Patents
Literature
318 results about "Information representation" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Representation information is the extra structural or semantic information, which converts raw data into something more meaningful.
Joint multi-modal entity relationship extraction method and system based on information representation and semantic alignment
ActiveCN121859903ADigital data information retrievalSemantic analysisPattern recognitionCorrelation coefficient
The invention discloses a joint multi-modal entity relationship extraction method and system based on information representation and semantic alignment, and the method comprises the steps: obtaining sample data composed of an original image and a text, and obtaining the feature representation of visual information and text information based on the sample data; aligning the feature representation of the visual information and the feature representation of the text information by using a progressive modal semantic alignment strategy; by introducing a multi-layer correlation mapping mechanism guided by fine granularity, the correlation coefficient represented by the features of the aligned visual information and text information is judged, and features irrelevant to a task core are filtered; performing visual representation and text interaction by using a multi-modal interaction module to obtain multi-modal semantic features; carrying out weighted mapping on the multi-modal semantic features by utilizing a routing weighting function, and finally obtaining multi-modal feature representation; and sending the multi-modal feature representation into a word pair relation label extractor, and extracting an entity, an entity relation and an entity attribute quintuple.
Owner:YANBIAN UNIV
Power load prediction method based on interpretable multi-modal enhancement
The invention belongs to the technical field of power load prediction, and relates to a power load prediction method based on interpretable multi-mode enhancement, which comprises the following steps: 1, constructing a text representation mode of an original load time sequence through a multi-mode enhancement module; 2, time sequence modal information and text representation information of the load are embedded into a high-dimensional vector space through a two-channel coding module; 3, receiving an embedded vector of a time sequence mode through a multi-mode prediction module, and taking a representation vector of a multi-mode text as input; 4, realizing an interpretable multi-mode alignment module; according to the method, the effects among the multi-modal information are divided into uniqueness, redundancy and collaboration; by constructing a negative sample pair for training, alignment of multi-modal information representation is enhanced, and then the prediction performance of the model is improved.
Owner:XI AN JIAOTONG UNIV
Systems and methods according to LLM-based agent groups for generating and enhancing engineering data funnel output
Embodiments of the present disclosure relate to systems and methods according to LLM-based agent groups for generating and enhancing engineering data funnel outputs. A method of obtaining a target structured information representation from one or more documents indicating the same process plant by using an interactive large language model (LLM)-based agent group in the context of an industrial plant is disclosed. The method includes obtaining at least one of the one or more documents at the LLM-based agent group. Each LLM agent from the group of LLM-based agents is given a task and a role, and is associated with one or more data processing tools from a set of predetermined data processing tools based on the given task and role. The method includes: selecting two or more LLM-based agents from a group of LLM-based agents for processing the document; processing the document by one of the selected two or more LLM agents, and outputting a structured information representation as a result of the processing; causing the selected two or more LLM agents to interact with the structured information representation based on a task and a role given to the selected two or more LLM agents; and obtaining a target structured information representation based on a result of the interaction.
Owner:ABB (SCHWEIZ) AG
Neuromorphic data classification method based on gated space-time self-attention mechanism and spiking neural network
The invention discloses a neuromorphic data classification method based on a gating space-time self-attention mechanism and a spiking neural network, and the method comprises the following steps: 1, selecting a public neuromorphic data set, carrying out the data preprocessing, and dividing the data into a training set, a verification set and a test set; 2, constructing a pulse neural network model to perform neuromorphic data classification, and introducing a gating space-time self-attention mechanism into the model to adaptively capture a global dependency relationship of space and time dimensions and enhance the space-time information representation capability of the model; and 3, training the constructed spiking neural network model by using the training set and the verification set, testing the trained model by using the samples in the preprocessed test set after training is completed, and outputting a prediction classification result of the samples by the model. According to the method, the representation capability of the spiking neural network in spatial-temporal feature modeling is remarkably enhanced through a gating spatial-temporal self-attention mechanism, and the precision of a neuromorphic data classification task is improved.
Owner:XI AN JIAOTONG UNIV
Geographic space entity vectorization method and system based on multi-modal fusion and metric learning
The invention discloses a geographic space entity vectorization method and a geographic space entity vectorization system based on multi-modal fusion and metric learning, which are used for solving the problems that the traditional geographic information representation is single and multi-source data cannot be effectively fused. The method comprises the following steps: firstly, carrying out multi-modal feature extraction on text and coordinate information of a geographic space entity; then, through a neural network model with an independent coding stream and a deep fusion layer, intelligently fusing the multi-modal features and projecting the multi-modal features to a unified embedded vector space; and finally, optimizing the model by adopting a metric learning normal form through a hybrid triple sampling strategy combining semantic and spatial constraints. The invention also provides a system for realizing the method. The system comprises a feature engineering module, a training set generation module, a model training module and a reasoning application module. The system can automatically complete the whole process from data preprocessing, model training to vectorization reasoning. Compared with the prior art, the method has the advantages that the embedded vector with high semantic distinction degree and accurate spatial perception capability can be generated, and the computability and intelligence of geographic spatial data are effectively improved.
Owner:SHANGHAI DIGITAL CITY PLANNING RESEARCH CENTER
A robot cognitive development method based on ontology semantics
The application discloses a robot cognitive development method based on ontology semantics, and comprises the following steps: constructing a robot article identification professional knowledge base based on attribute function and ontology information representation of article definition; information determination based on attribute discrimination and semantic search; and robot cognitive development based on attribute information addition. The application simulates the process of human memory, learning and cognition of articles based on an ontology semantic knowledge base, and through machine learning and sensor attribute information, the robot can actively cognize, learn, expand and accumulate learned knowledge and experience according to information data; the robot can continuously develop its cognitive ability through learning, automatically construct a robot article identification professional knowledge base of unknown articles, and based on a semantic structure of triplets, share knowledge and exchange operation logic between man and machine, so that the cognitive level of the robot is improved and the operation experience of an operator is improved.
Owner:SOUTH CHINA AGRICULTURAL UNIVERSITY
Power grid attack defense method, terminal equipment and storage medium
PendingCN121283669ASecuring communicationInformation technology support systemPathPingElectric power system
The invention is suitable for the field of power systems, and provides a power grid attack defense method, terminal equipment and a storage medium. The power grid attack defense method comprises the following steps: an edge node determines local abnormal information and a first response strategy according to local communication data, wherein the local abnormal information represents power grid attack information suffered by the edge node; determining local association information according to the local exception information and shared exception information of the adjacent nodes, wherein the local association information represents an association relationship between the edge node and the plurality of adjacent nodes; sending the local association information to the central node; obtaining traceability information obtained by the central node according to the local association information, wherein the traceability information represents attack source information and attack path information of the power grid attack; and determining a second response strategy according to the traceability information and the local abnormal information. Through the synergistic effect of the edge nodes and the center node, the full-chain identification and multi-point protection capabilities of the power system in a complex attack environment are improved.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID QINGHAI ELECTRIC POWER COMPANY
Synthesizing content using diffusion models in content generation systems and applications
Approaches presented herein provide for the generation of synthesized data from input noise using a denoising diffusion network. A higher order differential equation solver can be used for the denoising process, with one or more higher-order terms being distilled into one or more separate efficient neural networks. A separate, efficient neural network can be called together with a primary denoising model at inference time without significant loss in sampling efficiency. The separate neural network can provide information about the curvature (or other higher-order term) of the differential equation, representing a denoising trajectory, that can be used by the primary diffusion network to denoise the image using fewer denoising iterations.
Owner:NVIDIA CORP
Method and apparatus for determining three-dimensional information, device, storage medium, and program product
A method for determining three-dimensional information of an object is performed by a computer device. The method includes: obtaining an image of an outer surface of a photographed object, the outer surface of the photographed object having n protruding stereoscopic units, and n being a positive integer; processing the image, to obtain frame information of at least one stereoscopic unit, the frame information including a first surface and a second surface of the stereoscopic unit in the image, the first surface being parallel to the second surface; and determining three-dimensional information of the stereoscopic unit based on the frame information of the stereoscopic unit, the three-dimensional information representing a position of the stereoscopic unit in the image and a protrusion degree of the stereoscopic unit in a direction perpendicular to the outer surface. This method helps reduce difficulty in obtaining three-dimensional information of a stereoscopic unit.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD
Method for predicting sinking posture of open caisson
The invention discloses an open caisson sinking posture prediction method, which belongs to the technical field of open caisson sinking prediction, and comprises the following steps: constructing a primary data matrix according to on-site actual measurement time sequence data; smoothing the first-level data matrix by using a Savitz-Gauge filtering algorithm to obtain a second-level data matrix; constructing a third-level data matrix in combination with the second-level data matrix and the construction excavation information representation matrix; performing correlation analysis on the three-level data matrix by using three analysis methods to obtain a correlation characterization matrix; screening key variables by using the correlation characterization matrix to construct a four-level data matrix; performing dimension reduction processing on the four-level data matrix by using a principal component analysis method to obtain a principal component matrix; and training a long-short-term memory network by using the principal component matrix to obtain an open caisson sinking posture prediction model to perform open caisson sinking posture prediction so as to obtain an open caisson sinking posture prediction result. According to the method, the accuracy and stability of deep water open caisson sinking posture prediction can be improved.
Owner:中铁桥隧技术有限公司
Route selection method and related device
This application discloses a route selection method and a related device. A control entity determines first metric information of a first segment routing (SR) path, generates a first border gateway protocol (BGP) update message including the first metric information, and sends the first BGP update message to an ingress node of the first SR path, where the first metric information represents quality of the first SR path, the first metric information is used for route selection on a plurality of paths, each of the plurality of paths has a same IP prefix of a destination node, and the plurality of paths include the first SR path. According to the method, the control entity can send, to the ingress node of the SR path by using the BGP update message, the metric information that represents the quality of the SR path.
Owner:HUAWEI TECH CO LTD
Automatic driving track prediction method and device based on self-attention coding
The invention discloses an automatic driving track prediction method and device based on self-attention coding, and relates to the technical field of automatic driving, and the method comprises the steps: obtaining the historical driving data of a target automatic driving vehicle; preprocessing the historical driving data to obtain standard historical driving data; based on a self-attention mechanism, carrying out coding fusion on the standard historical driving data to obtain target automatic driving vehicle information representation prediction data; and based on a self-attention mechanism, decoding the information representation prediction data of the target automatic driving vehicle to obtain a predicted driving track of the target automatic driving vehicle. The adaptability and generalization ability of the system in a complex and changeable road environment are enhanced, and the accuracy of a prediction result and the driving safety are improved.
Owner:ANHUI JIANGHUAI AUTOMOBILE GRP CORP LTD
Remote sensing image classification method and system based on change perception and space-time fusion
ActiveCN121505370AScene recognitionNeural learning methodsClassification methodsInformation representation
The invention discloses a remote sensing image classification method and system based on change perception and space-time fusion, and relates to the technical field of image data processing. The method takes a multi-temporal remote sensing image sequence as input, and adopts a hierarchical visual Transform backbone network to extract multi-level semantic features; extracting multi-stage change prior features through change prior branches based on the initial and end time phase difference images; performing scale alignment on the change prior features through a multi-stage feature time sequence fusion module, guiding and fusing the change prior features into a semantic feature sequence in a cross-time sequence injection mode, and executing time sequence pooling to generate multi-stage fusion features so as to enhance change information characterization and reduce interference caused by seasonal phenological difference; and finally, on the basis of the multi-stage fusion features, reconstructing high-resolution features stage by stage by adopting a multi-stage decoder comprising a guide fusion unit so as to improve boundary expression consistency and spatial detail fidelity, thereby improving the precision of a remote sensing image classification result.
Owner:THE ENG & TECHN COLLEGE OF CHENGDU UNIV OF TECH
Lake and reservoir chlorophyll concentration prediction method based on SO-KNN model
The invention belongs to the technical field of water environment monitoring and early warning, and discloses a lake and reservoir chlorophyll a concentration prediction method based on an SO-KNN model. According to the invention, multi-time scale meteorological cumulative effect features are introduced to enrich information representation, and an SO-KNN intelligent prediction model is constructed. According to the method, under the conditions of data scarcity and non-equilibrium, the chlorophyll a concentration, especially the high-precision and strong-generalization prediction capability of the water bloom risk critical point, is remarkably improved. The model is simple in structure and efficient in calculation, the common defects of overfitting, insufficient generalization ability and the like of a complex machine learning model in the scene are effectively overcome, and a reliable and practical innovative technical solution is provided for early water bloom warning of northern reservoirs and water areas with similar data conditions.
Owner:DALIAN UNIV OF TECH
Cooperative transmission method, device, medium and product
Owner:SANECHIPS TECH CO LTD
Object grasping method, computer-readable storage medium, electronic device
Embodiments of the present application disclose an object grabbing method, a computer readable storage medium and an electronic device. The method comprises: obtaining an RGB image collected by an image collection device for a target container in a grabbing work area, the RGB image comprising image content related to a plurality of objects stacked in the target container; calling a feature extraction model with the RGB image as input, and determining a target object to be grabbed and extracting feature information of the target object from the RGB image by the model; if the feature information indicates that a physical label is attached to the outer packaging of the target object, and the hardness information of the outer packaging material is not greater than the hardness information of the physical label, determining a region where the physical label is located as a grabbing region; determining a target end effector capable of performing a grabbing operation on the physical label; and controlling an intelligent grabbing device to perform a grabbing operation on the grabbing region of the target object by the target end effector, thereby realizing intelligent grabbing of the target object. This helps to improve the success rate of grabbing, and the grabbing strategy is more universal and compatible.
Owner:SHANGHAI HEMA ZHIYAN TECHNOLOGY CO LTD
A method for representing highway vehicle driving identity information
The application discloses a highway vehicle driving identity information representation method, constructs a driving identity index system containing vehicle relative characteristic indexes and vehicle dynamic characteristic indexes, combines multi-dimensional data acquisition and an improved matter-element extension model, and realizes accurate representation of vehicle identity. Specifically, the method comprises the following steps: collecting highway vehicle driving data, constructing a highway global historical data set and a vehicle historical data set; designing double-layer section matter elements and classical domain matter elements, and optimizing characteristic evaluation; calculating a vehicle driving characteristic comprehensive evaluation index value through a correlation coefficient, quantifying the correlation degree of a target vehicle and historical data, and combining a preset threshold to judge the identity identity of the vehicle. The application has the advantages of strong interpretability and low complexity by fusing the matter-element extension theory and multi-dimensional data analysis, can effectively identify escape behaviors such as fake license plates and abnormal trajectories, and provides technical support for intelligent monitoring and auditing of highways.
Owner:CHENGDU HIGH SPEED OPERATION MANAGEMENT CO LTD +1
Software testing method and device, electronic equipment and storage medium
The invention provides a software testing method and device, electronic equipment and a storage medium. The method comprises the steps that a source code file of to-be-tested software is compiled based on a WebAssembly compiler to obtain a compiling result and first debugging information, and the first debugging information represents the mapping relation between code lines in the source code file and instructions in the compiling result; the compiling result is converted into a to-be-tested binary file based on a format conversion relation, second debugging information is determined according to the first debugging information, the compiling result and the to-be-tested binary file, the format conversion relation is used for converting the WebAssembly binary file into a binary file in a preset format, and the format conversion relation is used for converting the WebAssembly binary file into the to-be-tested binary file. The second debugging information represents a mapping relation between a code line in the source code file and an instruction in the to-be-tested binary file; and running the to-be-tested binary file in a virtual machine used for running the binary file in the preset format, and debugging the to-be-tested binary file based on the second debugging information in the virtual machine.
Owner:BEIJING CEC HUADA ELECTRONIC DESIGN CO LTD
Model training and fault detection method and device, electronic equipment and storage medium
ActiveCN116910531BHardware monitoringEnergy efficient computingEngineeringInformation representation
The embodiment discloses a model training and fault detection method and device, electronic equipment and a computer storage medium, the method comprising: clustering at least two log sequences according to the weight of each log event in the at least two log sequences, obtaining a first clustering result; obtaining first weight information, the first weight information representing the weight of each log event in the at least two log sequences, the first weight information being determined according to at least one of first reference information and second reference information, the first reference information representing the number of groups in which the log event appears in the first clustering result, and the second reference information representing the number of times the log event appears in each group of the first clustering result; clustering each group of log sequences in the first clustering result according to the first weight information, obtaining a second clustering result; and obtaining a trained log grouping model according to the second clustering result.
Owner:CHINA MOBILE COMM LTD RES INST +1
Image projection method, program product, and information processing device
PendingCN121644777APicture reproducers using projection devicesInformation processingComputer graphics (images)
An image projection method, a program product, and an information processing apparatus. The present invention reduces the trouble of adjustment by a user when moving the position of a first image on a projection surface on which the first image and a second image are projected. The image projection method includes: acquiring first shape information in advance, the first shape information indicating a shape of a first image at each position when the first image is projected from a first projector to each of a plurality of positions on a projection surface; acquiring first information for moving the position of the first image on the projection surface when the second projector projects a second image on a position overlapping at least a part of the first image on the projection surface; outputting second information for moving the position of the second image on the projection surface by a movement amount corresponding to the first information; and generating, on the basis of the first shape information and the first information, first correction information for performing geometric correction on the first image corresponding to the moved position of the first image.
Owner:SEIKO EPSON CORP
Expert preference meta-cognitive agent fused question and evaluation generation system and method
PendingCN121981595Aquality improvementMathematical modelsData processing applicationsInformation repositoryEvaluation result
The invention relates to a question and evaluation generation system and method fusing expert preference meta-cognitive intelligent agents, and belongs to the technical field of intelligent education. The system comprises an automatic question generation module used for calling a large language model to generate questions and evaluations according to a subject information base and an expert preference model; the meta-cognitive agent evaluation and optimization module is used for calling a meta-cognitive agent to perform multi-dimensional evaluation on questions and evaluation according to the expert preference model and generating an evaluation result and an optimization suggestion; and the expert interaction module is used for obtaining feedback information of the expert on the questions, the evaluation, the evaluation results and the optimization suggestions, and if the feedback information shows that the expert does not pass the verification, adjusting model parameters of the expert preference model, the large language model and the meta-cognitive agent according to the feedback information until the expert passes the verification. According to the invention, a deep cooperation mechanism between experts and artificial intelligence is established, artificial intelligence is guided to learn expert experience and preference through interaction, and high-quality questions and evaluation and assessment results are generated.
Owner:WUHAN UNIV OF TECH
Control method and apparatus for pipetting device, and storage medium
PCT designated stageWO2026129788A1Programme control in sequence/logic controllersComputer hardwareInformation control
A control method and apparatus for a pipetting device, and a storage medium. The control method for the pipetting device comprises: acquiring layout information and liquid type information, the layout information representing the layout of a working platform of the pipetting device, and the liquid type information representing liquid parameters of a pipetting operation executed by the pipetting device; acquiring script information, the script information comprising variable information and script command information, and the variable information being associated with parameters in the script command information; parsing the script information to obtain operation information for executing the pipetting operation on the working platform of the pipetting device; and on the basis of the operation information, the layout information and the liquid type information, controlling the pipetting device to execute the pipetting operation.
Owner:SHANGHAI MEGA INTELLIGENT TECHNOLOGY CO LTD
A knowledge representation learning method and system
ActiveCN116644811BBiological modelsKnowledge representationSemantic representationInformation representation
The application provides a knowledge representation learning method and system, and relates to the field of representation learning, wherein a constructed knowledge representation model is trained by using a knowledge base to be modeled, knowledge representation of triples in the knowledge base is learned, and modeling of the knowledge base is completed; the knowledge representation model comprises an information extraction module and an encoder; the information extraction module is used for extracting relation path information representation, text description information representation and entity hierarchical type information representation of the triples; the encoder takes the relation path information representation, the text description information representation, the entity hierarchical type information representation and structured information representation of the triples as input, and outputs vector representation of entities and relations of the triples; by fusing the relation path, the text description information and the hierarchical type information of the entity and considering other effective information in the triples, the application effectively solves the problem of incomplete semantic representation of the entities and the relations, improves the effect of knowledge representation learning, and efficiently realizes knowledge graph link prediction and triple classification tasks.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)
A neural network based on recurrent spiking neurons and a construction method thereof
This invention discloses a method for constructing a spiking neural network based on recurrent firing neurons, comprising: S1: constructing a recurrent firing spiking neuron model; S2: calculating positive and negative pulses based on the gradient function corresponding to each time step in the recurrent firing spiking neuron model to obtain cross-time-step positive and negative pulses; S3: backpropagating the cross-time-step positive and negative pulses back through the recurrent firing spiking neuron model to obtain a spiking neural network; S4: training the spiking neural network using a positive and negative membrane potential balance loss function to obtain a recurrent firing spiking neural network. This invention significantly improves the learning ability and information representation ability of the spiking neural network, while enhancing its robustness.
Owner:TIANJIN UNIV
Information processing device, information processing method, and computer program
An information processing device (100) comprises: an acquiring unit (121) that acquires image information representing a two-dimensional image; a determining unit (122) that determines a reference object to serve as a reference from among one or more image objects included in the two-dimensional image represented by the acquired image information, and, on the basis of the dimensions of the determined reference object, determines display information representing a display region in which the two-dimensional image is displayed in a virtual space; and an output unit (123) that outputs the determined display information.
Owner:PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA
A method and system for incremental retrieval and index updating of heterogeneous data
PendingCN122086983ADatabase updatingSpecial data processing applicationsTheoretical computer scienceEngineering
This invention provides a method and system for incremental retrieval index update of heterogeneous data, relating to the field of data processing technology. The method includes the following steps: batch transferring newly added information representation values from the real-time cache layer to the recently active layer and performing local index optimization; analyzing the information representation values in the recently active layer and the information representation values in the historically stable layer and establishing jump edges; identifying invalid pointers and duplicate information fragments in the index for quickly finding similar information, and deleting invalid pointers and merging duplicate information fragments. This invention aims to solve the problems of traditional incremental update methods failing to effectively integrate different types of data when intelligent question-answering systems process massive, heterogeneous data, leading to limited retrieval efficiency and accuracy, as well as inconsistencies in internal index logic, invalid pointers, and duplicate information fragments, effectively improving system response speed and query result confidence.
Owner:FOSHAN POWER SUPPLY BUREAU GUANGDONG POWER GRID
Tool to build and store a data model and queries for a graph database
A system is disclosed to build and store a conceptual model and queries for a graph database. In various embodiments, data defining one or more aspects of a conceptual model associated with a graph database is received. A logical model of the conceptual model is created based at least in part on the conceptual model. The logical model includes information defining how data is physically stored. A set of data that represents the conceptual model is stored as a graph that includes one or more nodes to represent each of the following: conceptual model metadata, one or more node labels comprising the graph database, one or more relationship types of the graph database, and one or more property definitions each associated with a property of at least one of a node label and a relationship type of the graph database.
Owner:NEO4J SWEDEN AB
Substrate processing apparatus, substrate processing method, learning data generation method, learning method, learning device, learning completed model generation method, and learning completed model
ActiveCN115428123BPhotosensitive material processingMachine learningInformation controlLearning data
A substrate processing apparatus (100) of the present application includes a substrate holding section (120), a liquid supply section (130), a substrate information acquisition section (22a), a liquid processing condition information acquisition section (22b), and a control section (22). The substrate information acquisition section (22a) acquires substrate information including hardening layer thickness information or ion implantation condition information, the hardening layer thickness information indicating a thickness of a hardening layer in a resist layer of a substrate to be processed, and the ion implantation condition information indicating a condition of ion implantation for forming the hardening layer in the resist layer. The liquid processing condition information acquisition section (22b) acquires liquid processing condition information indicating a liquid processing condition for the substrate to be processed from a learning completion model based on the substrate information. The control section (22) controls the substrate holding section (120) and the liquid supply section (130) in accordance with the liquid processing condition information to process the substrate to be processed with a liquid.
Owner:SCREEN HOLDINGS CO LTD
SYSTEMS, METHOD AND NON-VOID COMPUTER-READABLE MEDIA FOR CONTROLLING SPRAY DEVICES
PendingDE102025131463A1Movable spraying apparatusLiquid fertiliser regulation systemsControl engineeringAgricultural engineering
Systems, methods, and non-volatile, computer-readable media for controlling a crop spraying device are described. A system comprises one or more sensing devices configured to generate sensing information, where the sensing information represents a spray coverage, and a processing circuit arrangement configured to cause the system to determine adapted tuning parameters based on the sensing information using a machine learning process, wherein the adapted tuning parameters differ from actual tuning parameters corresponding to the sensing information, and to control a spraying device based on the adapted tuning parameters.
Owner:DEERE & CO
Generating maps from crowdsourced drive information
A system may receive drive information from each of a plurality of harvesting vehicles that traversed a road segment and provide a representation of the drive information as input to a trained model. The trained model may be configured to determine that at least a first sub-portion of a first trajectory representation and second sub-portion of a second trajectory representation correspond to a common road interval included in a road segment and output an indication of a correlation between the first sub-portion, the second sub-portion, and the common road interval, align and aggregate the drive information associated with the common road interval based on the output of the trained model to generate a location indicator for at least one map feature of the road segment, store the location indicator for at least one map feature in the map, and distribute the map
Owner:MOBILEYE VISION TECH LTD