1476 results about "Server-side" patented technology

The invention provides a five-axis series-parallel numerical control machine tool machining process virtual monitoring simulation method and system based on digital twinning, and the method comprises the steps: building an information interaction mechanism between a physical machine tool and a digital twinning model, enabling a server side to collect sensor data, and transmitting the real-time data to a client side through a communication protocol; the client processes the data and drives the digital twin model. And aiming at potential errors of twin system forecast, tool setting error compensation can be carried out in real time, so that the machining precision is improved. Meanwhile, the system supports an offline simulation function, combines an inverse kinematics algorithm and an NC code, fuses a material removal model, simulates a machining process, evaluates machining performance and errors, and provides an optimization basis for machining strategies of workpieces with different geometrical shapes and materials. According to the method, bidirectional interaction between the physical entity and the virtual model is achieved, the real-time monitoring and visualization capability of the machining process is enhanced, a reliable simulation evaluation and optimization means is provided for machining of complex parts, and the method has wide industrial application prospects.

Disclosed in the present invention are a large language model federated fine-tuning method and apparatus based on gradient compression. The method comprises the following steps: constructing, on the basis of a gradient tensor generated during fine tuning of a large language model, a raw data set having a time series relationship, performing inference by means of an autoencoder to obtain a reconstructed gradient data set, and constructing a reconstruction loss function to optimize the autoencoder; and initializing a base model of the large language model as a global model at a server end, the server end updating the global model to a client, using a pre-trained encoder to obtain a compressed gradient at the client, and at the server end, using a pre-trained decoder to decode and aggregate the compressed gradient, and then updating the global model. The present invention can improve the fine-tuning efficiency of the large language model and reduce computing resource requirements while ensuring data privacy protection, and is suitable for application scenarios such as communication optimization improvement and privacy protection enhancement in the process of scientific computing-oriented large model fine-tuning and training.

The invention provides a multi-mode medical record intelligent generation and interaction system and method based on a wearable terminal and an MOE architecture, and relates to the technical field of AI large models. The terminal comprises a wearable terminal used for carrying out real-time acquisition and interaction on multi-modal data in a medical scene to obtain multi-modal medical data; the communication network is used for realizing data interaction between the wearable terminal and the server-side AI large model processing system; the server side AI large model processing system is used for performing semantic analysis, structured extraction and medical record document generation based on the multi-modal medical data to obtain an editable first draft of a medical record document; and the wearable terminal is also used for receiving and presenting the first draft of the medical record document returned by the server side AI large model processing system, and editing and confirming the first draft of the medical record document to form a returned draft of the medical record document. The problem that in the prior art, a terminal lacks multi-modal real-time fusion and LLM closed loop, and doctor duplication interaction cannot be achieved is solved.

The invention discloses a federal large model knowledge collaborative training method supporting multi-modal heterogeneous clients, which comprises the following steps: each client receives a model initialization parameter issued by a central server, and applies adaptive differential privacy noise to independently train a heterogeneous lightweight model based on local private data; updating the model to which the noise is applied and uploading a modal identifier of the model to a central server side; after model updating and modal identification of each client are received, based on a modal perception weighted consensus fusion mechanism, knowledge of each client is fused to update a global large model; and the central server side issues the updated presentation layer parameters of the global large model to the client side for initialization of the next round of local training. According to the method, on the premise that a public data set or specific task setting is not needed, comprehensive compatibility of data isomerism, client dynamic participation, model diversity and privacy protection requirements is achieved, and the adaptability, stability and knowledge utilization efficiency of large model federation training are remarkably improved.

The invention discloses a WebSocket-based instant message task assigning system. The system comprises two parts, i.e., a server and clients, wherein the server is deployed on an application server and configured with ports for providing external services, and the server is then started; the clients comprises an APP client and a PC client; and information data transmission among the server, the APP client and the PC client is achieved based on the WebSocket protocol, that is, the server provides the instant messaging service, and the clients achieve acquisition of data from the server. Compared with the prior art, the system provided by the invention has the advantages that WebSocket-based instant message task assigning is achieved, and information can be synchronized between the information acquisition clients, so that high timeliness, effectiveness and safety of the information are ensured.

The invention discloses a storage and calculation separation key value storage delay optimization method based on prediction driving, and aims to solve the problems of performance bottleneck and high tail delay caused by passive management and high network delay in a key value storage system in a storage and calculation separation scene. The method comprises the following steps: time load prediction: deploying a time sequence prediction model at a client, and predicting a future read-write request based on a historical access sequence; active cache prefetching: according to the predicted read request, actively preloading hotspot data from a server side to a client side for caching so as to improve the cache hit rate and hide network delay; active write-in optimization: according to the predicted write request, executing maintenance at a server side through predictive pre-insertion and active node splitting, and moving high index structure adjustment overhead out of a key request path to eliminate a write delay peak; and structure sensing batch synchronization: pre-fragmenting a local write buffer by using a server index top layer model of a client cache, and combining multiple independent remote insertion operations into one efficient batch update to reduce data synchronization overhead. Compared with an existing passive management system, the characteristics of model prediction and active cooperation are fully utilized, and the average delay and the tail delay of the system are reduced.

The invention relates to the technical field of network security, in particular to a defense method and system for federated learning backdoor attacks, a server initializes a federated learning global model, and identifies at least one key layer easy to implant a backdoor in the global model; distributing the current global model parameters to a plurality of clients, receiving model update information uploaded by each client, extracting a multi-dimensional gradient feature vector of each client based on gradient information of each client in a key layer, calculating a mahalanobis distance anomaly score of each client relative to the gradient distribution of the whole client, and calculating the mahalanobis distance anomaly score of each client according to the mahalanobis distance anomaly score; and screening and rejecting the clients which are judged to be abnormal, aggregating model updates uploaded by the clients which are judged to be benign, and generating a new global model. Malicious updating is effectively isolated while the performance of the main task is ensured, and the robustness and safety of a global model are improved.

The invention discloses a vertical federal learning feature selection method based on context awareness, and belongs to the technical field of artificial intelligence and data privacy protection. According to the method, firstly, an unsupervised sparse network is utilized at a client to initialize the importance of local features so as to accelerate convergence and reduce calculation complexity; and then, obtaining the embedded representation of each client in a pre-training stage, and screening the embedded representation by combining context features through a server side, thereby indirectly identifying key features. In the feature selection stage, the client side performs local feature screening according to the significant embedded index issued by the server, and the influence of irrelevant features on calculation and communication is further reduced. According to the invention, an attention mechanism is introduced to dynamically evaluate contributions of different participants, so that fair weight distribution is realized. According to the method, through staged joint optimization, the communication and calculation cost in the federation training process is effectively reduced, and meanwhile, the prediction precision and interpretability of the model are improved.

The invention discloses a privacy protection federated learning method and system based on Transform and knowledge distillation, and belongs to the technical field of artificial intelligence and network security, and the method comprises the steps: taking an attention mechanism of a Transform model as a core component of local feature extraction, so as to capture a data long-distance dependency relationship and improve the feature representation quality; a Paillier encryption protocol is introduced to realize homomorphic encryption transmission of model weights; the knowledge distillation technology is adopted at the central server side, the aggregation global model serves as a teacher model to extract soft knowledge, and the feedback client side compresses the model and optimizes the model; according to the invention, the Transform is used as a local feature extractor, the Paillier encryption protocol is combined, and the knowledge distillation technology is adopted after the central server is aggregated, so that the detection performance under Non-IID data is optimized, and both data security and detection efficiency are realized.

The invention discloses a federal learning method and system based on global prototype guidance. The method comprises the following steps: a server sends a global model and a global prototype to a local client; the local client performs rebalance comparison learning by using the global prototype, and updates the local model; the local client generates a balanced confrontation positive prototype instance set and trains a classifier; the local client side calculates a local prototype and uploads the local prototype and the updated local model to the server side; and the service aggregates the updated local model and local prototype, and updates the global model and global prototype. The system comprises a server and a local client. According to the method, the Non-IID problem in federated learning is solved, and the accuracy and generalization of the model are improved. The method can be widely applied to the technical field of distributed machine learning.

The invention relates to the technical field of video processing, in particular to a multi-video semantic collaborative analysis method and system based on federated learning. Obtaining task complexity reported by the plurality of end-side computing devices respectively; dividing the plurality of end-side computing devices into K device groups based on the plurality of task complexities; respectively initializing K semantic analysis models for the K equipment groups at a server side; based on a federated learning framework, cooperating with a plurality of end-side computing devices and a server side to carry out layered distillation training on the K semantic analysis models; and correspondingly issuing the trained K semantic analysis models to each end-side computing device in the K device groups for video semantic analysis. According to the method, the overall efficiency, accuracy and generalization ability of multi-video semantic collaborative analysis can be improved, and configuration of computing resources is optimized.

The invention discloses a physical enhancement federation continuous fault diagnosis method for a complex electromechanical system, and belongs to the technical field of electromechanical system fault diagnosis. The method aims at solving the problem that an existing complex electromechanical system fault diagnosis method has the contradiction between privacy protection and distributed training. According to the method, continuous fault diagnosis of the complex electromechanical system is carried out based on a federated diagnosis system, and a server side distributes a generator and a global model to each client side for the client side to carry out continuous learning; the generator synthesizes the potential noise vector obeying normal distribution, the working condition vector encoding the working condition information and the classification label representing the fault type as input and outputs a synthesized vibration signal; in the federated learning process, the client determines whether to select the historical generator into a playback set according to the physical similarity between a current task and a historical task, the client generates synthetic samples from the playback generator set to construct a playback buffer area, and the number of the synthetic samples generated by each historical generator is distributed according to a preset proportion.

The invention discloses an LLM-DoS attack protection method based on a multi-level defense strategy and a related device, and belongs to the field of artificial intelligence security. According to the method, denial of service attacks aiming at a large language model are effectively prevented through a three-layer defense strategy: firstly, dynamic frequency control is carried out on an API request, a three-stage rate limiting system is established, a load-aware dynamic adjustment algorithm is introduced, and when the system load is too high, the quota is automatically adjusted; secondly, constructing an input perception classifier by adopting a lightweight Transform model, breaking through context limitation in combination with a random fragment compression and length penalty strategy, and realizing hierarchical interception of attack requests through a harmfulness scoring function; and finally, a request hash mapping and streaming response multiplexing technology is implemented at a server side, and real-time detection and response multiplexing are performed on repeated high-concurrency attack requests, so that consumption of computing resources is reduced. According to the method, the security and availability of the large language model service can be effectively improved, and the influence of DoS attacks on the system is reduced.

The invention discloses a target equipment upgrading method and device based on an equipment grading strategy, equipment, a medium and a product, and relates to the field of mobile terminal software upgrading, and the method comprises the steps that a server collects hardware features of target equipment and automatically grades the equipment by using a K-means clustering algorithm; generating a differential OTA upgrade package based on the grading result; segmenting the differential packet into data fragments with fixed sizes, and generating a hash value and a digital signature for each fragment; the equipment end downloads one by one, verifies integrity and signatures in real time, and supports breakpoint resume; the server side predicts the OTA upgrade failure risk through the trained random forest model, and dynamically adjusts a push strategy; the equipment adopts an A / B partition mechanism to realize safe rollback; in a non-secure network environment, the server and the device cooperatively generate a temporary key based on a device ID and a timestamp to encrypt and transmit fragments. The volume of the upgrade package is effectively reduced, the transmission efficiency is improved, the security is enhanced, and the upgrade failure rate is remarkably reduced.

The invention provides an interaction method and system for thromboembolism risk assessment, and can be applied to the technical field of artificial intelligence. The method comprises the steps that a first server side responds to an inquiry request sent by a first terminal, and inquiry diagnosis data and historical clinical data are sent to a second server side; the second server obtains an initial risk assessment score according to the inquiry diagnosis data and the historical clinical data; under the condition that the initial risk assessment score is greater than a preset risk threshold value, the second server side sends inquiry diagnosis data and historical clinical data to a second terminal; the second terminal determines risk influence factors according to the inquiry diagnosis data and the historical clinical data; the second server obtains the detection result, and performs hospital thromboembolism risk assessment on the detection data by using a Bayesian network to obtain a target risk assessment result; and the second server determines a rehabilitation guidance strategy according to the target risk assessment result and the discharge diagnosis result, and sends the rehabilitation guidance strategy to the first terminal.

The invention discloses a bacterial selenoprotein online resource platform, an application method, a terminal and a medium, and relates to the technical field of biological medicine, the online resource platform is deployed on a server, the cloud server is a Ubuntu cloud server, and Nginx, Waitpress and Flask are configured; the server side is in butt joint with a background resource, and the background resource is in butt joint with the constructed bacterial selenoprotein database; the server is in butt joint with a user interface of the front end, the user interface designs a corresponding interface framework and an interaction function based on static resources hosted by Nginx, and the interaction function is used for realizing query, analysis and use of relevant information of the bacterial selenoprotein. According to the method, a convenient online access channel of an integrated database and a real-time data analysis tool are provided for users in related fields, and important support is provided for accurate annotation of selenoprotein genes in a bacterial genome plan.

The invention belongs to the technical field of federated learning, and more specifically relates to a non-data-driven quantum federated learning method based on single communication. The method comprises the following steps: a plurality of clients independently train classical models by depending on respective local data, only perform single communication after training is completed, and upload model representation information to a server; after receiving the model representation information uploaded by each client, the server uniformly fuses the information to construct an integrated teacher model; the server synthesizes a pseudo sample from the random noise by using a pseudo sample generator under the guidance of the integrated teacher model; and migrating the knowledge of the integrated teacher model to the quantum student model through soft label distillation by using the generated pseudo sample, and finally obtaining a unified quantum student model at a server side. The technical problems that in existing quantum federation learning, communication overhead is large, privacy protection and efficiency are difficult to consider, and quantum hardware resources are seriously limited are solved.

The invention discloses an internet of things heterogeneous equipment federated learning method based on cross-modal knowledge distillation, belongs to the field of internet of things, and proposes a two-stage federated learning framework, introduces a knowledge distillation mechanism at a client side, uniformly distills local models with different structures and parameter scales into isomorphic models, and finally obtains the isomorphic models. And uploading the distilled model parameters to a server for aggregation. On the premise that original data and local model privacy are not leaked, the method realizes effective support for model heterogeneity, so that feasibility and stability of a single-round federal learning process are guaranteed. According to the method, an auxiliary knowledge distillation strategy based on the CLIP is further provided, and text-level semantic supervision information generated by a pre-trained CLIP model is utilized to guide a client image classification model to perform knowledge distillation and feature alignment, so that the generalization ability and the knowledge migration effect of the model are enhanced. According to the method, the effectiveness of knowledge distillation is remarkably improved in a non-independent identically distributed and long-tail data environment, and the overall performance of single-round federated learning is improved.

The invention belongs to the field of equipment information transmission, and particularly relates to a communication point-to-point uploading method and system for equipment in a transformer substation. Comprising the following steps: after communication point-to-point is started, generating a point-to-point file containing self-described communication point-to-point information corresponding to a communication protocol through a server side of a transformer substation according to the selected and matched communication protocol, and uploading the point-to-point file to a client side of the transformer substation; the communication point-to-point information with the self-description is mainly composed of a time sequence keyword used for representing the uploading time and sequence of information points, a name keyword used for representing the name description of the information points, and a protocol keyword used for representing the communication protocol model information of the information points; and analyzing the point-to-point file through a client according to the formats of a time sequence keyword, a name keyword and a protocol keyword to obtain communication point-to-point information with self description for communication point-to-point.

The invention discloses a self-adaptive processing method of a Kafka message queue system, which is characterized in that the message throughput is predicted based on an AI prediction method, and a resource scheduling instruction is generated according to a prediction result and a performance target to control the consumption concurrency; after local anomaly detection model training is carried out on each distributed node, model updating data are uploaded to a server side for safe aggregation, and global model updating parameters are generated and returned to optimize the detection capability of each node; carrying out parallel consumption processing on the message according to the instruction, carrying out classification retry and isolation on errors, and collecting processing performance indexes; and finally, the collected indexes are fed back to the resource scheduling and model updating step to form closed-loop control. According to the method, distributed collaborative anomaly detection of dynamic resource allocation and privacy security is realized, the throughput of the system is remarkably improved, the processing delay is reduced, and the reliability, the adaptability and the operation and maintenance automation level of the system are enhanced.

The invention provides an agent interaction processing method and system based on end-cloud cooperation and an electronic system, and relates to the technical field of artificial intelligence. The method comprises the following steps: in response to a user interaction request from a client, driving a target agent to perform reasoning and determining a target tool from a unified tool pool aggregated with a cloud tool and a client tool according to a reasoning result; if the target tool is a cloud tool, executing the target tool at the server side and generating an execution result, and if the target tool is a client tool, generating a calling mark object used for indicating a client to call a corresponding native function; converting the execution result or the calling mark object into a first standard instruction frame, and sending the first standard instruction frame to the client, so that the client executes a corresponding local operation; and receiving result data returned by the client, and recovering the context state of the target agent according to the result data so as to drive subsequent reasoning. According to the scheme, the problem that the end-side capability is difficult to directly call by a cloud large model can be solved.

The invention provides an equipment debugging system based on a serial port, which relates to the technical field of data processing, and comprises a server side and a client side which are in communication connection through the serial port, the server side comprises a memory, a command parser, a command distributor and a function executor; the memory is used for storing a debugging command registry; the command parser is used for parsing a protocol data packet which is transmitted through a serial port and comes from a client side, querying a debugging command registry and determining a debugging function corresponding to a command ID; the command distributor is used for distributing debugging functions to the function executor; the function executor is used for executing operation corresponding to the debugging function; the client side comprises a compiler, a description file analyzer and a graphical user interface; the compiler is used for generating a debugging description file after compiling the MCU program; the description file analyzer is used for analyzing the debugging description file, generating a protocol data packet and sending the protocol data packet to the server side through a serial port; the graphical user interface is used for displaying debugging information.

The invention discloses a federated learning image classification method based on time extension gradient cumulative average. Each client uses a local data set to train a local model to obtain gradient information of a current communication round, and uploads the gradient information to the central server after compression; the client continues to perform local training in a time period from the time when the client starts to upload the compression gradient information of the current communication round to the time when the server completes the compression gradient information aggregation of the current communication round; the central server side aggregates the compression gradient information to obtain average compression gradient information of the current communication round, and issues the average compression gradient information to the client side to update a local model of the (t + beta) th communication round; and repeating the steps until the training is completed, and inputting the to-be-detected image into the local model to obtain an image classification result. The method shows excellent performance under various data sets and different compression levels, has higher convergence speed and model precision, and solves the problem of low communication efficiency caused by network delay and bandwidth limitation in image classification of federated learning.

The invention relates to the field of computer data processing and artificial intelligence, and discloses a mobile phone APP intelligent code scanning and AI automatic identification system which comprises a mobile terminal, an internet network and a local server. The mobile terminal is provided with an acquisition detection module, and a mobile phone end code scanning module automatically controls light supplement when the image brightness is lower than a threshold value. A server-side AI intelligent recognition module executes Gaussian filtering, binarization and geometric correction preprocessing on a code scanning image, and a text is extracted by using a deep convolutional neural network and a bidirectional long-short-term memory network. And the system further executes semantic analysis by traversing the business template library, judges the attribution of key fields by using a spatial Euclidean distance, and generates structured JSON data. The statistical module calculates a real-time production efficiency index, and the remote viewing module associates and displays a process optimization suggestion when the data is abnormal. According to the invention, high-precision identification, business semantic understanding and intelligent decision support of code scanning data are realized.

A fashion show matchmaking virtual incubator system based on metaverse, and a method thereof are disclosed. A matchmaking database host stores a fashion show item and a matchmaking message, and a server-end device performs a virtual incubator platform. When a user logs in a platform, the server-end device drives a display device to display the 3D virtual fashion display space and the fashion show item. When detecting that the user selects the show item and corresponding matchmaking message, the server-end device generates a design commission request for the user to edit, transmits the design commission request to an order taking device. After the order taking device transmits back a design result, the server-end device displays the design result. After the user confirms, the server-end device displays the purchasing message and generates an order message to perform purchase, thereby improving convenience and efficiency of matchmaking transactions.

The invention relates to the technical field of data analysis and privacy protection, in particular to a privacy medical analysis method and system based on federated learning. The method comprises the steps that unified semantic modeling and ontology mapping are conducted on medical institution tasks through a server side, a multi-layer semantic ontology is constructed, and a mapping matrix is generated; the client performs semantic weighting by using the alignment features and confidence, constructs a local cross-domain feature association matrix, performs hierarchical privacy coding, generates abstract vectors and uploads the abstract vectors to the server; the server aggregates local model parameters based on abstract weights, optimizes a global model in combination with multilayer semantic consistency loss, and dynamically adjusts aggregation weights according to prediction errors; a dynamic self-adaptive fine tuning mechanism and a strategy generation mechanism are introduced, cross-domain migration and strategy optimization of the model are realized, and a closed-loop dynamic evolution system of the privacy strategy model is formed through a privacy constraint matrix and feedback credibility. According to the method, the accuracy, privacy and cross-mechanism adaptability of medical data analysis are improved.

The invention discloses an auditing method and device during function execution in reproductive medical service. A server side method comprises the steps that an information operation request sent by a client side is received; the information operation request carries a globally unique identifier and auditing parameters of the patient; checking whether the information operation request has an operation authority or not; when the information operation request has the operation authority and the parameter state of the auditing parameter is to-be-stored, performing data desensitization on original medical information in the auditing parameter to obtain to-be-stored medical information; constructing a first operation log based on a data operation function expression and a service attribute in the audit parameter; and storing the to-be-stored medical information to the medical data table by adopting the global unique identifier, and storing the first operation log to the audit data table. By adopting the embodiment of the invention, the security of data transmission and storage can be improved. Meanwhile, the operation behavior of each link is accurately recorded and monitored through a refined management mode, and the transparency and traceability of data are improved.

The invention belongs to the technical field of computers, and relates to a federal continuous learning method based on multi-scale expert collaboration. The method comprises the following steps: 1) each client constructs a multi-adapter enhancement architecture based on a pre-training basic model, and adapter parameter fine tuning is carried out in a first task stage; 2) performing prototype initialization on each client by using the semantic features of the old task and the sample features of the new task, and fusing historical knowledge into new category representation learning; 3) each client divides the pre-training model into a plurality of feature learning expert modules, extracts feature representations of different levels, and collaboratively optimizes the classification performance of each expert through multi-scale feature learning loss; 4) each client adopts an uncertainty weighted multi-teacher self-distillation mechanism to dynamically fuse shallow texture features and deep semantic knowledge to a final expert, and 5) the server integrates adapter parameters and multi-scale category prototypes of each client through a weighted aggregation mechanism to form a global knowledge base and distributes the global knowledge base to all clients.

The embodiment of the invention provides a batch retrieval method based on a verifiable bloom filter and electronic equipment, and relates to the technical field of data security. The method comprises the following steps: converting a server data set into a key value pair form, and mapping keywords in the data set in the key value pair form into equal repeated codes through an equal repeated code mapping algorithm to obtain an equal repeated code data set; determining a storage position of a second verifiable bloom filter according to a keyword in the equal-repetition-code data set, and storing a data entry corresponding to the keyword in the equal-repetition-code data set and a check code generated based on the data entry to the storage position; the client receives the query keyword set and maps the query keyword set to the first verifiable Bloom filter; and taking each bit of the first verifiable Bloom filter as a selection vector to execute an oblivious transmission protocol to obtain a return result of the server side. The embodiment provided by the invention provides a safe and efficient batch retrieval method based on the verifiable Bloom filter.

An active chatbot system with behavioral awareness and on-demand conversation and a method thereof are disclosed. In the active chatbot system, a client-end host continuously senses a client behavior state, and transmits the sensed client behavior state and an on-demand conversation setting to a server-end host to generate a rough question message having a natural language structure, and input the rough question message to a plurality of finite state machines to generate a precise question message. The server-end host transmits the precise question message to an artificial intelligence platform to obtain a corresponding answer message, stores the answer message to an answer list, filters out an answer message matching the on-demand conversation setting as an on-demand conversation message, transmits the on-demand conversation message to the client-end host for output. Therefore, the technical effect of improving human-computer interaction and initiative of chatbot can be achieved.