the control command from the server and converts the control command into a control signal to send to a control device, the control device controls the working state of a stepping motor and a lifting motor respectively through the control signal to control the horizontal rotation and vertical rotation of the prism, so as to remotely adjust the azimuth angle and vertical angle of the prism. By using the application, the labor cost of control network re-measurement can be effectively reduced without affecting the application of other observation scenes of the prism and the accuracy of control network re-measurement results.

The invention relates to the technical field of pharmacy and biology, in particular to a high-content drug screening method and system based on ControlNet-PPO. The method comprises the following specific steps: according to a current cell state, adopting a PPO algorithm reinforcement learning strategy to generate a combined action instruction for controlling release of various drugs; applying drug disturbance to cells based on the combined action instruction, and obtaining a disturbed cell image; inputting the cell image as a condition into a pre-trained ControlNet, and generating an expected cell state image under the action instruction; calculating a composite reward value based on a state difference between the expected cell state image and a normal cell reference image; and updating the reinforcement learning strategy by using the composite reward value, and iteratively optimizing the drug combination action until the cell state is converged to be close to the normal state, thereby obtaining an optimal drug combination path. By adopting the method, the synergistic effect of multiple drugs can be effectively captured and utilized, and the method has the characteristic of high optimization capacity.

A charging and discharging management system (10), comprising a cloud platform (100), a control gateway (200) and a charging and discharging device (300), wherein the charging and discharging device is connected to the cloud platform by means of the control gateway; the charging and discharging device is configured with the function of charging an electric device (400) connected to the charging and discharging device and the function of collecting and reporting device data, the device data comprising data of the electric device and / or data of the charging and discharging device; and the control gateway is configured with a first data security processing function, the first data security processing function comprising performing first data security processing on the device data and then reporting same to a cloud platform. The system performs, on the basis of the control gateway, first data security processing on the device data reported by the charging and discharging device, and uploads to the cloud platform security data which has been subjected to the first data security processing, thereby improving the security of data transmission during charging of the electric device.

The invention relates to the technical field of energy storage unit control, and discloses a method, a device and equipment for controlling the wide short-circuit ratio of a full-power pumped storage unit, and a medium. The method comprises the following steps of: controlling a grid-side converter by using a wide short-circuit ratio network construction type control strategy; wherein the control strategy of the wide short-circuit ratio network construction type comprises the following steps: tracking a reference voltage obtained according to a first output voltage output by a network-side current inner loop and a network-side three-phase current transmitted by a network-side converter by using a voltage and current double closed-loop control strategy, and obtaining a second output voltage of a network-side current loop; generating a first switching signal according to grid-side phase information of operation of the grid-side converter and the second output voltage so as to drive the grid-side converter; acquiring voltages at two ends of the direct-current capacitor to obtain a capacitor voltage actual value; and generating a second switching signal according to the capacitor voltage actual value and the capacitor voltage reference value so as to drive the machine-side converter. Therefore, the stability of the full-power pumped storage unit is improved.

The utility model belongs to the technical field of bridge vibration control, and provides a large-span split type steel box girder bridge vortex vibration control device. The novel control concept and measure are provided, the lifting lugs, the lock catches and the control net are utilized to assemble the efficient and reliable control device which is low in cost, convenient to assemble and disassemble, light, handy and durable, and the control device is installed at the open groove in the daily operation state of a single-width or double-width bridge to restrain vortex vibration response. According to weather forecast, before extremely strong wind comes, the device is quickly dismantled, the original aerodynamic configuration of the bridge is recovered, the flutter stability is ensured, and installation is recovered after the strong wind. The large-span split type steel box girder bridge vortex vibration control device is simple in structure, free of complex mechanical parts, convenient to assemble and disassemble, economical, practical, not limited by the bridge vortex vibration frequency and the vortex vibration order, capable of reducing the lateral wind load of a bridge and excellent in comprehensive performance.

The embodiment of the invention discloses an equipment control method and device and an ad hoc network system, and the method comprises the steps: setting a plurality of semantic tags for node equipment of an ad hoc network from a plurality of different dimensions, embedding a target node equipment tag group in equipment control information when scene control or group control is carried out, and carrying out the scene control or group control. And positioning the target node equipment needing to be controlled by using the target node equipment label group, and sending the equipment control information in the ad hoc network in a broadcast mode. And meanwhile, each node device matches and judges whether a target node device exists or not based on a semantic tag of the node device and a target node device tag group by broadcasting the received device control information, and executes an action instruction in the device control information when judging that the node device is the target node device. Thus, scene control or group control can be realized in a low-latency manner without controlling a command or address translation of the gateway device.

The invention discloses a speed-up railway precision conductor construction method with virtual control points added, which comprises the following steps: S1, arranging conductor points in a staggered manner along two sides of the advancing direction of a speed-up railway line, and arranging the virtual control points between the adjacent conductor points; s2, arranging total stations on each traverse point one by one, and arranging prisms on two front and back adjacent traverse points and adjacent virtual control points; observing each prism by using a total station to obtain a horizontal direction, a slant distance and a vertical angle from the center of the total station to the center of each prism; s3, performing gross error detection analysis on the observation values, and rejecting the detected gross error observation values or re-measuring the observation stations where the gross error observation values are located; and S4, establishing an acceleration railway conductor control network with virtual control points by using all reliable horizontal angles and horizontal distances. According to the method provided by the invention, on the premise of not increasing the burying cost of the control points, on the basis of the connecting wires, only several temporary target points are observed by each observation station, so that the effect of remarkably improving the precision and reliability of the control network is achieved.

Provided are a call recovery method, a communication apparatus, a storage medium and a program product. The call recovery method comprises: after creating a first session in response to a first session creation request of a proxy call session control function (P-CSCF), a policy control network element determining whether a core network element associated with the first session has failed; and when the core network element associated with the first session has failed, the policy control network element sending a first request message to the P-CSCF, wherein the first request message is used for requesting the termination of the first session and triggering a failure recovery process of the P-CSCF.

The utility model relates to the technical field of filtering devices, and discloses a ceramic slurry filtering device capable of controlling the net diameter through cross combination, which comprises a material receiving frame, one side of the material receiving frame is communicated and connected with a discharging pipe, two sides of the material receiving frame are fixedly connected with connecting plates, and a feeding frame is fixedly connected between the two connecting plates. A sliding sleeve is fixedly connected to the middle of the connecting plate, fixing rods are slidably connected to the interior of the sliding sleeve, a mounting frame is fixedly connected to the upper surfaces of the two fixing rods, and an adjusting assembly is arranged in the mounting frame; the adjusting assembly comprises a plurality of longitudinal rods. By utilizing the adjustability of the cross rods and the longitudinal rods in the crossing process, the diameter of the filtering net in the filtering device can be flexibly adjusted according to filtering requirements and slurry with different particle sizes and textures, in addition, the mounting frame is favorably driven to shake by utilizing the connection of the springs, and the filtering effect is improved. And the phenomenon that the slurry is blocked in the mounting frame and is difficult to circulate and discharge is effectively reduced.

Systems, methods, and other embodiments described herein relate to controlling a model using data fusion and a multi-modal conditional embedding for generating an object design. In one embodiment, a method includes constructing a completed parameter and an assembled component using completion models from an assembly graph, an incomplete parameter, and a component image about an object design. The method also includes generating input embeddings using encoding models associated with the completed parameter, the assembled component, and a text description. The method also includes computing a multi-modal conditional embedding using multi-modal fusion from the input embeddings. The method also includes controlling a foundational model using the multi-modal conditional embedding with a controlnet and outputting a generated object.

The invention relates to a combined monitoring system and method for power plant control equipment and security monitoring equipment. The combined monitoring system of the power plant control equipment and the security and protection monitoring equipment comprises a DCS control network, a DCS control cabinet, an NVR hard disk video recorder and a security and protection integrated network. The DCS control cabinet is provided with a DCS cabinet-to-DCS control network interface and a DCS input and output interface, and the DCS control cabinet is connected with a DCS control network through the DCS cabinet-to-DCS control network interface; the NVR hard disk video recorder is provided with an NVR input and output interface and an NVR-to-security integrated network interface. A DO digital output interface of the DCS control cabinet is connected with a DI digital input interface of the NVR hard disk video recorder through a hard wiring. And a DO digital output interface of the NVR hard disk video recorder is connected with a DI digital input interface of the DCS control cabinet through a hard wiring. According to the combined monitoring system of the power plant control equipment and the security and protection monitoring equipment, the power plant control equipment and the security and protection monitoring equipment can perform combined monitoring, the network security can be improved, and the network reinforcement difficulty is reduced.

This invention provides a mirroring traffic control method and apparatus. The method is applied to gateway devices in a gateway cluster, where the gateway cluster includes multiple gateway devices, each storing a mirroring configuration. The method includes: if the mirroring configuration contains the gateway address of a gateway device, then sending service traffic to a mirroring service node. The mirroring configuration is used to control some gateway devices in the gateway cluster to perform mirroring services. This allows service traffic to be mirrored to a test environment through mirroring configuration without changing the existing network architecture, thus achieving control over the traffic mirroring service.

The application discloses an online target point sky window period measurement method and system based on PPK post-processing, and on the basis of a GNSS RTK measurement method, proposes a data solution method of PPK post-processing, can carry out the sky window period measurement of the online target point under the premise that the offline basic control network result is not obtained, and completes the target point layout, measurement and vehicle-mounted Li DAR scanning measurement work through one time of going online, effectively solves the difficulties of tight working period of business line railway re-measurement, short sky window time, great safety risk of existing line operation and the like while reducing the going online frequency of workers, compares and checks the method of the leveling actual measurement result and the fitting result, reduces the error probability of data processing, effectively guarantees the target control network result quality, and proposes a new solution method for the online target control network measurement in the re-measurement work in the railway operation period.