Smart tourism service platform based on big data

Abstract

The invention discloses a smart tourism service platform based on big data, and relates to the technical field of smart tourism, and the system comprises a data collection and preprocessing module, a risk prediction and analysis module, a travel change suggestion and generation module, and a compensation scheme execution and feedback module. The data acquisition and preprocessing module is responsible for acquiring tourism-related data from a plurality of data sources in real time and cleaning, integrating and preprocessing the acquired data, the risk prediction and analysis module is used for analyzing various tourism-related data in real time, unpredictable factors influencing the travel itinerary are effectively predicted, and the risk of the travel itinerary is effectively predicted. According to the method and the system, a plurality of travel route change suggestions are automatically generated for tourists to select on the basis of the prediction results, so that the flexibility of the travel route is greatly improved, and meanwhile, through timely risk early warning and travel route adjustment, the travel risk caused by force majeure factors is effectively reduced, and the sense of safety of the tourists is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of smart tourism technology, and in particular to a smart tourism service platform based on big data. Background Art

[0002] With the vigorous development of the tourism industry, tourists' demands for travel experience are becoming increasingly diversified and personalized. At the same time, the rapid advancement of science and technology, especially the widespread application of big data and artificial intelligence technologies, has provided a strong impetus for the intelligent transformation of the tourism industry. In the field of smart tourism technology, the use of big data analysis and machine learning technologies to predict unforeseen factors and provide customized services to tourists based on this has become an important trend to improve the quality of tourism services and enhance the tourist experience.

[0003] Traditional travel itinerary management systems often have significant limitations when dealing with unforeseen factors. On the one hand, in terms of risk prediction and analysis, traditional methods rely on manual experience and judgment, lack big data support and intelligent analysis methods, resulting in inaccurate prediction results and slow response speed, which not only increases the uncertainty of travel itineraries, but also brings unnecessary risks and losses to tourists. On the other hand, in terms of itinerary changes and compensation services, traditional methods often rely on manual operations, which are not only cumbersome and time-consuming, but also prone to unfair compensation or omissions due to human factors, making it difficult to fully protect the rights and interests and satisfaction of tourists. In addition, traditional systems lack flexibility and intelligence, and it is difficult to provide personalized itinerary change suggestions and compensation plans based on the specific needs and preferences of tourists.

[0004] In response to the above problems, it is necessary to optimize the existing travel itinerary management system by integrating multiple data sources and using big data analysis and machine learning technology to achieve accurate prediction and rapid response to unforeseen factors. At the same time, combined with tourists' travel plans and preferences, personalized itinerary change suggestions and flexible compensation plans can be automatically generated. Therefore, it is of great significance to develop a big data-based smart tourism service platform that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a smart tourism service platform based on big data. It can integrate multiple data sources, use big data analysis and machine learning technology, achieve accurate prediction and rapid response to unforeseen factors, and combine tourists' travel plans and preferences to automatically generate a variety of itinerary change suggestions, providing tourists with convenient and efficient decision-making support.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart tourism service platform based on big data, the system comprising: a data collection and preprocessing module, a risk prediction and analysis module, an itinerary change suggestion and generation module and a compensation plan execution and feedback module;

[0007] The data collection and preprocessing module is responsible for collecting tourism-related data from multiple data sources in real time, and cleaning, integrating and preprocessing the collected data;

[0008] The risk prediction and analysis module uses big data analysis and machine learning algorithms to conduct in-depth mining and correlation analysis on pre-processed data, predict unforeseen factors that affect travel itineraries, including weather changes, natural disasters and traffic disruptions, and assess their impact and probability;

[0009] The itinerary change suggestion and generation module automatically generates a variety of itinerary change suggestions based on the results of the risk prediction and analysis module and in combination with the tourists' travel plans and preferences;

[0010] The compensation plan execution and feedback module automatically communicates and exchanges data with the partner after the tourist confirms the itinerary change, and generates and executes the adjustment plan based on the partner's policy and the tourist's original booking information.

[0011] Furthermore, the data collection and preprocessing module clearly defines the types of data that need to be collected, including but not limited to weather forecasts, traffic conditions, scenic spot opening conditions, social media public opinion and tourists' personal itinerary plans. Through API interfaces, crawler technology and data sharing protocols, data is collected from various data sources in real time, duplicate, erroneous and incomplete data items are removed, the data is formatted, and the cleaned data is integrated into a unified data format according to certain rules and stored in the database.

[0012] Furthermore, the risk prediction and analysis module extracts features useful for risk prediction from the original data, including weather type, wind level, road congestion index and scenic spot crowd density, trains the extracted features using machine learning algorithms, builds a risk prediction model and uses cross-validation technology to evaluate the performance of the model configuration, inputs real-time data into the trained model, predicts unforeseen factors that may occur in the future and their degree of impact, and based on the prediction results, evaluates the potential impact of different factors on the travel itinerary to determine the risk level and priority.

[0013] Furthermore, the risk prediction and analysis module uses a chi-square test algorithm to extract features from the original data, and the calculation formula is: Among them, X 2 is the chi-square statistic, used to quantify the observed frequency O i and the expected frequency E iThe difference between them, k is the number of categories, O i is the observed frequency of the ith category, that is, the actual observed data, E i is the expected frequency of the ith category. According to the value of the chi-square statistic, the features with a strong correlation with the target variable are selected as the final extracted feature set.

[0014] Furthermore, the specific steps of the risk prediction and analysis module using the training data set to train the machine learning model are:

[0015] (1) Obtaining the preprocessed data after cleaning, denoising, and normalization from the data acquisition and preprocessing module, and dividing the preprocessed data into a training set, a validation set, and a test set;

[0016] (2) Use the training set data to train the selected machine learning model. During the training process, the model learns the patterns in the data and adjusts its internal parameters;

[0017] (3) Use the validation set to evaluate the trained model, check its generalization ability, and adjust the model parameters based on the evaluation results;

[0018] (4) Use the test set to evaluate the final performance of the model. Based on the evaluation results, tune the model, use cross-validation techniques to evaluate the performance of different model configurations, and select the optimal model configuration.

[0019] (5) Deploy the trained model to the intelligent analysis and prediction module to process new data in real time and generate prediction results.

[0020] Furthermore, the risk prediction and analysis module uses a support vector machine algorithm to build a model for risk prediction, and its calculation formula is: Among them, f(x) is the prediction result of the input feature vector x, sign is the sign function used to determine the category of the prediction result, and α i is the Lagrange multiplier, y i is the training sample x i The label of K(x i ,x) is the kernel function, which predicts the unforeseen factors that affect the travel itinerary based on the prediction result f(x) and evaluates their impact degree and probability.

[0021] Furthermore, the itinerary change suggestion and generation module analyzes tourists' itinerary preferences according to their historical behaviors, personal preferences and travel purpose information, and automatically generates a variety of feasible itinerary change plans based on risk prediction results and tourists' preferences, evaluates the generated change plans, removes unreasonable and unfeasible plans, optimizes and adjusts the plans, and presents the optimized change plans to tourists.

[0022] Furthermore, the specific steps of the itinerary change suggestion and generation module evaluating the generated change plan are:

[0023] (1) Evaluate the relationship between the cost, time and comfort required for the change and the losses saved or avoided by tourists;

[0024] (2) Analyze tourists’ potential acceptance and preference for itinerary changes based on their historical behavior, personal preferences, and travel purpose information, and communicate with partners to understand their opinions and suggestions on the change plan;

[0025] (3) Based on the evaluation indicators, use a greedy algorithm to quantify and score or rate each change plan, compare and analyze different change plans, find out their respective advantages and disadvantages and applicable scenarios, and evaluate the impact of different factors on the effect of the change plan;

[0026] Based on the evaluation results and comparative analysis, the initially generated change plan is optimized and adjusted, and the change plan that best suits tourists' needs is selected for implementation.

[0027] Furthermore, the itinerary change suggestion and generation module uses a greedy algorithm to quantitatively score or rate each change plan, and its calculation formula is: Score(x)=α·Cost(x)+β·TimeEfficiency(x)+γ·Comfort(x)+δ·Satisfaction(x), where x represents an itinerary change plan, Score(x) represents the evaluation score of the plan, and α, β, γ, and δ are weight coefficients of each evaluation indicator.

[0028] Furthermore, the compensation plan execution and feedback module queries the applicable compensation terms and conditions based on the original booking information of the tourists and the compensation policy of the partners, automatically generates a compensation plan for the tourists based on the risk prediction results and the compensation policy, communicates and exchanges data with the partners, and executes the compensation plan. At the same time, it collects tourists' feedback on itinerary changes and compensation plans through questionnaires and online evaluations, analyzes the collected feedback, identifies deficiencies and improvement points in the service, and uses them to optimize system algorithms and service processes.

[0029] Compared with the existing technology, this smart tourism service platform based on big data has the following beneficial effects:

[0030] 1. The present invention analyzes various tourism-related data in real time through the risk prediction and analysis module, effectively predicts the unforeseen factors that affect the travel itinerary, and automatically generates a variety of itinerary change suggestions based on these prediction results for tourists to choose from, thereby greatly improving the flexibility of the travel itinerary. At the same time, through timely risk warnings and itinerary adjustments, it effectively reduces the travel risks caused by force majeure factors and enhances the sense of security of tourists.

[0031] 2. After the tourists confirm the itinerary change, the present invention automatically communicates and exchanges data with partners through the compensation plan execution and feedback module to generate and execute flexible compensation or adjustment plans to ensure the rights and interests of tourists. At the same time, by collecting tourists' feedback on itinerary changes and compensation plans, the system algorithm and service process are continuously optimized to further improve tourists' satisfaction and service quality.

[0032] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 This is a process operation diagram of a smart tourism service platform based on big data.

[0035] Figure 2 This is a flow chart of a smart tourism service platform based on big data. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Example 1

[0038] This embodiment describes in detail a specific application of risk prediction and analysis using big data analysis and machine learning algorithms on a smart tourism service platform based on big data.

[0039] The system uses the data collection and preprocessing module to collect key tourism-related data in real time from a variety of data sources, including but not limited to meteorological stations, transportation departments, social media, and travel websites and apps. The system performs preliminary cleaning on the collected raw data to remove duplicate, erroneous or invalid data entries, for example, abnormal weather data caused by equipment failure and social media noise information that is not directly related to tourism. The cleaned data is integrated according to a unified format and standard to ensure data consistency and integrity. The integrated data is preprocessed, such as data standardization and normalization, to facilitate subsequent algorithm processing and analysis.

[0040] The intelligent analysis and prediction module uses the chi-square test algorithm to extract features from the original data. The calculation formula is: Among them, X 2 is the chi-square statistic, used to quantify the observed frequency O i and the expected frequency E i The difference between them, k is the number of categories, O i is the observed frequency of the ith category, that is, the actual observed data, E i is the expected frequency of the i-th category. According to the value of the chi-square statistic, the features with a strong correlation with the target variable are selected as the final extracted feature set. The selected machine learning model is trained using historical data. The specific training steps are:

[0041] (1) Obtaining the preprocessed data after cleaning, denoising, and normalization from the data acquisition and preprocessing module, and dividing the preprocessed data into a training set, a validation set, and a test set;

[0042] (2) Use the training set data to train the selected machine learning model. During the training process, the model learns the patterns in the data and adjusts its internal parameters;

[0043] (3) Use the validation set to evaluate the trained model, check its generalization ability, and adjust the model parameters based on the evaluation results;

[0044] (4) Use the test set to evaluate the final performance of the model. Based on the evaluation results, tune the model, use cross-validation techniques to evaluate the performance of different model configurations, and select the optimal model configuration.

[0045] (5) Deploy the trained model to the intelligent analysis and prediction module to process new data in real time and generate prediction results.

[0046] The preprocessed data is fed into the trained machine learning model for deep mining and association analysis. The calculation formula is: Among them, f(x) is the prediction result of the input feature vector x, sign is the sign function used to determine the category of the prediction result, and α i is the Lagrange multiplier, y i is the training sample x i The label of K(x i ,x) is the kernel function. According to the prediction result f(x), the unforeseen factors that will occur in the future and their impact are predicted. The system may also combine historical data and expert knowledge base to calibrate and verify the prediction results to improve the accuracy of risk assessment.

[0047] The intelligent analysis and prediction module outputs the prediction results and risk assessment reports in a visual form, including weather forecasts, traffic conditions and scenic spot flow estimates for the next few days. The prediction results and risk assessment reports are transmitted in real time to the itinerary change suggestion and generation module as the data basis for the subsequent generation of itinerary change suggestions. At the same time, data docking with partners is carried out to ensure timely sharing and collaborative processing of information. The system continuously optimizes the algorithms and parameter settings of the machine learning model based on feedback and effect evaluation in actual applications to improve prediction accuracy and efficiency. At the same time, feedback from tourists on itinerary change suggestions and compensation plans is collected to further optimize the system algorithm and service processes.

[0048] Example 2

[0049] The system consists of the following components:

[0050] This embodiment describes in detail a specific application of itinerary change and compensation plan execution of a smart tourism service platform based on big data.

[0051] The itinerary change suggestion and generation module first establishes a data interface with the intelligent analysis and prediction module to receive prediction results and risk assessment reports in real time. These data include but are not limited to weather change forecasts, traffic condition forecasts, scenic spot passenger flow estimates, and corresponding risk assessment reports. The system parses the received prediction results and risk assessment reports and extracts key information, such as the affected time period, location, degree of impact, etc., to provide basic data for subsequent analysis.

[0052] According to the prediction results and the tourist preference model, the system formulates an itinerary change strategy. Factors considered in the strategy-making process include but are not limited to risk factors, tourist preferences, travel time limits, and transportation resources. Based on the formulated strategy, the system automatically generates a variety of feasible itinerary change plans. Each plan details the changed itinerary arrangements, including the choice of alternative scenic spots, the adjustment of transportation methods, and the re-planning of activity times. When generating change plans, the system fully considers the personalized needs of tourists, such as special dietary requirements, physical conditions, and family member composition, to ensure that the generated plan not only meets the preferences of tourists, but is also operational and comfortable.

[0053] The system evaluates the rationality of the generated change plan and checks whether the plan has logical errors, time conflicts or insufficient resources. For unreasonable plans, the system will automatically eliminate or adjust them. On the basis of retaining reasonable plans, the system further optimizes the plans. The optimization process includes adjusting the itinerary sequence to reduce distance waste, optimizing traffic routes to shorten travel time, and adding special activities to enhance travel experience. Finally, the system conducts a comprehensive evaluation of the optimized change plan and uses a greedy algorithm to quantitatively score or rate each change plan. The calculation formula is: Score(x)=α·Cost(x)+β·TimeEfficiency(x)+γ·Comfort(x)+δ·Satisfaction(x), where x represents an itinerary change plan, Score(x) represents the evaluation score of the plan, α, β, γ, δ are the weight coefficients of each evaluation indicator, and the advantages and disadvantages of each plan are compared to recommend the best plan for tourists.

[0054] The system will present the optimized change plan to tourists through a user-friendly interface. The display content includes the detailed itinerary of the plan, comparison charts before and after the change, and recommended reasons. Tourists can view multiple change plans on the interface and compare them. When tourists choose a plan, the system provides detailed change instructions and recommended reasons to help tourists make more informed decisions. At the same time, the system also allows tourists to fine-tune the plan according to their own needs or make customized demands. After the tourists confirm the selection of the plan, the system automatically generates the changed itinerary order and notifies the relevant service providers to prepare for subsequent services. At the same time, the system also sends itinerary change notifications and precautions reminders to tourists.

[0055] Example 3

[0056] The steps of the system based on Example 1 and Example 2 are as follows:

[0057] (1) Registration and Login: Visitors who use this system for the first time need to register and fill in their basic personal information. After successful registration, visitors log in to the system using the account and password they filled in during registration;

[0058] (2) Itinerary planning and entry: After logging in, tourists can create a new travel itinerary in the system, enter the itinerary's starting time, destination, major attractions, and accommodation information. When creating or editing an itinerary, tourists can set their own travel preferences so that the system can generate itinerary change suggestions more accurately;

[0059] (3) Data collection and preprocessing: The system collects tourism-related data from multiple data sources in real time and cleans, integrates and preprocesses them to ensure the accuracy of subsequent analysis and prediction;

[0060] (4) Risk prediction and itinerary change suggestions: The system uses big data analysis and machine learning algorithms to conduct in-depth mining and correlation analysis on pre-processed data, predict unforeseen factors that may affect the travel itinerary, and evaluate their impact and probability. Based on the prediction results and the tourists' travel plans and preferences, the system automatically generates a variety of itinerary change suggestions and displays them to tourists through the user interface. Tourists can view the details of each change suggestion, including the changed itinerary and the reasons for the recommendation;

[0061] (5) Selecting a change plan: Visitors can compare different change plans on the interface provided by the system and select the most appropriate plan based on their needs and preferences. After selecting a change plan, visitors click the confirmation button, and the system will start executing the subsequent compensation plan execution process;

[0062] (6) Compensation plan execution and feedback: After confirming the itinerary change with the tourist, the system will automatically communicate and exchange data with the partner, generate and execute a flexible compensation or adjustment plan based on the partner's policy and the tourist's original booking information. At the same time, the system will also collect tourists' feedback on itinerary changes and compensation plans to optimize system algorithms and service processes and continuously improve user experience;

[0063] (7) Itinerary continuation and follow-up services: After the change plan is implemented, tourists can continue their travel activities according to the new itinerary. The system will keep an eye on tourists throughout the travel process and provide necessary follow-up service support.

[0064] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A smart tourism service platform based on big data, It is characterized in that The system includes: data collection and preprocessing module, risk prediction and analysis module, itinerary change suggestion and generation module and compensation plan execution and feedback module; The data collection and preprocessing module is responsible for collecting tourism-related data from multiple data sources in real time, and cleaning, integrating and preprocessing the collected data; The risk prediction and analysis module uses big data analysis and machine learning algorithms to conduct in-depth mining and correlation analysis on pre-processed data, predict unforeseen factors that affect travel itineraries, including weather changes, natural disasters and traffic disruptions, and assess their impact and probability; The itinerary change suggestion and generation module automatically generates a variety of itinerary change suggestions based on the results of the risk prediction and analysis module and in combination with the tourists' travel plans and preferences; The compensation plan execution and feedback module automatically communicates and exchanges data with the partner after the tourist confirms the itinerary change, and generates and executes the adjustment plan based on the partner's policy and the tourist's original booking information.

2. According to the big data-based smart tourism service platform of claim 1, It is characterized in that The data collection and preprocessing module specifies the types of data that need to be collected, including but not limited to weather forecasts, traffic conditions, scenic spot opening conditions, social media public opinion and tourists' personal itinerary plans. It collects data from various data sources in real time through API interfaces, crawler technology and data sharing protocols, removes duplicate, erroneous and incomplete data items, formats the data, and integrates the cleaned data into a unified data format according to certain rules and stores it in the database.

3. According to the big data-based smart tourism service platform of claim 1, It is characterized in that The risk prediction and analysis module extracts features useful for risk prediction from the original data, including weather type, wind level, road congestion index and scenic spot crowd density, uses machine learning algorithms to train the extracted features, builds a risk prediction model and uses cross-validation technology to evaluate the performance of the model configuration, inputs real-time data into the trained model, predicts unforeseen factors that may occur in the future and their impact, and based on the prediction results, evaluates the potential impact of different factors on the travel itinerary and determines the risk level and priority.

4. According to the big data-based smart tourism service platform of claim 3, It is characterized in that The risk prediction and analysis module uses the chi-square test algorithm to extract features from the original data, and its calculation formula is: Among them, X 2 is the chi-square statistic, used to quantify the observed frequency O i and the expected frequency E i The difference between them, k is the number of categories, O i is the observed frequency of the ith category, that is, the actual observed data, E i is the expected frequency of the ith category. According to the value of the chi-square statistic, the features with a strong correlation with the target variable are selected as the final extracted feature set.

5. According to the big data-based smart tourism service platform of claim 3, It is characterized in that The specific steps of the risk prediction and analysis module using the training data set to train the machine learning model are: (1) Obtaining the preprocessed data after cleaning, denoising, and normalization from the data acquisition and preprocessing module, and dividing the preprocessed data into a training set, a validation set, and a test set; (2) Use the training set data to train the selected machine learning model. During the training process, the model learns the patterns in the data and adjusts its internal parameters; (3) Use the validation set to evaluate the trained model, check its generalization ability, and adjust the model parameters based on the evaluation results; (4) Use the test set to evaluate the final performance of the model. Based on the evaluation results, tune the model, use cross-validation techniques to evaluate the performance of different model configurations, and select the optimal model configuration. (5) Deploy the trained model to the intelligent analysis and prediction module to process new data in real time and generate prediction results.

6. According to the big data-based smart tourism service platform of claim 3, It is characterized in that The risk prediction and analysis module uses the support vector machine algorithm to build a model for risk prediction, and its calculation formula is: Among them, f(x) is the prediction result of the input feature vector x, sign is the sign function used to determine the category of the prediction result, and α i is the Lagrange multiplier, y i is the training sample x i The label of K(x i ,x) is the kernel function, which predicts the unforeseen factors that affect the travel itinerary based on the prediction result f(x) and evaluates their impact degree and probability.

7. According to the big data-based smart tourism service platform of claim 1, It is characterized in that The itinerary change suggestion and generation module analyzes tourists' itinerary preferences according to their historical behaviors, personal preferences and travel purpose information, automatically generates a variety of feasible itinerary change plans based on risk prediction results and tourists' preferences, evaluates the generated change plans, removes unreasonable and unfeasible plans, optimizes and adjusts the plans, and presents the optimized change plans to tourists.

8. According to the big data-based smart tourism service platform of claim 7, It is characterized in that The specific steps of the itinerary change suggestion and generation module to evaluate the generated change plan are: (1) Evaluate the relationship between the cost, time and comfort required for the change and the losses saved or avoided by tourists; (2) Analyze tourists’ potential acceptance and preference for itinerary changes based on their historical behavior, personal preferences, and travel purpose information, and communicate with partners to understand their opinions and suggestions on the change plan; (3) Based on the evaluation indicators, use a greedy algorithm to quantify and score or rate each change plan, compare and analyze different change plans, find out their respective advantages and disadvantages and applicable scenarios, and evaluate the impact of different factors on the effect of the change plan; (4) Based on the evaluation results and comparative analysis, the initially generated change plan is optimized and adjusted, and the change plan that best suits the needs of tourists is selected for implementation.

9. According to the big data-based smart tourism service platform of claim 8, It is characterized in that The itinerary change suggestion and generation module uses a greedy algorithm to quantitatively score or rate each change plan, and its calculation formula is: Score(x)=α·Cost(x)+β·TimeEfficiency(x)+γ·Comfort(x)+δ·Satisfaction(x), where x represents an itinerary change plan, Score(x) represents the evaluation score of the plan, and α, β, γ, and δ are weight coefficients of each evaluation indicator.

10. According to the big data-based smart tourism service platform of claim 1, It is characterized in that The compensation plan execution and feedback module queries the applicable compensation terms and conditions based on the original booking information of the tourists and the compensation policy of the partners, automatically generates a compensation plan for the tourists in combination with the risk prediction results and the compensation policy, communicates and exchanges data with the partners, and executes the compensation plan. At the same time, it collects tourists' feedback on itinerary changes and compensation plans through questionnaires and online evaluations, analyzes the collected feedback, identifies deficiencies and improvement points in the service, and uses them to optimize system algorithms and service processes.

Images