25 results about "Acquisition technique" patented technology

A power transmission tower grounding resistance intelligent measurement method based on ground potential field distributed sensing comprises the steps that a ground potential sensing network is arranged around a power transmission tower grounding device, and a ground potential field distributed measurement system with an iron tower as the center is established; a broadband characteristic coding current signal is injected into the grounding system through a weak current injection module; acquiring potential response data of each node of the ground potential sensing network excited by the feature coding current signal by adopting a distributed synchronous acquisition technology, and reconstructing complete ground potential field spatial distribution from sparse node observation data based on a compressed sensing theory through a signal reconstruction algorithm; and inputting the reconstructed complete ground potential field spatial distribution map into a pre-trained map neural network model, and outputting an intelligent identification result and an anomaly diagnosis conclusion of the ground resistance. According to the invention, non-contact, distributed and high-precision grounding resistance measurement under the condition that a grounding lead does not need to be disconnected is realized, and the measurement precision and reliability under a complex working condition are remarkably improved.

The invention discloses a rock particle interface deformation identification method based on an image identification algorithm, and belongs to the field of rock particle interface deformation identification, and the method comprises the steps: obtaining a particle distribution range through a high-resolution image collection and multi-scale scanning technology, and when the scale span is detected to exceed a preset threshold value, determining the particle distribution range; and separating particle regions with different sizes by adopting a layered segmentation method. The texture mode of each layer is analyzed by using a convolutional neural network, a deformation feature vector is extracted, and algorithm granularity parameters are adjusted through iterative optimization so as to match the actual particle size. And when the matching degree is insufficient, a feedback loop mechanism is introduced to reprocess the image data and a noise filtering link is fused, so that the deformation identification precision is remarkably improved. Finally, an integrated calculation method is adopted to fuse multi-scale analysis results, accurate judgment of the deformation state of the whole particle interface is achieved, reliable comprehensive indexes are provided for rock stability evaluation, and the technical problem that a traditional method is insufficient in precision in cross-scale particle deformation recognition is solved.

We provide the system. [Solution] A means of receiving inquiries from users in natural language, A means for analyzing the aforementioned query and extracting keywords, A means of obtaining related information using vector search technology with extracted keywords, A means of automatically generating a response in natural language based on the acquired information, A means of providing the generated answer to the user, A means for monitoring the operation of the aforementioned means and accumulating feedback for use in learning, An information processing system that includes this.

This invention relates to the field of pose estimation technology, specifically to a multi-view, multi-person 3D pose estimation method, apparatus, and device. The method includes: acquiring image information and depth information of the target using multi-view acquisition technology; segmenting the person in a single view based on the image information and extracting 2D semantic features; reconstructing the point cloud based on the depth information to obtain a 3D point cloud in a preset world coordinate system; segmenting the point cloud for different human figures based on the 3D point cloud and calculating the point cloud boundaries as human body boundaries; mapping the 2D semantic features to the 3D point cloud to obtain 3D features; and classifying different human figures and constructing 3D poses based on the 3D features and human body boundaries. This technical solution can segment the point cloud for different human figures based on the 3D point cloud, accurately define the joint positions of different figures, and achieve differentiation and matching of different figures. Furthermore, based on discrete point cloud data, it has better flexibility and fault tolerance.

This invention relates to a computer-implemented method comprising: - acquiring (406) first training images (108) using a first image acquisition technique (104), each first training image depicting a plant-related motivation; - acquiring (402) second training images (106) using a second image acquisition technique (102), each second training image depicting a motivation depicted in a corresponding first training image; - automatically assigning (404) at least one label (150, 152, 154) to each acquired second training image; - describing the motivation... The first and second training images with the same motivation are spatially aligned (408) into aligned training image pairs; - a machine learning model (132) is trained (410) based on the aligned training image pairs and the labels, wherein, during training, the machine learning model (132) learns to automatically assign one or more labels (250, 252, 254) to any test image (205) acquired using the first image acquisition technique that depicts plant-related motivations; and - the trained machine learning model (132) is provided (412).

This invention relates to a method and system for intelligent sensing of drilling tool information based on RFID and visual recognition collaboration. It includes: a data acquisition terminal, used to acquire identification information and coded graphic information on drilling tool tags based on RFID and visual recognition collaboration technology during the drilling tool tripping process, and transmit this information to a data processing terminal; and a data processing terminal, used to perform image processing and damage assessment inversion on the acquired identification information and coded graphic information using image recognition and coded graphic damage inversion algorithms, obtaining quantitative damage indicators for the drilling tool tags, and recording them to form a dataset of operating conditions and tag status throughout the entire lifecycle of the drilling tool. This invention can be widely applied in the field of intelligent monitoring and digital management technology for downhole drilling tools in oil and gas exploration and development.

The present application relates to power distribution diagnosis technical field, specifically, it is a kind of intelligent electric appliance box power distribution fault self-diagnosis method, it includes the following steps: using sensor is deployed at the node and environmental point of intelligent electric appliance box, the multi-source data of voltage current, temperature vibration is obtained by synchronous acquisition technology, the voltage sag, harmonic distortion characteristics are extracted by power quality analysis, combined with temperature vibration and image information constructs multidimensional feature vector, the fault of power distribution module is decomposed into bottom event, constructs fault tree, determines top event by bottom event state evaluation and logic reasoning, uploads fault diagnosis result and processing suggestion to cloud platform, obtains the diagnosis module of continuous optimization by dynamic adjustment model parameter and feature extraction strategy of reinforcement learning algorithm.The present application solves the problems that traditional intelligent electric appliance box power distribution fault diagnosis relies on artificial inspection, diagnosis result reliability is poor and diagnosis module lacks continuous optimization ability.

The application relates to the technical field of industrial visual detection, and particularly discloses a waste metal classification and recognition method and system based on image recognition, which obtains metal surface visual information through an image acquisition system, extracts multi-level depth features after preprocessing, and generates a preliminary classification result and a confidence evaluation; when the confidence is insufficient, a multi-modal verification mechanism is started, laser-induced breakdown spectroscopy technology is used to obtain element composition data, and a structured light three-dimensional scanning technology is used to obtain surface topological features; the element data is matched with a composition database to generate a composition verification result, and the topological features are compared with a topological feature library to generate a topological feature verification result; finally, a weighted fusion algorithm is used to integrate the three types of results to generate a final classification decision, and a sorting mechanism is controlled to complete accurate sorting.

The invention discloses a comprehensive product type selection evaluation method based on autonomy of an information system, and relates to the technical field of autonomy of the information system, and the method comprises the steps: carrying out the all-directional and multi-angle evaluation of candidate products through setting a plurality of dimensions, including performance, safety and technical suitability; specific characteristic parameters are subdivided under each dimension, in the performance aspect, such as processing speed, response time and resource occupancy rate, in the security aspect, such as encryption, authentication, authorization, auditing and vulnerability management, in the technical suitability aspect, such as compatibility with the system and integration difficulty. In addition, big data and Internet acquisition technologies are adopted to obtain feedback records of the user on the information system product, and bid evaluation of the characteristic parameters is determined according to the feedback records; meanwhile, by calculating the distance from the characteristic parameter corresponding to each quality attribute of each candidate product to bid evaluation and dividing a characteristic parameter evaluation interval, powerful support is provided for product model selection.

This technology enhances user satisfaction with the results of assessments regarding the possibility of acquiring intellectual property rights. [Solution] The information processing device includes: a related technology acquisition unit that acquires related technical information related to the intellectual property to be analyzed based on information about the intellectual property to be analyzed described in natural language; a positive opinion generation unit that generates a positive opinion regarding the possibility of obtaining rights to the intellectual property to be analyzed using a first large-scale language model; a negative opinion generation unit that generates a negative opinion regarding the possibility of obtaining rights to the intellectual property to be analyzed using a second large-scale language model; and a conclusion generation unit that generates a conclusion regarding the possibility of obtaining rights to the intellectual property to be analyzed using a third large-scale language model.

The application discloses a self-learning and detection method, in particular to a self-learning and detection method of product manual assembly process on a production line. Firstly, the working area is divided by the edge detection and rectangle detection technology of OpenCV, the spatial information of the working area is saved, and the learning and debugging stage is started; in this stage, multiple skilled workers simulate the assembly action on the work station, the hand positioning frame with direction is acquired by the palm recognition technology in MediaPipe to position the palm position, the region and trajectory information of the palm are determined by comparing the region information, and the trajectory data is aligned to ensure the consistency in time; next, the genetic algorithm is used to find the optimal trajectory; when the workers actually assemble, MediaPipe tracks the palm position and judges the region information, and then compares it with the standard process. The application solves the technical problem of providing the self-learning and detection method of product manual assembly process on a production line, and has the advantages of faster speed, lower cost, easy popularization and the like.

The present disclosure relates to deriving one or more of a precision, a recall, or an F-score metric. In accordance with the disclosed techniques a set of data is acquired or accessed. The data is continuously distributed. Based on an expected signal and an observed signal, one or more of a precision, a recall, or an F-score are determined for one or more automated routines configured to operate on the set of data. One or more of the precision, the recall, or the F-score provide a comparative measure of the accuracy of the one or more automated routines.

The invention relates to the technical field of logistics, and discloses a logistics abnormal cost node detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining logistics node data based on a multi-channel asynchronous collection technology, fusing the logistics node data based on a graph neural network feature fusion method, so as to obtain a comprehensive cost feature vector, training a conditional quantile regression model based on historical events, inputting the comprehensive cost feature vector data into the conditional quantile regression model, screening out suspected abnormal nodes, obtaining a preset threshold value of node abnormal scores, calculating the node abnormal scores of the suspected abnormal nodes based on an improved isolation forest algorithm, and when the node abnormal scores exceed the preset threshold value of the node abnormal scores, determining that the abnormal nodes are abnormal. According to the scheme, the method and the device have the advantages that the defects of false report and missing report of the traditional scheme are overcome, the scene adaptability is high, and the accuracy of abnormal cost node detection is ensured.

Techniques are described for complex preprocessing steps to ensure consistency of sorted sets of reference measurement data, which have conventionally been required when sorting reference measurement data sets for DPG algorithms captured using an EPI technique, to be omitted because items of reference measurement data captured via the described techniques are already consistent in themselves. Therefore, for each polarity of the read-out gradients, a set of fully sampled reference measurement data is available, which is already suitable for carrying out a dual-polarity (DP) algorithm without any further measures.

The invention discloses a personalized credit product intelligent recommendation system for small and micro enterprises. The system comprises a data acquisition and preprocessing module, a risk assessment and demand analysis module, a credit product knowledge base module, a personalized recommendation algorithm module, a user interaction and feedback module and a system management and monitoring module. The data acquisition module acquires enterprise full-dimension information through multiple interface technologies such as RESTFulAPI, JDBC / ODBC and HTTPS protocols, abnormal value detection is carried out by adopting an isolated forest algorithm, and data preprocessing is carried out by using methods such as a K-nearest neighbor interpolation method and one-hot coding. The risk assessment module adopts a feature screening method combining recursive feature elimination and random forest feature importance to construct a random forest and support vector machine fusion model, and realizes credit risk quantitative scoring through logarithmic function mapping. According to the invention, credit demands of small and micro enterprises can be accurately matched, recommendation accuracy and credit approval efficiency are significantly improved, and credit risks of financial institutions are effectively reduced.

The invention relates to a computer-implemented method comprising: - acquiring (406) first training images (108) using a first image acquisition technique (104), each first training image representing a plant-related motif; - acquiring (402) second training images (106) using a second image acquisition technique (102), each second training image representing the motif depicted in a respective first training image; - automatically assigning (404) at least one label (150, 152, 154) to each of the acquired second training images; - spatially aligning (408) the first and second training images representing the same motif into a pair of aligned training images;- training (410) a machine learning model (132) based on the aligned training image pairs and labels, wherein during training the machine learning model (132) learns to automatically assign one or more labels (250, 252, 254) to any test image (205) acquired with the first image acquisition technique depicting a plant-related motif; and - providing (412) the trained machine learning model (132).

An information processing apparatus includes a related art acquisition unit that acquires related art information indicating related art related to an analysis target intellectual property based on analysis target information, a positive opinion generation unit that generates a positive opinion regarding a possibility of acquiring a right to the analysis target intellectual property based on the analysis target information and the related art information by using a first model, a negative opinion generation unit that generates a negative opinion regarding the possibility based on the analysis target information and the related art information by using a second model, and a conclusion generation unit that generates a conclusion regarding the possibility based on the positive opinion and the negative opinion by using a third model. This information processing apparatus enhances patentability evaluation through AI-driven decision making support.

A computer-implemented method can include acquiring first training images using a first image acquisition technique, where each first training image depicts a plant-related motive; and acquiring second training images using a second image acquisition technique, where each second training image depicts the motive depicted in a respective one of the first training images. The method can include automatically assigning at least one label to each of the acquired second training images. The method can include spatially aligning the first and second training images which are depicting the same one of the motives into an aligned training image pair. The method can include training a machine-learning model as a function of the aligned training image pairs and the labels, wherein during the training the machine-learning model learns to automatically assign one or more labels to any test image acquired with the first image acquisition technique which depicts a plant-related motive.

The invention discloses a boiler online expansion real-time measurement system, and relates to the field of power plant boiler detection equipment. According to the system, a data acquisition module, a dynamic compensation module, a data processing module, a control module, a remote monitoring module and a zero calibration module are integrated according to universal online expansion measurement requirements of various boilers, and thermal expansion displacement of a pressure-bearing part of the boiler is obtained through a non-contact laser measurement technology. A basic dynamic compensation algorithm is combined to eliminate measurement errors caused by vibration and temperature, and real-time and accurate measurement and simple control of thermal expansion displacement are achieved. The core innovation of the system lies in universal measuring point layout, lightweight compensation algorithm and concise control logic, has the characteristics of simple structure, controllable cost, convenient installation and strong adaptability, effectively solves the problems of complex structure, high cost and poor universality in the prior art, meets the online expansion measurement requirements of various boilers, and has wide application prospects. And the operation safety and reliability of the boiler are improved.

The application relates to a high-precision ancient building digital building block system and a modeling method thereof, relates to the technical field of digital cultural heritage protection and education, and comprises a three-dimensional modeling module used for acquiring millimeter-level precision geometric data of ancient building components by adopting a laser point cloud and multi-view image fusion technology, the module collects data by means of a laser scanner and a single-lens reflex camera, and realizes spatial registration by using a feature point matching algorithm. By means of the laser point cloud and multi-view image fusion technology, the application realizes the acquisition of millimeter-level precision geometric data of ancient building components, ensures the accuracy of the digital model, the application of the parametric modeling algorithm enables the building block units to be generated and scaled in proportion, adapts to different application scenarios, meanwhile, the consistency of geometric characteristics is maintained, the design of the standardized plug-in interface module is based on topological optimization, the connection requirements of different ancient building elements are automatically adapted, and the characteristics of the mortise and tenon structure are reserved.

The invention discloses an industrial image acquisition method based on time-sharing stroboflash and related equipment, and the method comprises the steps: employing a time-sharing stroboflash technology, and obtaining industrial product diagrams of a same product under different imaging dimensions; performing gray value anti-shake sorting on each industrial product image of the same product to obtain a sorting result; and based on the sorting result, performing combination and image enhancement on the industrial product images of the same product to generate an industrial image. Therefore, the time-sharing stroboscopic technology and the gray value anti-shake sorting technology can be integrated, interference of other imaging dimension acquisition processes during single imaging dimension image acquisition can be eliminated, spatial position alignment, reliable matching of feature points and effective enhancement of detail features during multi-imaging dimension image fusion can be ensured, and thus the accuracy of image fusion can be improved. And the precision and reliability of multi-imaging-dimension visual quality inspection are improved.

The invention discloses a vision screening data analysis system based on an image technology, and particularly relates to the technical field of data analysis, the vision screening data analysis system comprises an image data acquisition module, a patient evaluation module, a vision data acquisition module and a logistic regression module, eye data of a patient are acquired through the image technology, and the vision screening data are analyzed according to historical cases of the patient. The credibility of historical cases is determined through fuzzy reasoning, the reliability degree of judging the illness state through the eye images is quantified, a high-precision vision detection instrument is used for conducting vision detection on a patient, a quantified result of vision data of the patient is obtained, and the disease assessment coefficient and the quantified result of the vision data of the patient are combined and analyzed. According to the method, through automatic image processing and a machine learning model, the efficiency and accuracy of eye lesion recognition are improved, and a doctor is helped to combine image features and vision data to reduce the misdiagnosis rate.

Techniques for automated documentation of medical imaging exams are disclosed. Acquired medical images are stored in an image buffer. A quality metric is determined for at least a portion of the medical images, and the quality metric is compared to a first threshold value. A content metric is determined for the at least a portion of the medical images, the content metric including an abnormality score characterizing at least one abnormality in the at least a portion of the medical images, and the content metric is compared to a second threshold value. At least a subset of the medical images is identified as representative images based on the first threshold value and the second threshold value, and the representative images are stored outside the buffer. The quality metric and / or the content metric can be generated using a neural network.

Disclosed are techniques for sensor fusion. In an aspect, a processing device may obtain a first set of detection information for a current detection frame based on a first sensing technology, the first set of detection information indicating a first detected object. The processing device may obtain a second set of detection information for the current detection frame based on a second sensing technology. The processing device may determine whether the first detected object is omitted in a current sensor fusion based object detection session for the current detection frame based on: a static status of the first detected object, a previously detected traversable status of the first detected object, a displacement of the first detected object with respect to a previous detection frame, a currently detected traversable status of the first detected object, or any combination thereof.