69results about How to "Exact search" patented technology

The invention discloses a multi-modal model-based RPA element anchor point automatic searching method. The method comprises the following steps of S1, acquiring coordinates, text information and regional screenshots of target elements and candidate anchor point elements in a webpage; s2, according to the area screenshot, obtaining element categories of target elements and candidate anchor point elements through a target detection model; s3, inputting the coordinates, the text information, the regional screenshots and the element categories of the target elements and the candidate anchor point elements into a multi-modal model, performing vector conversion, vector alignment, element distinguishing, element attention and element judgment by utilizing the multi-modal model, and detecting and determining the target anchor point elements; s4, recording a relative relation between the target element and the anchor point element, wherein the relative relation is used for positioning the target element when the robot process automatically runs; the anchor point elements of the webpage are dynamically recognized through the webpage screenshot, the element coordinates and the element types, and the method has the advantages of being wide in application range and reliable in recognition.

The invention discloses a two-dimensional MUSIC spectrum peak searching method based on an improved Archimedes algorithm, and the method comprises the steps: carrying out the one-dimensional MUSIC spatial spectrum function derivation of a signal model, and expanding the one-dimensional MUSIC spatial spectrum function to a two-dimensional MUSIC spatial spectrum function; secondly, taking a spatial spectrum function of the two-dimensional MUSIC as a target function of an Archimedes optimization algorithm; and then, in combination with an objective function, introducing a fusion chaos algorithm strategy to initialize a population, introducing a mutation algorithm, disturbing positions, and improving an Archimedes optimization algorithm. And finally, carrying out two-dimensional MUSIC spectral peak search through an improved Archimedes optimization algorithm, and taking the direction of arrival, namely, a pitch angle and an azimuth angle, obtained in a mode of solving maximum and minimum values through a target function as spectral peak values. The two-dimensional MUSIC spectrum peak searching method has the advantages that the optimization speed is higher, the optimization precision is higher, the robustness is better, and the two-dimensional MUSIC spectrum peak searching can be quickly and accurately carried out.

The invention provides a customer service interaction optimization method and device, equipment, a storage medium and a program product, and relates to the technical field of computers. The customer service interaction optimization method comprises the following steps: in response to a received user question, performing intention recognition on the user question based on a mental model; determining a corresponding domain knowledge base for semantic enhancement based on a result of intention recognition; rewriting the user question based on a query operation on the semantic space alignment spectrogram to obtain to-be-retrieved information; retrieving a corresponding field knowledge base based on the to-be-retrieved information to obtain a business knowledge fragment for enhancing the user question; and inputting the business knowledge fragments into the large language model for response, and outputting reply information of the user question. Through the technical scheme disclosed by the invention, the semantic barrier between the knowledge base and the questions of the user can be effectively made up, the understanding accuracy of the big language model on the intention of the user is improved, and the use experience of the user in interaction of the intelligent customer service system is further improved.

The application discloses a three-dimensional model fast retrieval method, equipment and medium, and relates to the computer technical field. The method comprises the following steps: in response to receiving a part of a two-dimensional sketch of a three-dimensional model drawn by a user, performing image segmentation on the part of the two-dimensional sketch to obtain a plurality of sub-images; performing mapping processing on each sub-image to obtain an initial feature corresponding to each sub-image, and performing attention calculation on the initial features corresponding to the plurality of sub-images to obtain a plurality of first key features; fusing the plurality of first key features to obtain a second key feature corresponding to the part of the two-dimensional sketch; based on the second key feature, performing similarity matching on a feature database to obtain a plurality of target features, and searching a three-dimensional model set corresponding to the plurality of target features from a three-dimensional model database. In this way, the target three-dimensional model meeting the design intention of the user can be quickly and accurately retrieved according to the part of the sketch of the model drawn by the user, so that the design efficiency and the user experience are significantly improved.

The present disclosure relates to an anti-confusion factor based hash image retrieval method, which comprises: obtaining a query image, the query image comprising a reason factor and a confusion factor; inputting the query image into a trained hash network to obtain a hash code expressing the reason factor in the query image; calculating the similarity between the hash code of the query image and hash codes of a plurality of historical images, and taking the historical image corresponding to the hash code with the highest similarity as the image retrieval result. The anti-confusion factor based hash image retrieval method provided by the present disclosure trains a hash network, so that the hash network ignores the confusion factor and focuses on expressing the reason factor in the image in the process of generating a hash code, thereby generating an accurate hash code. Then, by calculating the similarity between the hash codes, an accurate image retrieval result is retrieved.

The present disclosure provides a message processing method and device, equipment and storage medium, comprising: in response to receiving a to-be-processed message, extracting quintuple information from the to-be-processed message; matching the quintuple information with the index key of the session table to determine the type of the to-be-processed message, wherein the index key of the session table is constructed based on the quintuple information of the established session; in response to the type of the to-be-processed message being a first packet, matching the quintuple information with the index key of the association mapping table to determine whether the to-be-processed message is an associated session of the main session, wherein the index key of the association mapping table is constructed based on the IP address and port information obtained by parsing the application layer of the control channel message of the multi-channel protocol, and the main session is the session of the control channel; in response to the to-be-processed message being an associated session of the main session, performing forwarding processing on the to-be-processed message.

Provided are a simultaneous localization and mapping method and device. The simultaneous localization and mapping method comprises: acquiring a current frame image input by a camera; performing scene recognition on the current frame image to obtain a key frame image having the greatest similarity to the current frame image in a global map; and determining a camera pose of the current frame image according to the key frame image. The simultaneous localization and mapping method comprises: acquiring a current frame image input by a camera; determining a key frame image having a similarity to the current frame image; acquiring a feature point matching relationship between the current frame image and the key frame image; and calculating a camera pose of the current frame image based on the feature point matching relationship between the current frame image and the key frame image. According to the simultaneous localization and mapping method and device of the example embodiments of the present disclosure, the camera pose can be calculated by a traditional method, and the camera pose can also be determined by loop detection and repositioning through a deep learning model.

The application provides a performance testing method and device for a platoon automatic driving vehicle, the method comprising: in response to receiving a search condition input by a user, determining a target scene matching the search condition based on a pre-constructed scene database, wherein the pre-constructed scene database stores at least a plurality of first-level scene tags and second-level scene tags, the first-level scene tags comprise a plurality of second-level scene tags, and the plurality of second-level scene tags are in a mutual exclusion relationship; running the platoon automatic driving vehicle in the target scene and obtaining performance data of the platoon automatic driving vehicle; and verifying an automatic driving strategy of the platoon automatic driving vehicle according to the performance data. Through the application, automatic label management is realized, and new and old data are uniformly managed. When the judgment standard of the scene database is updated, only the historical data needs to be refreshed according to the new clustering standard, the historical data can be effectively utilized, and the retrieval difficulty or loss of the historical data is avoided.

This invention discloses a supervised multimodal hash retrieval method and system based on label enhancement, belonging to the field of artificial intelligence and multimedia retrieval technology. The technical problem this invention aims to solve is how to better capture the similarity information between multimodal data points and achieve better performance and accuracy in multimodal retrieval tasks. The technical solution includes: data preprocessing: acquiring and organizing public datasets of image and text modalities, and dividing each public dataset into training, testing, and retrieval datasets; extracting deep features: using a pre-trained network model to extract features from the raw data of the public datasets of image and text modalities respectively, obtaining deep features of the image modality and the text modality; offline training; variable update and optimization; and online query. The system includes a data preprocessing unit, a feature extraction unit, an offline training unit, a variable update and optimization unit, and an online query unit.

The invention provides a pulmonary artery stimulation ablation catheter and an ablation system. The pulmonary artery stimulation ablation catheter comprises a catheter body; the electrode device is arranged at the far end of the catheter body, the electrode device can be contracted and expanded and is configured to be of an annular structure or a cage-shaped structure allowing blood flow to pass through, the electrode device comprises an electrode mounting pipe section and a plurality of electrode sets arranged on the electrode mounting pipe section, and the electrode sets are sequentially arranged in the circumferential direction of the electrode device; each electrode group comprises an ablation electrode and a stimulation electrode which are arranged along the axial direction of the electrode mounting pipe section, and the stimulation electrode and the ablation electrode are ring electrodes; and the ring control device is connected with the electrode device and is used for adjusting the radial size of the electrode device. Therefore, when the pulmonary arterial hypertension is treated, the device can meet the requirements of different individuals, surgery is carried out at a more accurate sympathetic nerve position through the combination of stimulation and ablation, and the treatment effect is improved.

The invention relates to the field of drug utilization value analysis, and particularly discloses a data stream-based drug utilization value analysis system, which comprises a data layer, an application layer and a user layer, according to the method, the multi-source drug data stream is constructed and stored in the multi-source drug database, and based on systematic management of drug information, drug use errors caused by drug name confusion, dosage errors and dosage form confusion can be reduced, the drug use safety is improved, and the method is beneficial to quickly and accurately retrieving and querying specific types of drug information; by integrating the elderly physiological features and the drug feature information, the drug utilization value analysis model is constructed, the elderly physiological features and the drug features are comprehensively considered, the utilization value of the drug on the elderly can be comprehensively evaluated, and the influence of the drug on the elderly patient can be predicted more accurately.

This invention provides a method for predicting the dominant frequency of blasting vibration by integrating parameter fluctuation processing and the Dream Optimization Algorithm (DOA), belonging to the field of underground engineering safety control technology. The system includes a data acquisition and uncertainty modeling module, a data preprocessing and feature construction module, a hyperparameter optimization module, and a prediction model training and result output module. The method obtains relevant parameters through on-site investigation and monitoring, and generates an extended sample set using a combination of probabilistic perturbation modeling and fuzzy triangular modeling. The data is preprocessed and features are selected. The DOA algorithm is used to globally search the hyperparameters of the Support Vector Regression (SVR) model, and the optimal hyperparameter combination is selected by combining a robustness fitness function. The SVR model is trained, and prediction results and uncertainty prediction intervals are generated. This invention can explicitly characterize the uncertainty of geological parameters, achieve efficient global optimization of hyperparameters, improve prediction accuracy, robustness, and generalization ability, and is applicable to different geological conditions and blasting scenarios. It can be extended to various blasting dynamic response prediction tasks.

The present invention relates to the field of data management technology, and in particular to a method and system for intelligent classification of electronic medical records of traditional Chinese medicine based on a knowledge graph. The method comprises: obtaining a knowledge graph of traditional Chinese medicine, which is composed of a plurality of first knowledge entities of traditional Chinese medicine; extracting a second knowledge entity of the electronic medical record of traditional Chinese medicine, and matching the first knowledge entity of traditional Chinese medicine in the knowledge graph of traditional Chinese medicine based on the second knowledge entity of traditional Chinese medicine; obtaining a storage address of the electronic medical record of traditional Chinese medicine, and linking the storage address and the first knowledge entity of traditional Chinese medicine matching the corresponding second knowledge entity of traditional Chinese medicine; setting a target knowledge entity of traditional Chinese medicine, and matching the first knowledge entity of traditional Chinese medicine in the knowledge graph of traditional Chinese medicine based on the target knowledge entity; obtaining the electronic medical record of traditional Chinese medicine matching the target knowledge entity based on the storage address linked to the first knowledge entity of traditional Chinese medicine; the present invention can not only improve the intelligent management level of electronic medical records, but also provide a convenient tool for clinical diagnosis and research in the field of traditional Chinese medicine.

The invention relates to the technical field of alloy materials, and discloses an alloy material component screening method, system and equipment and a medium. The method comprises the following steps: constructing an alloy component performance data set; constructing a multi-model performance prediction model, and training the multi-model performance prediction model according to the alloy component performance data set to screen out a performance prediction reference model; performing global search according to a genetic algorithm and the performance prediction reference model to obtain an alloy component scheme and a corresponding performance prediction result; according to the alloy component scheme and the performance prediction result, weighted assignment sorting is carried out to screen out a target alloy combination; and performing simulation verification and process analysis on the target alloy combination to optimize the performance prediction reference model. According to the method, deviation of a single model is avoided through a multi-model performance prediction model, the genetic algorithm is introduced to ensure global search and avoid local optimization, the closed-loop process design is formed by combining simulation verification and process analysis, the target alloy combination meeting the requirements is rapidly and accurately screened, and the development efficiency is improved.

The application discloses a kind of self-adapting terminology normalization methods based on double-tower model. The original word of terminology is retrieved in standard terminology dictionary to retrieve multiple similar standard terminology of the original word of terminology;Sample pair is formed, and balanced processing obtains balanced sample pair set;Balanced sample pair set is input into Sentence-BERT double-tower model for training, Sentence-BERT double-tower model outputs label and prediction result, and the standard terminology dictionary is processed using the trained Sentence-BERT double-tower model, to obtain sentence vector and save in offline vector database;The original word of terminology to be predicted is processed using the trained Sentence-BERT double-tower model, and then combined with offline vector database processing to predict and obtain high similarity standard terminology, and then match additional to the original word of terminology to be predicted.The application can normalize and match a non-standard terminology text, optimize processing in industrial scene, has small amount of calculation, fast operation speed, and greatly improves the efficiency of matching normalization.

The present application relates to the technical field of three-dimensional mobile robot path automatic planning, and particularly relates to a robot three-dimensional global path planning method based on sunlight irradiation principle, comprising the following steps: dividing a search space into an obstacle region and a free region, determining a directed graph set and a dynamic update dataset of robot path nodes; setting a heuristic function to select a sunlight point from the dataset; using a circular conical tangent point search function to determine an obstacle edge path tangent point; using a grid restriction sampling mechanism to screen the path tangent point; repeating the above steps until a preset maximum number of sampling nodes is reached, generating several feasible paths; selecting the feasible path with the minimum path length for backend optimization processing, and outputting an optimal feasible path. The present application quickly searches for an obstacle edge tangent point to construct a feasible path by simulating the sunlight irradiation principle, screens nodes in combination with a grid restriction sampling mechanism, improves the algorithm convergence speed, and realizes rapid and smooth planning of the shortest path in a three-dimensional space.

The invention relates to the technical field of data processing, in particular to a stereo garage positioning system and method.The stereo garage positioning system comprises a parking space obtaining subsystem, a model generating subsystem, a garage monitoring subsystem and a license plate number searching subsystem, and the parking space obtaining subsystem obtains all parking space information in a stereo garage; the model generation subsystem generates a parking garage model based on all the parking space information; the garage monitoring subsystem monitors vehicles in the three-dimensional parking garage based on the parking garage model to obtain a position information base with positions of all the vehicles; a user inputs a target license plate through the license plate number searching subsystem, the target license plate is used for matching from the position information base, the target position is obtained, the target position corresponds to the parking garage model, and a searching route is obtained. The problem that a large amount of time needs to be wasted for searching vehicles in an existing three-dimensional parking garage is solved.

This application belongs to the field of artificial intelligence and healthcare technology, specifically disclosing a multi-memory large model enhancement method and system based on adaptive resonance theory. The method includes: obtaining memory units from the plot memory module based on a new medical dialogue event; processing the new medical dialogue event through a large model based on multi-source memory; multi-source memory is constructed based on information stored in memory units, working memory modules, and semantic memory modules; the plot memory module is used to: determine candidate plot prototypes by analyzing attribute similarity; determine whether there is resonance between the new medical dialogue event and the candidate plot prototype; if there is resonance, use historical dialogue events in the event set of the resonant plot prototype as memory units and update the resonant plot prototype; if there is no resonance, create a new plot prototype. This application enables effective memory management and improves the stability and accuracy of large model reasoning in medical dialogue scenarios.

This application discloses a context generation method and apparatus, relating to the fields of artificial intelligence and other technologies. The context generation method includes: acquiring text data input by a user and encoding it to obtain a text vector; calculating the vector similarity between the text vector and knowledge vector data to obtain target data; obtaining initial context data based on the target data and text data; and performing alignment optimization processing based on the initial context data, text data, and target data to obtain target context data.

The present application relates to the field of data processing, and particularly relates to a sewer network pollutant tracing method, device and system. The present application fuses multi-source pollution data to construct an uncertainty quantification framework, which is used to determine adaptive pollution source tracing positioning. The experience probability of the relevant historical pollution path is obtained by mining the historical pollution events, and the suspected pollution source point and the suspected pollution path are obtained. Then, the asynchronous strength and the blind area gain of each suspected pollution path are accurately quantified. In the final adaptive tracing positioning process, the experience probability, the asynchronous strength and the blind area gain of the suspected pollution path are fused to obtain an adaptive search radius, and the tracing positioning is performed within the adaptive search radius. The final adaptive search radius obtained by the present application can differentiate the scheduling of search resources, reduce the waste of tracing resources and reduce the tracing cost.

The application provides a self-checking method and system for corrosion self-marking of an outer surface of a submarine pipeline. The method comprises: acquiring an initial pipeline image; obtaining an HSV space image, calculating depth information; performing joint bilateral filtering processing on the depth information, calculating transmittance; calculating a stray light signal; generating a non-stray light image to be restored from a diffuse reflection model; analyzing and judging the non-stray light image to obtain a rusted surface of the outer surface of the submarine pipeline and generate rust point coordinates. The application models the depth information of the collected image, obtains model parameters to restore the depth information of the image, and with the aid of the depth information of the collected image, the transmittance and stray light estimates can be calculated through the diffuse reflection model, and then the image is effectively restored to be clear, the rust point coordinates can be accurately found, corrosion hidden dangers can be effectively found, the operation safety of the submarine pipeline is ensured, and the problems of low detection precision and difficult positioning of the existing marine pipeline exploration method are solved.

The invention discloses a parking space searching method and device, and the method comprises the steps: obtaining the current position of a user and pre-stored parking space information in response to a parking space searching instruction of the user, and enabling the parking space information to comprise a parking space identifier and a current parking position corresponding to the parking space identifier; generating a search route map according to the current position and the current parking position; searching the parking space according to the search route map; wherein the current parking position of the vehicle is determined by scanning first identification information adjacent to the parking space by a user when the vehicle is used each time; or the user determines the current parking position through Bluetooth positioning, and the position information corresponding to the first identification information is determined.

The invention discloses a multi-modal large model-based remote sensing image-text cross-modal retrieval method and system, and the method comprises the steps: constructing a retrieval model and carrying out training, and the framework of the model comprises initial modal feature extraction, fine-grained image-text representation enhancement, group perception image-text similarity scoring function design and a multi-view contrast learning strategy; respectively extracting initial representations of the text and the image; respectively enhancing the two types of fine granularity representations; for the image, three learning tasks of feature reconstruction, scene classification and background information alignment are taken as guidance, the background information of each image block is separated from target features, and meanwhile, the relationship between targets is reinforced through image learning; key word information is emphasized for the text; and calculating correlation scores and generating the similarity of the image-text pairs. The system comprises a model building unit, a model training unit and a retrieval unit. By using the method and the device, the cross-modal retrieval precision can be improved. The method can be applied to the field of cross-modal retrieval.

The invention relates to the technical field of computer 3D modeling, and discloses an urban three-dimensional terrain rapid modeling method and system based on AI point cloud semantic segmentation, and the method comprises the steps: carrying out the high-quality modeling of a feature object three-dimensional model in a target urban terrain according to an urban terrain semantic point cloud fusion preprocessing data set in cooperation with a point cloud three-dimensional modeling platform; precise modeling of the urban terrain in a finite point cloud data state is realized based on semantic segmentation and point cloud fusion; urban terrain three-dimensional model image information is accurately collected through a point cloud three-dimensional modeling platform and screenshot software, and urban terrain three-dimensional model modeling defect intelligent identification is carried out in combination with an AI algorithm and urban terrain feature object standard modeling defect image data; and based on the urban terrain three-dimensional model data and in cooperation with a point cloud three-dimensional modeling platform, performing dynamic and efficient repair and reconstruction processing on modeling defects of the urban terrain three-dimensional model, and realizing accurate modeling repair and reconstruction in an urban terrain finite point cloud data state based on model repair.

The present invention discloses a multi-objective endmember identification method based on meme optimization, comprising: obtaining an original hyperspectral image of an endmember to be identified; constructing a self-dictionary based on the data of the original hyperspectral image and pruning the pixels of the hyperspectral image using vertex component analysis based on a pure pixel hypothesis; constructing a multi-objective optimization model for endmember identification of hyperspectral images based on the self-dictionary; obtaining a non-dominated solution set of the multi-objective optimization problem model based on a meme optimization algorithm; and determining an optimal endmember combination based on a knee method using the non-dominated solution set of the multi-objective optimization problem model. The present invention can integrate the global search capability of an evolutionary algorithm and the local optimization capability of a local search operator to improve the accuracy and efficiency of endmember identification, and can also determine an optimal endmember combination from a non-dominated solution set based on a knee method.

Embodiments of the present application provide a video segment retrieval model generation method, device and equipment, and a storage medium, relating to the field of artificial intelligence. The method comprises: obtaining a plurality of video blocks and their corresponding video text information and prior boxes by performing segmentation processing on a video segment; performing feature coding processing on the plurality of video blocks and their corresponding video text information to generate video coding information and text coding information corresponding to the plurality of video blocks; constructing a first graph network structure; updating nodes in the first graph network structure according to the video coding information and the text coding information to obtain a second graph network structure; determining a loss function of a video segment retrieval model according to labels corresponding to the prior boxes; and training the video segment retrieval model based on the second graph network structure and the loss function to obtain a target video segment retrieval model. The present application aims to solve the problem that complete videos cannot be accurately retrieved through video segments in related technologies.

The invention relates to the technical field of computer vision, and discloses a filter stick motion trail tracking method, which comprises the following steps of S1, acquiring a filter stick motion video, and extracting each frame of image of the filter stick motion video; and S2, obtaining the coordinates of the filter rod in each frame of image, obtaining the corresponding coordinates of the filter rod in the next frame of image according to the coordinates of the filter rod in the current frame of image, and linking the corresponding coordinates of the filter rod in each frame of image to generate a complete path. In the step S2, a threshold value is set according to the radius of the filter stick; and searching the next frame of image within the range of a circle with the circle center of the filter stick in the current frame of image as the circle center and the radius as the threshold value, and obtaining the circle center coordinate of the filter stick in the next frame of image as the next frame coordinate value corresponding to the circle center of the filter stick in the current frame of image. The motion trail tracking accuracy is high, the time consumption is low, and the efficiency is improved. The invention also provides a filter stick motion trail tracking system for realizing the method.

The embodiment of the present disclosure provides a coding method, a communication device, a storage medium and a program product, relates to the technical field of video processing, and is used for improving the accuracy of a motion vector used in a coding process. The method comprises the following steps: a decoding end receives a code stream, the code stream comprises first indication information, the first indication information is used for indicating at least one first motion vector in a motion candidate list of a current coding block; at least one second motion vector of the current coding block is determined based on the at least one first motion vector, wherein a vector difference between each first motion vector and a corresponding second motion vector in the at least one second motion vector satisfies a first condition, and the at least one second motion vector is related to a motion vector of the current coding block.

The invention discloses a landscaping method based on landscaping feature migration, which comprises the following steps: a designer only needs to input a landscaping shape graph of a landscaping area, a system automatically constructs feature data of the landscaping area, and automatically matches a template shape graph with the maximum feature similarity from a scheme library; calculating an inward shrinkage or outward expansion relation between landscaping vertexes in the landscaping shape graph and template vertexes having an association relation with the landscaping vertexes in the template shape graph, and calculating fusion coordinates of template landscape points in each sub-region of an intersection region of the template shape graph and the landscaping shape graph after the template landscape points are migrated to a landscaping region; the system can automatically adjust the position of the template landscape point migrated to the landscaping area; low-dimension processing is carried out on the fused coordinates, so that the data volume when a system processes a large number of landscaping requirements at the same time is reduced, and the landscaping speed is increased; and the high-dimensional processing takes the landscaping vertex of the sub-region as a reconstruction reference, and the landscaping position of the template landscape point is subjected to secondary adjustment.

The invention belongs to a document generation method, and provides a document analysis and enhancement generation method and a related device aiming at the technical problem that factual errors or information missing easily occur in generated contents when table contents are designed by an existing document retrieval enhancement generation technology. The method comprises the following steps: analyzing a document image through a layout detection model, identifying to obtain different functional regions of the document image, then constructing a document structure tree for representing a spatial and hierarchical relationship between the functional regions, respectively performing fine-grained semantic analysis on each functional region by using a visual language model, inputting semantic analysis into a large language model, and constructing a document structure tree for representing the spatial and hierarchical relationship between the functional regions; the corresponding natural language description is obtained, then the natural language description is coded into dense vectors, and all the dense vectors are constructed into a vector index database; according to the method, fine-grained layout detection, multi-modal structure understanding and structured language representation are introduced into a retrieval enhancement generation process, and an end-to-end analytic framework is formed.