21results about How to "Precise personalized recommendation" patented technology

The invention discloses a regional document travel intelligent recommendation method, which comprises the following steps of: S1, collecting a large amount of data, and preprocessing the data; s2, constructing a user portrait by using a machine learning algorithm based on the behavior data of the user; s3, performing feature extraction on the data, processing text description related to the cultural resources by using a text mining technology, and extracting specified information; s4, designing a recommendation model, matching the user portrait with the text travel resource features, and calculating the preference degree of the user to the specific text travel resource; s5, generating a personalized regional travel recommendation result for the user by using the recommendation model, and selecting the most suitable recommendation result from the database of the travel resources according to the portrait and the historical behavior of the user; and S6, updating the user portrait and the recommendation model in real time, and providing a dynamic personalized recommendation result. According to the invention, the prediction score of the target user can be improved, and more accurate tourism place recommendation can be carried out on the target user.

The invention relates to the technical field of data processing, and discloses a multimodal recommendation method and system based on a spectrogram polynomial filter.The method comprises the steps that user data and project data are input into a PolyRec model, and the PolyRec model comprises a multimodal encoder, a behavior encoder and a multimodal alignment module; encoding and fusing the user data and the project data by using a multi-mode encoder to obtain a first feature; encoding the user data by using a behavior encoder to obtain a second feature; and inputting the first feature and the second feature into a multi-modal alignment module for fusion, and outputting a personalized recommendation result. According to the method, the multi-modal characteristics of the user and the behavior information of different frequencies are integrated, so that the user preferences can be captured more comprehensively; and a frequency signal scaler and a unified spectrogram neural network function are adopted, so that the model can flexibly adapt to the characteristics of different frequency signals, and the robustness and adaptability of the recommendation system are further enhanced.

The invention discloses a recommendation method and device based on user interest points, and relates to the technical field of interest point recommendation, and the method comprises the steps: S1, obtaining behavior data, time information and attributes of interactive items of a user on a platform, and carrying out the preprocessing of the obtained data; and S2, performing short-term preference analysis and long-term preference analysis based on the processed user data, modeling interest points of the user, generating a user portrait and the like. According to the method, short-term preference analysis and long-term preference analysis are respectively carried out by utilizing the user data, and a unified user portrait is formed by combining short-term and long-term preference characteristics, so that more accurate personalized recommendation is provided for the user, the user satisfaction and the scene matching degree are improved, and the user experience is improved through a long-term and short-term preference fusion strategy. Therefore, the recommendation system can utilize the existing resources more efficiently and obtain more comprehensive and abundant preference representation of the user, so that more efficient and accurate interest point recommendation is realized.

The invention relates to a portrait generation and feature similarity recommendation method and system based on a large language model, and the system comprises a data collection module, a feature extraction module, a similarity calculation module and a recommendation module, the data collection module collects multi-modal data from a social media platform, and covers audio, video, text and interactive data information; the feature extraction module performs deep feature analysis and processing based on the collected multi-modal data, and extracts features in multiple dimensions; the similarity calculation module generates a training sample based on the feature matrix generated by the multi-dimensional feature extraction module in combination with a large language model, constructs a similarity matrix of audio, video, text and interactive data features, and calculates similarity scores to determine candidate objects; the recommendation module provides personalized recommendation based on the comprehensive similarity score generated by the similarity determination module. Through combination of a large language model and multi-modal features, the system can accurately analyze behaviors and expressions and generate personalized recommendation.

The invention relates to the technical field of information recommendation, in particular to an AI-driven customer segmentation and personalized recommendation system which comprises a user acquisition module, a data classification module, a user division module, a training module, a preference link generation module, a retrieval link generation module, a push output module, a monitoring verification module and an analysis module. According to the method, users are subdivided into different groups and divided into a plurality of user categories, personalized link recommendation is provided for each user category, accurate user subdivision and personalized recommendation are realized by collecting and analyzing a large amount of user data, and the data processing efficiency is improved.

The invention discloses an intelligent curriculum recommendation method based on implicit vector space, and relates to an artificial intelligence technology. Comprising the steps of 1, carrying out data collection and preprocessing, 2, constructing implicit vectors of users and courses, 3, calculating similarity and generating recommendation information: establishing a recommendation model, calculating the similarity or correlation between the users and the courses based on the implicit vectors by utilizing the recommendation model, carrying out sorting according to the similarity, generating a personalized course recommendation list for the users, and carrying out recommendation on the courses according to the personalized course recommendation list. And 4, optimization and feedback circulation: continuously optimizing the recommendation model through a machine learning algorithm, establishing a user feedback mechanism, and collecting satisfaction evaluation of a user on a recommendation result for improving the recommendation model.

The invention relates to the technical field of e-commerce data management, in particular to a big data management system based on cross-border e-commerce, which comprises a data acquisition module, a multi-layer graph construction module, a multi-layer graph processing module and a multi-layer graph application module, and is characterized in that the data acquisition module collects commodity data used by users, including the users, commodities, operation behaviors and user emotions; the multi-layer graph construction module is used for forming a commodity recommendation multi-layer graph and constructing nodes and edges in emotion, behavior and time layer graphs so as to realize fine modeling of a complex relation; the multi-layer graph processing module calculates embedded vectors of all layers of graphs, and the embedded vectors are fused into aggregation embedded vectors through a full connection layer; and the multi-layer graph application module optimizes the training of a recommendation model by using an aggregation embedded vector, identifies potential interested commodities of the user by predicting a recommendation list, and particularly improves the relevance and individuation of recommendation in combination with an emotion layer graph weight, so that the problem that a recommendation system cannot timely and accurately respond to user requirements is solved, and the user experience is improved. And the user satisfaction and the platform viscosity are improved.

The invention provides an interaction method which can be applied to the technical fields of Internet technology, electronic technology, artificial intelligence and the like. The interaction method comprises the following steps: in response to a search operation of a user on a search interface, displaying an interaction control corresponding to a target category to which a search keyword belongs; in response to a trigger operation of the user on the interaction control, initiating interaction information for the target category to the user in a dialogue window of the interaction control; under the condition that the user intention is determined to be an article recommendation intention according to the reply of the user, performing user preference interaction with the user, and determining preference information of the user for a target category; and according to the preference information of the user, recommending a target article to the user, the target article being determined from all articles of the target category. The invention further provides an interaction device, equipment, a medium and a program product.

The invention relates to the technical field of image processing, in particular to an intelligent art work image display system which comprises a work image acquisition module, a work image processing module, a work information input module, a work classification module, a control display module and a display adjustment module. Through combination of the work image acquisition module and the image processing module, high-quality work image presentation is ensured, the display effect is enhanced, art works are intelligently classified according to the input work information, accurate data support is provided for intelligent display of images, and the work quality is improved. The control display module effectively calls corresponding art work blocks by receiving selection information of a user and displays the art work blocks according to different modes and sequences, and the display adjustment module further evaluates the effectiveness of the art work blocks according to the residence time of the user before the art work and dynamically adjusts the follow-up display sequence. The intelligent display of the art work image is facilitated, and the display efficiency of the art work is improved.

The invention discloses a user portrait generation method and device based on big data and electronic equipment, and relates to the field of data analysis, and the method comprises the following steps: 1, defining a plurality of project attributes based on a user personal data information base; step 2, after user authorization, acquiring a data acquisition authority under a specified item in a user personal data information base, performing data acquisition, and cleaning the acquired data; step 3, selecting a demand attribute of a certain application target; step 4, determining as selection, defining a keyword capturing template by taking a preset application target demand attribute as a reference, performing keyword capturing on the cleaned data by using the capturing template, and performing tagged classification; according to the method, data cleaning, keyword capturing and label mining are utilized to ensure that the used data are highly related to target requirements, an accurate user portrait is generated, and a keyword capturing template and label classification can be adjusted according to different application targets.

The present invention relates to the technical field of recommendation systems, and in particular to a recommendation system method based on an NSGC-GRU integrated model. The present invention comprises the following steps: S1: collect public data sets, process outliers in the data sets; uniformly perform normalization processing; for each data set, randomly divide it into training, validation and test sets, and set the ratio of each user to 80:10:10; S2: set the hyperparameters of the model, such as the maximum number of training, learning rate, batch size, L2 regular term coefficient, etc.; S3: construct a bipartite graph of the relationship between users and commodities based on the data set to generate an adjacency matrix A of the corresponding graph, and then put it into N-SGC training; S4: put the feature fusion result obtained in S3 into a GRU model for training; S5: predict the result obtained in S4 using a softmax linear model; S6: calculate the recall rate recall and the normalized discounted cumulative gain NDCG through the predicted data obtained in S5 to measure the model performance.

The invention relates to the technical field of big data processing and intelligent recommendation, in particular to an intelligent recommendation system driven by big data. The method comprises the following steps: collecting user behavior data and article feature data, and generating a user feature set and an article feature set; a user feature weight is introduced, a relative deviation degree is calculated, a recommendation value is calculated, and a recommendation list is generated; displaying the recommendation list to the user to obtain a feedback value; and dynamically adjusting the user feature weight based on the feedback value, the recommendation value and the relative deviation degree, calculating the relative deviation degree and the recommendation value based on the obtained final user feature weight, and finally generating a personalized recommendation list. The problem that a traditional recommendation system mainly depends on static similarity calculation of users and articles, so that personalized recommendation accuracy is insufficient is solved; the response capability to the user interest change is weak, so that the recommendation system easily misjudges the user demand; and a global performance optimization and regulation and control mechanism is lacked, so that a recommendation system is easy to fall into local optimum.

The invention discloses a computer intelligent service management system, method and device and a storage medium, and the method comprises the following steps: obtaining related information of computer service used by a user, and storing the related information in a system database; analyzing input data and use behavior data of the user, and generating decision support information based on an analysis result; user portraits are completed by means of big data mining, user service demand features are clarified, and personalized service recommendation is provided; personalized service recommendation effects are monitored, user evaluation is collected, summarized and arranged, and a data analysis mode and a service strategy are optimized according to evaluation service quality and improvement effects; user precise service effects are collected, operation is repeated, a management method is optimized, and precise service management is achieved. According to the method, the use data of different services are processed in a centralized manner, the use behaviors, input data and preferences of the user are analyzed, a final analysis result of the heterogeneous information network relation graph is constructed by analyzing and mining the data, and accurate personalized recommendation is provided for the user.

The invention discloses a user outlier behavior recognition and similar behavior recommendation method based on domain name access, which belongs to the technical field of network security, and specifically comprises the following steps: constructing a domain name evaluation index system according to behavior characteristics such as domain name access frequency and domain name access frequency of a user, quantizing the concentration degree and the dispersion degree of domain name access behaviors of global users from multi-dimensional features; based on a domain name evaluation system, an outlier degree of a domain name access behavior of a user is quantified through an outlier detection method, so that a domain name access extreme outlier behavior recognition system of the user is built; users with common domain name access behaviors are associated with domain names as bridges, behavior characteristics of domain name access of the users are described by an outlier degree characteristic matrix, and in combination with a machine learning algorithm, in-depth similarity analysis is carried out on user behaviors; therefore, potential abnormal behavior modes and similar behavior users can be identified.

The present invention discloses a multimodal recommendation method and system based on intra-modal and inter-modal contrastive learning. The present invention includes obtaining an output user's recommendation list by using a pre-trained multimodal recommendation network model for images, description texts and IDs: obtaining input images, description texts and IDs, extracting image features and text features from the images and description texts; constructing user-item graphs in visual and textual modalities, and then using graph convolutional networks to capture high-order features to obtain image and text feature vectors respectively; performing intra-modal feature enhancement and inter-modal feature alignment to obtain user and item feature vectors and calculating the user's predicted score for the item to generate a recommendation list. The present invention aims to improve the prediction accuracy of the recommendation system by using multimodal information, solve the corresponding problems of introducing multimodal information based on contrastive learning tasks, and achieve more accurate personalized recommendations for users. It can be widely used in various multimodal recommendation scenarios.

The present invention relates to the field of big data, and in particular to a method for identifying high-value advertising users based on big data, comprising obtaining an advertising information data set, a user information data set and a flow data set; dividing the flow data set to obtain multiple groups of user flow samples, pre-processing each group of user flow samples to obtain corresponding training samples, constructing an advertising high-value user identification model, and using the training sample set to train the advertising high-value user identification model; and optimizing the parameters of the advertising high-value user identification model through double threshold contrast loss and partial weight cross entropy loss until the model converges; obtaining user data to be identified and inputting it into the trained advertising high-value user identification model to obtain a user value identification result; the present invention improves identification accuracy.

The embodiment of the application provides a communication package recommendation method, system, device and storage medium, the method comprises: calculating the activity value based on the page access time length, the page access times and the recent access time; in the case where the activity value is greater than the first preset threshold, query whether there is a package change record in the historical package information; in the case where there is no package change record in the historical package information, respectively, the statistical feature of the historical call information and the historical traffic information is calculated to obtain the call feature value and the traffic feature value; in the case where the call feature value is greater than the first threshold, and the traffic feature value is greater than the second threshold, the exposure weight of the communication package corresponding to the comprehensive package type in the exposure weight list is increased; at least one target communication package in the adjusted exposure weight list whose exposure weight is greater than the preset weight threshold is exposed in the preset network page. The scheme can adapt to different needs of users for personalized exposure of communication packages.

The invention relates to a privacy protection recommendation method and system based on matrix decomposition, and belongs to the technical field of privacy protection recommendation. Comprises: obtaining a historical score matrix of a user; performing matrix decomposition on the historical score matrix to obtain a shared score matrix; sending the shared scoring matrix and the scored item set to a recommendation server, and generating public parameters, a decomposition matrix and a decomposition matrix shared value; generating an inner product triple and a multiplication triple by using a triple server; calculating an error between the real score and the predicted score by using the recommendation server, and generating an error sharing matrix; the error sharing matrixes are optimized until the error sum of squares of all the error sharing matrixes is smaller than a threshold value; calculating a partial derivative of the loss function to the decomposition matrix to obtain a gradient sharing matrix; updating the decomposition matrix to obtain a user decomposition shared matrix; and generating a privacy protection recommendation result of the user by using the user decomposition sharing matrix. According to the invention, powerful guarantee is provided in the aspect of protecting user privacy.

The application relates to the computer technical field and discloses a pet traditional Chinese medicine diagnosis and treatment service platform and a matching method based on multi-condition screening, aiming to solve the problem of diagnosis and treatment resource mismatch caused by the single screening dimension and the lack of standardized matching mechanism of traditional Chinese medicine characteristic attributes in the prior art. The method comprises the following steps: collecting multi-dimensional attribute data of pet physical sign information, traditional Chinese medicine syndrome characteristics, user preferences, and disease types and severity; establishing a standardized veterinary diagnosis and treatment resource attribute system and generating a matching rule library; performing matching calculation by using a weighted matching algorithm or a similarity model; displaying candidate results in order of matching degree, comprehensive score and distance; collecting feedback data to dynamically adjust the weight coefficient and realize algorithm optimization. The system also comprises diagnosis and treatment scheme recommendation, cost estimation and payment docking, and matching closed-loop verification modules. By incorporating traditional Chinese medicine characteristic attributes such as pet physical quality identification, traditional Chinese medicine syndrome classification, and veterinary professional skill level into the screening conditions, the application realizes precise personalized recommendation for pet traditional Chinese medicine diagnosis and treatment, effectively solves the diagnosis and treatment resource mismatch problem, and can realize dynamic evolution and continuous improvement of the matching system accuracy.

The invention discloses a television media resource data recommendation processing method and device, computer equipment and a readable storage medium, and the method comprises the steps: firstly, generating media resource vector data according to the vectorization processing of a local media resource library, and then obtaining a recommendation model through the training of a pre-training base model and a specific strategy; the method comprises the following steps: firstly, acquiring a user television operation behavior to generate a family portrait, and finally, according to the family portrait and media asset vector data, reasoning and fusing through a recommendation model to generate a final family user sheet recommendation result, thereby realizing accurate and personalized recommendation of the television media asset data.