429 results about "Background information" patented technology

The invention discloses a supply chain risk identification method and system based on a knowledge graph, belongs to the technical field of supply chain management and artificial intelligence crossing, and aims to solve the technical problem of how to realize dynamic monitoring, accurate identification and active early warning of supply chain risks, improve full star, real-time performance and interpretability of supply chain risk identification, and improve the risk identification efficiency. According to the technical scheme, the method comprises the following steps: collecting and treating multi-source data: collecting static background information and dynamic risk information of a supplier, and carrying out highly intelligent data treatment on the collected static background information and dynamic risk information of the supplier through a data treatment engine to ensure data quality and consistency; constructing a dynamic knowledge graph; intelligent risk identification: based on a graph topological structure and dynamic attributes, identifying key risk nodes and communities, tracing in time, marking risks, and performing early warning; decision support and visualization are carried out; and dynamically optimizing and feeding back.

The invention provides a system and a method for evaluating the independent living ability of old people. The method comprises the following steps: acquiring multi-modal original data (including physiology, behavior and interaction data) of target old people; performing modal coding, query vector interactive fusion (including missing information completion) and feature compression on the multi-modal original data to obtain a standardized feature vector; a first-layer model evaluates behavior and cognitive ability indexes, and a second-layer model combines individual background information to predict a living ability grade and a degradation risk; optimizing the first-layer model through a feature feedback mechanism; and finally, outputting and visualizing a structured evaluation result. The method breaks through the limitation of traditional manual evaluation, achieves the deep fusion of multi-modal data, improves the objectivity, robustness and interpretability of evaluation, and can meet the precise evaluation demands of home care, community monitoring and smart medical scenes.

The invention discloses a digital animation role dynamic generation method based on a generative model. The method comprises the following steps: inputting a role original image and scene background information, extracting skeleton key points and scene features, analyzing an action sequence, predicting a motion track, calculating an optimal position of a role in a picture, and carrying out dynamic adjustment. And according to the role position, obtaining morphological feature data, evaluating the quality grade, and optimizing the coordination of the role image. And finally, comprehensively scoring by adopting a multi-dimensional quality evaluation system, and determining the visual presentation quality of the role. According to the method, deep fusion of role actions, positions and scenes is realized, the dynamic expressive force and visual coordination of animation pictures are improved, and an efficient solution is provided for generating high-quality animation contents.

The invention discloses an artificial intelligence home management system, which relates to the technical field of smart home and comprises a data acquisition module, a behavior analysis module, an environment sensing module, a cooperative control module and an energy consumption optimization module. According to the artificial intelligence home management system provided by the invention, through multi-source data fusion and cross-equipment collaborative decision, the intelligent management level of a home scene is remarkably improved, user behavior data can be deeply analyzed, a dynamic behavior model can be constructed, and a user habit mode can be accurately identified and predicted, so that the initiative and adaptability of equipment control are realized, and the user experience is improved. The system comprehensively senses environmental parameters, constructs an environmental state map, provides accurate environmental background information for a cooperative control strategy, ensures the accuracy of an equipment control strategy, combines equipment operation data with a user behavior scene, generates an energy consumption optimization scheme, ensures the comfort of a user, realizes high efficiency and energy conservation, and improves the user experience. And user privacy leakage is effectively prevented, and potential faults are early warned.

The invention provides a large model test case generation method, system and device based on multi-Agent collaboration. The method comprises the steps of obtaining product information of target product demand information; if the product demand information is incomplete, performing structured supplement on the extracted product demand information according to a slot filling technology to obtain complete product demand information; performing assembly according to the complete product demand information and the background information, and determining a first prompt word used for requesting the large model to generate a test case; and generating a first edition test case according to the first prompt word by using the plurality of agents, reviewing the first edition test case, generating an optimization suggestion, and fusing the first edition test case based on the optimization suggestion to generate a final test case. Through knowledge injection and structured requirements, the test case not only covers functional requirements, but also improves the accuracy of the test case; dynamic verification and correction of the use cases are achieved through cooperation of the multiple agents, the generation efficiency of the test use cases is improved, and the coverage rate is increased.

The invention relates to the technical field of finance, and provides a time series data prediction method and system based on an auto-reflection mechanism large language model, and the method comprises the steps: firstly collecting structured transaction data and public unstructured text information in a preset historical time window, inputting a first large language model, and generating structured market background information in combination with a preset cue word; inputting the data and preset risk preference data into a second large language model to generate first causal reasoning training data; and inputting a third language model for reflection correction, checking whether the argument can be verified in the background information, and if so, reserving and strengthening to obtain second causal reasoning training data. And constructing a prediction large language model, optimizing parameters by means of a group relative strategy optimization algorithm, and then outputting the parameters. The system and the method depend on an auto-reflection mechanism, the model considers risk preferences in financial time sequence prediction to generate various risk strategies, manual annotation dependence is greatly reduced, the cost is reduced, and the risk preference module is independent and configurable and can be flexibly expanded.

The invention discloses an image sensitive content auditing method and system, and the method comprises the steps: obtaining the original description of a to-be-audited image, and the original description comprises the text summarization of the visual content of the image and the text content in the image; extracting an entity area in the to-be-audited image, retrieving related external background information based on the to-be-audited image and the entity area, eliminating interference information by using a label of the entity area, and generating a retrieval enhancement result; semantic correlation screening based on sensitive topics is carried out on the retrieval enhancement results, the screened retrieval enhancement results are fused into the original description in an iteration mode, and final fusion description is generated; and constructing a training data set containing positive and negative judgment sample pairs based on the fusion description, performing fine tuning on the visual language model, and performing sensitive content auditing on a new image by using the fine-tuned visual language model. The method can effectively improve the recognition accuracy and reliability of the sensitive content of the image.

According to the Transform unmanned aerial vehicle target tracking method based on adaptive feature enhancement, a visual Transform is taken as a trunk, feature extraction is performed on a template and a search area image, an EGA-Score module is introduced to score search area Token one by one, enhancement, retention or dormancy operation is performed according to a scoring result, redundant background information is effectively inhibited, and salient area features are enhanced. And then, the model is accessed to an LSA-Enhancer module, local space details are enhanced hierarchically through a mode of combining large kernel receptive field modeling and a small kernel residual structure, and the identification capability of small targets and shielding areas is improved. And finally, the head output target position and the matching confidence are predicted through regression and classification. According to the method, the overall structure is reasonable, challenges of small targets, deformation, shielding, complex environments and the like in unmanned aerial vehicle tasks can be effectively handled, and high stability and robustness are kept while the tracking precision is improved.

The invention relates to the technical field of artificial intelligence, in particular to a large model dialogue management method and device.The method comprises the steps that dialogue information of a user input dialogue initiated by a user to a large model is intercepted; obtaining user information corresponding to a user; filling the first cue word template based on dialogue information of a dialogue input by a user and user information to obtain a first cue word; sending the first cue word as first-round user input dialogue information to the large model, so that the large model generates large model output dialogue information for the first-round user input dialogue based on the first cue word; and in response to establishment of the update trigger condition, updating the user contour information based on the historical round dialogue of the current session and / or the dialogue content of the current round dialogue. According to the method, the structured user background information is provided for the large model at the beginning of the dialogue, so that the reply accuracy and pertinence of the large model are remarkably improved, and cross-session personalized interaction experience is realized.

The invention belongs to the technical field of physical exploration, and particularly discloses a deep geophysical prospecting weak abnormal signal enhancement method and system, and the method comprises the steps: generating a geostructured prior guide field, carrying out the targeted decomposition of an original geophysical prospecting signal, and synchronously estimating an uncertainty region, thereby achieving the real-time enhancement of a weak abnormal signal while maintaining the fidelity of background information; focusing the enhanced resources in the information fuzzy region; the decomposition signals are input into a dynamic learning model, and random noise and structured interference generated by multiplicity are effectively suppressed through antagonistic learning; the enhanced sub-band signals are fused into reconstructed signals with high geological interpretability by using a deep reconstruction network through a self-attention mechanism and compound loss function optimization; a closed-loop feedback mechanism is established, newly disclosed high-confidence anomaly features are fed back and integrated to a prior field, an iteration guide field is formed to drive multi-round iteration, step-by-step mining and locking of weak anomalies are achieved, and finally a high-reliability result is stably converged.

The invention discloses a complex instruction image editing method based on a multi-modal large language model, and the method comprises the steps: firstly constructing a data set expansion strategy based on a data set of multi-round image editing, carrying out the two-stage preprocessing, and constructing a complex instruction image editing data set; secondly, constructing a context prompt template, decoupling an editing instruction in a complex instruction image editing data set by using a multi-modal large language model to obtain a sub-editing instruction and an editing area, injecting a diffusion model with space-time perception background enhancement, including a space-time perception cross attention module and a background enhancement module, and carrying out weighted fusion on the obtained features to obtain an editing result; and an edited image is decoupled, output and edited through the variational auto-encoder. And finally, carrying out fine tuning by adopting a two-stage training strategy, and continuously training until the whole model is converged. According to the method, the instruction and background consistency of complex instruction image editing is remarkably improved, and the problems that complex instructions are neglected, background information is lost, and non-intention editing exists in an existing method are solved.

The invention relates to a multi-target pose estimation and sorting method based on an optimization template, and the method comprises the steps: importing a model of a target workpiece, and making a model point cloud library; collecting a scene point cloud of the target workpiece by using a depth camera; extracting model point cloud and scene features; loading the scene point cloud; removing scene background information through an RANSAC (Random Sample Consensus) algorithm; sparsification is carried out on the scene point cloud after the background is removed; segmenting the sparsified scene point clouds through clustering, analyzing point cloud features in each cluster according to PCA, dividing the point clouds with the same features into the same category, and obtaining point cloud information of each object in each category; further adopting a point pair feature PPF voting algorithm to carry out coarse registration on the object point cloud and the model point cloud to obtain a pose cluster; and on the basis of the coarse registration, performing fine registration on the object point cloud and the template by adopting an iterative closest point (ICP) algorithm. The method has the advantages that all target objects in a scattered state can be recognized and distinguished through one-time shooting, the poses of all the targets are obtained, the robot is controlled to sequentially execute sorting according to the estimated poses, and the operation efficiency is high.

The invention discloses a remote sensing target detection method for an open set scene, and belongs to the technical field of open set target detection. The open set remote sensing target detection network introduces a cascade target positioning network, a background feature enhancement module and reciprocal point prototype learning on the basis of a Faster-RCNN model; the cascade target positioning network can effectively adapt to multi-scale features, calculates the quality of a candidate box through centrality loss, and replaces a foreground-background classification mode in a traditional region suggestion network, so that the recall rate of objects is increased, and the possibility that unknown objects are misjudged as backgrounds is reduced; the background feature enhancement module fuses various background region information so as to enhance the adaptability to a complex environment and reduce the interference of background noise on target recognition; according to reciprocal point prototype learning, a reciprocal point prototype of a known category and a background is constructed, and an embedded network metric learning strategy is combined, so that background information and the known category jointly participate in candidate box classification, and a known target, an unknown target and the background are effectively distinguished.

A game controller includes gameplaying controls, at least one input device for providing information to a virtual assistant (artificial intelligence assistant), and at least one output device for providing output from the virtual assistant. The virtual assistant may use artificial intelligence to provide information to a user of the game controller, for example information relating to the game being played, such as gameplaying hints, game information, or background information regarding persons, events, and / or objects in the game. Example input devices include a camera and a microphone, and an example output device includes a speaker for providing verbal information or nonverbal sounds to the user.

The invention discloses a warranty service processing method and device, equipment, a storage medium and a product, and relates to the technical field of text generation, and the warranty service processing method comprises the steps: obtaining target background data of a warranty application, and based on a large language model, recognizing warranty application elements in the target background data, and filling the obtained target warranty elements into a warranty application template to obtain a target warranty text, and visually displaying the target warranty text to enable a user to preview the warranty text, and submitting the target warranty text to a warranty service system to complete warranty service processing. According to the method, the client is assisted in filling the form through the background data, the corresponding warranty text is generated and visually displayed, so that the user does not need to manually fill tedious and error-prone warranty application elements and can preview the warranty text before submission, repeated warranty text modification, submission and approval processes are avoided, and the user experience is improved. Therefore, the processing efficiency of the warranty service is improved.

The invention relates to the technical field of employee evaluation, in particular to a high-risk industry multi-dimensional dynamic weight employee evaluation method, which comprises the following steps of: obtaining quantitative scores of three-level indexes of employees and normalizing the quantitative scores by constructing a multi-level evaluation index system; inputting the standardized score vector into a Transform-based weight learning model, dynamically learning an index weight through a self-attention mechanism, carrying out step-by-step aggregation through a multi-layer perceptron, and outputting a comprehensive score of the employee on each first-level index; inputting the comprehensive score and the historical background information into a pre-established large language model, and performing fusion analysis according to a structured template to generate a personalized evaluation text; and finally, based on the score, the text and the employee information, automatically synthesizing a visual comprehensive evaluation report containing the radar map, the information bar and the text. According to the invention, objectiveness, individuation and operability of employee evaluation are realized.

The invention discloses a wide-area gas traceability method and device based on multistage sensing asynchronous cooperative triggering, a medium and a product, and relates to the field of wide-area gas leakage traceability, and the method comprises the steps: carrying out the adaptive three-dimensional grid division of a to-be-detected region; environment background information is detected; smoke plume discovery is carried out by adopting a random walk strategy and introducing a weight avoidance mechanism; determining a threshold value of binary detection according to the mean value of the environment background noise, and carrying out binary calculation on the sampled data; determining a near-field region according to a binary calculation result; performing concentration tracking according to the near-field region, and performing near-field state evaluation in real time; adjusting the size of the near-field region according to an evaluation result; continuously judging whether to exit the concentration detection of the near-field region; when the concentration detection of the near-field area is quitted and switched to the far-field area, a binary detection cycle is entered; determining a concentration peak value according to the concentration detection data of all the near-field regions; according to the invention, efficient, accurate and low-cost pollution source positioning in a complex wide-area environment can be realized.

The invention relates to the technical field of data processing, and discloses a literature image-text pair quality control method, which comprises the following steps: inputting academic literatures, identifying and extracting related descriptive characters of an image in a text, and generating a preliminary image-text pair; extracting a picture title text, calculating a semantic matching degree between the picture title text and the related descriptive text, filtering the preliminary image-text pair based on a first matching degree threshold, and generating a first candidate image-text pair; generating a semantic vector of the academic literature theme, mapping the title text to generate a picture title vector, calculating a correlation degree between the picture title vector and the semantic vector, filtering the first candidate image-text pair based on a second correlation degree threshold, and generating a second candidate image-text pair; processing the pictures in the second candidate image-text pair, taking the full text as background information, generating a corresponding picture description text, performing semantic similarity comparison on the corresponding picture description text and the related descriptive text, and outputting image-text pair data higher than a third similarity threshold value through the preset third similarity threshold value. The method can improve the control quality of literature image-text pairs.

The invention relates to the technical field of agricultural automation equipment, and discloses a water and fertilizer integrated irrigation device and method based on the Internet of Things and an intelligent strategy, and the device comprises a crop and environment sensing unit which obtains crop image information and environment parameters; the intelligent decision-making unit is used for generating a target irrigation strategy and fertilization concentration; the source water management unit is used for analyzing a water source before irrigation and providing water quality background information; the water-fertilizer synthesis and control unit is used for dynamically synthesizing and outputting a nutrient solution in real time by combining the target concentration and the water quality background; and the cloud management and optimization unit is used for collecting data of each unit and is used for storage, remote monitoring and management. According to the invention, an on-line spectrum analysis technology and a high-frequency pulse microfluidic technology are coupled, a real-time closed-loop control system for directly measuring chemical components is constructed, and high consistency of a digital decision instruction and the chemical components of a physically output nutrient solution is achieved.

The invention provides a domain knowledge enhancement method and device for an infrastructure defect detection large model. The method comprises the following steps: firstly, constructing a multi-modal data set in the field of infrastructure defect detection, constructing a knowledge base containing defect types and background information, and converting the knowledge base into a knowledge graph; and based on the map, generating a high-dimensional feature vector fusing domain knowledge through a map neural network. Meanwhile, single-mode features are extracted from multi-mode data such as images, point clouds and depth maps, fusion is carried out by using a cross attention mechanism, and multi-mode fusion features are obtained. Then, the domain knowledge vector and the multi-modal fusion vector are spliced and input into the large model for training, and high-precision detection of the infrastructure defects is achieved. According to the method, by introducing structured domain knowledge and a multi-modal fusion mechanism, the defect detection accuracy and robustness of a large model in a complex infrastructure scene are effectively improved, and the method has good engineering applicability and popularization value.

The invention discloses a radar unsupervised neural network CFAR detection method based on local clutter power estimation, relates to the technical field of radar detection, and aims to solve the problem of low CFAR detection accuracy caused by low local clutter power estimation accuracy of an existing adaptive CFAR detector in a complex non-uniform environment. According to the method, the local clutter power at the to-be-detected unit is accurately estimated by using the neural network, and the technical scheme of the invention prevents background information loss after mask shielding caused by too dense CUT (peak point), thereby improving the prediction accuracy of the local clutter power at the mask, and improving the prediction accuracy of the local clutter power at the to-be-detected unit. And finally, the CFAR detection accuracy under the complex non-uniform background is improved. Moreover, the method avoids the training of real manual annotation data, can achieve the training through the large-scale unannotated data in actual use, and improves the generalization of the method for the measured data compared with an intelligent radar target.

The embodiment of the invention provides an SQL statement generation method and system, electronic equipment and a storage medium, and belongs to the technical field of data processing. The method comprises the following steps: loading a preset total data table, and obtaining an original natural statement input by a user and identity information representing user attributes; if the statement conversion permission is matched with the user conversion permission, determining a minimum data subset having a mapping relationship with the original natural statement from the full-amount data table; if the complexity score represents that the original natural statement belongs to the complex query range, generating multi-source semantic fusion information based on the background information; and splicing the minimum data subset and the multi-source semantic fusion information to obtain a target prompt word, inputting the original natural statement and the target prompt word into a preset large language model, and generating a target SQL statement corresponding to the original natural statement. According to the method, the corresponding SQL statement can be intelligently generated based on the natural statement, and meanwhile, the privacy of bottom data of a user and the generation efficiency of the SQL statement are improved.

The invention belongs to the technical field of lunar subsurface material attribute inversion, and relates to a diffraction-reflection combined constraint dielectric constant inversion method for lunar exploration radar data, which comprises the following steps: preprocessing the lunar exploration radar data to obtain a radar profile; diffracted waves and reflected waves are separated from the radar profile; performing medium background impedance inversion based on the diffracted wave to obtain background impedance, and converting the background impedance into logarithmic impedance to obtain logarithmic background impedance; dielectric impedance disturbance inversion is carried out based on the reflected waves, and logarithmic impedance disturbance is obtained; matching and fusing the logarithmic background impedance and logarithmic impedance disturbance in a frequency domain to obtain a full-band impedance model; a dielectric constant distribution is calculated based on the full-band impedance model. By comprehensively utilizing complementary advantages of diffracted waves and reflected waves in dielectric constant inversion, stable constraint of dielectric constant low-frequency background information and fine description of high-frequency change characteristics are realized, so that the overall reliability and resolution capability of a dielectric constant inversion result are improved.

A system for detecting retinal detachment is provided herein. The system includes an imaging device configured to capture a retinal fundus image of an individual, a processor, and a memory storing instructions. When executed by the processor, the instructions cause the system to preprocess the retinal fundus image to remove extraneous background information and enhance retinal features, input the preprocessed retinal fundus image into a trained machine learning model, generate a determination of whether the retinal fundus image indicates presence of retinal detachment using the trained machine learning model, and output the determination to a user interface. The machine learning model is trained on a set of labeled retinal fundus images to classify images as indicating presence or absence of retinal detachment.

The invention discloses a space remote sensing image analysis method for detecting surface water and underground water exchange in a river region based on surface temperature, and belongs to the field of remote sensing detection surface temperature anomaly analysis. According to the method, background field construction is carried out on pixels in a space by combining single-scene high-resolution surface temperature data and land cover classification data, and temperature thermal anomaly of a river main stream is extracted by adopting an adjacent pixel temperature anomaly analysis method, namely, the temperature thermal anomaly of the river main stream is extracted by analyzing subtle change of surface temperature in a remote sensing image; and identifying abnormal pixels which are obviously different from the temperature characteristics of the surrounding area. The abnormal pixels often correspond to areas where surface water and underground water exchange is active, such as permeable zones, spring water exposure points and the like. The method can be applied to drainage basin water resource management and ecological protection, and the conversion path and intensity between surface water and underground water can be deduced by further analyzing and processing the abnormal pixels extracted by the method and combining background information such as geology and hydrology.

The invention provides a laser interference coding image restoration optimization method, and belongs to the technical field of photoelectric imaging in image processing. According to the method, comprehensive optimization of image quality is realized through directional search and removal of light spot noise, restoration of coding information and restoration of background information.

The invention discloses a health management scheme generation method and system based on deep learning. The method comprises the steps of obtaining a user physical examination report and portrait information; extracting structured and unstructured data in the report through preprocessing and an OCR (Optical Character Recognition) technology; encoding the extracted data into a vector by using a pre-training language model, and obtaining associated medical background information from a medical knowledge base through vector retrieval; in combination with the user portrait, the original data and the retrieval information, analysis is performed based on a pre-trained large language model, key abnormal indexes are identified, abnormal levels are judged, and associated risks are analyzed; and generating a personalized health management scheme containing a specific quantitative execution standard, and carrying out visual display on the personalized health management scheme. The system comprises corresponding function modules. According to the method and the system, end-to-end automatic generation from a non-standardized physical examination report to a personalized and executable health management scheme is realized, and report analysis precision, health risk understanding depth and operability and practicability of the scheme are remarkably improved.

The present application relates to water quality detection and analysis technical field, specifically to a kind of water total phosphorus multi-parameter synchronous detection method based on water, comprising: after the original water sample is pretreated, the standard test solution obtained is simultaneously introduced into parallel digestion tank and optical cell, and the digestion and conversion of phosphorus compound and the collection of water sample background spectrum are completed synchronously.Digestion liquid is distributed to multiple independent color developing channels, each channel uses characteristic color developing agent configured for different concentration interval or interference condition, concurrent color developing reaction is carried out under the same environment, and the reaction kinetics time sequence spectrum of each channel is collected.The background spectrum and all kinetic spectrum sequences are input into integrated calibration model for data fusion and cross analysis, and total phosphorus content detection result is directly output.The method realizes wide concentration range, high anti-interference capability of water total phosphorus rapid and accurate detection by parallel acquisition of homologous background information and multi-reaction channel kinetic data.

The application relates to the technical field of remote sensing image detection, and discloses a hyperspectral remote sensing image anomaly detection method, a system, equipment and a storage medium. The method comprises the following steps: acquiring a hyperspectral remote sensing image to be detected; inputting the hyperspectral remote sensing image to be detected into a pre-trained anomaly detection model to perform anomaly detection, and obtaining a detection result of the hyperspectral remote sensing image to be detected; and the anomaly detection model comprises a first convolution module, a second convolution module, a first Transform module, a first Resize layer and a first full connection layer which are sequentially connected. The application detects background and abnormal samples through clustering inspiration, effectively reduces the dependence of a network model on artificial labeling samples, and not only distinguishes abnormal information and background information during the training of the anomaly detection model, but also utilizes a reconstructed image of the hyperspectral image to improve the training effect of the model, so that the whole model has a local and global receptive field, and the detection precision of the anomaly detection model is effectively improved.

This invention belongs to the field of coaxial holographic reconstruction and discloses a holographic reconstruction method based on a wavelet domain feature correlation complex-valued neural network. Specifically, the method involves: adding a phase term to the coaxial hologram A to construct a complex amplitude B, and performing an n-level discrete wavelet transform on it. The transformed result and the complex amplitude B are used as inputs to the complex-valued neural network, outputting the object field complex amplitude C. Next, noise suppression is applied to the object field complex amplitude C, and the suppressed complex amplitude D is used to simulate the forward propagation process of coaxial holography to generate a hologram E. Finally, the similarity between coaxial hologram A and hologram E is calculated, and a smoothing total variational constraint is applied to the phase of the complex amplitude D. Holographic reconstruction is achieved through a gradient descent optimization algorithm of the complex-valued neural network. This invention aims to utilize the inherent coupling relationship between the wavefront amplitude and phase terms in optical holography to construct a complex-valued feature correlation model to separate the target object from the background information, preserving target features while suppressing noise, thus achieving superior holographic reconstruction.