213 results about "Service optimization" patented technology

The invention belongs to the technical field of bandwidth access management, and particularly relates to an internet access service optimization method and system for adaptive bandwidth management. Through the distributed probe technology, network state parameters and user terminal metadata can be collected in real time, a deep learning network model such as an LSTM-Transformer hybrid neural network is utilized to process and analyze the collected data, the bandwidth requirement in a period of time in the future is predicted, time periodicity and traffic mutation characteristics are considered, and the bandwidth requirement in a period of time in the future is predicted. Equipment association characteristics are introduced, so that the prediction accuracy and reliability are improved, virtual channels are dynamically divided according to the service emergency degree and predicted bandwidth requirements, bandwidth resources are allocated to the virtual channels, it is ensured that high-priority services can obtain enough bandwidth resources in the network peak period, and the network performance is improved. Therefore, the stability and the quality of network service are ensured, and in addition, a bandwidth expansion mechanism and a bandwidth recovery strategy are introduced to cope with the dynamic change of the network bandwidth.

The invention discloses a computer system service optimization scheduling method for a photoelectric system, and particularly relates to the technical field of computer service optimization, which comprises the following steps of: sensing and extracting information such as task types and time constraints through task characteristics, and constructing a multi-dimensional resource model such as processing capability and idle degree by combining resource modeling; a weighting mechanism is used for evaluating task priorities and generating a scheduling queue, tasks are dynamically mapped to matched resources, a scheduling strategy is adjusted according to system loads and feedback, model parameters are optimized through service feedback, and efficient, self-adaptive and intelligent optimization of task scheduling of the photoelectric system is achieved; according to the method, a dynamic scheduling mechanism based on task characteristics and resource prediction is realized, and the response speed of the high-optimal task is improved; optimizing the resource utilization rate by adopting resource state modeling and prospective mapping; and reinforcement learning and a feedback closed loop are introduced, a sustainable optimization scheduling system is constructed, and the adaptability and stability of the system in a complex photoelectric task environment are enhanced.

The invention discloses an insurance customer service optimization system based on artificial intelligence, and relates to the technical field of intelligent customer service, and the system comprises a data collection and analysis module which collects the multi-mode interaction data of a customer in real time, extracts the fundamental frequency change rate and MFCC coefficient of voice voiceprint, and calculates an emotion polarity value; meanwhile, analyzing the semantic content of the text to obtain an intention classification label and an emergency degree score, and detecting the coordinates of a text missing region in the image and the micro-expression action frequency in the video stream; and the closed-loop optimization module is used for pushing an audit conclusion and the revised visual decision graph to the client, synchronously returning feedback data, and dynamically optimizing dynamic weight distribution model parameters and causal knowledge graph clause node connection weights. According to the method, accurate quantification of customer emotion and service emergency degree is realized through multi-modal data fusion and PPO dynamic weight distribution.

The invention relates to the technical field of business service dynamic optimization, in particular to a customer demand dynamic analysis and consultation service optimization platform based on deep learning, which comprises a user portrait module, an intention analysis module, a knowledge graph module, a learning engine and a recommendation module, the intention analysis module is connected with the knowledge graph module, the knowledge graph module is connected with the learning engine and the recommendation module, the learning engine is connected with the user portrait module and the recommendation module, and the recommendation module is connected with the user portrait module; according to the method, the accuracy of new user demand understanding is remarkably improved, the system can still provide accurate services in the absence of historical data through dynamic extension of the knowledge graph and an incremental learning mechanism, the problem of insufficient personalization caused by user portrait missing is thoroughly solved, and the user experience is improved. And meanwhile, the security and adaptability of data processing are ensured through multi-modal analysis and federal learning.

The invention discloses an e-commerce intelligent customer service AI dynamic duty and automatic recovery system, and relates to the technical field of e-commerce service optimization, and the system comprises the steps: calculating a problem emergency degree value based on a multi-dimensional evaluation index through a problem emergency degree judgment module, and achieving the dynamic evaluation of the priority of a problem; through a manual customer service switching module, a dynamic weight distribution mechanism is adopted to distribute problems to manual service seats corresponding to professional skills; analyzing the dialogue content of the customer service and the user in real time through a dialogue context analysis module, and generating a dialogue satisfaction curve; through an AI customer service switching module, when the satisfaction curve tends to be stable, the dialogue is handed over to the AI customer service for continuous service; and service strategy optimization is carried out based on the dialogue historical record and the knowledge base through an optimization module. According to the invention, an efficient and intelligent service mechanism is constructed from the aspects of emergency degree evaluation, manual and AI customer service collaborative service, dynamic optimization and the like, and the response efficiency and user experience of a customer service system are improved.

The invention discloses a method and a system for carrying out government affair service interaction by utilizing a large model, and relates to a government affair service optimization technology in the field of government affair. Comprising the steps of 1, directly obtaining OCR data and ASR records from existing communication records of a cloud hall, 2, carrying out RAG updating and timed fine tuning on a large model according to the OCR data and the ASR records, and 3, deploying a client based on a pc end of the cloud hall, obtaining communication information in real time through the client, and sending the communication information to the cloud hall. Wherein screen information in the government affair service handling process is recorded through screen recording of the client side, the screen information comprises key steps and an operation interface, and voice content of a client is converted into text content in real time through a voice recognition method; and 5, automatically arranging and executing a government affair handling process based on a matching result, and carrying out authenticity judgment when the certificate is involved.

The invention discloses a low earth orbit satellite edge computing service optimization method and system based on double time scales, and relates to the technical field of satellite networks and edge computing, and the method comprises the steps: obtaining a plurality of time frames and time slots, the plurality of time frames and time slots are divided based on time, and the time scales of the time frames are larger than the time scales of the time slots; dynamically adjusting satellite selection and request scheduling based on the visibility and resource state of the current satellite in each time slot; according to the method, a service deployment and migration strategy is dynamically adjusted based on long-term service requirements and resource states in each time frame, and the dynamic adjustment method is an optimization algorithm based on double time scales, so that the service quality can be improved, and the system cost can be reduced.

The invention relates to the field of large models, and provides an e-commerce intelligent customer service optimization method, a related device, a storage medium and a program product, which are used for an e-commerce customer service system and comprise a federal query engine and an intelligent customer service. The intelligent customer service integrates an event knowledge graph and a plurality of static knowledge graphs which are federated nodes; the method comprises the steps that if it is determined that a commodity query intention conforms to a multi-hop query mode based on a federated query engine, cross-knowledge-graph joint query is conducted, a first class of results based on all static knowledge graphs and a second class of results based on event knowledge graphs are obtained, and the first class of results and the second class of results are fused and then transmitted into an intelligent customer service; and the intelligent customer service generates a multi-hop reasoning chain based on the fusion result, generates an initial answer according to the combination of the multiple reasoning chains and the fusion result, adjusts the temperature parameter of each hop to enhance the initial answer according to the knowledge graph coverage rate and confidence of the fusion result and the number of reasoning hops, and obtains and outputs a target answer. According to the scheme, the expansibility and accuracy of intelligent customer service and the questioning and answering ability can be balanced.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a dynamic state portrait driven service optimization method, device and equipment and a medium. And constructing a dynamic state portrait of the individual, analyzing the state portrait to generate a state abnormality level, adjusting strategy optimization service parameters according to the state abnormality level and the service parameters, and matching knowledge contents based on the state data and the abnormality level to output guidance information. According to the method, the multi-source state data of the individual is integrated, the state portrait is dynamically constructed, and the state abnormal level is identified, so that the self-adaptive adjustment of the service parameters and the personalized matching of the knowledge content are realized, and the timeliness and pertinence of service customization are improved.

The invention provides a networking scene-oriented multipath service optimization method and system, and relates to the technical field of network scheduling optimization, and the method comprises the steps: obtaining topological structure information and service demand information of a communication network in a networking scene, and employing a depth-first search algorithm in combination with a pruning mechanism to generate a candidate path set; on the basis of a marginal value contribution degree theory, calculating a transmission value factor and a path complementary factor of each candidate path in the candidate path set, calculating marginal value contribution degrees of different candidate path combinations according to the two factors, and taking the path combination with the highest marginal value contribution degree as an optimal path combination; and aiming at each path in the optimal path combination, establishing a multi-objective optimization model, and obtaining a final scheduling scheme of the service flow among the paths in the optimal path combination. According to the invention, the problems of lack of differentiated path selection mechanism, poor fault tolerance of single-path transmission, insufficient resource coordination capability and the like in multi-service transmission in the prior art can be solved.

The invention provides a customer feedback intelligent processing and service optimization system and method. The system comprises a multi-source feedback access module, an NLP semantic analysis module, an intelligent classification matching module, a work order intelligent scheduling module, an AI reply template generation module and a closed-loop tracking management module. The method comprises the following steps: firstly, collecting a multi-channel customer feedback text through the multi-source feedback access module; performing word segmentation, sentiment analysis and entity recognition through an NLP semantic analysis module, extracting key information and determining a feedback category; the intelligent classification matching module matches the feedback to a preset service module; the work order intelligent scheduling system generates and distributes a work order according to the information; the AI reply template generation module generates a personalized reply in combination with the feedback category and the sentiment analysis result; and the closed-loop tracking management module monitors the progress of the work order, triggers AI return visit and collects evaluation after the work order is completed, and re-dispatches the work order if the work order is not satisfied so as to form a processing closed loop. According to the invention, feedback processing automation is realized, efficiency and accuracy are improved, and customer experience is optimized.

The invention discloses an entity chain store management system based on the Internet of Things, and the system comprises an Internet of Things sensing module, an intelligent analysis and decision support module, a dynamic resource scheduling module, a customer service optimization module, a safety monitoring and emergency response module, and an innovation marketing module. The Internet of Things sensing module is used for comprehensively sensing data of temperature, humidity and illumination in a chain store, positions and stock of commodities and browsing tracks and purchase records of customers. According to the entity chain store management system based on the Internet of Things, the dynamic resource scheduling module captures subtle changes of the stock quantity, the personnel state and the equipment parameters of each chain store in real time through high-frequency data acquisition once every five minutes, the limitation of data lag in traditional static scheduling is broken through, a virtual mapping model is constructed based on 1000 resource nodes, and the real-time performance of the system is improved. A local resource state of a single store is converted into a global visual digital resource network, so that a scheduling decision can cover resource pools of all chain stores.

The invention discloses a big data-based government affair service window behavior analysis system and method, and relates to the technical field of government affair service analysis. A government affair service window behavior analysis system based on big data comprises a data acquisition module, an object identification module, a behavior analysis module, a service personnel evaluation module, a feature association module and a service optimization module. A correlation analysis model and a graph neural network technology are utilized to perform multi-dimensional analysis on service features of service personnel, group features of service objects and key features of window behaviors, dynamic correlation between service behaviors and feedback behaviors is accurately identified, scores of service efficiency, service attitude, user satisfaction and the like are generated, and the service efficiency, service attitude, user satisfaction and the like are improved. And the accuracy and depth of behavior analysis are obviously improved.

The invention relates to the technical field of information, and provides a high-value power customer oriented service optimization method and equipment, and the method comprises the steps: judging a power customer feature correlation coefficient through a correlation coefficient matrix, and removing redundant features; marking high-value power customers according to the power customer feature set after dimension reduction; obtaining dynamic behavior data of the high-value power customers from the high-value customer group to obtain dynamic feature vectors of behaviors of the high-value power customers; aiming at the dynamic feature vector, the long-short-term memory network model outputs a behavior prediction result; complaint records and interaction logs of high-value power customers are obtained, and complex appeals are marked; determining a priority service object by adopting a weighted scoring method; and adopting a recommendation algorithm to generate a personalized service strategy for the priority service object. According to the method, accurate identification, behavior prediction and service optimization of high-value power customers are realized, the service quality and satisfaction of the power customers are effectively improved, and technical support is provided for fine operation and differentiated services of power enterprises.

The invention discloses a customer service optimization method and system based on generative artificial intelligence, and relates to the technical field of artificial intelligence, and the method comprises the steps: reading the retention parcel attribute and retention duration, and setting a reminding short message sending frequency and configuring a sending time zone in combination with the site load and the historical average pickup duration of a user; retrieving a sample data set from a parcel operation database based on the user portrait and a preset parcel taking association factor; training a generative artificial intelligence model by using the sample data, and constructing a pickup probability predictor; and in the short message sending time zone, a predictor is used for optimizing and determining an optimal time node corresponding to the maximum predicted pickup probability, and a reminding short message is sent to a user. Therefore, the technical effects of accurate reminding, improvement of processing efficiency and improvement of user experience are achieved.

The invention discloses a cross-platform member unified management and service optimization system. A data fusion processing module breaks a data island, fuses multi-platform member data, and constructs a complete member portrait; the member value evaluation module comprehensively and accurately evaluates the member value by using a member value evaluation formula based on the comprehensive data, insights the contribution and potential of the member value, and provides a basis for a marketing strategy; the member layering module divides levels according to values and dynamic thresholds, enterprises can formulate personalized management strategies accordingly, resources are reasonably distributed, and the management efficiency and the member satisfaction degree are improved; the service recommendation module calculates and recommends personalized services according to a matching degree formula in combination with the hierarchy and historical behavior data; all the modules are tightly matched, a complete closed loop is formed from data integration, value evaluation, hierarchical division and service recommendation, the member experience is effectively improved, and the recognition sense and stickiness of members to enterprises are enhanced.

The present disclosure relates to a service providing system and method for supporting service optimization operation maintenance and decision-making. In more detail, the present disclosure relates to a service providing system and method for supporting service optimization operation maintenance and decision-making, the system and method being able to create prediction information about the usage and capacity of each of resources optimized through an optimization algorithm on the basis of current status-related status information about the usage and capacity of each of resources that are invested into a service when using an IT service (information communication service), being able to support decision-making for service optimization by providing a result of an optimal service driving environment considering an economic feasibility through comparison analysis using the status information and the prediction information, and being able to support automation of such service optimization.

The invention provides an industrial edge network micro-service optimization method based on dynamic arrangement and migration expansion, which comprises the following steps: abstracting an industrial edge network into an intelligent industrial network model formed by heterogeneous edge nodes and links, modeling an industrial application request into a request chain formed by combining a plurality of micro-services with a data dependency relationship in sequence, calculating a micro-service instance deployment scheme and a request routing scheme; counting a time-varying request stream, analyzing the minimum core number meeting the time delay constraint in a statistical result by using a multivariate performance analysis model based on an m / m / c queue network and a binary search algorithm, and carrying out dynamic expansion and contraction adjustment on core resources of deployed micro-service instances; and solving a mixed integer nonlinear programming migration decision problem according to the initial dynamic scaling adjustment result and the migration cost so as to optimize the optimal collaborative deployment and request routing of the micro-service instance between the edge nodes. According to the invention, the service continuity and the overall energy efficiency of the industrial edge network system are improved.

The invention discloses an intelligent system for customer service quality inspection based on multi-source data, and particularly relates to the technical field of customer service quality inspection. The method comprises the following steps: acquiring session texts generated in a customer service process and associated product purchase and consumption data in a customer account in real time, and performing cleaning and standardization processing; a large-model automatic marking algorithm is constructed to carry out category marking on customer problems, and recognition of problem backgrounds and customer appeals is realized through context correlation analysis; performing double evaluation on customer attitude and customer service quality by using an emotion analysis model and a customer service verbal skill analysis model; and generating a comprehensive evaluation result of the overall quality of the customer service through fusion analysis, finally predicting a customer conversion rate and a contract extension rate based on the overall quality evaluation result, and generating a targeted customer service optimization strategy, thereby realizing accurate evaluation of the customer service quality and intelligent management of the customer relationship.

The invention provides a customer service optimization method based on computing power of an intelligent computing center and a related device. The customer service optimization method comprises the following steps: S1, receiving consultation information sent by a user through an interaction end; s2, in response to the consultation information, calling a target GPT-Neo large language model deployed in an intelligent computing center to extract key information and emotion information in the consultation information; s3, generating a plurality of to-be-selected reply texts according to the key information, determining a text from the plurality of to-be-selected reply texts as a target reply text according to the emotion information, and sending the target reply text to the interaction end; the obtained target reply text can accurately match the actual consultation demand of the user; the target reply text can be matched with the actual emotion when the user puts forward the consultation, so that the consultation experience of the user is effectively improved; and reasoning of the target GPT-Neo large language model is realized by adopting the abundant computing power of the intelligent computing center, so that the consultation experience of the user is improved.

The invention relates to the technical field of marketing, and particularly discloses a service optimization method and system based on combination of online marketing and offline drainage. By acquiring online marketing and offline service multi-dimensional data in real time, constructing a quantitative evaluation system and dynamically optimizing service collaboration, the method comprises the following steps: firstly, acquiring original data from a user behavior log, an activity configuration library and an offline business system, covering core information such as a user identifier, an activity identifier, a service network state and the like; sequentially calculating a marketing load coefficient, a drainage congestion coefficient, an online marketing behavior coefficient and an offline service bearing coefficient, finally carrying out weighted fusion on the online and offline coefficients to generate a comprehensive service coefficient, verifying an over-limit state by adopting a synchronous non-blocking mechanism and a dynamic threshold value, predicting a resource demand increment in combination with a time sequence, generating a coordination strategy set, and carrying out resource scheduling. Accurate adaptation of online drainage and offline service is realized, the experience is improved, and the system risk is reduced.

The invention provides a smart city-oriented power supply service optimization method and device. The method comprises the steps of 1, preprocessing multi-modal data; step 2, carrying out cross-modal feature fusion; 3, dynamically predicting the power consumption; and step 4, power supply strategy optimization. According to the method, through multi-modal data fusion and dynamic user behavior modeling, the bottlenecks of high data isomerism, insufficient cross-domain collaboration, difficulty in random behavior quantification and the like in a traditional method are overcome. According to the method, multi-source heterogeneous data such as power sensor data, policy texts and meteorological information are deeply fused, a time sequence prediction model and user behavior probability analysis of a non-homogeneous Markov chain are combined, a cross-domain collaborative intelligent optimization framework is constructed, comprehensive perception and accurate prediction of power supply data in a power system link are realized, and the power supply efficiency is improved. The prediction model is used to predict and adjust the power consumption demand, the distribution and balance of the power consumption load are optimized, and the power consumption service quality and the customer satisfaction are improved.

The invention discloses a user feedback text emotion recognition method for venue service optimization. The method comprises the steps of 1, collecting data based on online comment information of venue users; 2, carrying out data preprocessing on the collected original data, and carrying out dynamic elimination or weight adjustment on the processed data based on a sample credibility scoring model; 3, performing emotion label assignment on the preprocessed text data to perform data emotion labeling by adopting an automatic labeling process based on combination of an emotion dictionary and a rule algorithm; and 4, based on the semantic features and context structure information of the text data, constructing an ESBA emotion recognition model fusing a pre-training language model ERNIE, a scene perception emotion hierarchical coding mechanism, a bidirectional long-short term memory network BiLSTM and an attention mechanism, and inputting a text sequence into the ESBA emotion recognition model to realize multi-category emotion recognition.

The invention provides a smart campus task collaboration method and system oriented to multi-group service optimization, and relates to the technical field of campus service management. According to the method, historical service logs are called, and storage nodes are distributed according to a service process to generate data sets before and after collaboration; determining a group cooperation state based on the data set, and constructing an exclusive task measurement set and a group behavior feature set; quantifying a cross-group task cooperation priority through a double-evaluation mode mark; generating a group-task collaborative set in combination with iterative operation, and screening and optimizing by using a segmentation coefficient (cohesion + separation degree); the system correspondingly comprises a data acquisition and storage module, a task and feature construction module, a collaborative priority quantification module and a collaborative adaptation analysis and optimization module. According to the method, the problems of lack of precise adaptation, fuzzy priority quantization and the like in multi-group coordination in the prior art are solved, directional optimal configuration of service resources is realized, task coordination efficiency and group satisfaction are improved, and an efficient solution is provided for multi-group differentiated services of the smart campus.

The invention discloses a computing service optimization method for a machine learning task, and particularly relates to the technical field of distributed computing, and the method comprises the steps: collecting multi-dimensional behavior data of a training terminal, constructing an original data set, generating a delay offset index and a training deviation index, and judging whether to trigger a disturbance level evaluation process or not. The method comprises the following steps of: acquiring an influence evaluation model, inputting the influence evaluation model to generate a multi-level disturbance level, executing matching behaviors such as interpolation compensation, reconnection recovery or task priority adjustment according to a level result, realizing accurate identification and dynamic response to upload failure or abnormal training, and improving the stability of model aggregation and the adaptability of calculation service; according to the method, pre-recognition of uploading and training disturbance is achieved by constructing a double-index evaluation mechanism, the model aggregation stability is improved in combination with a multi-stage response strategy, the evaluation model is dynamically selected according to behavior time sequence characteristics, evaluation precision and execution efficiency are both considered, and the method is suitable for large-scale popularization and application. And the adaptability and robustness of the computing service in a complex terminal machine learning task environment are enhanced.

The invention discloses a multi-user video transmission fairness improvement method NetABR based on double-layer optimization. According to the method, a multi-agent adaptive bit rate (ABR) algorithm framework aiming at different terminal devices is provided, and the service quality of different users is optimized in a targeted manner by deploying an ABR module with a device sensing capability at a client. Besides, the optimization of global fairness is realized by introducing a bandwidth allocation module, and a training architecture based on a double-layer optimization model is provided, so that the optimization effect is remarkably improved. According to the method, the ABR module with the equipment perception capability and the training architecture based on the double-layer optimization model are successfully combined, the optimization effect of global fairness is improved while fine-grained service quality optimization is achieved, and high robustness is shown in different network scenes.

An omni-channel member integration service system relates to the field of information management systems and comprises a multi-source data acquisition module, a data cleaning and standardization module, a member data integration and storage module, a member right and interest unified management module, a personalized marketing and service recommendation module and a cross-channel service collaboration module. According to the method, the members are uniformly collected into a system which is powerful in function and easy to operate, so that an enterprise can clearly insight into complete information of the members from a global perspective, including but not limited to consumption habits, purchase frequency, preference categories and the like, and comprehensively grasp portraits of the members, and meanwhile, the system intelligently identifies and clears repeated data, so that the efficiency of the enterprise is improved. By means of the method, manual repeated input and check work is avoided, the work process is optimized, the overall efficiency of enterprise member management work is remarkably improved, and an enterprise can put more energy into targeted member service optimization and marketing activity planning.

The invention belongs to the technical field of intelligent traffic Internet of Vehicles, and discloses an Internet of Vehicles big data real-time monitoring and user service optimization platform for an intelligent traffic system, and the platform comprises a preprocessing unit which carries out the real-time denoising of collected data, unifies the format, and extracts core semantic features. Realizing cross-node semantic feature encryption sharing by relying on a federated learning framework, completing semantic consistency verification by combining a traffic scene knowledge graph, and eliminating conflict abnormal data; the transmission unit identifies the data causal correlation degree based on 5G network slices, and high-correlation data is transmitted through low-delay slices, so that the data correlation is guaranteed; the data fusion unit can dynamically adjust the weight according to the traffic event type, for example, the data weight of the laser radar is improved in an accident scene, high-precision timestamps and dual-mode positioning calibration space-time migration are matched, and finally cross-modal data accurate fusion is achieved; the causal inference unit deploys a lightweight causal Markov model at a roadside edge terminal, and quickly locates traffic anomaly core inducements.

The invention provides a multi-modal map data service method and device, computer equipment and a medium, and belongs to the field of map service optimizing.The method comprises the steps that by analyzing service metadata of multiple types of map services, corresponding first attribute fields are extracted from the multiple types of map services according to the OGC standard; matching a second attribute field of a request message input by a user with the first attribute field to generate a service calling link conforming to an OGC standard, distributing the service calling link in combination with a load balancing strategy, processing the service calling link by adopting a differentiated loading strategy according to different service types, and returning a processing result to the user; and capturing the operation of the user on the service data in real time, identifying the service type, analyzing the modified content, and carrying out data updating on the difference part. Thus, under the condition that the cost is not increased, management and access optimization of the multi-modal map data are completed, and various high concurrency problems existing under the condition of various map services can be solved.

The invention discloses a platform passenger flow arrival generation and service efficiency evaluation method based on travel trajectory data, and relates to the technical field of urban rail transit passenger flow safety monitoring and organization. Comprising the following steps: constructing a data-driven tag identification model based on passenger travel trajectory data, and marking feature tags for passengers; passenger portraits are generated based on the passenger travel trajectory data with the feature tags, and a passenger travel preference portrait dictionary is constructed; based on the passenger feature tags and the travel preference portrait dictionary, constructing a passenger portrait tag identification model, and adopting a Gaussian mixture model to train and calibrate the passenger portrait tag identification model; a Monte Carlo method is utilized to simulate a mode that all passengers arrive at a platform, and each passenger generates a plurality of parallel samples; and according to a queuing theory, constructing a dynamic queuing model fusing the mixed flow and calculating a service performance index. According to the method, the average waiting time, the queuing length and the service utilization rate of different time periods can be accurately evaluated, and an accurate and efficient tool is provided for urban rail transit passenger flow management and service optimization.