1112 results about "User satisfaction" patented technology

The invention discloses an airport intelligent service question answering method and system based on AI, relates to the technical field of artificial intelligence, and comprises the steps of performing combined modeling by using a time sequence and a multi-head attention mechanism, extracting key behavior characteristics, fusing intention recognition and behavior prediction, and improving the answer reasoning accuracy. The method comprises the following steps: selecting a semantic knowledge base, constructing deep semantic representation and accurately matching the deep semantic representation with the semantic knowledge base, extracting high-weight phrases in combination with a sliding window mechanism, generating unique semantic fingerprints by utilizing a Karp-Rabin hash function, improving the speed and accuracy of answer matching, and performing fuzzy control and redundant information elimination on candidate answers by adopting a rough set tolerance model. Semantic similarity judgment is carried out according to the intersection and union set proportion between the upper and lower approximate sets, the problems of semantic drift and repeated candidates in traditional matching are effectively relieved, and through reinforcement learning and A / B testing, the question and answer strategy is continuously optimized, and the response effect of the system and the user satisfaction degree are enhanced.

The invention provides a distributed storage resource intelligent scheduling method and device, and relates to the technical field of data processing, and the method comprises the steps: carrying out the feature splicing of feature vectors of different modes, so as to obtain a multi-mode feature vector; predicting the user satisfaction based on the multi-modal feature vector and the resource adjustment parameter; establishing a resource demand priority mapping table under different service scenes according to the user satisfaction; constructing a multi-objective optimization model according to the resource demand priority mapping table; on the basis of the multi-objective optimization model, predicting the resource state and the load condition of each node in the distributed storage system; and according to the resource state and the load condition of each node, lightweight rule scheduling is carried out to obtain a preliminary scheduling scheme. According to the invention, intelligent scheduling management of distributed storage resources is realized.

The invention discloses an e-government affair platform management method and system based on cloud data, and relates to the technical field of data processing, and the method comprises the steps: collecting multi-source data, carrying out the preprocessing, extracting keywords, carrying out the multi-scale time coding and multi-scale space coding of the data, and storing the data in a database; constructing a government affair knowledge graph based on the database, mining association relationships of department services and analyzing affair handling habits of users; generating a government affair examination and approval path based on the knowledge graph, optimizing the government affair examination and approval path through reinforcement learning, dynamically adjusting the examination and approval process, performing a simulation test by using a digital twinning technology, and verifying the user satisfaction after the examination and approval process is optimized; and storing the government affair data in a database and performing authority management. According to the method, the electronic government affair data processing capability can be improved, the examination and approval efficiency is improved, the verifiability of an optimization strategy is enhanced, and technical support is provided for digital and intelligent transformation of government affair services.

The invention provides an intelligent recommendation method and system for an e-commerce platform, and the method comprises the steps: collecting user interaction behaviors and time-space context data in real time, and constructing a user behavior multi-modal feature matrix; extracting commodity multi-level features, and generating a commodity comprehensive feature matrix; identifying and predicting a user intention based on the user behavior feature matrix, and generating an intention distribution vector; a recommendation candidate set is obtained by combining the commodity feature matrix and utilizing a context awareness collaborative filtering enhancement technology; a multi-objective optimization function is constructed, and after the user intention vector is input, a personalized recommendation sequence is generated in combination with an optimization result and the candidate set; and user feedback is monitored in real time, online learning and reinforcement learning algorithms are adopted, and a recommendation strategy is continuously optimized based on user instant feedback and long-term satisfaction. According to the scheme, the recommendation accuracy, the diversity of recommendation results and the user experience can be improved.

The invention relates to the technical field of information retrieval, in particular to an intelligent RAG knowledge base system fused with a dynamic knowledge graph. Comprising a data processing module for preprocessing original data to obtain a standardized data set; the graph construction and updating module is used for carrying out knowledge extraction on the standardized data set by utilizing a large model, constructing a knowledge graph and carrying out dynamic updating; the dialogue management and understanding module is used for recording complete information construction of a current dialogue, updating a dialogue state and calculating a retrieval weight adjustment amount; the mixed retrieval module is used for performing mixed retrieval in combination with DPR and PPR retrieval methods to obtain a first retrieval result and a second retrieval result, setting an initial retrieval weight according to the question type, and obtaining a comprehensive retrieval result in combination with the retrieval weight adjustment amount; and the response optimization module is used for outputting an optimal response according to the comprehensive retrieval result and user feedback by utilizing reinforcement learning based on strategy gradient. According to the method, the retrieval and response generation effect can be optimized, and the user satisfaction is improved.

The invention discloses a digital intelligent service system for enterprise services, which belongs to the field of enterprise digital services and comprises a user demand analysis module, an intelligent data adaptation module, a service resource matching module, a service efficiency evaluation module and a user-friendly interface. The user demand analysis module is used for semantic analysis and classification decision making; the intelligent data adaptation module identifies and analyzes the protocol type, and establishes an intelligent data transmission channel; the service resource matching module carries out resource pre-screening and accurate matching; the service efficiency evaluation module tracks an identifier and captures a four-dimensional index system in real time, and the dynamic evaluation unit realizes service state grading early warning through a sliding window algorithm; according to the invention, accurate demand identification is realized, the response speed and the data transmission efficiency are improved, the user satisfaction is improved, the service matching accuracy is enhanced, the resource utilization efficiency is optimized, the service capability and the customer experience are improved, and maximization of economic benefits and social values is realized.

The invention relates to the technical field of retrieval enhancement generation, in particular to a method for automatically adjusting retrieval enhancement generation parameters based on content feature modeling. The method comprises the following steps: receiving an original query text of a user, performing component analysis, identifying terminologies, general vocabularies and question entities, and quantifying to form query fingerprints; acquiring a historical behavior sequence of the user, and constructing a score reflecting the level of the user by combining the query fingerprints and adopting a time decay weighting algorithm; the user level score is converted into specific retrieval parameter configuration, and a retrieval strategy blueprint is formed; guiding document library retrieval according to the retrieval strategy blueprint, and screening out a candidate knowledge set which is most matched with the professional level of the user; and according to the user level score, a preset instruction template is intelligently filled, and a situational generation instruction is constructed. According to the method, the problem of non-uniform cognitive load caused by a traditional system is solved through a retrieval enhancement generation technology, and the technical knowledge transmission efficiency and the user satisfaction are remarkably improved.

The invention discloses a multi-elevator linkage dynamic response intelligent scheduling system and a scheduling method thereof. The scheduling method comprises the following steps: acquiring an operation rule of an elevator, constructing a historical operation database and updating the historical operation database in real time; capturing a field state in real time through a monitoring system, and generating a real-time data stream according to a time sequence; a digital twinborn model is constructed through a historical database and real-time data flow, and the elevator calling probability and the congestion risk of each floor are predicted; the elevator calling probability of each floor in the next five minutes is predicted based on a digital twinborn model, the congestion risk is calculated, a real-time demand thermodynamic diagram fusing the space-time sequence dimension is generated, and intelligent scheduling is conducted on the elevator through the thermodynamic diagram; by reducing the waiting time, the overall operation efficiency is improved, the user satisfaction is enhanced, and smoother vertical traffic experience is provided for high-rise buildings.

The invention discloses a terminal equipment interface display method and system based on user habits, and belongs to the technical field of digital display, key features such as user intention deviation degree and interface attention stability index are extracted by collecting behavior data of a user for interaction objects and function modules, and a user preference weight table is calculated and dynamically updated; interface module sorting is further carried out in combination with a deep learning model, a fuzzy logic evaluation mechanism is introduced to carry out interpretable scoring on a sorting result, when a scoring result is lower than a threshold value, the system automatically corrects a sorting strategy based on user feedback, and finally optimized interface display content is output. Personalization, dynamics and controllability of interface display are achieved, and the man-machine interaction experience and the user satisfaction degree of the terminal equipment are effectively improved.

According to the large model-based real-time voice interaction method and system provided by the invention, multiple rounds of historical dialogue data of the user are collected, the context can be deeply understood, and a subsequent strategy is adjusted according to the evolution of historical dialogue content. Through accurate construction of the dynamic context and strong semantic understanding capability of the large model, the system can better understand user intention and dialogue logic, the generated reply better conforms to human language habits, and the interaction naturalness is greatly improved. The intelligent decision of the large model is optimized based on a reinforcement learning algorithm and human feedback, so that the large model can continuously learn in real-time interaction, a reply strategy is adjusted according to user feedback and dialogue progress, and the relativity, continuity and user satisfaction of reply are improved. By setting the interruption mechanism, the interruption intention of the user can be effectively processed in the real-time voice interaction process, the effectiveness of the real-time voice interaction is ensured, and the accuracy and smoothness of the real-time voice interaction are improved.

The invention relates to the technical field of artificial intelligence and natural language processing, in particular to an intelligent customer service method and system based on a large model, and the method comprises the steps: generating a unique session ID based on a user identity, and associating a historical context; multi-modal input of texts, voices, images and the like is carried out, and data standardization is carried out through a unified interface; realizing mixed intention recognition by combining a rule engine and a large model; constructing a dynamic customer portrait through multiple rounds of dialogue records, historical work orders and business data; according to the question emergency degree and customer value grading response, analyzing customer emotion in real time, adjusting a reply style, and outputting an answer; the manual operation process of the traditional customer service is converted into an AI automatic closed loop; the method has the beneficial effects that customer intention deep understanding, multi-mode interaction, emotion perception and service process automation are realized through a large language model (LLM) technology, and the service efficiency and the user satisfaction are remarkably improved.

The embodiment of the invention relates to a reply text generation method and device, computer equipment and a storage medium. After an input text is preprocessed, a target text is obtained; acquiring context information corresponding to the target text, a first prompt word template and a first keyword; retrieving related information corresponding to the input text from a first database according to the input text, the context information, the first cue word template and the first keyword to obtain a retrieval result; generating cue words of a large language model according to the input text, the context information, the first cue word template, the first keyword and the retrieval result; and inputting the cue word into the large language model to output the reply text through the large language model. Therefore, after the input text is combined with the context information, the cue word template of the industry and the keyword to retrieve the related information, the cue word of the large language model is generated according to the retrieval information, the reply text is accurately generated through the large language model, and the question and answer accuracy and the user satisfaction degree are improved.

The invention discloses a multi-modal-based digital intelligent customer service system. Data compensation is carried out on initial multi-modal problem data by adopting a dynamic adaptive compensation mechanism through a multi-modal input module. And carrying out dynamic weight distribution on the target multi-modal problem data by adopting a cross-modal attention mechanism through a multi-modal comparison learning module. And performing intention recognition on the target multi-modal semantic vector through an intention recognition module according to the historical interaction data and a preset dynamic knowledge graph. And inputting the user intention data into the target reinforcement learning reply model through a reply generation module to construct reply data. And performing potential problem prediction by adopting the target multi-modal semantic vector, the historical interaction sequence corresponding to the user and the time data through a potential problem prediction module. And by utilizing the dynamic updating capability of the knowledge graph, the context sensitive identification of the user problem is realized, and the identification accuracy is improved. And the potential problem prediction module turns from passive response to active service, so that the interaction efficiency and the user satisfaction are remarkably improved.

The invention provides a design style intelligent recommendation and generation method and system based on user preferences, and relates to the technical field of design styles, and the method comprises the steps: constructing a user preference feature vector; analyzing a user preference evolution rule, and generating a user preference evolution curve; calculating the time sequence correlation degree between the icon design features and the user preference features, and constructing a resonance scoring matrix; designing an adaptive resonance threshold screening model based on the resonance scoring matrix; creating an initial icon design scheme by using a deep generative adversarial network; and optimizing the design parameters through transfer learning and deep reinforcement learning, and outputting a personalized icon design recommendation scheme. According to the method, intelligent recommendation and generation of icon design can be realized, and the design efficiency and the user satisfaction are improved.

The invention discloses a charging user behavior pattern analysis system and method, and relates to the technical field of electric vehicle charging management, and the method comprises the steps: obtaining and building a multi-source data pool, fusing the multi-source data pool, analyzing a charging behavior pattern of a user, calculating the abnormal behavior probability, building a dynamic scheduling rule according to the charging behavior pattern of the user, and carrying out the dynamic scheduling according to the abnormal behavior probability. According to the method, through multi-source data collection and analysis, the user charging behavior is accurately predicted, resource distribution is dynamically optimized, the charging station operation efficiency and the user satisfaction degree are improved, virtual power plant integration is promoted, and the power generation efficiency is improved. According to the method, a vehicle-to-power grid strategy optimization module is constructed, the user participation power grid peak regulation potential is quantified, regional energy scheduling is optimized, in addition, an anomaly detection and response mechanism is provided, safety and stability are ensured, and the charging service is promoted to develop towards the efficient, intelligent and sustainable direction.

The invention relates to the technical field of information processing, in particular to a supply chain cross-packet vulnerability detection method, device and equipment and a storage medium. A vulnerability packet name, a sensitive API, a trigger parameter and vulnerability description are integrated into tetrad information; if so, performing cross-packet call chain analysis on the source code file by using a cross-packet chain reachability analysis algorithm, obtaining a function call sequence of the sensitive API based on a cross-packet call chain analysis result, realizing vulnerability detection on a cross-packet call chain, generating a vulnerability verification code based on tetrad information by using a preset large language model, and performing vulnerability verification on the vulnerability verification code. The method comprises the following steps: establishing a function call sequence of a bug verification code, verifying the accessibility of the bug verification code in the function call sequence, determining the bug confidence according to the energy consumption condition of a large language model, and generating bug alarm information when the accessibility verification result is that the bug is accessible and the bug confidence is high, thereby realizing double judgment of the bug, reducing the false alarm rate of the bug and improving the user satisfaction.

The invention relates to the technical field of artificial intelligence, in particular to an AI digital human-based customer service method and system, and the method comprises the steps: receiving a voice stream, a visual stream and auxiliary sensor data inputted by a user, achieving the time-space alignment of multi-modal data through a cross-modal feature synchronization engine, and fusing the multi-modal data into a unified fusion data packet; based on the fused data packet, extracting an emotion intensity value and an emotion type code in real time, generating a dynamic emotion label, and extracting service demand characteristics to generate a demand vector; inputting the dynamic emotion label and the demand vector into a strategy decision tree, and generating a strategy identifier containing an emotion pacifying coefficient and a response emergency degree; the AI digital human is driven to generate the multi-modal response based on the strategy identifier, deep perception and flexible response to the user state can be achieved, the interaction naturalness and the user satisfaction of a digital human service system are effectively improved, and the method is suitable for multiple intelligent service scenes such as online customer service and intelligent terminal assistants.

The invention relates to an intelligent customer service self-learning method and system, and the method comprises the steps: collecting the interaction data of a user and an intelligent customer service, and forming a multi-dimensional data set; based on a PID (Proportion Integration Differentiation) controller, processing the performance indexes in the multi-dimensional data set, calculating a current error signal, and generating a corresponding control instruction according to the current error signal so as to adjust the response behavior of the intelligent customer service system in real time; evaluating the system performance data adjusted by the control instruction to obtain evaluation feedback; and according to the evaluation feedback, dynamically adjusting the parameters of the PID controller through a self-adaptive control strategy, and feeding back the adjusted parameters to the PID controller in the step S2. According to the invention, by introducing a closed-loop feedback mechanism based on the PID controller and a parameter adaptive optimization strategy, real-time regulation and control of the response behavior of the intelligent customer service system are realized, and the stability, the response speed and the user satisfaction of the system are remarkably improved.

The invention discloses a personalized recommendation method driven by user intention recognition, which comprises the following steps of: collecting multi-dimensional information such as browsing records, click behaviors and comment data of a user, and constructing a user behavior data set; preprocessing the collected user behavior data to obtain a session sequence; the current demand of the user is speculated by analyzing the input text and the behavior mode of the user, and the intention of the user is recognized; constructing a user interest preference prediction model according to the identified user intention; and in combination with real-time feedback of the user, the recommendation model is dynamically updated, and the response speed and the individuation degree of the recommendation system are improved. The problem that a traditional recommendation system only depends on static data and does not comprehensively consider real-time feedback of users is solved, self-adaptive ability is injected for personalized recommendation, intention behaviors of different users in multiple scenes can be analyzed and understood, accurate recommendation service is provided, and recommendation accuracy and user satisfaction are improved.

The invention relates to the technical field of smart home, discloses a full-life-cycle fault prediction and management method and system for smart home equipment, and aims to solve the problems of high fault rate and low operation and maintenance efficiency of the smart home equipment in the prior art. The method comprises the steps that multi-source heterogeneous data are collected and preprocessed; time domain and frequency domain features are extracted and fused to generate a comprehensive feature vector; predicting the fault probability and type by using a deep transfer learning model; a dynamic risk score is calculated through a weighted risk assessment model, and risk grades are divided; and triggering a differential response strategy according to the risk level. The system comprises a multi-source heterogeneous data sensing module, a dynamic feature extraction and fusion module, an adaptive fault prediction module, a quantitative risk assessment module, an intelligent response and decision module and a full life cycle data management module. According to the technical scheme, comprehensive and accurate monitoring, efficient fault prediction and intelligent management of the smart home equipment can be achieved, the fault rate is remarkably reduced, and the overall performance of the system and the user satisfaction degree are improved.

The invention relates to the technical field of intelligent recommendation, and discloses an AI intelligent matching method based on a knowledge graph, and the method comprises the steps: constructing a quaternary knowledge graph containing a time dimension; identifying legal entities and semantic relationships by adopting an entity identification and relationship extraction technology; multi-level semantic features are extracted through a two-layer progressive semantic matching algorithm of a grammar layer, a semantic layer and a reasoning layer; constructing lawyer ability portraits based on a heterogeneous graph neural network and a time sequence perception graph convolution technology; progressive matching calculation is adopted, the optimal matching weight is learned through a multi-layer attention mechanism, and dynamically optimized intelligent matching is achieved. The technical problems of cold start, insufficient semantic understanding ability and poor timeliness processing ability in the existing legal consultation matching system can be solved, and the matching precision and the user satisfaction are improved.

The invention discloses an online video content intelligent pushing method combined with a learning interest model. The method comprises the following steps: constructing a dynamic interest vector based on multi-source user behavior data, generating a user interest portrait vector set, and performing interest dimension clustering and weight distribution; generating a video content feature vector set according to a clustering result of the user interest portrait vector set; establishing a multi-dimensional association relationship between the user interest portrait vector set and the video content feature vector set, and outputting a user-video matching confidence matrix; converting the user-video matching confidence coefficient matrix into a push sequence based on a multi-objective optimization strategy and issuing the push sequence; and feedback behaviors of the user on the pushed video are collected in real time to realize closed-loop optimization. The method has the following advantages and effects: accurate perception and deep semantic matching of the dynamic learning interest of the user can be realized, and the accuracy, timeliness and user satisfaction of content distribution are remarkably improved, so that the learning efficiency and experience are optimized.

The invention belongs to the technical field of information management, and discloses an intelligent management system and method for large model technology government affairs, and the system comprises four layers of architectures of data collection and access, processing and storage, intelligent analysis and decision, and user interaction and application. Through federated learning and large model fusion governance data, a business process is optimized based on a knowledge graph and a large model, and intelligent service interaction is realized by applying multi-modal interaction and the large model. Experiments prove that the system and the method can significantly improve the business handling efficiency, enhance the decision accuracy, improve the user satisfaction, provide effective technical support for intelligent transformation of government affair management, and assist in improving the government service efficiency and decision scientificity.

The invention discloses an air-railway combined transportation path optimization method based on XGBoost and a space-time attention network, and particularly relates to the field of intelligent transportation systems.According to the method, a traffic network basis is constructed by integrating flight and train historical data, topological information and weather data, delay time and consumed time of a critical path are predicted by means of an XGBoost model, and the time consumption of the critical path is predicted by means of the XGBoost model; a space-time dependency relationship is modeled through a space-time attention network, and complex space-time association is captured in combination with a space and time attention module and a multi-head mechanism; an optimal path is generated based on a weighted multi-objective function (covering time, economy, reliability and comfort), and users are supported to dynamically adjust weights to adapt to personalized requirements; and meanwhile, real-time adjustment of model parameters is realized by adopting an exponential weighted moving average and self-adaptive updating strategy, so that the prediction precision is remarkably improved, the reliability of the path and the user satisfaction are optimized, the real-time performance is ensured through a lightweight closed-loop updating mechanism, and a high-precision, personalized and real-time response intelligent solution is provided for air-railway combined transportation.

The invention relates to a ship user behavior self-learning recommendation system based on a large model, and relates to the technical field of ship informatization. According to the system, through collection and fusion of multi-source heterogeneous ship user behavior data, a large-scale pre-training language model (large model) is utilized to carry out deep understanding and semantic mining on massive ship field text information and user behavior sequences, and a ship field knowledge graph or semantic vector space is constructed. The large model can identify and predict potential demands, behavior patterns and preference changes of ship users, and generates highly personalized, accurate and prospective ship service, product, route or information recommendations in combination with real-time operation data and external environment factors. Besides, a user feedback self-learning mechanism is introduced into the system, recommendation strategies and model parameters are continuously optimized according to interaction behaviors and explicit evaluation of the users in modes of reinforcement learning or continuous learning and the like, and intelligent iteration of the system and continuous improvement of the recommendation effect are achieved. According to the method, the challenges of a traditional recommendation system in the aspects of data complexity, semantic gaps and dynamic demand adaptability in the ship field are effectively solved, and the ship operation efficiency and the user satisfaction degree are remarkably improved.

The present invention provides an intelligent marketing method and system based on user portraits; first, basic information and browsing behavior data of users are collected through an authorization agreement to establish an initial user portrait. Further, by comparing the basic information in the user portrait with a pre-set similarity vector, users with similar characteristics are grouped into a similar user group and share a set of similar product tags. Finally, personalized marketing information is pushed according to the similar user group where the user belongs, and at the same time, the product tag set is dynamically adjusted and optimized according to the feedback of newly launched users to ensure the continuity and effectiveness of marketing activities. This method effectively integrates user data, optimizes marketing strategies, improves the targeting and conversion rate of advertisements, and thus significantly enhances user satisfaction and the market competitiveness of enterprises.

The invention provides an intelligent stadium operation analysis method and system based on multi-source data fusion, and the method comprises the steps: obtaining internal data, operation data and external environment data of a stadium, carrying out the cleaning and preprocessing of the multi-source data, building a distributed storage architecture, and carrying out the cleaning and preprocessing of the multi-source data; and performing multi-source data fusion analysis based on the standardized data, constructing a correlation analysis model, generating a data analysis result, executing venue operation optimization, and performing real-time monitoring and continuous optimization on the operation optimization result. According to the system, a complete closed loop of data acquisition-processing-application is constructed, the problems of inaccurate people flow statistics, low resource utilization rate, lack of data support in operation decision and the like in traditional stadium operation are solved, omnibearing intelligent management of stadium operation is realized, the stadium utilization rate is improved, the operation cost is reduced, and the user satisfaction is improved.

The invention discloses a large model task scheduling optimization method and device, and the method comprises the steps: analyzing a task type and a service quality requirement corresponding to a large model reasoning task when a scheduling request of the large model reasoning task is received; determining current state information and historical execution information corresponding to the large model reasoning task; inputting the task type, the service quality requirement, the current state information and the historical execution information into a pre-trained scheduling agent, so that the scheduling agent outputs a scheduling action corresponding to the large model reasoning task; executing a scheduling action on the large model reasoning task, and recording corresponding performance data of the scheduling action in an execution process; and inputting the performance data into the scheduling agent, so that the scheduling agent updates a weight parameter of the scheduling agent according to the performance data and a preset reward function. The problem that a traditional static scheduling strategy cannot adapt to a complex heterogeneous environment is effectively solved, and the system response efficiency, the resource utilization rate and the user satisfaction degree are remarkably improved.

The invention relates to the technical field of image processing, and provides an indoor three-dimensional image intelligent rendering method based on image processing. Comprising the following steps of indoor multi-view image acquisition, image preprocessing, intelligent analysis of indoor scene elements, construction of an indoor three-dimensional initial model with attributes, intelligent generation of rendering parameters, adaptive LOD real-time rendering and intelligent interaction optimization. According to the intelligent interaction optimization system, through deep fusion of natural language processing, user preference learning and real-time rendering technologies, a set of efficient, visual and personalized virtual scene rendering interaction process is constructed. According to the method, the problems that traditional graphic software is complex in operation, high in learning cost and low in debugging efficiency are solved, and the user satisfaction and creation efficiency are remarkably improved through an intelligent recommendation and rapid iteration mechanism.

The invention belongs to the technical field of artificial intelligence personalized services, and particularly relates to a reinforcement learning-fused user portrait dynamic construction and personalized recommendation implementation method, which comprises the following steps of: acquiring multi-dimensional user data; using the multi-dimensional user data to construct a multi-dimensional dynamic user portrait through a preset algorithm; based on the multi-dimensional dynamic user portrait, combining a collaborative filtering algorithm and a deep learning algorithm to generate a scene recommendation strategy; and monitoring user feedback and behavior data in real time, and optimizing the scenarized recommendation strategy by using the real-time monitored user feedback and behavior data. According to the method, the dynamic user portrait is constructed, scene recommendation is generated, and the strategy is optimized in real time by relying on reinforcement learning, so that the individuation degree, recommendation accuracy and user satisfaction of the service are remarkably improved, and the limitation of a traditional service mode is effectively broken through.