94 results about "Preference analysis" patented technology

The invention relates to the technical field of data processing, and discloses a cross-border e-commerce commodity recommendation system and method based on multi-source data fusion. The system comprises an acquisition module for performing data acquisition to obtain a cross-border unified data warehouse and federal learning cooperation data; the classification module performs text classification processing to obtain a user preference analysis result and an interpretable attention mark; a quantization module carries out quantization processing to obtain a cross-border selection feature matrix; the fusion module carries out weighted fusion processing to obtain a basic comprehensive score and a weight convergence detection result; the evaluation module performs risk evaluation processing to obtain risk probability distribution and cross-border compliance evaluation results; and the sorting module carries out real-time processing through lightweight preprocessing and a flow-type calculation pipeline to obtain a comprehensive score sorting list of cross-border selected products. The problem that a traditional cross-border e-commerce product selection method cannot effectively integrate multi-source heterogeneous data and cannot analyze user feedback text semantic information is solved.

The invention discloses an intelligent verification system and method for full-process review based on multi-modal analysis, and belongs to the technical field of intelligent review. Comprising a processing analysis module, an experiment extraction module, a risk early warning module, a reproduction verification module, a chart comparison module, a dispute tracing module, a feedback analysis module, a load monitoring module, a report generation module and a preference analysis module. According to the invention, comprehensive and multi-angle intelligent review can be realized, more detailed risk early warning and positioning information can be generated, the experiment reproducibility can be quickly verified at low cost, the manual verification burden is greatly reduced, the innovation and risk of the thesis viewpoint are scientifically evaluated, the fatigue of a manuscript reviewer is relieved, the manuscript review efficiency and quality are improved, and the method is suitable for popularization and application. And dynamically adjusting the review content recommendation sequence.

The invention discloses a personalized costume design recommendation system and method based on AI and big data, and relates to the technical field of personalized recommendation data processing, the system comprises an information acquisition module, a feature analysis module, a preference analysis module and a design recommendation module; the information acquisition module is used for acquiring user multi-modal information; the feature analysis module is used for extracting and fusing user preference features from the user multi-modal information and calculating a user multi-modal interest expression vector; the preference analysis module is used for carrying out joint modeling by combining a Transform network and a GRU structure based on the user multi-modal interest expression vector, and generating a user multi-dimensional dynamic preference vector through fusion of a gating mechanism; and the design recommendation module is used for outputting a personalized costume design recommendation result through a reinforcement learning model in combination with the multi-dimensional dynamic preference vector of the user.

The invention discloses a metro operation decision optimization method based on a knowledge graph and cross-modal association, and relates to the related technical field of metro operation, and the method comprises the steps: deploying an edge computing node at edge equipment of a metro, and configuring a universal weak classifier; computing preference analysis is executed, and a preference database is generated; reinforcement learning is carried out on the universal weak classifier; after communication data is received, fault decision recognition is carried out, and an edge fault decision recognition result is established; and obtaining subway operation environment data and user feedback data, and after synchronizing the data to the subway knowledge graph, generating a subway operation and maintenance decision optimization result. The technical problems that in the prior art, multi-modal big data cannot be efficiently processed, potential correlation of different-modal data cannot be fully mined, and consequently subway fault decision recognition accuracy is insufficient and operation efficiency is poor are solved, dynamically-updated and multi-modal fused subway operation knowledge graph construction is achieved, and the metro operation knowledge graph construction efficiency is improved. The technical effect of improving subway operation decision accuracy and operation efficiency is achieved.

The invention discloses a personalized travel route planning method and system based on a large language model, and a terminal. The method comprises the steps: collecting multi-source data information, carrying out the extraction and standardization of the multi-source data information, obtaining a target multi-source data set, and constructing a travel knowledge graph according to the target multi-source data set; the method comprises the following steps: constructing a big language model, performing instruction type fine tuning on the big language model according to a tourism knowledge graph and a preset fine tuning task, enhancing the big language model after instruction type fine tuning through a knowledge distillation technology to obtain a tourism route planning model, and outputting a user preference vector and a candidate scenic spot set according to the tourism route planning model. And according to a user preference vector and the candidate scenic spot set, generating a personalized travel route plan through a traditional route optimization algorithm. According to the method, entity extraction and knowledge graph dynamic modeling are carried out on the multi-source heterogeneous tourism data, deep semantic understanding and preference analysis are carried out in combination with a large language model, personalized tourism routes can be provided, and the travel efficiency of users is improved.

The invention relates to the technical field of intelligent recommendation systems, and discloses a personalized resource recommendation method and system.The personalized resource recommendation method comprises the steps that real-time interaction logs and course resource data are collected, and preprocessing and feature extraction are conducted on the real-time interaction logs; performing structured processing on the course resource data; performing occupational skill mapping based on the layered resource data; performing feature extraction and semantic coding; performing multi-level user interest analysis; constructing a curriculum-to-skill mapping model and training, and deducing pre-repair dependence between curriculums; strategy mixed recommendation is carried out, and weighted fusion is carried out on mixed recommendation results; performing user diversity preference analysis, evaluating the diversity of the personalized recommendation candidate set, and performing optimization in combination with an evaluation result; performing multi-dimensional interpretation and interpretation quality optimization on the final recommendation result; in combination with a scene adaptive fusion mechanism, the learning requirements of the user in different time dimensions can be accurately captured, and the recommendation accuracy is improved.

The invention discloses an application preloading method and device, equipment and a storage medium, and relates to the technical field of application management, and the method comprises the steps: obtaining user behavior data of a target user and current network environment data; inputting the user behavior data into a user preference prediction model for preference analysis to obtain user preference information output by the user preference prediction model; inputting the user preference information and the current network environment data into an application recommendation engine for recommendation analysis to obtain an application recommendation list and a resource preloading strategy output by the application recommendation engine; and based on the resource preloading strategy, performing application preloading on the application recommendation list through a preset back-end cache library. According to the application, the application needing to be preloaded is selected through the user preference and the network environment, unnecessary resource loading is avoided, the resource utilization efficiency is improved while the loading time is remarkably shortened, personalized application recommendation is provided for the user, and the personalized requirement of the user is met.

The invention discloses a service platform for completing bidding document production based on automation technology assistance, and belongs to the technical field of bidding services, and the service platform specifically comprises the steps that a user behavior collection module collects operation behavior data of a user in the bidding document production process; the decision preference analysis module processes the operation behavior data through an analysis model to generate user decision preference parameters; the strategy generation module generates a candidate bidding strategy set based on historical cases; the scene simulation module constructs a bidding scene simulation environment and records market competition data in a strategy execution process; the strategy evaluation module calculates a strategy competitiveness index according to the market competition data; the strategy execution module screens an optimal bidding strategy and converts the optimal bidding strategy into a specific bidding file making scheme; through intelligent analysis of user behaviors and dynamic simulation of a bidding environment, the accuracy and competitiveness of bidding document production are effectively improved.

The invention discloses a cross-border e-commerce product recommendation matching system based on artificial intelligence, particularly relates to the technical field of international trade, and comprises a user behavior preference analysis module which is used for deeply knowing interests and demands of a user by analyzing behavior data and emotion feedback of the user so as to realize personalized recommendation. The user portrait is accurately constructed by analyzing the behavior data, emotion feedback and historical purchase records of the user, personalized product recommendation is realized by using deep learning and reinforcement learning technologies, and the system combines logistics, price, culture and payment preferences of the region where the user is located, so that the user experience is improved. The optimal cross-border logistics scheme, price optimization and localization payment mode are intelligently matched, it is ensured that products can be smoothly delivered and meet the requirements of local users, through real-time monitoring and user feedback collection, the system continuously optimizes the recommendation algorithm and improves the performance, the recommendation accuracy and stable operation of the system are ensured, and the user experience is improved. Therefore, the conversion rate and the user satisfaction degree are improved.

The invention relates to the field of product selection service management, and discloses a product selection service management method and system based on real-time big data calculation, and the method comprises the steps: combining the current behavior data of a user with the historical behavior data, analyzing the preference of the user, recognizing a product preferred by the user, and carrying out the calculation of the product selection service. By analyzing the similarity between the product and the product interested by the user, the product closely associated with the user is screened out, and by analyzing the whole process of the user from product contact to final purchase, the behavior path of the user is tracked in real time, so that the user experience is improved. Based on comprehensive analysis of a user preference analysis result, a product association analysis result and a user behavior path analysis result, all related products meeting user requirements are screened out, and the screened products meeting the user requirements are sorted and recommended, so that a more comprehensive and more personalized recommendation strategy can be formulated, and the user experience is improved. The accuracy and effectiveness of recommendation are improved, and diversified requirements of users are met.

The embodiment of the invention provides a resource recommendation method and device, equipment and a storage medium, and is applied to the technical field of data personalized recommendation. According to the method, the local lightweight resource index pool and the local user behavior database are constructed, preference analysis and multi-dimensional scoring recommendation are directly performed on the terminal, the hysteresis of cloud computing is avoided, quick and accurate response can be realized, network dependence and server pressure are remarkably reduced, and the user experience is improved. Therefore, the problem of poor recommendation timeliness and accuracy in the existing user personalized data pushing scheme is solved.

The invention discloses a dynamic trapping network deployment method and system fusing attack behavior preferences, and relates to the technical field of network security. The method comprises the following steps: modeling a network topology into a directed acyclic graph, and constructing a dynamic trapping network topology structure fused with attack behavior preference based on attacker behavior preference analysis in combination with situation awareness; modeling an attack and defense confrontation process as a Markov multi-stage dynamic game process, and solving Nash equilibrium to obtain an optimal strategy of each stage; the behavior preference of an attacker is updated in real time by using Bayesian learning and a sliding window mechanism, and the adaptability of a dynamic trapping network to attack and defense situations is enhanced. According to the method, the problems of configuration stiffness and poor attack and defense situation change adaptability in dynamic trap network deployment are solved, the active defense capability aiming at attacker behaviors can be improved, and an effective solution is provided for dynamic deployment of a trap network in a dynamic network environment.

The invention provides a short video content personalized recommendation method and system based on big data, and relates to the technical field of short video recommendation. The method comprises the following steps: acquiring historical short video watching data of a user, determining a plurality of fragment watching events and constructing a plurality of watching content sequences; constructing an event behavior vector of each watching content sequence, performing watching scene division on a plurality of fragment watching events to generate a plurality of watching scene clusters, performing content adaptation analysis on each watching scene cluster, constructing a content adaptation map of each watching scene cluster, and obtaining a content adaptation map of each watching scene cluster; and performing content preference analysis on each watching scene cluster and constructing a content preference sequence, generating a plurality of video recommendation optimization units of the user based on the content adaptation map and the content preference sequence, and performing personalized short video content recommendation on the user based on the plurality of video recommendation optimization units. According to the invention, the accuracy of personalized recommendation of the short video is improved.

An object of a system according to an embodiment is to propose a way of spending leisure on the basis of a user's preference.SOLUTION: A system according to an embodiment includes an information collection unit, a preference analysis unit, and a proposal generation unit. The information collection unit collects an answer to a simple question from a user. The preference analysis section analyzes the user's answer collected by the information collection section and understands the user's preference. The proposal generation unit proposes a way of spending leisure on the basis of the preference of the user analyzed by the preference analysis unit.SELECTED DRAWING: Figure 1

The application discloses a subway operation decision optimization method based on a knowledge graph and cross-modal correlation, relates to the technical field of subway operation, and comprises the following steps: deploying an edge computing node on an edge device of a subway and configuring a general weak classifier; performing calculation preference analysis to generate a preference database; performing reinforcement learning on the general weak classifier; identifying fault decision after receiving communication data, establishing an edge fault decision identification result; obtaining operation environment data and user feedback data of the subway, synchronizing the data to a subway knowledge graph, and generating a subway operation and maintenance decision optimization result. The method solves the technical problems that the prior art cannot efficiently process multi-modal big data, cannot fully mine the potential correlation of different modal data, and results in insufficient accuracy of subway fault decision identification and poor operation efficiency, realizes dynamic updating and multi-modal fusion of the subway operation knowledge graph, and achieves the technical effect of improving the accuracy of subway operation decision and operation efficiency.

The invention discloses a big data-based universe scenic area multi-modal interaction special effect generation method and system, and relates to the technical field of virtual reality, and the method comprises the steps: obtaining universe scenic area information, obtaining historical tourist information according to the universe scenic area information, and generating a universe scenic area multi-modal interaction special effect according to the historical tourist information; and obtaining historical interaction time information and historical interaction tourist information corresponding to each interaction special effect. According to the method, the preferred tourists of each interaction special effect are accurately analyzed through the preferred tourist feature information, a data basis is provided for subsequent interaction special effect generation, the interaction deviation angle model is constructed through the special effect visual position and the tourist position, the special effect interaction degree is calculated in combination with the interaction time, single interaction duration judgment is replaced, and the interaction efficiency is improved. The tourist preference analysis accuracy is improved, the appropriate interaction special effect is selected by screening the interaction special effects corresponding to the meta universe scenic spots, the special effect individuation adaptation degree is improved, and the tourist immersion experience is optimized.

The application belongs to the technical field of bioinformatics analysis, and discloses a kind of anti-new coronavirus neutralizing antibody VJ gene preference analysis method, including antibody database acquisition data, data screening, selection frequency statistics, selection preference analysis, selection frequency and preference visualization, pairing frequency statistics, pairing preference analysis, pairing frequency and preference visualization.The beneficial aspects of the present application are that the neutralizing antibody and VJ selection and pairing frequency are tested by scientific statistical methods, and are visualized to make the result interpretation more simple and intuitive.Therefore, according to the above method, a new method for early prediction of anti-new coronavirus neutralizing antibody production based on peripheral blood B cell VJ gene frequency and preference is established, which can predict whether the probability of producing neutralizing antibody by the subject is higher than the baseline level of healthy people.

An object of a system according to an embodiment is to perform matching with clothes that a user has in consideration of a preference of the user.SOLUTION: A system includes a preference analysis unit, a matching unit, and a proposal unit. The preference analyzer includes a generation AI. The matching unit performs matching with clothes that the user has on the basis of the preference of the user analyzed by the preference analysis unit. The proposal unit displays the proposal of the clothes matched by the matching unit on the digital signage.SELECTED DRAWING: Figure 1

The invention relates to the technical field of child behavior analysis, and discloses a multi-age child recreation behavior preference analysis system, which comprises a multi-dimensional acquisition module and an intelligent analysis module. According to the system, management data of urban green space and recreation behavior management data of participated children are acquired through a multi-dimensional acquisition module and are classified to form a data set, and an intelligent analysis module evaluates the popularity degree of each green space and generates an attraction index, so that data support is provided for facility configuration optimization and people flow guidance; the practical value of the green space is improved, the correlation coefficients of the age, the height and the duration of two recreation behaviors are accurately calculated, the adaptation rule of the child growth stage and the recreation behaviors is revealed, the preference index is generated, the matching level of green space configuration and child preference is accurately reflected, the comprehensive analysis precision is high, optimization measures are specifically triggered, and the method is suitable for popularization and application. Through the modes of adjusting the facility layout, dividing exclusive areas, adding facilities and the like, the greenbelt space is ensured to be adaptive to the multi-age children, and personalized management and recreation experience are good.

The invention discloses a train carriage vending robot intelligent prediction and dynamic verbal skill adjustment system based on multi-dimensional data, and relates to the technical field of intelligent retail and data analysis. The system comprises a user attention recognition module (for recognizing expressions and body movements of passengers), an intelligent prediction and conversion analysis module (for generating a product conversion rate and a preference analysis report in combination with information such as interactive data, purchase behaviors, train numbers, stations, time periods and regional air temperatures), and a dynamic verbal skill adjustment module (for optimizing selling verbal skill based on an analysis result, and adjusting the verbal skill. According to the method, through multi-dimensional data fusion analysis, accurate prediction of product conversion and intelligent optimization of verbal skills are achieved, the selling conversion rate is effectively improved, meanwhile, the comfort degree of user interaction is enhanced, and the method is suitable for automatic selling requirements of specific scenes such as train carriages.

The application relates to the technical field of vehicle maintenance service, in particular to a personalized vehicle maintenance reminding and pushing system based on owner historical data, which obtains a plurality of vehicle use features according to owner historical data through a feature extraction module, obtains a user portrait label according to the vehicle use features through a user analysis module, obtains reference weights of the plurality of vehicle use features according to the user portrait label through a preference analysis module, obtains a maintenance cycle correction amount according to a preset multi-expert hybrid model based on the vehicle use features and the reference weights through a correction and calibration module, and then performs vehicle maintenance reminding and pushing according to the maintenance cycle correction amount through a reminding and pushing module. Compared with the prior art, the application adopts an innovative multi-expert hybrid model architecture, outputs a scientific and reliable maintenance cycle correction amount, and solves the problem that the vehicle maintenance reminding scheme in the prior art lacks personalization.

The application discloses a multi-target-oriented power distribution network safety domain operation point screening method, medium and equipment, belongs to the field of power system operation and optimal control, and comprises the following steps: firstly, constructing a static safety domain containing a power flow equation and multiple constraints based on power distribution network nodes, branch information and safety criteria; secondly, accurately obtaining a safety domain boundary through adaptive direction search and error correction; thirdly, generating a candidate operation point by Monte Carlo sampling, combining economic and reliable indexes, and obtaining a Pareto optimal solution set through fast non-dominated sorting; finally, screening an optimal operation point considering safety, economy and reliability through fuzzy multi-attribute decision and decision maker preference analysis; the application realizes three-dimensional target collaborative optimization, is high in calculation efficiency and strong in robustness, can adapt to real-time optimization requirements of high-proportion distributed power distribution networks, and can be widely applied to active power distribution network safety evaluation, energy storage configuration and economic dispatching scenes.

The invention discloses an intelligent information technology consultation system based on a knowledge graph, and relates to the technical field of artificial intelligence. According to the method, the knowledge graph is constructed, a semantic association technology is introduced, and a complex dependency relationship between technical concepts is accurately captured by utilizing a word vector embedding technology and a graph neural network propagation algorithm, so that the problem that a traditional technical consultation scheme lacks deep semantic association capability when processing cross-domain technical problems is solved; through a user portrait and preference analysis module, a query intention understanding module, a perception query understanding module and the like, the problem that an existing system cannot carry out dynamic adaptation according to a specific business scene and historical interaction of a user is solved, and individuation and practicability of consultation service are improved. And the suggestion generation and optimization module performs iterative optimization according to user feedback through a natural language generation technology and a semantic analysis model, so that the problem that a traditional scheme lacks a continuous learning mechanism is solved, the service quality is continuously improved, and higher-quality and more efficient technical consultation service is provided for the user.

An object of a system according to an embodiment is to provide a family quest customized based on the preference or interest of a family member.SOLUTION: A system according to an embodiment includes a preference analysis unit, a fusion design unit, and a quest generation unit. The preference analysis unit analyzes the preferences, interests, and strengths of the family. The integration design unit designs the customized family quest in which the real world and the virtual world are integrated based on the preference, the interest, and the strength of the family analyzed by the preference analysis unit. The quest generation unit generates the family quest designed by the integration design unit.SELECTED DRAWING: Figure 1

The invention provides a commodity recommendation method and system based on multi-dimensional entity analysis and mixed retrieval, and belongs to the field of natural language processing. The method comprises the following steps: preprocessing a user problem to obtain a preliminary user optimization problem and a general suggestion; key entities of the preliminary user optimization problem are extracted, and commodity recommendation related problems are screened based on entity matching; obtaining a preference entity based on the user behavior record; performing semantic extension on the key entity and the preference entity of the commodity recommendation related problem to obtain an extended entity; the extended entities are spliced and recombined, and historical recommendation results are matched based on mixed retrieval of semantic retrieval and full-text retrieval; and aggregating the historical recommendation results, generating commodity recommendation key point statements based on a specified format and word number, and outputting the commodity recommendation key point statements and the general suggestions. Therefore, the defects of the conventional technology in the aspects of problem screening, preference analysis, retrieval, result presentation and the like are overcome, and the commodity recommendation efficiency and quality are comprehensively improved in multiple links.

The invention discloses a localized service recommendation system based on a hotel guest room service robot, and the system comprises a geographic position recognition module which is used for obtaining the information of the current position of a customer, and comprises a GPS module and a Wi-Fi module; the localized service database module is used for storing local scenic spots, food, specialty products, shopping information, local characteristic activities, recommended scenic spots and hot restaurant content; the personalized preference analysis module is used for analyzing personalized preferences of clients; the intelligent recommendation algorithm module is used for generating recommendation content meeting customer requirements by adopting an intelligent recommendation algorithm on the basis of customer positions, personalized preferences and a localized service database; the real-time interaction and feedback module performs real-time interaction with the client through the robot, adjusts recommendation content according to feedback and selection of the client, and optimizes a recommendation result; according to the localized service recommendation system based on the hotel guest room service robot, preferences of customers can be known, so that more accurate localized service recommendation is provided, and the experience of the customers during hotel accommodation is greatly improved.

The invention provides an AI-based intelligent audio player and a control method thereof. Belongs to the technical field of artificial intelligence and music players. The method comprises the steps of performing multi-dimensional data collection on a user of the intelligent audio player, and generating a user music preference comprehensive data set; based on the comprehensive data set, constructing an initial user music preference analysis model through a machine learning algorithm; a plurality of environment sensors are integrated on the intelligent audio player, data of a playing environment are collected in real time through the environment sensors, and environment real-time data are generated. Through multi-dimensional data collection and machine learning algorithm analysis, in combination with the song listening history, collection preference and active feedback of the user, the intelligent audio player can accurately generate a music preference comprehensive data set of the user and construct an initial personalized music recommendation model, so that the deviation between recommended songs and user preferences is reduced, and the user experience is improved. And the recommendation accuracy and personalized experience are improved.

The invention belongs to the technical field of data analysis, and particularly discloses a marketing method and system based on user behavior analysis and a program product, through a multi-dimensional behavior quantification mechanism, the preference condition of a user for each product type can be distinguished according to the corresponding behavior data of the user for different product types, the preference identification accuracy is high, and the user experience is improved. The preference analysis result can better reflect the interest of the user; the user behavior value index and the group preference similarity are fused through the comprehensive preference degree, the advantages of personalization and collaborative filtering are considered, and the product pushing conversion rate can be effectively increased; high-dimensional vector operation and clustering iteration are not needed, the calculation overhead can be greatly reduced, and the method is suitable for a real-time marketing scene; and the preference analysis result can be traced back to the specific behavior type, the interaction depth and the group portrait matching label, so that the platform can carry out marketing strategy adjustment and optimization conveniently, and the platform marketing transparency and the user credibility are improved.

The embodiment of the invention relates to a preference analysis model training method and a video recommendation method. The preference analysis model training method comprises the steps of obtaining user behavior data of a first user; generating model cue words based on the user behavior data of the first user, the plurality of video feature dimensions and the plurality of preference level features, inputting the model cue words into a large language model, and driving the large language model based on the model cue words to generate at least one group of video preference contents with preference grading tags, the video preference information serves as video preference information of the first user; constructing a training sample based on the user behavior data and the video preference information, inputting the user behavior data in the training sample into a model, outputting a predicted video preference corresponding to the user behavior data by the model, and verifying the predicted video preference by using the video preference information in the training sample, and adjusting parameters of the model according to the verification result until the model reaches a preset convergence condition, and taking the model as a preference analysis model.

The application discloses a virtual-real fusion exhibition display interaction system and a multi-modal perception method, aiming at solving the problems of single interaction mode, insufficient perception accuracy and the like of the existing system. The system comprises a virtual-real fusion display, a multi-modal perception, an interaction control, a data processing and a storage module, can load virtual content and accurately fuse with the entity scene. The multi-modal perception module synchronously collects visual, motion and voice data, identifies user intention after pre-processing, feature fusion and semantic analysis, and the interaction control module generates instructions accordingly to drive the display module to adjust the content and feedback. The method realizes efficient interaction through initialization, data collection, pre-processing, feature fusion, intention recognition, interaction feedback and preference analysis. The application improves the interaction intention recognition accuracy and virtual-real fusion accuracy, guarantees real-time response, enhances the sense of immersion and personalized service ability, and is suitable for various exhibition scenes.