268results about How to "Improve relevance" patented technology

The invention discloses an intelligent question and answer method and system based on a mine safety large model. The method comprises the following steps: constructing a vector database based on a mine document data set; obtaining an input user question, and generating a corresponding similar question based on the user question; after the similar questions and the user questions are combined, vectorization processing is carried out, and user question vectors are generated; performing correlation retrieval of the text blocks in a vector database based on the user question vector to obtain a corresponding preliminarily screened text block set; reordering the preliminarily screened text block set to obtain a finely arranged text block set; and inputting the user question and the reordered finely-arranged text block set into a large model for correlation analysis, outputting the text blocks most relevant to the user question, and sorting the text blocks according to similarity to form a data set as a retrieval result. According to the method, related questions are generated on the basis of user questions to cover more possible query intentions and expression modes, so that the accuracy and efficiency of mine risk hidden danger question answering are improved.

The invention provides a method and system for optimizing a commodity title and computing equipment, and the method comprises the steps: obtaining commodity information which comprises an original title of a commodity and a commodity attribute; obtaining related flow words associated with the commodity by using an algorithm recommendation system; based on the commodity information, first candidate traffic words used for being added into the original title are selected from the related traffic words through a large language model; based on the commodity information and the first recommended traffic word, utilizing a large language model to generate a second candidate traffic word used for being added into the original title; based on the commodity information, the first candidate traffic word and the second candidate traffic word, determining excluded risk traffic words by using a large language model to obtain a third candidate traffic word; and selecting an optimized traffic word from the third candidate traffic words by utilizing a large language model based on the commodity information, and adding the optimized traffic word into the original title, thereby generating a new title. According to the technical scheme, merchants can be better helped to screen drainage keywords, commodity titles can be more conveniently optimized, and commodity competitiveness is improved.

The invention relates to a fusion sorting recommendation method and system based on multi-path recall, and belongs to the field of recommendation systems. Comprising the steps of obtaining commodity information and an interaction behavior between a user and a commodity; calculating a first recommendation score of each commodity through a content-based recall mode on the basis of the similarity between the commodity attribute features and the user portraits; calculating a second recommendation score of each commodity through a recall mode based on collaborative filtering based on the user behavior characteristics; based on click rates of different recall modes, performing weighted average on the first recommendation score and the second recommendation score, and calculating a weighted average score of each commodity; sorting the commodities in a descending order according to the weighted average score to obtain a commodity recommendation list; and preprocessing the commodity recommendation list to generate a final recommendation list. And the correlation, diversity and effectiveness of recommendation results are improved.

The invention relates to the technical field of user personalized content pushing, in particular to a user personalized content pushing system based on big data and a promotion method. The method comprises the following steps: collecting user behavior and preference data through multiple channels; dynamically constructing user portraits, and enriching the user portraits in combination with multi-dimensional data; based on user portraits and content features, a recommendation model is constructed by using a deep neural network, and user preferences are accurately predicted through multiple hidden layers; through a push model and a multi-objective optimization method, the probability of pushed content is calculated in combination with indexes such as a click rate and a conversion rate, the push frequency and content selection are optimized, and the correlation of the pushed content and the user satisfaction are ensured; by monitoring user feedback in real time and adjusting a pushing strategy, intelligent decision and personalized recommendation of content pushing are realized, and long-term accurate pushing and improvement of user experience are ensured. According to the method, the accurate user portrait is constructed through multi-data source collection and processing, so that personalized content pushing is realized.

The invention discloses an intelligent compilation system and method of a building construction scheme, and the system comprises a data preprocessing module which is used for obtaining historical construction scheme text data of each building engineering project category; the knowledge base construction module is used for constructing a construction scheme knowledge base of each construction engineering project category by establishing a vector index of a construction scheme vector database of each construction engineering project category; the retrieval information extraction module is used for performing keyword extraction on the construction scheme retrieval statement of the construction engineering project input by the user, and mapping and recalling the construction scheme text data of a plurality of corresponding construction engineering projects; and the construction scheme compiling module is used for obtaining a construction scheme compiling basis of the construction engineering project. Associated storage and value utilization of previous engineering construction schemes are achieved, the scheme compiling efficiency and reliability are improved through intelligent generation of the scheme compiling basis, and effective guarantee is provided for the scheme compiling quality.

The invention discloses a method for extracting plant available cadmium in neutral-alkaline rice field soil, which comprises the following steps: naturally air-drying the soil, grinding and sieving to obtain a soil sample, weighing the soil sample, adding deionized water to enable the water content of the soil to be 35-110% of the maximum water-holding capacity of the soil, balancing at room temperature for 12-48 hours, adding a calcium chloride solution, oscillating and extracting at constant temperature, and filtering to obtain the plant available cadmium in the neutral-alkaline rice field soil. And filtering to obtain an extracting solution, measuring the concentration of cadmium in the extracting solution, and calculating the content of the plant available cadmium in the measured soil sample according to the measured mass of the soil sample and the measured concentration of cadmium in the extracting solution. The method is easy and convenient to operate and low in cost, the change characteristics of the plant effectiveness of cadmium in the neutral-alkaline rice field soil in a field water management mode can be well reflected, and the measured plant effective-state cadmium content in the neutral-alkaline rice field soil and the rice cadmium content have a better linear correlation relationship.

The invention relates to the technical field of intelligent robots, and provides an intelligent question answering method and device, electronic equipment and a storage medium, the intelligent question answering method comprises the following steps: obtaining voice information corresponding to a question asked by a user, and carrying out text conversion on the voice information to obtain a question text of the user; obtaining a user portrait model of the user, wherein the user portrait model is generated according to at least one of a mood feature, an emotion feature, a dialogue habit feature and an age feature of the user; and according to the question text and the user portrait model, querying a plurality of corresponding candidate answers, further determining a target answer from the plurality of candidate answers, performing secondary processing on the target answer to enable the processed target answer to accord with the cognitive level of the age group of the user, and outputting the target answer. The accuracy and correlation of question answering are effectively improved, and the user experience and loyalty are improved.

The invention relates to the technical field of bioinformatics, in particular to a mining method and system for synthetic biology functional elements and a storage medium. The method comprises the following steps: acquiring functional demand data of a target metabolic pathway; performing evolutionary distance analysis and function prediction on homologous genes of a plurality of species according to the function demand data, and performing protein structural domain conservative classification on preset genome sequence data to obtain candidate element cluster data with function relevance; obtaining expression system data of the host cells; and according to the candidate element cluster data and the expression system data, scoring each functional element based on codon optimization degree, protein folding stability and metabolic load prediction to obtain hierarchical element suitability data. According to the method, factors such as sequence characteristics, expression efficiency and regulation and control network interaction are considered at the same time, multi-level accurate screening is achieved, and therefore the low efficiency and limitation of a traditional screening mode are overcome.

The invention discloses a polyester fabric defect detection method and system based on a visual image, and relates to the field of fabric detection.The method comprises the steps that a multi-scale feature map of a polyester fabric is obtained; generating change track characteristics of each key process; extracting integrated features from the multi-scale feature map of the polyester fabric by using a convolutional neural network, and constructing a multi-granularity feature matrix in combination with the change trajectory features of each key process; based on federated learning and a random forest technology, performing importance scoring on each feature in the multi-granularity feature matrix, and performing feature screening according to importance scores to obtain polyester fabric defect identification input features; and performing score prediction on the polyester fabric defect identification input features through a neural network, and identifying a potential polyester fabric defect area. According to the method, the accuracy and robustness of defect detection of the polyester fabric are improved, and the method has the advantages of data privacy protection and multi-source information integration.

The invention discloses a shale oil geological engineering dessert evaluation method and device based on geological modeling, and the method comprises the steps: determining a shale oil facies classification scheme and shale oil dessert evaluation key parameter values according to the shale oil geological engineering logging interpretation data, determining the corresponding scores of different shale rocks, and obtaining the shale oil dessert evaluation key parameter values of the shale oil facies classification scheme and the shale oil dessert evaluation key parameter values of the shale oil facies classification scheme; and determining a target sweet spot evaluation parameter weight based on sweet spot evaluation attributes of the lithofacies three-dimensional model and actual well drilling productivity data, establishing a shale oil geological engineering integrated comprehensive sweet spot factor, and determining a shale oil geological engineering comprehensive sweet spot evaluation result based on the sweet spot factor and the target sweet spot evaluation parameter value. Through the technical scheme of the embodiment of the invention, comprehensive evaluation of shale oil geological engineering desserts is realized, complexity of shale oil geological features can be adapted, correlation between geological and engineering dessert evaluation parameters is improved, and fine evaluation of shale oil dessert space distribution is ensured.

The invention discloses a metal piece service life prediction method and device, a controller and a storage medium, relates to the technical field of metal material performance prediction, and at least solves the problem of low prediction result precision of a prediction model constructed on the basis of uniaxial smooth sample test data. The method comprises the following steps: determining a first pure fatigue life of a target metal piece in a notch structure in a non-notch smooth structure state, target holding time of creep and a target notch stress concentration coefficient; obtaining a corresponding target preset model associated with the target metal material of the target metal piece; the target preset model represents the stress concentration coefficient, the load holding time, and the mapping relation between the pure fatigue service life and the creep-fatigue service life in the unnotched smooth structure state; and based on the target preset model, obtaining the target service life of the target metal piece under the first pure fatigue life, the target holding time and the target notch stress concentration coefficient.

The invention provides a social engineering attack detection method based on context awareness, and aims to solve the problem that dynamically changing social engineering attacks cannot be effectively handled in the prior art. According to the method, the emotional state, the decision-making mode and the daily behavior mode of a user are continuously monitored by constructing a context awareness system, and user behaviors are analyzed and monitored in real time in combination with a personalized behavior baseline model. The system measures the deviation between the user behavior and the baseline model by using a composite function and a multi-dimensional feature fusion technology, and when an abnormal behavior is detected, the system automatically triggers security policy adjustment, such as starting multi-factor authentication or limiting high-risk operation. Experimental results show that social engineering attacks can be effectively recognized in complex and changeable attack scenes, and the detection accuracy and response speed are remarkably improved. The method can be widely applied to the field of network security, and is especially suitable for an environment requiring highly customized security protection.

The invention relates to the technical field of computer vision, and discloses a visual saliency target detection method based on an RGB-D image, and the method comprises the following steps: S1, carrying out the channel alignment and spatial calibration of a mutual relation between corresponding features of different modals through an MI module, and obtaining a cross-modal representation; s2, then, an IGF module is added to the tail end of the Swin Transform encoder, and the IGF module is added to the tail end of the Swin Transform encoder; s3, the cross-modal fusion feature # imgabs0 # is subjected to channel cross fusion through a CCT module, and relevant information about significance is further obtained; and S4, finally, carrying out modeling on the remote dependency of the fusion features from a global perspective by using a decoding block based on Swin-Transform. According to the visual saliency target detection method based on the RGB-D image, by designing a modal interaction module and a channel cross fusion mechanism, the fusion effect of multi-modal features and the fine modeling capability of multi-scale features are fundamentally improved, and therefore the problems of saliency target detection precision and robustness which are difficult to overcome in the prior art are effectively solved.

The invention discloses an information retrieval method and device, electronic equipment, a storage medium and a computer program product, and the method comprises the steps: receiving a first query statement input by a user; judging whether a first list contains the first query statement or not to obtain a judgment result; the first list comprises one or more query statements, and each query statement in the first list is associated with zero or one or more answers in a set database; when the judgment result represents that the first list contains the first query statement and the first query statement is associated with one or more answers in the set database, randomly selecting a first answer from the one or more answers, and calculating a first score based on user interaction information of the first answer; and when the first score is greater than a first score threshold value, outputting the first answer as a retrieval result of the first query statement.

The invention relates to a data processing method and device based on a large language model, equipment and a storage medium. The method comprises the following steps: acquiring input data, matching the input data with a plurality of pre-constructed data matrixes to obtain a data matrix matched with the data type of the input data, and determining the matched data matrix as a current data matrix; constructing an inference tree model based on the input data and the current data matrix; determining a plurality of candidate sequences based on the inference tree model; and performing parallel verification on the plurality of candidate sequences, determining the output probability distribution of each candidate sequence, and obtaining an output sequence matched with the data content of the input data according to the output probability distribution. Compared with the prior art, the data processing efficiency can be improved, and the data output quality and accuracy can also be improved.

The invention discloses a software test case generation method based on a bidirectional long and short memory algorithm, and belongs to the technical field of software testing. The method comprises the steps of obtaining a to-be-processed file; preprocessing the to-be-processed file to obtain preprocessed text data; inputting the preprocessed text data into the trained Bi-LSTM network for feature extraction to obtain text features; and generating a test case according to the text features. According to the method, the software test case is automatically generated by innovatively applying the bidirectional long and short memory network, and deep understanding of software requirement documents, codes and logs is realized through a deep learning algorithm, so that the correlation and accuracy of the test case are improved. According to the method, the test process can be optimized, and it is ensured that the test cases can cover more test scenes including conventional operation and potential abnormal conditions.

The embodiment of the invention provides an archive management method and system based on big data analysis, and belongs to the technical field of data processing. The method comprises the steps of obtaining initial text data and initial image data corresponding to an initial user; performing deduplication processing on the initial text data to obtain target text data, and performing deduplication processing on the initial image data to obtain target image data; performing association relationship analysis on the target text data and the target image data to obtain a target relationship corresponding to the target text data and the target image data; performing text classification on the target text data to obtain a target type corresponding to the target text data; and performing data storage on the target text data and the target image data according to the target type and the target relationship to obtain a target storage result. The problems that in the prior art, the occupied storage space is increased and the data access and retrieval efficiency is reduced due to the fact that texts and images are often used as independent information units to be processed and an effective integration mechanism is lacked are solved.

The invention discloses a commodity recommendation system based on artificial intelligence, and the system comprises a user behavior tracking module which is used for collecting and processing the multi-source behavior data of a user; the commodity feature extraction and fusion module is used for acquiring and analyzing multi-modal information of commodities; the dynamic updating module is used for adjusting a recommendation list in real time according to instant user behaviors and long-term preferences in combination with short-term memory and long-term memory; the situation awareness module takes external factors such as time, place and weather as input; the explanatory enhancement module is used for adding an explanatory layer for a black box model by using an explanatory machine learning model; the personalized sorting optimization module is used for dynamically adjusting the feature weight and improving the click rate and the conversion rate; and the privacy protection module is used for protecting user privacy by adopting a differential privacy technology. According to the commodity recommendation system and method provided by the invention, many problems existing in a traditional recommendation system are overcome, and a more efficient, more intelligent and safer commodity recommendation service is realized.

The invention relates to a medical emotion support large model and a generation method thereof, and belongs to the field of medical data processing. Comprising an emotion detection module which is used for recognizing the current negative emotion of a patient through dialogue history and inputting a detection result into a response generation module; the short-term memory storage module is used for storing the dialogue between the patient and the response generation module as a dialogue history record, compiling the dialogue history exceeding the upper limit into background information through a large language model, and inputting the background information into the response generation module; the dialogue strategy guidance module is used for judging a dialogue communication strategy which should be used by the response generation module according to the dialogue historical record; the response generation module is used for setting personal background information and current confronted conditions and generating proper response; and the correction module is used for performing self-reflection according to the feedback of the patient to the response of the medical emotion support framework, and updating the recommendation experience of the dialogue strategy guidance module. According to the method, the medical emotional dialogue data set can be generated through the constructed framework.

The invention provides a factory monitoring method and system based on digital twinning, belongs to the field of intelligent control, and solves the problems that video monitoring in a factory has a monitoring dead angle and also has a large amount of non-key information, and the monitoring efficiency is poor. If undifferentiated analysis is carried out on video data in real time, a large number of computing resources are consumed on meaningless data, and in addition, the problem that personnel video information and a digital twinborn model are difficult to fuse in video monitoring is solved. The method comprises the following steps: acquiring a manual control signal of operation equipment in a factory; based on the manual control signal, determining manual operation information currently implemented by an operator for the operation equipment; and deducing the current operation action of the operator in the digital twin model through the manual operation information so as to simulate the three-dimensional simulation dynamic effect of the operator corresponding to the operation action.

The invention discloses a PPG blood pressure estimation method and system combining deep learning and clinical priori knowledge. The PPG blood pressure estimation method combining deep learning and clinical priori knowledge comprises the following steps: firstly, acquiring a pulse wave signal through a signal acquisition module; preprocessing the pulse wave signal, and respectively outputting a first branch pulse wave signal and a second branch pulse wave signal; performing dimension conversion on the first branch pulse wave signal, extracting multi-dimensional features through a deep learning network, and extracting clinical priori knowledge features in the second branch pulse wave signal; and finally, constructing a blood pressure estimation model of a corresponding time period according to the multi-dimensional features and the clinical priori knowledge features, and predicting and outputting a blood pressure value of the corresponding time period through the blood pressure estimation model, so that the correlation between the extracted PPG features and BP and the blood pressure measurement precision are improved by combining deep learning and double-branch feature extraction of clinical priori knowledge. The effectiveness and interpretability of the blood pressure estimation method are ensured, and the credibility of the estimated blood pressure value is improved.

The invention provides a tumor medical image classification method of zero sample evolution NAS based on double-index collaborative evaluation, which comprises the following steps: collecting tumor medical image data, and constructing a data set containing a tumor focus image and a normal tissue image; constructing an extended search space based on a cell structure, wherein the search space comprises a basic operation set, the cell structure and a network overall structure; steady-state evolution algorithm parameters are set, and steady-state evolution initialization is carried out to obtain an initial candidate architecture; taking a double-index comprehensive score calculated by the information rate and the FIM stability as a comprehensive index for evaluating the current candidate architecture, updating the candidate architecture through a steady-state evolutionary algorithm based on a dynamic optimization mechanism until the maximum evolutionary algebra is reached, and obtaining an optimal architecture; and training the optimal architecture by using the data set, and carrying out tumor medical image classification by using the trained optimal architecture. According to the method, the dependence on the annotated data is reduced, the consumption of computing resources is reduced, and meanwhile, the diagnosis efficiency and accuracy are improved.

The invention relates to an intelligent recommendation technology, and discloses a recommendation method based on adaptive feature map comparative learning, which comprises the following steps: acquiring user-article original interaction data, and constructing an interaction matrix by using the user-article original interaction data; performing normalization processing on the interaction matrix to obtain a normalized adjacent matrix, and performing data enhancement on the normalized adjacent matrix to obtain reconstructed interaction data; performing multi-layer graph convolution operation on the normalized adjacent matrix to obtain a first interaction feature, and performing multi-layer graph convolution operation on the reconstructed interaction data to obtain a second interaction feature; performing weighted summation processing on the first interaction feature and the second interaction feature to obtain a final interaction feature; and inputting the final interaction feature to a pre-trained recommendation model to obtain a final recommendation result. The invention further provides a recommendation device based on adaptive feature map comparative learning, electronic equipment and a storage medium. According to the invention, the accuracy of article recommendation can be improved.

The invention discloses an enhanced generation query method and system based on multi-granularity retrieval and reinforcement learning strategies. According to the method, semantic analysis is carried out on an original query by utilizing a large language model, the original query is decomposed into a plurality of sub-problems, and each sub-problem generates a query vector; in the multi-granularity vector knowledge base, respectively executing vector similarity retrieval on the query vector of each sub-problem to obtain a related document fragment vector of each sub-problem under each granularity, and further generating a multi-granularity vector set of each sub-problem; weighting the multi-granularity vector set of each sub-problem to obtain a comprehensive context information block, determining the weight of the multi-granularity vector set of each sub-problem through a multi-arm reinforcement learning strategy, and inputting the comprehensive context information block into a large language model to output a query result. According to the method, the retrieval accuracy is improved through semantic decomposition and multi-granularity knowledge collaborative retrieval, results are intelligently integrated through a self-learning mechanism, and lightweight self-adaptive optimization is achieved.

The invention relates to a short-term OD passenger flow prediction method for urban rail transit passenger flow, and the method comprises the steps: 1) constructing a label of a scene feature based on an influence factor set which influences the short-term OD passenger flow prediction of multiple scenes, and embedding the scene feature into a time sequence of historical OD passenger flow; 2) constructing a subway network space-time diagram according to the time sequence of the historical OD passenger flow embedded with the scene features, and constructing a sparse graph convolutional network for capturing spatial features; 3) according to the time sequence of the historical OD passenger flow embedded with the scene features, constructing a cross attention mechanism for capturing the time features; and 4) based on the sparse graph convolutional network and a cross attention mechanism, constructing a Transform-based multi-scene short-term passenger flow prediction combination model, and outputting a final predicted OD passenger flow matrix.

The invention discloses a weak supervision target positioning method based on a semantic-driven Transform model, and the method comprises the following steps: S1, carrying out the preprocessing of a to-be-detected picture, and converting the to-be-detected picture into a format suitable for neural network processing; s2, sending the preprocessed to-be-detected picture and the label of the corresponding picture level into a neural network; the neural network comprises a Transform backbone network, a semantic kernel integration module SKI and a semantic enhancement adaptation module SBA; s3, the neural network processes the picture, and outputs a probability value of the to-be-detected picture corresponding to each category in a training process; s4, outputting the coordinate, category and score of the frame predicted by the to-be-detected picture in the test process; according to the method, the attention graph is more focused on the foreground region, and more accurate semantic perception target positioning is realized in a weak supervision environment, so that the explanation precision and correlation of the model are improved.

The invention provides a data classification and grading method and system based on a large model, and the method comprises the steps: mining a text representation array of a government affair training text based on a basic government affair text classification model in a debugging stage of the large model; obtaining a first centroid array representation of a priori real classification and second centroid array representations of other classifications from connection influence variables of the full-connection network, correcting a first cosine similarity between a text representation array and the second centroid array representations, and obtaining a target cosine similarity greater than the first cosine similarity, and determining a distance cost value according to the target cosine similarity, the text representation array, the first centroid array representation, the second centroid array representation and the second cosine similarity so as to correct model parameters of the model and obtain a target government affair text classification model. According to the method, the training quality of the government affair text classification model for training texts with unclear classification boundaries, difficulty in classification and complexity can be improved, and the government affair text classification precision of the target government affair text classification model is improved.

The invention belongs to the technical field of tea polyphenol prediction, particularly relates to a tea polyphenol quantitative prediction method based on a hyperspectral image, and aims to solve the problem of low tea polyphenol prediction accuracy caused by single tea polyphenol characterization parameter in a tea polyphenol measurement method in the prior art. According to the method, the tea polyphenol can be predicted by inputting the hyperspectral image of the tea into the prediction model. The step of training the prediction model comprises the steps of collecting a hyperspectral image of tea, screening spectral band features in the hyperspectral image and image fusion features fused by color features and texture features, obtaining a tea polyphenol sample, and training the prediction model according to the spectral band features, the image fusion features and the tea polyphenol sample. According to the method, the hyperspectral image of the tea is collected, and the spectral band characteristics of the tea and the texture and color characteristics of the tea image are extracted, so that the problem of inaccurate tea polyphenol content prediction caused by only single characteristic in the prior art can be solved, and high-precision tea polyphenol content prediction is realized.

The invention belongs to the technical field of commodity recommendation, and discloses an e-commerce commodity recommendation optimization management system, which comprises the steps of collecting e-commerce comprehensive data, and preprocessing the collected e-commerce comprehensive data to generate a comprehensive data set; weight values are distributed for the user behavior characteristics through a comprehensive data set; in combination with the weights of the user behavior characteristics, scores of the users for all the commodities are calculated, and a user-commodity interaction matrix is constructed according to the scores; the festivals and the user positions are comprehensively considered, the preference degree of the users for the commodities is calculated through the user-commodity interaction matrix, and the optimal commodity category recommendation list for attracting the users is generated, so that the problems of improper regional difference processing and difficult recommendation system performance optimization are solved, the commodity recommendation accuracy is improved, the user experience is enhanced, and the user experience is improved. And the user experience and the operation efficiency of the e-commerce platform are improved.

The invention provides a channel prediction method and system based on a multi-cycle feature convolutional network. According to the method, context sensing weighted input and a dynamic multi-model pool mechanism are introduced. A terminal device obtains environmental context features in real time, dynamically calculates the weight of each time step in a historical channel state information sequence based on the features, and generates a weighted optimized input sequence. Meanwhile, the network equipment pre-trains and maintains a plurality of multi-period feature convolutional network models specific to different environments, and the network can effectively capture the complex time-varying rules in the period and during the weeks in the channel, so that the accuracy of channel state information prediction is improved. And the terminal equipment immediately selects and activates the optimal sub-model in the model pool for prediction according to the real-time context features, and locally performs increment fine adjustment. According to the invention, through management of the data input end and rapid and adaptive switching of the prediction model end, the precision of channel prediction and the adaptive capacity to environmental sudden change are effectively improved.