347 results about "Local machine" patented technology

The invention discloses a method for generating and constructing a database test knowledge base based on an open source large language model and retrieval enhancement, and relates to the technical field of database testing, and the method comprises the steps: building a local deployment system on a local computer system or server, and achieving the efficient local operation of the open source large language model and the stable output of language processing service; on a local computer system or a server, a retrieval enhancement generation framework is constructed, and accurate knowledge support and reliable content output are provided for local language processing service by integrating multi-modal knowledge, optimizing retrieval and generation processes and guaranteeing safety and compliance; on a local computer system or a server, a personalized database knowledge base is built, database related information is collected and processed from multiple channels and is output in an adaptive form, and the specified information requirement of local personalized language processing service is met. According to the method, efficient and stable operation of the open source large language model is realized, accurate and reliable language processing output is realized, and personalized services meet specific requirements.

The invention relates to a heading machine cutting path planning system and method. The method comprises the steps that at least one coordinate value of a roadway under a local machine coordinate system is determined; acquiring a preset cutting path of the tunneling equipment according to the coordinate value; in response to tunneling equipment for tunneling based on the preset cutting path, obtaining a deviation between the real-time pose of the cutting head and the preset cutting path; and adjusting the cutting head according to the deviation. By determining the coordinate value of the roadway under the coordinate system of the machine, the tunneling equipment can obtain a more accurate preset cutting path according to the coordinate value; when the tunneling equipment carries out tunneling based on the preset cutting path, feedback adjustment is carried out on the swing of the cutting head through the deviation between the real-time pose of the cutting head and the preset cutting path, so that the tunneling equipment can obtain a more accurate cutting path through feedback adjustment, unnecessary repeated movement is avoided, manual intervention is reduced to the maximum extent, and the tunneling efficiency is improved. And the method has wide applicability.

A network system of pattern analysis includes a centralized AI-based pattern analysis engine and each computing device comprises a local AI-based pattern analysis engine. The pattern analysis engine(s) each analyze computing operations on a local machine basis or a on a network basis depending on where installed. The AI-based pattern analysis engines identify common activity patterns for each machine and exclude the common activity patterns from further analysis of the computing operations, leading to more efficient identification of activity patterns indicative of nefarious activity. Once detected, the AI-based pattern analysis engines trigger an incident response to counter the nefarious activities. The AI-based pattern analysis engines include AI models that are continually or periodically trained to update the baseline common activity patterns.

Techniques of updating machine learning models in a network include combining global and local models at each electronic entity of a network. For example, a first electronic entity (e.g., a user device) may train a local machine learning (ML) model based on data collected by the first electronic entity or other entities (e.g., other user devices, servers) and make predictions based on that model. Nevertheless, other electronic entities may also train or store their own local ML models. Accordingly, for more insight about the network and better predictability of the ML models, the first electronic entity may obtain a ML model from a second electronic entity, i.e., a global ML model. Upon receipt of the global ML model, the first electronic entity may aggregate the local ML model and the global ML model to produce an updated global ML model.

The invention discloses a cooperative low-altitude small and medium-sized unmanned aerial vehicle collision avoidance system, and the system comprises a flight path prediction module which is used for receiving the flight data of a local aircraft and the flight information of other targets in a low-altitude airspace, and predicting the flight paths of the local aircraft and other flight targets; the conflict detection module is used for receiving the flight path prediction information of the local machine and other targets sent by the flight path prediction module, receiving the local map information in the task data storage module at the same time, performing conflict judgment according to the prediction information and the map information, and sending a conflict judgment result to the planning anti-collision processing module; and the planning anti-collision processing module is used for receiving the conflict judgment result, if no conflict exists, task execution is carried out according to an original plan, and if the conflict exists, anti-collision planning processing is carried out and anti-collision planning is carried out. Operation rule support and safety guarantee are provided for low-altitude operation, and meanwhile the low-altitude airspace utilization rate is increased.

The invention discloses an air combat intelligent decision-making method combining imitation learning and reinforcement learning, and belongs to the field of air combat, and the method comprises the steps: processing battlefield situation information through an air combat intelligent decision-making model, and obtaining a decision-making result used for guiding a local machine. The pre-trained air combat intelligent decision-making model is obtained through the following steps: for sparse expert strategy data with coarse granularity, using a behavior cloning algorithm to train a neural network architecture for imitation learning and reinforcement learning to obtain a strategy network Q1; taking the strategy network Q1 as an initial network in a generative adversarial imitation learning algorithm, and performing imitation learning on a fine-granularity dense expert strategy to obtain a strategy network Q2; and taking the strategy network Q2 as an initial network of a decision network in the reinforcement learning algorithm framework, and carrying out network training by adopting a strategy gradient method until convergence to obtain an air combat intelligent decision model. According to the invention, the sample utilization rate can be effectively improved, and accumulative errors are reduced.

The invention discloses a multimedia resource access method and electronic equipment, and relates to the technical field of terminals, and the electronic equipment can flexibly access multimedia resources in image libraries of other electronic equipment in a local machine. The method comprises the steps that a first device displays a first interface, the first interface comprises a first area and a second area, a first option, a second option and a third option are displayed in the first area, the first option corresponds to the first device, the second option corresponds to the second device, and the third option corresponds to the third device; preview information of a photo album in the first equipment is displayed in the second area. And in response to a selection operation on the second option, the first equipment displays preview information of the photo album in the second equipment in the second area. And in response to a selection operation on the third option, the first equipment displays preview information of the photo album in the third equipment in the second area.

The systems and methods for improving pose estimation models are disclosed herein. Digital image data of an environment can be obtained and provided to a first machine learning model. A first confidence metric can be computed for the image. The first confidence metric can be compared with a threshold value and provided to a second machine learning model. A second confidence metric can be generated for training of machine learning models for pose estimation. A generic machine learning model can be updated using model parameters from trained local machine learning models.

The invention provides a data security circulation and updating method based on a block chain and federal learning. The method comprises the steps that a model publisher publishes trained model parameters to the block chain; each terminal user obtains a corresponding initial model parameter from the block chain, and a new parameter is trained through local machine learning; the local training parameters are uploaded to the block chain safely and efficiently through a network; the block chain regards model parameters trained each time as a transaction, and when the model converges, the transaction is packaged into a block; according to the method, the problems of data potential safety hazards, single-point faults and opaque data flow caused by a centralized architecture in the federated learning process are solved, a decentralized, transparent and efficient model parameter flow mechanism is constructed, and the method is suitable for being applied to a federated learning system. It is ensured that federated learning participants can safely share and update model parameters, the safety of the whole system is improved, and privacy protection is achieved.

The invention provides an emergency communication network generation method, a terminal device and an electronic device, the method is applied to a first node device in a wireless communication network, and when the communication of the wireless communication network is interrupted due to unforeseen circumstances, each node device monitors a neighbor node list broadcasted by other node devices to generate an emergency communication network. And comparing the received neighbor node list with the neighbor node list of the local machine, determining cluster head equipment, and forming a corresponding target communication cluster by taking the cluster head equipment as a central control node. And the cluster head device sends a cluster establishment message to the effective neighbor node in the neighbor node list, the effective neighbor node adds to the target communication cluster as the identity of the cluster member based on the received cluster establishment message, and finally each cluster member device carries out data receiving and sending according to the unified scheduling information sent by the cluster head device. Therefore, each node device can quickly form a communication cluster and then quickly recover communication according to the unified scheduling information sent by the cluster head device.

An example method of displaying windows in a remote desktop system, includes: obtaining, by a remote desktop client executing on a local computer having a local operating system (OS), information relating a first window to a first virtual desktop generated by the local OS; sending the information from the remote desktop client to a remote desktop server; setting, by the remote desktop server, a tag in a remote window object representing a remote window that corresponds to the first window based on the information, the remote window generated by a remote OS on a remote computer; receiving, at the remote desktop client, at least a portion of the remote window object including the tag; and displaying, by the remote desktop client in cooperation with the local OS based on the tag, the first window on the first virtual desktop.

The invention discloses a data security management and control method and device based on classification and grading, a medium and a product, and relates to the technical field of data security management, and the method comprises the steps: obtaining a data confidentiality grade labeling strategy; performing grade labeling on the data stored in each local computer and the data center according to a grade labeling strategy; establishing a data classification grading and security control model based on a neural network by adopting a transverse federated learning architecture; performing data set division based on the desensitized data, different from the data confidentiality level of the local computer, in the data center and the data in the local computer to obtain a training set and a test set; according to the training set and the test set, training the data classification and grading and security management and control model to obtain a trained model; and based on the trained data classification and grading and security management and control model, carrying out classification and grading on data with unknown confidentiality levels. According to the invention, accurate classification and security control can be carried out on the data with unknown confidentiality levels.

A method for performing a vehicle diagnostic process for diagnosing, scanning and / or programming a vehicle includes recording a diagnostic message from a diagnostic computer device to generate a recorded diagnostic message, transmitting the recorded diagnostic message to a local computer at a repair facility, with the diagnostic computer device being located remotely from the repair facility, and playing the recorded diagnostic message at the local computer for delivery via an interface device to an electronic system of a vehicle. The method then further includes recording with the local computer a vehicle message from the electronic system of the vehicle to generate a recorded vehicle message in response to playing the recorded diagnostic message, and transmitting the recorded vehicle message from the local computer to the diagnostic computer device.

A method for training a local machine learning model is provided. The method includes receiving a scanning electron microscope (SEM) image of semiconductor features. The method additionally includes determining a location and dimensions of a bounding box within the SEM image. The method yet further includes determining, whether a defect feature exists within the bounding box, based on an unsupervised object detection process. The method also includes, if the defect feature exists within the bounding box, receiving positive rewards. The method also includes, if the defect feature does not exist within the bounding box, receiving negative rewards.

Systems and methods for implementing a balanced client selection for decentralized machine learning (BCS-DL) that can be utilized in both decentralized machine learning and hybrid machine learning for vehicle environments are described. For example, a vehicle can include a processor device training a machine learning model using local data, and a controller device performing balanced client selection in real-time to communicate the local machine learning model with a connected vehicle for decentralized machine learning. Hybrid machine learning combines aspects from federated learning and decentralized machine learning approaches. The disclosed BCS-DL system is designed to execute balanced client selection in real-time for vehicles that are acting as clients in a hybrid machine learning infrastructure. The balanced client selection also calculates a training contribution estimation (TCE) and a model weight computation (MWC) to mitigate imbalance in the data distribution incurred by non-Independent, Identically Distributed (non-IID data) related to decentralized and hybrid machine learning.

The invention discloses a multi-robot path coordination system based on reinforcement learning, and the system comprises a state collection module which is used for collecting the operation state and environment perception information of each robot, and generating an original data set; the state modeling module is used for constructing local state representation for each robot in each decision period; the opponent perception module is used for executing opponent learning perception training and outputting opponent parameter estimation vectors; the improved LOLA module is used for generating a final estimation result on the basis of self-strategy updating of the traditional LOLA; the strategy updating module is used for correcting the updating direction of the reinforcement learning strategy of the local machine and generating a feasible action set; the arbitration decision module is used for executing arbitration solution in combination with the candidate path action distribution to generate a scheduling result; and the execution feedback module is used for issuing the control action to a robot executor for execution, generating a path coordination result and storing the path coordination result. According to the invention, path coordination of multiple robots is realized.

A network system of pattern analysis includes a centralized AI-based pattern analysis engine and each computing device comprises a local AI-based pattern analysis engine. The pattern analysis engine(s) each analyze computing operations on a local machine basis or a on a network basis depending on where installed. The AI-based pattern analysis engines identify common activity patterns for each machine and exclude the common activity patterns from further analysis of the computing operations, leading to more efficient identification of activity patterns indicative of nefarious activity. Once detected, the AI-based pattern analysis engines trigger an incident response to counter the nefarious activities. The AI-based pattern analysis engines include AI models that are continually or periodically trained to update the baseline common activity patterns.

In one embodiment, a supervisory device receives one or more goal parameters for trainer clients in a federated learning system configured to train local machine learning models using local datasets. The device configures, based on the one or more goal parameters, the trainer clients to quantize their local machine learning models prior to sending them for aggregation into a global model. The device determines an amount of resource savings associated with the trainer clients quantizing their local machine learning models. The device provides an indication of the amount of resource savings for presentation to a user.

The invention provides an unmanned aerial vehicle group obstacle avoidance method and system based on least square and distributed arbitration, and belongs to the field of multi-unmanned aerial vehicle path planning, and the method comprises the steps: maintaining the historical observation data of a dynamic obstacle; a trajectory prediction model is constructed based on historical observation data, and a future trajectory prediction set is generated through least square fitting; selecting an optimal prediction model from the trajectory prediction set through a backtracking verification strategy; on the basis of a preset distributed arbitration rule, whether the local machine obtains the release right of the obstacle prediction information or not is judged; packaging the trajectory information corresponding to the optimal prediction model into a standard message by using the unmanned aerial vehicle which obtains the release right, and broadcasting the standard message to the cluster; and incorporating the obtained predicted trajectory message into collision avoidance constraint of a planner, performing local trajectory planning, and generating a collision-free flight path. According to the method, the safety, the collaboration and the passing efficiency of the cluster system in a real complex scene are remarkably improved.

The invention discloses a historical record backtracking method based on LLM, and relates to the field of data retrieval and natural language processing, and the method comprises the steps: collecting various operation data of a user in a local computer, extracting text information in pictures and voices in combination with an OCR technology and an ASR technology, and storing the text information and related information in a database in a unified format; the method comprises the following steps of: processing collected multi-modal data information, firstly performing de-duplication and cleaning on the collected data, then converting a collected screenshot into a video, and finally performing vector embedding on a video image frame, an OCR (Optical Character Recognition) result and a voice transcription text and storing the video image frame, the OCR result and the voice transcription text into a vector database; optimizing the pre-trained LLM in a specific direction by adopting a fine tuning technology; according to the method, conversation with a historical timeline is realized, user input is captured and stored in a query queue, personalized response is generated through LLM interaction in combination with a memory module and an RAG technology, and answers and related image or audio links are displayed.

Embodiments are disclosed for a group security scheme for an autonomous vehicle engaged in a collaborative machine learning approach. As an example, a method comprises: generating, in a vehicle, a digital signature based on a first key and a second key, both of the first key and the second key received from a group manager, and transmitting a message signed with the digital signature to a collaborator, the message including coefficients of a local machine learning model of the vehicle. In this way, an accuracy of the local machine learning model of the vehicle may be increased, while a privacy of the vehicle is increased.

The invention provides an implementation method for converting a GB28181 protocol RTP video stream into a low-delay HTTP-PS video stream, which is applied to an HTTP-PS server and comprises the following steps: step 1, receiving a streaming media playing HTTP connection request of a client; step 2, analyzing a device code DEV1 and a channel code CHANNEL1 of a target video source from the streaming media playing HTTP connection request, and creating an HTTP response object; step 3, randomly acquiring an unused TCP port P1 from the local machine, and starting the Socket service S1 to monitor the port P1; step 4, initiating a stream taking request to the SIP server to request the SIP server to send the RTP video stream of the target video source to the Socket service S1; step 5, after the Socket service S1 receives the RTP data after each PS data packet is subpackaged sent by the target video source, the RTP data is packed in real time to obtain the PS data packet, and the PS data packet is written into the HTTP response object, so that the client obtains the PS packet data from the HTTP response object and displays a frame of live broadcast picture; and step 6, when monitoring that the HTTP connection is disconnected, stopping the Socket service S1.

The invention provides a multi-target positioning method based on single-point positioning of a photoelectric pod, and relates to the technical field of inertial navigation, and the method comprises the following steps: S1, connecting inertial navigation data into the photoelectric pod in flight, obtaining the position and attitude information of a local machine, then carrying out laser ranging on a central target of a field of view, and obtaining the target of the field of view; the laser optical axis is consistent with the optical axis of the current observation sensor; s2, acquiring the pixel position of a point of which the position needs to be mastered in the image, and calculating the coordinate of any selected point in the image; according to the method, on one hand, the laser ranging distance, current attitude information and local position information at the same moment are combined, on the other hand, the ground height is obtained through the target height obtained through last laser or in an advanced binding mode, and the current attitude information and the local position information are combined; and the two methods are mutually switched to calculate the position information of the selected point and the distance deviation from the center. According to the method, the distance of the center of the target can be measured through laser, and geographic coordinates of any point in a photoelectric pod observing and aiming picture are obtained.

Methods and systems for securely managing personal data associated with image processing include an image sensor configured to capture an image, a local computer system local to the image sensor, and a backend computer system remote from the image sensor. The local computer system has a processor with a trusted execution environment (TEE) that detects anomalies in images from the image sensor, extracts personal data from the image, and encrypts the personal data. The local computer system then sends the extracted, encrypted personal data to the backend computer system, where a backend TEE decrypts the extracted, encrypted personal data, and performs data processing by comparing the decrypted personal data to other personal data that is stored in a backend database in the backend computer system.

The invention provides a mobile terminal, a control method thereof and a program product. The mobile terminal and the control method thereof are used for achieving the functions that the mobile terminal supplies power to the outside, charges a local machine and carries out data communication with external equipment through an interface. The mobile terminal comprises a signal switching module which is used for conducting a signal path between an input charging module and a signal end of an interface module under the condition of a first working state, or conducting a signal path between an output discharging module and the signal end of the interface module under the condition of a second working state; the control module is coupled with the input charging module, the output discharging module and the signal switching module; the control module is configured to obtain an electric power role of the external device and a data communication demand identification result; the working state of the signal switching module is controlled based on the power role of the external equipment; and determining whether to perform data communication with the external device based on the data communication demand identification result.

A local machine learning based recording and audio transcribing system is proposed that operates in real-time in parallel and time-synchronized with a operating theatre recorder system, modifying encoding of the operating theatre recorder system outputs for generation of the pre-processed recording files to be transmitted to a remote cloud-based processing backend using operating a centralized machine learning model data architecture across a network. By modifying the recording or the generation of the pre-processed recording files, the system can be tuned for providing increased signal resolution at more relevant portions of time or frame portions to improve the accuracy and predictive capability of a backend machine learning model that is configured for operation using the pre-processed recording files while adapting for practical network bandwidth and computing resource limitations in cloud-based implementations.

The invention relates to a kernel-based federal learning method and system, computer equipment and a storage medium. Target clients are selected from a client set to form a client subset; sending a first parameter of the first machine learning model and the number of iterations to the client subset; wherein the target client is used for performing random feature sampling and double stochastic gradient evaluation according to the first parameter and the number of iterations, and updating a second machine learning model based on double stochastic gradients to generate a second parameter; the first machine learning model is a local machine learning model of the server, and the second machine learning model is a local machine learning model of the target client; receiving a second parameter returned by the client subset, and updating the first machine learning model according to the second parameter; the expansibility of the kernel method in a federated learning scene is improved; and model convergence acceleration is facilitated.

The invention provides a security and protection monitoring system based on a master-slave controller mode. The system comprises a master controller elected in advance through an election mechanism, and a plurality of slave controllers in communication connection with the master controller, each slave controller receives and processes a video processing task sent by the video monitoring equipment bound with the slave controller, and calculates a current computing power load according to the number of video frames which can be processed and output by a local machine per second, the number of targets needing to be processed in each frame of image and the number of tasks waiting to be processed in a task queue; according to the technical scheme of the invention, the current computing power load is sent to the master controller, so that the master controller can determine the overload slave controller and the low-load slave controller according to the current computing power load sent by each slave controller, and distributes a part of video processing tasks in the overload slave controller to the low-load slave controller, thereby reducing the response delay and improving the video processing efficiency. And system crash can be avoided, and computing power cooperation among the slave controllers is realized, so that the overall performance of the system is effectively improved.

The invention discloses a multi-cluster hot debugging method based on Service Mesh, and belongs to the technical field of cloud native software development. Through a debugging instruction, a multi-cluster intelligent routing gateway establishes a unified and logically isolated debugging session and a virtual network environment for a developer terminal and a plurality of target Kubernetes clusters; the gateway dynamically allocates a local port for a debugging task from a global resource pool, and instructs a target cluster to create a Pod; the gateway serves as a center node, performs cross-cluster routing conflict detection, generates a globally consistent dynamic routing rule and issues the dynamic routing rule to a target cluster; and finally, forwarding the online traffic matched with the rule to an appointed port of a developer local machine through a proxy Pod and a gateway. Through a centralized intelligent coordination architecture, various conflicts in a multi-cluster environment are fundamentally avoided, and the debugging efficiency, stability and automation level are remarkably improved.

The invention discloses a traffic signal lamp time service time adjusting method, and relates to the field of intelligent traffic, and the method comprises the steps: signal lamp equipment obtains a satellite time service data packet and a central time service data packet in real time in the operation process, and the satellite time service data packet and the central time service data packet comprise time service time provided by various time service modes; respectively calculating the stability magnitude P of each time service mode; when a time service deviation exists between the time service time provided by the time service mode selected by the equipment and the timing time of the local machine, determining the maximum duration allowed to be adjusted per second in the time service mode according to the corresponding P value and the time service deviation duration; and the equipment adjusts the time service time according to the maximum duration allowed to be adjusted per second, and calculates the maximum duration allowed to be adjusted per second at the next time until the time service deviation is eliminated. When the intelligent signal lamp equipment uses wireless or bus communication, precision time service can be realized among the equipment, and risks caused by time asynchronization of the signal control equipment are reduced as much as possible.