39results about How to "Improve recommendation accuracy" patented technology

The present disclosure provides an object recommendation method, an object recommendation device, an electronic device and a storage medium, which can be applied to the technical field of big data. The object recommendation method comprises: determining M first objective indexes, N second objective indexes and a target variable relationship matched with an application scene, the target variable relationship being used to determine a to-be-recommended object, the first objective indexes being used to represent transaction characteristics of a user, the second objective indexes being used to represent social relationship characteristics of the user, M being greater than or equal to 1, and N being greater than or equal to 1; obtaining a recommendation data set of a target user, the recommendation data set comprising first objective data corresponding to the first objective indexes and second objective data corresponding to the second objective indexes; and determining the to-be-recommended object according to the M first objective data, the N second objective data and the target variable relationship.

This application provides a recommendation processing method, apparatus, electronic device, computer-readable storage medium, and computer program product based on artificial intelligence. The method includes: acquiring the interaction features and object features of a target account; performing first attention processing on the interaction features based on a first object interest pool to obtain interaction interest features, and performing second attention processing on the object features based on a second object interest pool to obtain object interest features; acquiring the activity features of the target account, and performing selection processing on the interaction interest features and object interest features based on the activity features to obtain recall features of the target account; based on the recall features and the information features of the information to be recommended, obtaining target information from the information to be recommended, and performing a recommendation operation on the target account based on the target information. This application enables accurate personalized recommendations and improves recommendation processing efficiency.

The application provides a gift recommendation method, device and equipment and a storage medium; the method in the application comprises the following steps: receiving a gift recommendation request, extracting a target user corresponding to the gift recommendation request and user attribute characteristics of the target user; extracting historical user comments of the target user according to the user attribute characteristics, and performing sentiment tendency analysis on the historical user comments to obtain positive user comments; obtaining evaluation commodities corresponding to the positive user comments and target gift categories corresponding to the evaluation commodities, obtaining candidate gifts corresponding to the target gift categories in a preset gift database; obtaining historical gift comments of the candidate gifts, determining target gifts to be recommended according to the historical gift comments and the positive user comments, and recommending the target gifts to the target user. The target gifts that the target user is interested in are determined according to the historical user comments of the target user, and the recommendation accuracy of credit card gifts is improved.

A movie recommendation method based on collaborative enhancement and graph attention neural network, comprising: first, calculating the respective collaborative movie neighbor sets of users and movies, and obtaining corresponding collaborative interaction embedding vectors; then, mapping the entities in the sets to a movie knowledge graph for propagation to obtain corresponding layer knowledge graph embedding vectors and multi-hop knowledge graph embedding vectors; finally, combining the movie knowledge graph embedding vectors and the collaborative interaction embedding vectors to obtain final user embedding vectors and movie embedding vectors, and calculating the predicted click probability of the user on the movie to obtain the predicted ranking result of the movie recommended to the user from high to low according to the probability. The present application considers the sufficient combination of collaborative information and knowledge graph information, has high accuracy and good recommendation effect.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a mixed identifier generation type recommendation method and system based on local collaborative context, and the method comprises the steps: obtaining a user historical interaction sequence, and carrying out the multi-granularity clustering of users, and obtaining a group of each user; constructing a static identifier based on the article content, constructing a dynamic identifier in combination with the user group information and the local interaction sequence, and fusing to generate a mixed identifier of each article; constructing an instruction fine tuning task, embedding group information into an instruction prompt word, and learning by using a large language model to generate a mixed identifier of a next article from a historical sequence; and generating a recommendation result based on the optimized large language model according to the historical sequence of the target user and the group information thereof. According to the method, the local collaborative context is fused through multi-granularity group estimation, and the mixed article representation is constructed in combination with static and dynamic identifiers, so that the problems of single user interest modeling and semantic deficiency of article representation are effectively solved, and the accuracy and personalized level of generative recommendation are improved.

The application belongs to the API recommendation field, and particularly relates to an API recommendation method fusing network structure information and content information, which comprises the following steps: obtaining an original data set from a ProgrammableWeb data set, and preprocessing the original data set to obtain a new data set; performing vector processing on each function description text in the new data set to obtain a plurality of API content feature vectors and a plurality of Mashup content feature vectors; constructing a mashup-API-tag heterogeneous information network based on the new data set, and obtaining a plurality of Mashup structure feature vectors by adopting a multi-path aggregation attention mechanism; and obtaining an API recommendation list of a target mashup according to the Mashup content feature vectors and the Mashup structure feature vectors; and the application can reduce the loss of original description information.

This application discloses a content recommendation method, apparatus, device, and readable storage medium, relating to the field of artificial intelligence. The method includes: acquiring content features; performing a first feature processing on the content features through a task network to obtain task features; performing a second feature processing on the content features through at least two expert network layers to obtain at least two expert features; determining attention-focusing information corresponding to the recommendation task and the at least two expert network layers based on the task features and expert features; and recommending candidate content based on the attention-focusing information. By performing attention-focusing on the expression vector of the recommendation task with the expression vectors of all levels of the expert network layers, and using the focusing results as inputs to their respective subsequent prediction processes, this method replaces the simple gating approach of sharing expert features across layers. This achieves comprehensive focusing on feature expressions, thereby improving the prediction accuracy of the multi-task model and the recommendation accuracy of candidate content.

A site selection recommendation method based on custom size block classification comprises the steps that POI data of a target geographic area is acquired and preprocessed, and a structured data set is generated; dividing the target geographic area into a plurality of rectangular grid units; according to a preset rule, extracting an anchor point building facility which has an influence on the target business state from the POI data; quantifying the spatial influence strength of the anchor point building facility based on the Harverine distance between the rectangular grid unit and the anchor point building facility, and constructing a distance attenuation model; constructing a comprehensive feature set by combining historical deduction features extracted from the structured data set according to the space influence strength and distance attenuation model of the anchor point building facility; a prediction recommendation model is constructed, training is carried out on the comprehensive feature set, and target business state distribution prediction is generated; and according to the target business state distribution, constructing a final recommendation score of the rectangular grid unit, outputting a site selection recommendation list, and generating a visual decision support report.

The application discloses a double-embedding model hybrid training method, system, device and storage medium, which is applied to the technical field of recommendation systems and comprises the following steps: determining the routing parameters of each classification feature based on the historical access information of the classification features in a training data set; selecting a corresponding embedding table for the classification features input currently according to the routing parameters; wherein the embedding table comprises a first embedding table and a second embedding table; extracting the embedding vector corresponding to the classification features from the selected embedding table, and performing forward calculation and loss calculation of the model based on the embedding vector; and updating the parameters of the first embedding table, the second embedding table and a downstream model according to the result of the loss calculation. The application simulates the embedding hybrid use mode in reasoning in the training stage, enhances the collaborative ability of the two embedding tables, and improves the performance and robustness of the model in a real reasoning scene.

The application discloses a fair personalized recommendation method and device based on mutual information decoupling and a storage medium, and steps of the method comprise the following steps: 1. constructing original data, including a user-product rating matrix and a user sensitive attribute matrix; 2. constructing a sensitive embedding network to learn sensitive embedding of a user and a product, including a biased one-hot encoding layer, a sensitive information encoder and a sensitive attribute prediction layer; 3. constructing a hybrid embedding network to learn hybrid embedding of the user and the product, including a hybrid one-hot encoding layer, a hybrid information encoder and a preference prediction layer; and 4. constructing a non-sensitive embedding network to learn non-sensitive embedding of the user and the product, including an unbiased one-hot encoding layer, a mutual information lower bound optimization layer and a mutual information upper bound optimization layer. Through the double mutual information fairness constraints on the embedding vectors, the application improves the fairness of the recommendation system while ensuring the recommendation accuracy.

This application discloses a cross-domain multimodal recommendation method and system based on multi-agent attribute-driven architecture. Embodiments of this application can be applied to product recommendation scenarios in an e-commerce platform. The method includes: receiving multimodal features; processing the multimodal features using a first operation to generate reconstructed original multimodal features; the reconstructed original multimodal features include attribute-related representations and attribute-independent representations; then, processing the reconstructed original multimodal features using a second operation to generate a modal cue vector; then, processing the modal cue vector and the attribute-related representation to generate a new feature vector; and finally, processing the new feature vector using a sequence encoder to generate attribute-level multimodal sequence states. By sharing basic embeddings, the parameter overhead is significantly reduced, solving the problem that the parameter size of traditional cross-domain multimodal encoders increases linearly with the number of domains.

This invention discloses a generative recommendation system and method based on quantized vector retrieval and LLM, belonging to the technical field of computer information processing and artificial intelligence recommendation systems. The method includes: Step S1, extracting continuous collaborative features of users and items; Step S2, constructing and pre-training an AHPQ segmenter quantization module, mapping continuous collaborative features to discrete ID token sequences and optimizing the quantized codebook; Step S3, using the pre-trained codebook vector to collaboratively initialize the LLM's token embedding layer; Step S4, fine-tuning the LLM using a freeze-adapt strategy, and then generating user preference vectors through a collaborative semantic fusion module; Step S5, calculating the similarity between the user preference vector and the item database vector, and retrieving Top-K items based on cosine similarity as the recommendation result. This invention solves the problems of ID discretization difficulties and collaborative signal loss in LLM recommendation, preserving the high-order collaborative structure while leveraging the semantic reasoning capabilities of LLM, and simultaneously achieving efficient reasoning and cold-start generalization.

The invention discloses a human-post personalized matching recommendation method fused with a dynamic knowledge graph, which relates to the technical field of human resource management, and comprises the following steps: carrying out relation extraction on an original acquisition item set, generating a candidate triple set, loading the candidate triple set, generating a post map data set, and carrying out post map data processing on the post map data set; establishing a version index record for the position map data set, and generating a position map packet; performing position skill closure processing, shortest repair path search and reachability threshold calculation on the basis of the position map packet, and generating a position reachability table; carrying out difference set comparison according to the position reachable capability table to generate a reachable candidate list, carrying out time stamp screening and region screening on the reachable candidate list, and carrying out duplicate removal to generate a candidate fusion set; and performing relation sorting on the candidate fusion set, generating a disturbance scheme, performing constraint satisfaction verification on the disturbance scheme, and generating a causal enhancement sorting result. The reasonability and adaptability of the recommendation result are enhanced, and the credibility of the recommendation result is enhanced.

This invention discloses a method and system for personalized task recommendation for children's eye care, relating to the field of artificial intelligence recommendation technology. The method includes: acquiring children's behavioral data, preprocessing and splicing it to generate daily behavior vectors; normalizing the daily behavior vectors by setting boundaries to obtain normalized vectors; constructing a task library and generating tag vectors; constructing a Poincaré sphere space; mapping the normalized vectors and tag vectors to the Poincaré sphere space; calculating the vector matching degree; and generating a task recommendation list based on the matching degree for sending. Based on the recommendation list, task feedback is statistically analyzed; a dual loss function is constructed based on the task feedback; and a total loss function is constructed based on the dual loss function for iterative optimization to generate a final recommendation list as the basis for personalized task recommendation. This invention effectively improves the scientific rigor and feasibility of eye care task recommendation.

The invention provides an intelligent research journey recommendation method and system based on collaborative filtering and LSTM fusion, and the method comprises the steps: taking a multi-modal behavior time sequence as the input of a pre-constructed research behavior space-time attention network, and obtaining a time sequence preference implicit vector; calculating the matching degree of the time sequence preference implicit vector and the dynamic constraint factor, and correcting the time sequence preference implicit vector by using the constraint factor feature vector based on a calculation result to obtain a scene adaptive time sequence preference vector; extracting a time sequence behavior feature vector of the current research journey group, and performing weighted fusion on the time sequence behavior feature vector and the scene adaptive time sequence preference vector to obtain a final time sequence preference vector; the final time sequence preference vector is used for outputting a personalized research and study journey recommendation list. According to the multi-dimensional intelligent recommendation method, the group preference, the personal time sequence behavior, the research education attribute and the real-time resource state can be fused, so that the recommendation accuracy and the user experience are improved.

The invention relates to the technical field of text processing, and discloses a manuscript generation method and device, equipment and a storage medium. The method comprises the following steps: constructing a template library containing a plurality of template frames and a knowledge base containing a plurality of domain knowledge bases; obtaining use features of a user and each template frame, receiving a free prompt input by the user, and constructing a task feature vector; matching a target template frame based on the first sorting model, and generating a task instruction based on a standard prompt word of the target template frame; if the matching target template frame does not exist, generating a task instruction based on the free prompt word; matching a target knowledge fragment from the knowledge base based on a second sorting model; and forming a large model generation manuscript called by a generation instruction in combination with the target knowledge fragment and the task instruction, correcting the manuscript in response to interaction between a user and the manuscript until a finalized manuscript is generated, and collecting interaction data to perform quality evaluation on the finalized manuscript. According to the method, high-quality, personalized and automatic generation of the manuscripts in the specific field is realized.

This invention discloses a method for recommending official document approval opinions based on semantic matching and role awareness, comprising the following steps: S1. Constructing a historical document vector database and a structured metadata database; S2. Obtaining documents to be approved and performing feature extraction and preliminary screening; S3. Performing text block-level similarity retrieval on the documents and aggregating them; S4. Calculating job matching scores based on job information; S5. Calculating the final recommendation score and sorting the documents in descending order based on the final recommendation score, outputting the top 5 with the highest scores as the recommended results. This invention improves recommendation accuracy by using a pre-trained semantic embedding model to understand the deep semantics of document content. Furthermore, through job matching score calculation and approval node position alignment mechanisms, it deeply binds the recommended approval opinions to specific approval positions and approval process positions, achieving personalized recommendations.

This invention discloses an information push method, apparatus, device, and storage medium based on artificial intelligence, relating to the fields of artificial intelligence and information push technology, and applicable to the fields of medical insurance and financial insurance. The method includes: acquiring multi-dimensional data of target customers and generating a first customer profile feature vector; using an insurance intention prediction model to obtain a first insurance intention prediction value, thereby determining at least one first target insurance product and pushing it; if no insurance information is received within a preset time period, acquiring customer feedback data on the recommended products; correcting the first customer profile feature vector based on the feedback data to generate a second customer profile feature vector; re-inputting the insurance intention prediction model to obtain a second insurance intention prediction value; and re-determining at least one second target insurance product based on the second insurance intention prediction value and pushing it. This solution effectively improves the accuracy of recommendations.

This application discloses a product recommendation method, apparatus, storage medium, and electronic device. Relating to the field of artificial intelligence, the method includes: acquiring user target information, wherein the target information includes at least: interaction information between the user and financial products, and financial product information; determining the breadth of product categories of interest to the user based on the interaction information; and processing the target information and the breadth of product categories using a product recommendation model to obtain a target product recommendation list, wherein the product recommendation model employs a policy network based on deep reinforcement learning. This application solves the problem of low product recommendation accuracy in related technologies.

To address the issue of user viewing behavior being easily influenced by confounding factors such as video duration in short video recommendation, leading to distorted interest modeling, this paper proposes a short video recommendation method based on causal inference and graph convolutional networks. First, a do-operator is introduced to explicitly intervene in users' historical behavior, weakening the confounding effect of duration bias on interest expression and obtaining more realistic preference signals. Second, positive and negative sample sets are constructed, and representation learning and aggregation are performed separately through differentiated graph convolutional networks to achieve multi-dimensional user preference modeling. Furthermore, graph propagation mechanisms and expert network design are combined to enhance the model's ability to characterize complex interest structures. Experimental results show that this method can effectively alleviate confounding bias and improve recommendation performance and model robustness.

This invention discloses a method, apparatus, device, and storage medium for determining a course recommendation list. The method includes acquiring sample data; obtaining a target basic data dictionary based on the sample data; obtaining a target sparse vector based on the sample data and the target basic data dictionary; acquiring an initial feature vector of the object to be recommended; obtaining a target feature vector of the object to be recommended based on the target basic data dictionary, the target sparse vector, and the initial feature vector of the object to be recommended; and determining a course recommendation list for the object to be recommended based on the target basic data dictionary and the target feature vector. The technical solution of this invention provides a new method for determining a course recommendation list, fully considering the characteristic information of employees from various dimensions, effectively avoiding the scenario of only recommending courses of personal interest during subsequent course recommendations, and improving the quality and accuracy of course recommendations.

This application discloses a method, apparatus, and computer-readable storage medium for recommending technical objects. Relating to the field of big data technology, the method includes: receiving a work order text from a target account; converting the work order text into a target semantic vector; calculating the similarity between the target semantic vector and the semantic vectors corresponding to N preset historical work order texts, determining the similarity between the N historical work order texts, where N is a positive integer; selecting historical work order texts with similarity exceeding a preset threshold as target historical work order texts; selecting technical objects corresponding to the target historical work order texts based on a preset collaboration graph network, determining the target objects, where the collaboration graph network represents the relationship between the N historical work order texts and the technical objects; and determining the recommended technical objects corresponding to the work order texts based on the target objects. This application solves the problem that recommendations based on past experience by technical personnel in related technologies are inefficient and inaccurate.

The application discloses a turbulent flow model intelligent recommendation method based on clustering weight optimization and random forest, relates to the field of combination of fluid mechanics and artificial intelligence, and comprises the following steps: determining input working conditions and a candidate turbulent flow model set, and constructing an evaluation index system; constructing a fuzzy comprehensive evaluation model and initializing the index weight of the fuzzy comprehensive evaluation model; constructing a feature space, adopting K-means clustering to establish a physical consistency constraint, and establishing a loss function containing an entropy regularization term through a same-cluster similarity consistency principle to iteratively optimize the index weight and obtain adaptive weight; calculating the comprehensive score of each candidate turbulent flow model according to the adaptive weight, and taking the turbulent flow model with the highest score as an optimal model label; and training a random forest multi-classifier by using a training data set to obtain a turbulent flow model intelligent recommendation model. The application solves the problems that the existing method is highly dependent on experience, the evaluation weight is subjective and difficult to adapt to cross-working conditions, and there is a lack of an interpretable recommendation mechanism.

The invention discloses a big data intelligent recommendation method and system based on multi-scene dynamic adaptation. A dynamic user portrait is generated by constructing a three-dimensional scene feature space and fusing multi-source heterogeneous data; scene-feature weight adaptive adjustment is realized based on reinforcement learning, and a multi-scene model is trained in combination with a'shared-private 'neural network and transfer learning; and finally, dynamically allocating resources according to the scene priority to generate a recommendation result, and continuously optimizing through a feedback closed loop. The problems that a traditional recommendation system is insufficient in scene adaptation, poor in real-time performance and the like are solved, the recommendation precision and the resource utilization rate are remarkably improved, and the method is suitable for multiple fields such as e-commerce and content distribution.

The application discloses an intelligent medicine recommendation method and device based on semantic vector search, and belongs to the technical field of intelligent medicine recommendation. The method converts medicine information and user natural language queries into high-dimensional semantic vectors through a pre-training language model optimized in the medical field; a comprehensive query representation is constructed by fusing medical exclusive features and personalized preferences; a hybrid strategy combining vector retrieval and keyword indexing is adopted to obtain a preliminary recommendation set; a multidimensional comprehensive scoring algorithm containing medical safety verification is used for secondary screening and sorting; a user feedback reinforcement learning mechanism is introduced to realize dynamic optimization of the model; and the device corresponds to a medicine information processing module, a user query processing module, a vector database and a matching and recommendation engine module. The application improves complex semantic understanding capability, realizes personalized and accurate recommendation, guarantees medicine safety, considers both search efficiency and scene adaptability, and is suitable for internet medical and medical e-commerce scenes.

The invention discloses a recommendation object optimization method and device, electronic equipment and a program product, and relates to the technical field of content recommendation, the method comprises the following steps: obtaining theme features of a recommendation set, the recommendation set being used for representing multi-modal recommendation information; obtaining a matching relationship between the theme feature and an interest portrait of the first recommendation object, wherein the interest portrait is determined based on first interaction data of the first recommendation object; screening the first recommendation object based on the matching relationship to obtain a second recommendation object; recommending the recommendation set to a second recommendation object, and obtaining second interaction data of the second recommendation object for the recommendation set; and optimizing the second recommendation object by using the second interaction data. By implementing the technical scheme of the application, the target users can be screened and recommended based on accurate matching of the recommended collection theme and the user interests, and then the target user group is continuously and dynamically optimized by using the feedback data, so that the recommendation accuracy and the interaction conversion rate are effectively improved.

This invention discloses a heterogeneous attribute-enhanced collaborative comparison product recommendation method based on a large language model, belonging to the field of intelligent recommendation technology. The method first obtains collaborative representations of users and products through a graph neural network based on a user-product interaction graph. Then, it constructs an attribute value relationship graph based on user attribute value data and product attribute value data, and learns attribute value node representations using a graph attention network. On this basis, a large language model is introduced for semantic reasoning to obtain a set of heterogeneous attribute value information related to the semantics of static attribute values. Furthermore, the heterogeneous attribute value information is fused with the static attribute value information, and an attribute-aware representation is obtained through an attention mechanism. This representation is then gated and fused with the collaborative representation to form the final representation. Finally, the model is optimized by combining Bayesian personalized ranking loss and contrastive learning loss, and Top-n recommendation results are generated based on the predicted scores. This invention can improve the accuracy and personalization level of recommendation results.

This invention discloses a method and system for recommending bank points malls based on multi-dimensional user data analysis. The method constructs an intelligent recommendation closed loop through a six-step core process: First, it organizes users' regular consumption data, achieving multi-dimensional collection, cleaning, labeling, and dynamic updates; second, it collects and filters spatiotemporal hotspot data of the user's region to accurately match offline scenario needs; third, it integrates multi-channel online hotspot data, quantifying popularity and timeliness; fourth, it binds the two types of hotspot data with points mall products by weight; fifth, it calculates and dynamically adjusts the correlation between products; and finally, it generates a default recommendation list based on the hotspot correlation and dynamically switches to related product recommendations based on real-time user interaction behavior. This invention solves the problems of single recommendation dimensions, insufficient accuracy, and delayed timeliness in existing technologies. By integrating multi-dimensional data and a dynamic feedback mechanism, it significantly improves the accuracy of points mall recommendations, user interaction experience, and points redemption conversion rate.

This invention provides a method and system for intelligent analysis of catering service data, belonging to the field of data analysis and processing technology. The method includes: collecting historical ordering service records of the restaurant and performing table-type association analysis; constructing a time-series curve of the dish structure for each table type; performing global time-segment ordering distribution analysis for each table type and generating multiple global time-segment structure lists; constructing multiple crowd density distribution vectors; optimizing the crowd density distribution of the global time-segment structure lists; generating local time-segment structure lists for each table type; determining multiple dish types in the restaurant and performing local dish popularity analysis; constructing multiple local popularity lists; constructing multiple dish association graphs for each table type based on historical ordering service records; generating multiple target dish combinations based on the dish association graphs; and obtaining global dish combination recommendation data for each table type. This invention significantly improves the accuracy of dish recommendations and the dining experience for customers.

This invention relates to the field of dialogue recommendation systems, and discloses a dialogue recommendation method based on prompt-tuned large language models, comprising the following steps: S1: Data collection and preprocessing, collecting multi-turn dialogue data between the user and the system, and constructing a dialogue context representation reflecting the user's interests and preferences. S2: Pre-ranking of candidate recommendation items, generating a preliminary set of candidate recommendation items using knowledge graph structure information; S3: Re-ranking of candidate recommendation items, achieving fine-grained ranking of candidate recommendation items and generating the final recommendation result; S4: Generation of conversational responses, generating natural language recommendation responses using a pre-trained large language model; S5: System feedback and continuous optimization. This invention improves the accuracy and relevance of recommendation results through multi-turn dialogue semantic modeling, knowledge graph information fusion, and a hierarchical recommendation mechanism based on prompt-tuned large language models, while enhancing the interactivity and interpretability of the recommendation system, making it suitable for intelligent dialogue recommendation systems.