25results about How to "Improve recommendation effect" patented technology

The application provides a dynamic increment-based graph information gate aggregation knowledge graph recommendation method, solves the data instability caused by random sampling and the noise fusion problem caused by double diffusion in the knowledge graph convolution recommendation method. The method comprises: dynamically selecting Top-K adjacent edges and adjacent point fusion for the current node in the knowledge graph (K is a positive integer of 10-20) in sequence. On the one hand, the matching score value of the current node, user embedding, adjacent edge and adjacent point is calculated by using the attention mechanism, the high correlation of the adjacent edge, adjacent point graph information and the candidate node of the next step is selected by using the score value, on the other hand, the selected graph information is adaptively adjusted and fused by using the gate mechanism, the adjacent information is accurately integrated into the current node embedding, and then the candidate node is diffused in sequence. Finally, through the operation of the adjacent fusion, the current node information and the adjacent graph information can be directly fused once, so that the noise information in the double diffusion and multiple fusion graphs is prevented.

The application discloses a kind of individual and group-oriented behavior internet modeling and prediction recommendation method, the method includes the following steps: step 1: establish the behavior preference model of behavior internet based on hypergraph;Step 2: extract the relationship between behaviors based on the model of step 1;Step 3: discover the behavior mode of user based on the behavior relationship of step 2;Step 4: predict the behavior trend of user based on the behavior relationship of step 2 and the behavior mode of step 3;Step 5: personalized service recommendation is carried out for user based on step 2, step 3, step 4.The model of behavior internet is proposed in the application, and the personalized behavior internet is obtained by cause-effect inference and relationship discovery, and the recommendation is carried out by using the deep learning method based on external knowledge, which improves the recommendation efficiency and effect for individual and group, overcomes the shortcomings that the traditional recommendation method based on deep learning is difficult to fully utilize personalized knowledge, and realizes the personalized and efficient recommendation of service.

The invention provides a text generation method and related equipment. The method comprises the following steps: performing text recognition on a sample video about a sample object to obtain sample information of the sample object and a corresponding initial text; performing abnormal text correction and text screening on the initial text to obtain a screened text; performing model training based on the sample information and the screened text to obtain a text generation model; the text generation model generates a target text used for recommending the target object based on the target information of the target object.

This application provides a video recommendation method, apparatus, device, and storage medium, relating to the field of communication technology. The method includes: upon receiving a video acquisition request, acquiring a candidate video list; acquiring the interaction probability between the user and each candidate video in the candidate video list, the interaction probability being determined based on the user's reconstructed embedding vector and the candidate video's reconstructed embedding vector; the user's reconstructed embedding vector being determined based on the user's embedding vector, the user's feature vector, and a pre-trained vector reconstruction model; the candidate video's reconstructed embedding vector being determined based on the candidate video's embedding vector, the candidate video's feature vector, and the vector reconstruction model; simulating the input of sample data during cold start when training the vector reconstruction model; and determining the target video to recommend to the user from the candidate video list based on the interaction probability between the user and each candidate video in the candidate video list. This method can accurately recommend videos to users during cold start, improving the video recommendation effect during cold start.

This application provides a video recommendation method, apparatus, device, and storage medium, relating to the field of communication technology. The method includes: upon receiving a video acquisition request, acquiring a candidate video list; acquiring the interaction probability between the user and each candidate video in the candidate video list, the interaction probability being determined based on the user's reconstructed embedding vector and the candidate video's reconstructed embedding vector; the user's reconstructed embedding vector being determined based on the user's embedding vector, the user's feature vector, and a pre-trained vector reconstruction model; the candidate video's reconstructed embedding vector being determined based on the candidate video's embedding vector, the candidate video's feature vector, and the vector reconstruction model; simulating the input of sample data during cold start when training the vector reconstruction model; and determining the target video to recommend to the user from the candidate video list based on the interaction probability between the user and each candidate video in the candidate video list. This method can accurately recommend videos to users during cold start, improving the video recommendation effect during cold start.

The application discloses a user sensitive information protection method based on a data confusion technology, and comprises the following steps: step S1, generating a sensitive attribute association table based on the association between recommended items and user gender characteristics; step S2, adding confusion ratings to an existing user-item matrix through a sampling strategy according to the sensitive attribute association table obtained in step S1, and constructing a user-item matrix after adding the confusion ratings; step S3, recording the number of confusion ratings added in step S2, applying a removal strategy, and finally generating a confusion matrix after applying the removal strategy; the removal strategy is that the same number of confusion ratings are deleted to maintain the original data size; a user is randomly selected, and when the rating number of the user reaches a set threshold, the items with strong association of the opposite sex are deleted from the rating history of the user. The application can mislead attackers to conduct gender attribute inference, realize user privacy protection, and does not affect the existing personalized recommendation quality of the user.

The application provides a trusted recommendation model based on a double-dimension constraint large language model, and comprises the following steps: S1, a positive and negative sequence construction module: the positive and negative sequence construction module extracts high-score and low-score item sequences from user historical interactions as evidence bases for argumentation; S2, a user preference module: the user preference module counts the historical score distribution of a user to capture the individualized score scale as calibration information for subsequent prediction; S3, a multi-agent argumentation module: the multi-agent argumentation module first generates initial arguments, then mines contradictory evidence through cross-interrogation to form a complete round of argumentation, and a score prediction agent integrates the argumentation result and the user score preference to output the predicted score of the argumentation channel; and S4, a fusion module: the fusion module adjusts the adaptive weight to fuse the statistical result of a traditional recommendation channel and the reasoning result of the multi-agent argumentation channel to generate a final recommendation result, can solve the illusion and position ambiguity problem of a large language model, and enhances the recommendation performance by integrating a deep reasoning large language model.

This invention provides a video recommendation method, apparatus, electronic device, and storage medium. It generates a user status document based on multi-source heterogeneous user information, and then calls a large language model to generate a first semantic unit based on the user status document. Videos matching the first semantic unit are searched from a vector database, and at least a portion of these videos are recommended to the user, thereby improving the video recommendation effect.

The application discloses a review-aware recommendation method considering user preference uncertainty, comprising the following steps: 1. using user reviews and ratings to build a data set, 2. building an asymmetric user preference and product feature representation learning model, and fusing user preference and product features to build a rating prediction model, 3. model training and optimization. The application proposes an asymmetric deep learning recommendation method, which comprehensively considers the difference of user reviews in learning user preference and product representation, and introduces user preference uncertainty, so as to improve the product recommendation performance.

The application discloses a game-driven personalized privacy protection federated cross-domain recommendation method and system, the method of the application comprises the following steps: a server combines the individual privacy budget of each client in the current round with the self privacy preference, the historical state of the client in the current round and the budget configuration of other clients to solve the individual privacy budget of each client in the current round, and the individual privacy budget of the current round and global model parameters are sent to each client; receiving the local model parameters of each client after adding noise based on the individual privacy budget of the current round; calculating the recommendation performance score and recommendation perception gain according to the local model parameters of each client in the current round respectively, and updating the global model parameters according to the recommendation perception gain of each client in the current round. The application aims to realize that the individual budget allocation truly serves the improvement of recommendation performance without improving the overall budget level in the federated cross-domain recommendation scene, so that the personalized privacy budget allocation not only meets the mechanism rationality but also truly serves the optimization of recommendation performance.

The application discloses a kind of multi-modal new item recommendation method based on similar user exploration and information behavior guidance, which comprises the following steps: obtaining user historical interaction data, multi-modal item information and new item to be recommended;User representation is constructed and similar user set is explored;Combine target user, new item to be recommended and similar user history to build candidate behavior set;Fusion user similarity, item relevance and preference information for behavior retrieval;Information behavior set is obtained using large language model feedback mechanism;Behavior guidance knowledge is constructed and feature representation alignment is completed;Behavior guidance knowledge is input into large language model for reasoning, and the interaction prediction result of target user to new item to be recommended is generated.Have beneficial effect: the present application obtains reliable cooperative signal by similar user exploration, obtains high-value behavior knowledge by information behavior screening, and improves the accuracy, robustness and explainability of cold start recommendation by combining the reasoning ability of large language model.

Embodiments of the present application disclose a content recommendation method and device, computer equipment and a computer readable storage medium. Based on a plurality of historical interaction contents of a target object, content attribute information sequences under a plurality of attributes are obtained, each content attribute information sequence including attribute information of the plurality of historical interaction contents under the same attribute. The content attribute information sequences are subjected to attention feature mining processing to obtain an attention feature information sequence corresponding to each attribute. The attention feature information sequences are subjected to first feature fusion processing to obtain a fused attention feature information sequence. A behavior feature information sequence of the target object is generated according to a target content attribute information sequence belonging to a content identifier attribute in the content attribute information sequences. The fused attention feature information sequence and the behavior feature information sequence are subjected to second feature fusion processing to obtain object feature information of the target object. The object feature information is used to recommend content to the target object, and the content can be accurately recommended.

The invention belongs to the field of financial big data analysis, and discloses a financial customer grouping method based on double-self-paced learning multi-view clustering under complex behavior data, and the method comprises the steps: constructing a multi-view anchor graph tensor of the complex financial behavior data, and comprehensively integrating the high-order consistent information of different financial behavior data; a self-paced learning strategy is introduced into tensor decomposition to gradually optimize a decomposition process, and double self-paced learning tensor decomposition is performed from two levels of samples and features, so that noise interference in Fourier domain transform is effectively reduced, and definition of a financial customer grouping structure and accuracy of a grouping result under complex behavior data are ensured. According to the method, tensor comprehensive analysis is carried out on multiple pieces of behavior data from the perspective of combining different views, a tensor decomposition process is optimized by using a self-paced learning strategy of a tensor level, a high-order interaction relationship among complex behavior data is effectively mined, and customer grouping in a complex financial scene is effectively carried out.

The embodiment of the invention discloses a cross-domain recommendation method and device and a model training method and device. The method comprises the following steps: acquiring user portrait data of a user in at least one source field; generating a first prompt instruction based on the user portrait data, inputting the first prompt instruction into the first large language model, obtaining an initial recommendation object set generated by the first large language model, the first prompt instruction being used for prompting the first large language model to generate an initial recommendation object belonging to the target field according to the user portrait data; matching the candidate objects in a candidate object set of the target field based on the initial recommendation object set to obtain a target recommendation object set, each target recommendation object in the target recommendation object set being a candidate object matched with the initial recommendation object in the candidate object set, the candidate objects in the candidate object set are pre-configured objects which can be recommended. The cross-domain recommendation effect can be improved based on the semantic comprehension ability and the generative retrieval ability of the large language model.

The application relates to an Issue fixer recommendation method and device, equipment and a readable storage medium, relates to the open source software ecosystem field and the service recommendation technical field, and fully considers the cooperative interaction relationship between developers and Issues, that is, a cooperative interaction graph between developers and Issues is constructed according to the cooperative relationship between developers, the interaction behavior between developers and Issues and the similar relationship between Issues, feature learning is performed on the developers and Issues, and the fixer recommendation is performed by using the inner product result of the feature vectors of the developers and Issues, so that the fixer recommendation result is more comprehensive and accurate, and the Issue fixer recommendation performance is effectively improved.

The application discloses a kind of based on frozen semantic embedding guide's generative recommendation supervision fine-tuning data construction method.The application avoids the distortion of semantic space and noise interference of collaborative training by freezing the semantic embedding obtained externally as a stable anchor, effectively protecting the content priori knowledge. At the same time, on the basis of maintaining semantic consistency, the collaborative neighborhood and sequence transfer preservation loss are introduced, so that the item representation can still completely retain the behavior patterns and interest evolution law in the original collaborative filtering space during the alignment process to the semantic space, obtaining high-quality fusion representation with semantic enhancement and collaborative authenticity. Based on the fusion representation, it is discretized into multi-level semantic identifiers through residual clustering, and instruction-response samples suitable for large language model supervision fine-tuning are constructed, realizing the effective migration of traditional recommendation knowledge to generative recommendation paradigm, enabling large language model to have sequence recommendation capability, and significantly improving the recommendation effect in cold start scenario.

The present disclosure relates to an information display method and device, electronic equipment and storage medium. The method comprises displaying a first multimedia resource and at least one object interaction information associated with a target object on a first page, and any object interaction information comprises semantic description information associated with the target object; in response to a preset interaction instruction for any object interaction information, displaying associated detail information corresponding to a target semantic of target semantic description information on the first page; wherein the target semantic description information is the semantic description information contained in the object interaction information corresponding to the preset interaction instruction, and the associated detail information does not block the first multimedia resource. By using the embodiments of the present disclosure, the display of the associated detail information of the object can be performed without exiting the current page of the recommended object, the viewing operation convenience and browsing efficiency are improved, the coherence of the resource display in the current page is ensured, the user can more fully and comprehensively understand the object, and the object recommendation effect can be better improved.

The application discloses a kind of knowledge point-oriented scientific and technological resource recommendation method and system, the present application includes using paper vector representation model respectively calculate the final vector of candidate paper in submission paper and candidate paper set as target paper;The similarity of the final vector of submission paper and each candidate paper is calculated respectively to select the highest similarity of multiple candidate papers;Paper vector representation model includes text encoder, for mining knowledge points from the title T and abstract A of input target paper and the title T of n references of target paper and encoding into hidden state;Linear layer is used to linearly process hidden state to obtain vector representation;Citation parser is used to mine potential citation preference and possible missing knowledge points;Splicing layer is used to splice vector representation output.The present application aims to combine paper content text and existing citations to improve the accuracy of missing citation recommendation for submission papers, improve recommendation accuracy and citation recommendation efficiency.

This disclosure presents embodiments of a method, apparatus, device, medium, and program product for generating material sequences. One specific implementation of the method includes: in response to the existence of target creative materials in a set of creative materials to be recommended, determining a target set of creative materials to be recommended; for each target creative material to be recommended, selecting a predetermined number of target historical recommended creative materials from a set of historical recommended creative materials; generating an estimated click-through rate (CTR) for each target creative material to be recommended based on the CTR of each target historical recommended creative material; determining the CTR of each multiple recommended creative material; and sorting the creative materials to be recommended to obtain a sequence of creative materials to be recommended. This implementation is related to artificial intelligence; by determining the CTR corresponding to the target creative materials to be recommended, a more accurate material recommendation order can be generated for the set of creative materials to be recommended, improving the material recommendation effect.

The present disclosure relates to a kind of server and media recommendation method, relate to media recommendation technical field.Therein, server includes: controller, is configured as: receiving the first media identification sent by client;Obtain the first attribute information of the first media indicated by first media identification, first attribute information includes first media label, first media name, first media description, first media actor;According to first attribute information, determine the first text sequence of first media;First text sequence is input into pre-trained media recommendation model, obtains the recommended media matched with first attribute information that media recommendation model outputs;Obtain the first media indicated by first media identification;Recommended media and first media are sent to client.The embodiment of the present disclosure is used to improve the accuracy of media recommendation.

The application provides a test question recommendation method and device, an electronic device and a storage medium. The method comprises: generating recommended test questions corresponding to target test questions based on the target test questions corresponding to a target student and test question recommendation strategies corresponding to the target student; wherein the test question recommendation strategies are determined based on a first test question recommendation strategy and a reference test question recommendation strategy, the first test question recommendation strategy comprises a test question recommendation strategy of a target region to which the target student belongs, and the reference test question recommendation strategy comprises at least one of a test question recommendation strategy of an associated region of the target region and a general test question recommendation strategy. The technical solution of the application can improve the test question recommendation capability of the test question recommendation strategy without sharing the test question library of the associated region, and can improve the accuracy of test question recommendation while ensuring the data privacy and security of the test question resources of each region by combining the test question recommendation strategies determined by the test question library of the associated region and / or the general test question library of the region.

The application provides a commodity recommendation method, device, system and storage medium, and belongs to the commodity recommendation field.The method comprises the following steps: constructing user nodes, user node data, commodity item nodes and commodity item node data through user information and commodity information; updating the user node vector of the user nodes and the user node data to obtain an updated user node vector; and updating the commodity item node vector of the commodity item nodes and the commodity item node data to obtain an updated commodity item node vector.The application can capture global collaborative features and social influences between friends, can effectively filter node transition relationships irrelevant to current sequence transactions, and can further improve recommendation performance and accuracy.

The present disclosure provides a news recommendation method and device, electronic equipment and computer readable storage medium, and relates to the technical field of big data. The method comprises the following steps: constructing a keyword list of each news to be recommended; obtaining a keyword frequent item combination generated by a target user when browsing news in the past; scoring each news to be recommended according to the keywords in the keyword list and the keyword frequent item combination, to obtain a news score of each news to be recommended; and determining target news to be recommended to the target user from all the news to be recommended according to the news score of each news to be recommended. The present disclosure can not only recommend news to users with sufficient information, but also recommend news to users with less information, which is conducive to improving the accuracy and recommendation effect of news recommendation.

The application discloses a question recommendation method based on a schema in a question and answer community, and the steps include: 1, collecting data and constructing a question and answer community network; 2, using a schema mining algorithm to mine the schema in the user network, and constructing a schema network based on the schema; 3, using a network embedding learning algorithm to learn the node embedding of the network, and learning the preferences of the answerer for the questioner and the question; 4, fusing the preferences of the answerer in two aspects, using a scoring function to predict the matching degree of the answerer for a new question, arranging the answerer in descending order according to the matching score, and recommending the first N users to answer the question, so as to complete the question recommendation task. The application combines the schema mining algorithm and the embedding learning algorithm of the schema network, fully captures the historical interaction information of the users in the schema network by using the graph neural network, and fully fuses the personal feature information, network structure information and text semantic information of the users, so that more accurate recommendation effect is realized.

The invention relates to a recommendation processing method and device, electronic equipment, a medium and program product quality, and the method comprises the steps that in the display process of target media content comprising a preset object, target interaction recommendation information corresponding to a target account is displayed on a display page of the target media content, and the target account is a user account of the preset object; the release account of the target media content is not the target account; the target interaction recommendation information is used for indicating to execute an interaction operation for the target account; and in response to a trigger operation based on the target interaction recommendation information, executing an interaction operation for the target account. By utilizing the technical scheme provided by the embodiment of the invention, the association between the media content and the account corresponding to the included object can be established, while account recommendation is realized, a browsing user of the media content can be helped to quickly find the account of the interested object in the media content, the convenience of interaction between the browsing user and the recommended account is improved, and the user experience is improved. And therefore, the account recommendation effect and recommendation efficiency can be improved.