26results about How to "Solve technical problems with low accuracy" patented technology

The invention discloses a load prediction method and device, a storage medium and electronic equipment, and relates to the field of smart power grids and prediction analysis. The method comprises the following steps: acquiring a historical load sequence and first data of a first time period and second data of a second time period; decomposing the historical load sequence into N first components and M second components through target operation; dividing the N first components into Z sequences according to the numerical value change condition of each first component; adding the first data and the second data into each sequence of the Z sequences, and taking the sequence added with the first data and the second data as a target sequence to obtain Z target sequences; and determining a target load prediction result of the second time period according to the Z target sequences and the M second components. According to the invention, the technical problem of low accuracy of a load prediction result caused by difficulty in processing nonlinear and non-stationary data in a traditional prediction method is solved.

The invention discloses a method and device for evaluating obstacles around a power transmission line and electronic equipment. The method comprises the steps that attribute information of at least one obstacle around the power transmission line is recognized, and the attribute information is used for representing whether the obstacle affects the safety state of the power transmission line or not; determining at least one target obstacle of which the attribute information exceeds an attribute information threshold value from the at least one obstacle; based on a three-dimensional model around the power transmission line, at least one adjustment strategy of the target obstacle is determined, the three-dimensional model is used for representing features of the power transmission line and the obstacle in the spatial dimension, and the adjustment strategy is used for representing a rule for adjusting the target obstacle; screening out a target adjustment strategy from the at least one adjustment strategy, and adjusting the corresponding target obstacle according to the target adjustment strategy to obtain an adjustment result; and evaluating the adjustment result to obtain an evaluation result. The technical problem that the accuracy of obstacle adjustment is low is solved.

The invention discloses a fuel cell performance prediction method and device and a computer program product. The method comprises the following steps: acquiring real-time operation data corresponding to a fuel cell in a current time period; based on the real-time operation data, target voltage data corresponding to the fuel cell is obtained by adopting a cell performance prediction model, the cell performance prediction model is obtained through machine learning based on historical operation data in a historical time period and historical voltage data corresponding to the historical operation data, and the historical operation data comprises multiple operation parameters; the multiple operation parameters are screened out from the multiple input parameters based on historical voltage data. According to the invention, the technical problem of low accuracy of a battery performance prediction result caused by many and complex operation parameters used for constructing a model in related technologies is solved.

The application discloses a data processing method and device, a storage medium and an electronic device. It relates to the technical field of medical treatment. The method comprises the following steps: a tibia three-dimensional model is constructed, and a plurality of target steel nail three-dimensional models are obtained; a plurality of second medical images are obtained, and a plurality of target steel nail first two-dimensional pixel point sets and a tibia second two-dimensional pixel point set are obtained according to the plurality of second medical images; target space conversion parameters of the plurality of target steel nails in the tibia coordinates are obtained by calculation according to the target steel nail first two-dimensional pixel point sets, the tibia second two-dimensional pixel point set, the tibia three-dimensional model and the steel nail three-dimensional models; a guide plate model is obtained according to the target space conversion parameters, and a target space posture of a tibia osteotomy plane is obtained according to the guide plate model. Through the application, the technical problem that the space posture of the tibia osteotomy plane is relatively low in accuracy because the space posture of the tibia osteotomy plane is determined by relying on artificial experience is solved.

The invention discloses a loss analysis method and device of a lithium battery, a storage medium and electronic equipment. The method relates to the field of lithium batteries, and comprises the following steps: obtaining discharge data of a lithium battery in N charge and discharge cycles, N being a positive integer; determining the maximum discharge capacity of the lithium battery in each charge and discharge period based on the discharge data of each charge and discharge period; and for each of the N charge and discharge cycles, calculating loss information of the lithium battery in the charge and discharge cycles according to the initial maximum discharge capacity of the initial charge and discharge cycle and the maximum discharge capacity of the charge and discharge cycle, the loss information comprising at least one of the following: an active lithium loss ratio and active lithium loss mass. The technical problem of low accuracy of analyzing the loss information of the lithium battery in related technologies is solved.

The invention discloses a data processing method and device, a storage medium and electronic equipment. The method comprises the following steps: constructing a tibia three-dimensional model, and obtaining a steel nail three-dimensional model of a plurality of target steel nails; obtaining a plurality of orthogonal second medical images, and obtaining a first two-dimensional pixel point set of the plurality of target steel nails and a second two-dimensional pixel point set of the tibia according to the plurality of second medical images; calculating according to the first two-dimensional pixel point set, the second two-dimensional pixel point set, the tibia three-dimensional model and the steel nail three-dimensional model to obtain target space conversion parameters of the multiple target steel nails under the tibia coordinates; and obtaining a guide plate model according to the target space conversion parameters, and obtaining a target space attitude of the tibia osteotomy plane according to the guide plate model. By means of the method and device, the technical problem that the accuracy of the space posture of the tibia osteotomy plane is low due to the fact that the space posture of the tibia osteotomy plane is determined through related technologies depending on artificial experience is solved.

This application discloses a product recommendation method, apparatus, storage medium, and electronic device. Relating to fintech or other related fields, the method includes: acquiring N first financial products associated with a target user; for each first financial product, determining the influence of the first financial product based on a target heterogeneous information network, wherein the target heterogeneous information network includes at least the following types of nodes: user type, product type, and edges between nodes to represent the association relationships between nodes; calculating the similarity between the first financial product and each second financial product based on the target heterogeneous information network; and based on the influence of the N first financial products and the similarity between the N first financial products and each second financial product, determining a target financial product from the second financial products and recommending the target financial product to the target user. This application solves the problem of low accuracy in product recommendations in related technologies.

The invention discloses a power consumption data prediction method and device, electronic equipment and a storage medium. The method comprises the steps that current power consumption data of multiple users are acquired, and the similarity of the current power consumption data of the multiple users is larger than a threshold value; inputting the current power consumption data into a prediction model, and predicting the power consumption data of the plurality of users in the future time period by using the prediction model to obtain predicted power consumption data of the plurality of users; the predicted power consumption data is converted into a plurality of frequency components, and different frequency components are used for representing the frequencies of the power consumption data of different users at different times; and determining target power consumption data of the plurality of users based on the plurality of frequency components. According to the invention, the technical problem of low accuracy of power consumption data prediction in the prior art is solved.

The invention discloses a skeleton determination method and device for a combustion system in an engine and a vehicle. The method comprises the steps that a volume image of a cylinder cover combustion chamber in a combustion system of an engine is obtained, an initial skeleton model set of the combustion system is determined based on the volume image, and the volume image represents volume change results under different shed top included angles and different shed top heights; different volumes correspond to different initial skeleton models in the initial skeleton model set; based on first attribute information of a valve avoiding pit of a combustion system in the initial skeleton model, screening the initial skeleton model set to obtain a first screening result; based on second attribute information of an air inlet system and an exhaust system of the combustion system in the first screening result, the first screening result is screened, and a second screening result is obtained; and determining a target skeleton model of the combustion system from the second screening result based on the shape of the flow guide surface in the combustion system. The technical problem of low skeleton determination accuracy of the combustion system is solved.

The invention discloses a beam determination method, a nonvolatile storage medium and computer equipment. The method comprises the following steps: acquiring various beam selection data fed back by target equipment; the multiple kinds of beam selection data are input into a neural network model, the neural network model outputs respective preset search values of multiple beams, the neural network model comprises multiple sub-networks corresponding to the multiple kinds of beam selection data in a one-to-one mode, and the multiple sub-networks are used for searching the multiple beams according to the correspondingly input beam selection data. Determining a group of overall beam initial values and a group of offset beam initial values; determining a plurality of candidate beams in the plurality of beams according to the respective search values of the plurality of beams; and measuring the plurality of candidate beams to obtain measurement results of the plurality of candidate beams, and selecting a target beam communicating with the target device from the plurality of candidate beams. The technical problem that the accuracy of beam prediction is not high due to the fact that information which can be obtained is not fully utilized for beam prediction is solved.

This invention provides a price monitoring method, apparatus, and electronic device based on fine-tuning of a large language model, relating to the field of large language model optimization. The method acquires a task dataset and a large language model to be fine-tuned. The target tasks corresponding to the task dataset include mathematical reasoning and natural language understanding tasks. The task dataset is split into two training subsets according to a specified ratio. The model weights and guided selection vectors are alternately updated using the two training subsets, and the guided selection vectors are trained using a two-stage optimization algorithm to obtain optimized guided selection vectors. Based on the optimized guided selection vectors, the number of experts and the expert rank of each LoRA-MoE layer are dynamically allocated to obtain the allocated number of experts and expert rank. The large language model is fine-tuned using the allocated number of experts and expert rank to obtain a fine-tuned model adapted to the target task. The fine-tuned model is then used to perform price monitoring by executing the target task to obtain price monitoring results.

The utility model discloses a magnetism-driving bacterial superfluid viscosity measuring device, relates to the technical field of fluid viscosity measurement, and is used for solving the technical problem of low accuracy of a bacterial superfluid viscosity measuring result in the prior art. The superfluid viscosity measuring device comprises a base, a single-shaft air bearing table, a container barrel, a rotating assembly, a torsional rigidity connecting piece and a spectrum confocal sensor assembly, wherein the single-shaft air floating table is arranged on the base, and the container barrel is arranged on the single-shaft air floating table through the bottom surface; the rotating assembly is arranged at the top of the container barrel through a support arranged on the base, and any rotating part of the rotating assembly extends to the interior of a first annular barrel body of the container barrel from the top of the container barrel; the torsional rigidity connecting piece is arranged in the single-shaft air bearing table with the hollow structure, one end is connected with the base, and the other end is connected with the bottom surface of the container cylinder; the spectral confocal sensor assemblies are symmetrically arranged on the outer surface of the container cylinder along the central axis of the container cylinder.

The application discloses an error positioning method and device, a storage medium and a processor. The method comprises the following steps: obtaining a to-be-detected algorithm; performing program segmentation on the to-be-detected algorithm to obtain a program segmentation result, wherein the program segmentation result is obtained based on different functions of a plurality of algorithm modules in the to-be-detected algorithm; testing the program segmentation result based on a test sample set to obtain a target test matrix; and inputting the target test matrix into a neural network model to obtain an error positioning result. The application solves the technical problem of low accuracy of the existing error positioning method.

The present application discloses a battery status monitoring method, device and computer-readable storage medium. A battery status monitoring method includes: collecting battery monitoring information corresponding to a battery, wherein the battery monitoring information is used to indicate the voltage information, current information, temperature information and internal resistance information of the battery; extracting the main components of the battery monitoring information by a principal component analysis algorithm to generate the main component information of the battery; extracting the features of the main component information of the battery by a common space mode algorithm to generate the feature information of the battery; and determining the battery status of the battery according to the feature information of the battery by a status evaluation model, wherein the status evaluation model is used to evaluate whether the battery is in a normal state.

The invention discloses a method and a device for determining the direction of a tail end point of a sheathing canal, a processor and electronic equipment. The method comprises the steps that initial two-dimensional images of an endoscope in the process of stretching into a physiological channel are obtained from at least two angles, and the endoscope comprises a sheath tube and an endoscope body; respectively segmenting a first image region containing an endoscope main body and a second image region containing a sheath tube from the initial two-dimensional image; based on the first image area, determining a first target position of an endoscope tail end point of the endoscope main body in a three-dimensional space, and based on the second image area, determining a second target position of a sheathing canal tail end point of the sheathing canal in the three-dimensional space; and based on the first target position and the second target position, determining azimuth information between the tail end point of the sheathing canal and the reference point. The technical problem that the accuracy of determining the direction of the tail end point of the sheathing canal is low is solved.

The invention discloses an information processing method and device, a storage medium and electronic equipment. The method relates to the technical field of financial science and technology, and comprises the steps that a target portrait of a target object is acquired, and the target portrait is constructed at least based on historical code data output by the target object; performing knowledge point matching with a knowledge mapping model according to the target portrait and the code defect to obtain matched knowledge information; according to the matched knowledge information, a learning path card is generated, the learning path card is pushed to the target object, and the learning path card at least comprises a recommended knowledge resource link and predicted learning duration. Through the resource recommendation method and device, the problem that the accuracy of resource recommendation is low due to the fact that learning resources are recommended according to posts of developers in the prior art is solved.

The invention discloses a transformer substation load determination method and device, and relates to the technical field of new energy and energy conservation. The method comprises the following steps: acquiring N load data sets and M influence factor data sets of a transformer substation in a first time period; obtaining a correlation degree between each load data set and each influence factor data set; inputting the N load data sets, the M influence factor data sets and the correlation degree between each load data set and each influence factor data set into a target model; and converting the data in the N load data sets, the data in the M influence factor data sets and the correlation degree into feature vectors through a target model, and determining N target load data sets of the transformer substation in the second time period according to the feature vectors. The technical problem of low accuracy of the main transformer total load prediction result caused by the fact that the power load prediction always focuses on the analysis of the total load and does not consider other influence factors in the prior art is solved.

The application discloses a kind of based on multi-source data's wind farm key meteorological factor prediction method and system, it is related to intelligent data processing technical field, the method includes: connecting meteorological platform obtains historical wind farm meteorological factor data, carries out multidimensional data source analysis, determines A data source, B meteorological characteristic element;B meteorological characteristic element, A data source are input into meteorological characteristic prediction model and obtain wind farm meteorological characteristic information, identification is carried out in combination with historical wind farm meteorological data to multilevel meteorological factor response interval, generate multilevel meteorological factor sensitive index, then in combination with the meteorological factor prediction data collected, the key meteorological factor of target wind farm is forecasted.The application solves the technical problem that the accuracy of the prediction result caused by the single data source of wind farm weather forecast in the prior art is low, realizes the technical effect of improving the accuracy of wind farm key meteorological factor prediction result.

The invention discloses a data processing method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring a material set, and dividing materials in the material set into a first type of materials and a second type of materials; performing attribution analysis on the first type of materials and the second type of materials through the target model to obtain an initial analysis result, the initial analysis result at least comprising feature tags of differences between the first type of materials and the second type of materials; analyzing and verifying according to the initial analysis result to obtain a verification result, and generating a target analysis result corresponding to the material set according to the verification result and the initial analysis result, the target analysis result being used for providing a reference for generating the target material. According to the method and the device, the technical problem of relatively low accuracy of an analysis result caused by incomprehensive material analysis in related technologies is solved.

The invention provides a freight cableway transportation safety monitoring method, which comprises the following steps of S1, acquiring a video, obtaining a plurality of images with foreign matter invasion, and preprocessing the images; s2, labeling by adopting a LabImg tool to obtain an image set, and converting the labeled image set to obtain a data set; s3, configuring a YOLOv3 model; s4, training a YOLOv3 model by utilizing the data set obtained in the step S2 and adopting a transfer learning method, and exporting an optimal weight file; and S5, deploying the optimal weight file obtained in the step S4 to a monitoring system, performing joint debugging with a camera in the monitoring system, setting a foreign matter intrusion alarm threshold value, and when the threshold value is triggered, giving an alarm by the monitoring system. The invention further provides a freight cableway transportation safety monitoring device. The technical problem that an existing monitoring system for monitoring the periphery of a freight cableway is low in accuracy is solved, and the technical effects of achieving accurate recognition of foreign matter and improving the alarm accuracy of the monitoring system are achieved.

The present application relates to the field of artificial intelligence technology, and specifically discloses an iris recognition method and device, wherein the method comprises: obtaining standardized three-dimensional iris image data of an iris to be recognized; using a two-dimensional convolutional neural network to extract and classify features of the standardized three-dimensional iris image data, and obtaining target feature data and a target user label corresponding to the iris to be recognized, wherein the two-dimensional convolutional neural network comprises a three-dimensional image processing layer, and the three-dimensional image processing layer performs dimensionality reduction processing on the standardized three-dimensional iris image data to obtain multiple two-dimensional iris image data, and the multiple two-dimensional iris image data include oblique section data; retrieving iris feature data corresponding to the target user label from a three-dimensional iris image database, wherein the three-dimensional iris image database stores iris feature data of each user among multiple users; generating an iris recognition result according to the target feature data and the retrieved iris feature data. The above scheme can improve the accuracy of iris recognition.

Embodiments of the present application provide a load weight determination method and device, a storage medium and an electronic device. The method comprises: controlling a scissor mechanism of an automated guided vehicle to perform a first lifting operation; obtaining N pairs of displacement amounts in the process of performing the first lifting operation, and determining a target curve based on the N pairs of displacement amounts, wherein the N pairs of displacement amounts represent horizontal displacement amounts of a lead screw and vertical displacement amounts of a tray collected at N time points, and the target curve represents a change relationship between the horizontal displacement amounts of the lead screw and the vertical displacement amounts of the tray; and determining a weight of a target load according to the target curve and a preset M curves, wherein the M curves represent different change relationships between the horizontal displacement amounts of the lead screw and the vertical displacement amounts of the tray in the process of the scissor mechanism performing the first lifting operation when the tray respectively carries M loads with known weights. Through the present application, the technical problem of low accuracy in determining the weight of the load in the related art is solved.

The invention discloses a flight space query method and device, electronic equipment and a storage medium, and relates to the technical field of aviation. The method comprises the following steps: when a search engine receives a query request of a target agency, obtaining shielding information; determining a target agency state according to the shielding information, the target agency state being used for representing whether the target agency belongs to an airline ticket agency shielded by the airline company; the target flight space information is inquired from the cache region according to the target agency state, and the target agency with different target agency states inquires the target flight space information from different cache regions. The technical problem that in the prior art, due to the fact that a freight rate searching system cannot obtain shielding information of an airline company, the accuracy is low when an airline ticket agency queries flight space information is solved.

This application discloses a method, apparatus, and electronic device for acquiring motion information. Relating to the field of artificial intelligence, the method includes: querying M source documents in a database and generating N query statements based on the requirements for acquiring target motion information; performing query operations on the M source documents using each query statement to obtain a set of N source documents; performing tag matching operations on each source document in the N source document sets to obtain tag matching results, and performing document filtering operations on the N source document sets based on the tag matching results to obtain P target documents; splitting the P target documents according to the document structure of each target document to obtain multiple text blocks, and identifying the multiple text blocks as motion information of the target motion. This application solves the problem of low accuracy in determining motion information based on knowledge documents, literature, and other information collected from the internet in related technologies.

The invention discloses a method and device for determining the running state of a network. The method comprises the following steps: acquiring historical performance data of a target network in a detection period, the target network being a network running a netmeeting process, and the detection period being a time period when the target network runs the netmeeting process; a linear dependency relationship of the multiple pieces of historical performance data is determined, an objective function is constructed according to the linear dependency relationship, the objective function is used for describing dynamic characteristics of the historical performance data, and the dynamic characteristics are used for indicating a time-varying rule of the historical performance data; actual performance data of the target network at the current moment are obtained, the operation state of the target network at the current moment is determined according to the actual performance data and the target function, and the operation state comprises normal operation and abnormal operation. According to the invention, the technical problem of low detection result accuracy of a method for detecting whether a network conference has a fault in the prior art is solved.

The invention discloses a passenger identification method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring identity identification information of a target object; according to the identity identification information, passenger travel information of the target object is acquired; according to the passenger travel information, the travel type of the target object is identified, an identification result is obtained, and if the identification result represents that the travel type of the target object is a transfer travel, corresponding transfer service is provided for the target object. Through the method and the device, the problem of relatively low accuracy of identification of the transit passengers in related technologies is solved.