814 results about "Recommendation model" patented technology

The invention provides an anesthesia virtual simulation training system fusing knowledge, skills and a thinking closed loop. The anesthesia virtual simulation training system comprises a medical knowledge base module, a clinical thinking module, a skill training module, an examination question brushing module, a knowledge graph module and an intelligent platform bottom layer framework. The intelligent platform underlying architecture comprises a data middle platform, an AI engine and a 3D engine, collects student behavior data of each module, constructs a dynamic student ability portrait through a gradient boosting tree algorithm and a collaborative filtering recommendation model, analyzes knowledge blind areas and skill shortages, plans a personalized learning path and pushes targeted training content, and provides a personalized learning result. A closed-loop process of evaluation, learning, practice and re-evaluation is formed; and deep fusion of theoretical knowledge, clinical thinking and skill operation is realized through a cross-module collaboration mechanism. The problems that traditional anesthesia teaching is high in practical operation risk, scattered in resource and insufficient in individuation are solved, and the clinical comprehensive ability and teaching quality of anesthetists are effectively improved.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides an intelligent recommendation method and system based on the plasticizing industry, and the method comprises the steps: obtaining multi-source heterogeneous data from a plurality of third-party data sources of the plasticizing industry; constructing the multi-source heterogeneous data into a dynamic knowledge graph in combination with a plasticizing industry knowledge base; performing demand prediction on the dynamic knowledge graph based on a knowledge-guided hybrid particle swarm algorithm to obtain a first plasticizing recommendation strategy; enhancing a recommendation model through causal reasoning, and performing anti-fact prediction on the dynamic knowledge graph in combination with industry real-time change data to obtain a second plasticizing recommendation strategy; the first plasticizing recommendation strategy and the second plasticizing recommendation strategy are dynamically fused based on Bayesian optimization, a plasticizing industry recommendation report is generated, the plasticizing industry recommendation report comprises the industry flow relation change trend and the corresponding industry hotspot recommendation, and a user is assisted in marketing decision making. The method can shorten the time consumption of the whole supply-demand docking process, effectively alleviates the information asymmetry problem, and remarkably improves the industry operation efficiency.

A dynamic marketplace system leveraging store and warehouse mobility features a neuroevolution (NE) engine, an electronic device, and a request handler facilitating communication between the electronic device and the NE engine. The NE engine interfaces with a data storage system and an event handler receiving real-time event data from a public cloud services processor. An intentions handler interprets user intention data to predict user behavior. The NE engine, integrated with a processor, generates a predictive evolutionary model for the marketplace based on request, event, and intention data. An AI agent processor within the NE engine creates a recommendation model for mobile retail vendors, devises route plans, and deploys vendors to strategic locations.

The invention relates to a semantic collaboration modeling method and system for multi-modal sequence recommendation, belongs to the technical field of multi-modal sequence recommendation, and aims to solve the problems that an existing method depends on an article ID, multi-modal semantic collaboration signals are difficult to mine, the cross-scene migration capability is weak, and the representation precision is insufficient. The method comprises the steps that text information and image information of an article are extracted according to historical interaction behaviors of a user, and multi-level semantic representation is extracted through a multi-mode encoder; a multi-head attention module with a one-way mask is adopted to capture semantic collaboration signals, and the semantic collaboration signals are integrated into initial modal representation; performing fine-grained semantic focusing and optimization by using a hybrid expert structure; obtaining a final modal representation of the article through a hybrid expert fusion module; and constructing a multi-modal behavior sequence of the user based on the final modal representation of the article, and calculating preference scores after coding by a sequence recommendation model to realize next-step interaction prediction of the user. According to the method, recommendation accuracy, generalization ability and cross-scene knowledge migration efficiency can be remarkably improved.

The embodiment of the invention provides an intelligent recommendation method and system based on child digital picture book reading. The method comprises the following steps: constructing a recommendation model based on self-supervised learning and a convolutional neural network CNN; in the self-supervised learning module, feature representation of a comparison mechanism optimization model combined with user cognition is introduced; constructing a dynamically updated user portrait, wherein the user portrait comprises a current cognitive level label of the user; in response to a reading request of a user, self-adaptive fusion is carried out on a user portrait and the reading request, an age-worthiness evaluation factor of the picture book is introduced in the fusion process, and the age-worthiness evaluation factor is determined based on the matching degree of the character difficulty, the picture complexity and the user cognitive level of the picture book. And taking the fused label vector as the input of a trained recommendation model to obtain a recommendation list. According to the embodiment of the invention, the feature representation of the model is dynamically optimized in combination with the cognitive development stage of the user, the reading ability difference of different age groups is accurately adapted, and the recommendation accuracy and adaptability are improved.

The embodiment of the invention provides a content recommendation method and device and a double-tower content recommendation model training method and device, and the content recommendation method comprises the steps: obtaining the content information of to-be-recommended content and the user information of a target user in response to a content recommendation task; the user information and the content information are input into a double-tower content recommendation model, recommended content for the target user is obtained, the double-tower content recommendation model comprises a user tower and a content tower, the user tower is used for extracting user features based on the user information, and the content tower comprises a feature adaptation layer; the feature adaptation layer is used for obtaining target content features corresponding to a task target of the content recommendation task based on the content information, and the recommendation content is obtained by decoding based on the target content features and the user features. The content representation can be dynamically adjusted according to the task target through the feature adaptation layer, so that the same content presents differentiated feature expression under different tasks, and the adaptation precision of the recommendation result to the specific task target is improved on the premise of not changing the double-tower structure.

The invention discloses a recommendation system-oriented privacy sensitive parameter identification and accurate deletion method, and relates to the technical field of recommendation system model optimization and privacy protection. In order to solve the problems that privacy sensitive parameters in an existing recommendation system model are difficult to accurately position and the model performance loss is too large after deletion, according to the evaluation thought of parameter importance and data feature relevance, importance scores of model parameters on two types of data sets are calculated respectively by dividing a forgetting set and a reservation set, and the privacy sensitive parameters are obtained. The privacy sensitive parameters with the forgetting set importance higher than the reserved set importance are screened out, and mask zero setting processing is carried out. According to the method, the model does not need to be retrained or subjected to weight updating, sensitive parameter recognition and deletion can be completed only through single-time forward propagation, and the original recommendation performance of the model is reserved to the maximum extent while the privacy security of a recommendation system is guaranteed. According to the method, accurate identification of privacy sensitive parameters is realized on a mainstream recommendation model, the reduction range of model recommendation accuracy after deletion is controlled within an acceptable range, and the privacy leakage risk is remarkably reduced.

The invention belongs to the technical field of data processing, and particularly discloses a computer vision model service scenarized configuration generation method, which comprises the following steps: constructing a basic information database comprising a plurality of computer vision models, the database being used for storing model identification information and feature parameters; extracting structured features of the scene according to a scene analysis engine, wherein the structured features are used for describing operation conditions of the scene; calculating a model matching score according to the structured features and the feature parameters, and obtaining a recommendation model through a multi-condition weight matching function; executing a model selection strategy based on the matching score, and obtaining a model matched with the scene; and generating a configuration file conforming to a predetermined specification according to the recommendation model. The objective of the invention is to solve the problems of low efficiency and error proneness caused by the fact that a computer vision model in the prior art depends on a manual selection model and cannot quickly select and adapt to an optimal model in diversified scenes.

The invention discloses an innovative resource collaborative matching method and system oriented to distributed operation, and relates to the field of data processing recommendation, and the method comprises the steps: carrying out the standardization processing of a heterogeneous resource portrait description text through a large language model, constructing and forming a resource attribute knowledge graph, generating extension description information of the resources in the target industrial chain through the large language model, and constructing and forming an industrial chain knowledge graph; performing semantic alignment and hidden associated information mining on the fused graph by using a pre-trained SACN model, and constructing a resource collaborative knowledge graph representing resource attributes and collaborative logic in an industrial chain; and performing semantic fusion on the original description text representation of the resource and the resource collaborative knowledge graph representation based on a large language model, generating comprehensive vector representation through multi-modal fusion, and outputting a resource matching recommendation result by adopting a collaborative filtering recommendation model. According to the method, the cross-organization and cross-industry-chain innovative resource collaborative knowledge graph is constructed, instant and clear demands of users are accurately responded, and the resource allocation efficiency is improved.

The invention discloses a memory perception thinking enhancement type large model recommendation method and system, and belongs to the technical field of artificial intelligence and information recommendation. The method comprises the following steps: firstly, constructing user potential feature representation based on historical interaction data of a user; then keyword enhancement item semantics are introduced to synthesize recommendation samples, so that the model has recommendation ability and reasoning chain generation ability in the training process, and the thinking accuracy of the model is ensured through self-supervision correction; after model training, an optimal recommendation model is adaptively obtained, personalized recommendation decision is realized, and finally, a result text with a recommendation reason is output, so that the transparency of recommendation and the credibility of a user are improved.

The invention discloses a recommendation model training and application method and device based on multi-platform behaviors and a medium, and relates to the technical field of user recommendations, the method comprises the following steps: constructing a hybrid neural network model, the hybrid neural network model comprises a feature embedding module, a multi-cavity convolution module, a multi-level attention mechanism module and a prediction module, the feature embedding module processes the multi-platform behavior sequence to obtain a feature embedding vector, the multi-cavity convolution module processes the feature embedding vector to obtain a multi-scale feature vector, and the multi-level attention mechanism module processes the multi-scale feature vector and a commodity feature vector to obtain a user interest vector; and the prediction module predicts a predicted click rate of the user to the candidate commodities based on the user interest vector and the commodity feature vector, trains the hybrid neural network model to obtain a recommendation model, and performs recommendation by using the recommendation model. The recommendation model with better performance can be obtained through training, and the recommendation performance is improved.

The application discloses a multi-label text classification logistics supplier recommendation method, relates to the technical field of network logistics, and comprises the following steps: obtaining a historical text set of manufacturer and supplier information, and pre-training to obtain a training sample set; a text feature map of the training sample set is established based on a bidirectional gate recurrent unit; a text heterogeneous matrix is constructed according to the text feature map; semantic attention is integrated into the text feature map, and the text feature map is labeled to generate a multi-label text feature map; the multi-label text feature map is multiplied by the text heterogeneous matrix to obtain a multi-label text classification model; a graph convolutional neural network is fused with the multi-label text classification model to obtain a multi-label text classification logistics supplier recommendation model based on the graph convolutional neural network, the feature map is classified, and a prediction result is output; and the prediction result is evaluated to obtain an evaluation result. The application solves the problem of low matching efficiency of manufacturers and suppliers.

The invention provides a multi-scene user controllable personalized recommendation method and system based on super network adaptation. The method comprises the following steps: acquiring a natural language query input by a user; mapping the natural language query into a control condition text based on a large language model; encoding the control condition text into a condition embedding vector by using a pre-trained text encoder; inputting the condition embedding vector into a super network, and generating an adapter parameter matrix for at least one dense layer in the basic recommendation model by the super network; adding the adapter parameter matrix and an original weight matrix of a corresponding dense layer in the basic recommendation model to obtain an adapted recommendation model; and using the adapted recommendation model to predict preference scores of the user for the articles, and generating a recommendation list based on the preference scores. According to the technical scheme, the super network is introduced to dynamically generate the lightweight adapter, so that the limitation of a traditional recommendation system in the aspects of user controllability, scene adaptability and semantic comprehension is effectively solved.

The invention belongs to the technical field of recommendation interpretability optimization, and particularly provides an interpretability recommendation method and system based on collaborative optimization of double large language models. Collecting behavior data of a user to a project, and obtaining user features and project features; obtaining a candidate item set by using a recommendation model based on the user features and the item features; extracting features of the candidate item set, constructing an explanation input vector in combination with user features, and inputting the explanation input vector into an explanation generation model to generate an original explanation text; constructing a quantitative evaluation model, and performing quality scoring on the original interpretation text; and generating a new explanation text according to the original explanation text and the quality score through a large language model, and presenting the new explanation text to a user. According to the method, a quantifiable explanation quality evaluation function is introduced, and a unified executable process and a feedback closed loop are constructed, so that the generated explanation can be kept consistent with the inherent characteristic contribution of the recommendation model.

The invention relates to the technical field of intelligent medicine recommendation, and provides a medicine recommendation method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the time sequence coding processing of the current treatment information of a patient, and generating a semantic vector of the current treatment information; performing multi-message propagation processing on the heterogeneous medical graph based on a graph convolutional neural network to determine knowledge memory vectors of various medical entities, and determining knowledge vectors of the current doctor seeing information based on the knowledge memory vectors; determining fusion information according to the semantic vector and the knowledge vector; and inputting the fusion information into a drug recommendation model, carrying out probability calculation processing that new drugs are used and probability calculation processing that historical drugs are reserved and used on the fusion information, and based on the determined newly-added use probability of each drug, the reserved use probability of each historical drug and an adjacent matrix of drug interaction, carrying out drug recommendation. And determining the drug combination recommended to the patient. The safety of medicine combination is improved, and the accuracy of medicine recommendation is effectively improved.

The invention discloses an intelligent review method for compliance of an electric power security supervision document, which relates to the technical field of electric power security management, and comprises the following steps: establishing a security supervision knowledge base and an expert information base, collecting electric power security supervision document text data and electric power operation field image data, extracting text semantic features and image features, and establishing a security supervision database; a document data risk identification model based on a long short-term memory network and an attention mechanism and a field operation risk identification model based on a rule reasoning technology are adopted to identify document violation information and field violation information, a supervision problem list is generated, and a self-optimization expert recommendation model based on reinforcement learning is established. And outputting a recommended expert list and a key supervision list. According to the invention, by constructing the multi-model collaborative intelligent examination method, the automatic analysis of the electric power security supervision document and the field image, the accurate positioning of violation information, the dynamic optimization matching of expert resources and the active pre-control of pre-risk are realized, and the efficiency of supervision work is comprehensively improved.

The invention relates to the technical field of large models, in particular to a reading recommendation large model generation method and system based on big data resources. The method comprises the following steps: acquiring a to-be-assessed text, collecting reading materials with multiple learning segments and multiple styles, labeling the reading materials, carrying out aggregation and consistency verification on labeling results, and constructing a verified recommendation database; performing low-rank adaptive fine tuning on the general pre-training large model based on the recommendation database to obtain a domain model, and performing performance and deviation monitoring and correction in the training process; performing multi-dimensional analysis on a to-be-evaluated text to generate a text feature vector, and performing mixed retrieval on a recommendation database in combination with semantic vector similarity retrieval; according to the invention, through the construction of the large reading recommendation model, the reading recommendation is more accurate and efficient.

A text sequence recommendation method and system based on a large language model is disclosed, belonging to the technical field of recommendation algorithms. The method includes: a data preprocessing stage, a large language model pre-training stage, a sequence model fine-tuning stage and a matching stage. According to this disclosure, a large language model is introduced into a text sequence recommendation task, so that text can be better modeled by utilizing rich pre-training corpus of the large language model; meanwhile, sequence modeling is performed on the text, the capability of sequence recommendations modeling in a large model is activated, an ID-based recommendation paradigm in a traditional recommendation algorithm is eliminated, and recommendation task learning processing is better performed in a cold start scenario and a knowledge transfer scenario; and finally, a recommendation result is finally optimized by a sequence model.

The invention discloses a method for identifying financing expiration events based on public data to form business opportunities and pushing the business opportunities. The pushing method comprises the steps that S1, multivariate heterogeneous data collection and structured modeling are carried out; s2, constructing a financing expiration event business opportunity model; s3, calculation and sorting output of business opportunity recommendation scores; and S4, constructing a business opportunity intelligent pushing mechanism. The integration and structured modeling of multi-source heterogeneous data are realized, and the comprehensiveness and accuracy of financing event identification are improved. And constructing a business opportunity recommendation model fused with multi-dimensional features, and realizing dynamic evaluation and intelligent sorting of business opportunities.

The present application relates to a kind of place recommendation method based on hypergraph neural network and diffusion model, interest point recommendation model is constructed, interest point recommendation model successively includes local trajectory flow hypergraph module, space-time feature coding, multi-dimensional feature fusion network, global hypergraph representation learning module, feature optimization module, aggregation layer, frequency domain learning layer and linear prediction layer.Analysis of the long trajectory of user, and it is divided into space-time region, constructs three global hypergraphs, aims at comprehensively capturing the overall behavior pattern of user.In order to better optimize trajectory intention representation, propose feature optimization module based on improved diffusion model.Introduce multi-dimensional global representation to ensure a more stable and controllable reverse process, and use feature normalization and improved Transform network, enhanced diffusion model is more suitable for recommendation system.Loss function is designed to train interest point recommendation model, and the interest point recommendation model trained is used to recommend next interest point for new user.

A computerized-method for determining an agent personalized coaching. The computerized-method includes for each agent in an agents database: (i) retrieving by one or more processors historical data. The historical data includes at least one of: a) past feedback; b) KPIs; and c) coaching training sessions; (ii) cleaning and structuring the historical data by operating by the one or more processors a data processor; (iii) assessing a level of impact of a plurality of coaching-plans based on the structured historical data to predict an effective-score for each coaching-plan in the plurality of coaching-plans on the KPIs by operating a CATE estimator on the coaching-plan; (iv) normalizing the effective-score of each coaching-plan and storing the normalized effective-score of each coaching-plan in a data-storage; (v) automatically selecting the personalized coaching-plan by operating a recommendation model on effective-scores in the data-storage; and (vi) automatically scheduling the personalized coaching plan for the agent.

The invention relates to a course recommendation method for multi-level memory enhancement based on a large language model, and belongs to the field of intelligent education and recommendation systems. The method comprises the following steps: acquiring interaction data between a user and a course, and dividing the interaction data into multi-level memories such as feeling, work and long-term memories based on a cognitive psychology principle; constructing three types of cue word templates, and driving a large language model to perform semantic knowledge enhancement on user interaction data, course attribute information and multi-level memory comparison; and the enhanced semantic knowledge is encoded into vectors through a pre-training model, then enhancement processing is performed through a hierarchical attention expert network, and the output enhanced vectors are used for improving the performance of a downstream recommendation model. The problems that a recommendation system is insufficient in semantic understanding, inaccurate in cognitive memory modeling and limited in personalized recommendation ability are solved, the instant demand, the current learning state and the long-term occupational planning of the user are accurately understood, the course recommendation precision is remarkably improved, and the method is suitable for online education, occupational training and lifelong learning scenes.

The invention discloses a reservoir scheduling scheme making method based on multi-objective decision preference, and belongs to the field of water resource management and reservoir scheduling decision. Comprising the following steps: collecting reservoir inflow data, reservoir characteristic parameters and reservoir characteristic curve data of a typical hydrological year according to historical data; then, according to the actual demand condition and the capacity limitation of the unit, constructing constraint conditions and setting an objective function calculation module, and setting a calculation module based on the water balance principle and the water-electricity conversion relation of the unit in the time period to calculate the dam front water level and the unit output. And finally obtaining a multi-objective optimization scheduling and preference recommendation model, and solving through a non-dominated genetic algorithm to obtain a Pareto optimal solution set and different preference recommendation schemes. According to the method, the competitive cooperation relationship among the water conservancy targets is integrated, and the fuzzy preference is converted into an accurate and executable scheduling scheme.

The invention relates to a federated learning-based privacy protection personalized recommendation system, which comprises a user side, an edge side and a cloud side, and is characterized in that the user side is a basic unit for data generation and local training, each user maintains a personalized recommendation model on own local equipment, the edge side is used as an intermediate aggregation layer, and the cloud side is used as a cloud side; the cloud end is used for preliminarily aggregating local models of users in a certain geographic area or logic area, the edge end is generally deployed in an edge server or an area data center, and the cloud end is a central node for updating and distributing a global model and is used for secondarily aggregating area aggregation models uploaded by the edge ends to form a global recommendation model; according to the scheme, user privacy is strictly protected, and collaborative recommendation is realized under the condition of not transmitting original user data through a differential privacy and security aggregation dual protection mechanism.

The invention discloses a distributed operation-oriented multi-agent collaborative recommendation method and system, and relates to the technical field of intelligent recommendation, and the method comprises the steps: configuring a private domain operation agent in each independent private domain platform, deploying a big language model-based construction demand analysis agent at a user side to receive a natural language demand description input by a user, and constructing a multi-agent collaborative recommendation system; generating recommendation task instructions of different private domain platforms; the method comprises the following steps: receiving user preference description and recommendation object description, sending the description to a corresponding private domain operation agent, calling a recommendation model to generate a recommendation result list based on the received user preference description and recommendation object description, collecting recommendation result lists returned by all private domain operation agents by a demand analysis agent, and integrating and classifying the recommendation result lists to generate a comprehensive recommendation list. According to the method, an efficient, safe and extensible distributed recommendation architecture is constructed by introducing a user demand analysis agent, a private domain operation agent and a federal learning mechanism.

The invention discloses a performance self-improving large model recommendation system and method, and the system comprises an initialization module which is used for pre-training a large language model through supervision and fine tuning, and generating an initial recommendation model; the self-optimization module comprises three iteratively executed sub-modules; the sample selection sub-module is used for screening historical data samples of which the information amount is higher than a threshold value on the basis of comparison between the model prediction probability and the preset threshold value; the response fusion sub-module is used for generating K candidate responses for a selected sample and generating a preference data set based on model evaluation; and the DPO optimization sub-module is used for updating model parameters by utilizing the improved DPO loss function and generating an optimized recommendation model. According to the method, the dependence on static preference data in the prior art is broken, the recommendation quality and robustness are improved, and adaptive optimization is realized.

The invention discloses a multi-modal drug recommendation method and system based on large language model driving, and relates to the technical field of medical informatics and artificial intelligence. The invention aims to solve the limitation of an existing drug recommendation model in the aspects of patient characterization construction, drug multi-modal modeling and large language model application. Comprising the following steps: constructing patient characterization, and aligning a patient state and a potential medication space in a characterization learning stage through a cooperative prompt project driven by a large language model; multi-modal drug characterization is constructed, and clinical logic and chemical characteristics of drugs are deeply depicted through semantic expert and molecular structure expert dual-channel design; a'static anchoring dynamic 'time sequence reasoning mechanism is provided, context modulation is performed on a dynamic evolutionary clinical event sequence by utilizing a static treatment baseline formed by global medication history, and finally, an accurate and safe medication combination is generated through a label sensing prediction module. According to the method, the accuracy, safety and clinical logic self-consistency of drug recommendation are remarkably improved.

The invention discloses a tumor traditional Chinese medicine intelligent prescription recommendation method and system based on knowledge distillation and reinforcement learning, and the method comprises the steps: building an interpretable prescription recommendation model, inputting the tumor symptom data of a patient into the interpretable prescription recommendation model, and obtaining a traditional Chinese medicine prescription recommendation result; wherein the interpretable prescription recommendation model is obtained through training by adopting a knowledge distillation method and a reinforcement learning method, LoRA fine tuning is performed by utilizing a three-section distillation sample, and the fine-tuned model is subjected to reinforcement tuning by utilizing a direct preference optimization method; the three-stage distillation sample comprises symptom analysis, prescription recommendation and prescription analysis, the method can perform modeling on information such as clinical manifestation and tongue picture of a patient to identify typical syndromes, and explanation and description of monarch, minister, assistant and guide structures, medicine property compatibility logic, treatment rules and basis and the like are performed on the generated prescription.

The invention provides a full-scene adaptive intelligent recommendation method and system based on a graph neural network, and the method comprises the steps: constructing a parallel candidate recommendation model for generating a diversified candidate pool; a scene label of a user is determined through a CoT inference rule, the scene label is used as a query, a most matched strategy document is retrieved from a strategy knowledge base by utilizing an RAG module, and a currently recommended dynamic execution strategy is formulated; normalizing the original score of the parallel candidate recommendation model based on a dynamic execution strategy, calculating a preliminary fusion score according to a dynamic weight retrieved from a strategy knowledge base, and generating a preliminary sorting list; and performing rearrangement based on big language model reasoning on the preliminary sorting list in combination with scene and strategy guidance, and introducing evidence retrieved from a fact knowledge base based on an RAG module into a rearrangement result to obtain a final recommendation list with language interpretation. According to the method, the recommendation list which is highly personalized, self-adaptive in scene and clear in natural language interpretation can be obtained.