Visual processing method and system for displaying traffic big data

By identifying vehicle density and traffic speed, combining historical data to predict traffic peak periods and congested areas, and dynamically adjusting data views and interface design, the problems of inaccurate prediction and insufficient user experience of traditional traffic data visualization methods are solved, and traffic management is improved decision efficiency and data processing quality.

CN119049278AInactive Publication Date: 2024-11-29GUANGDONG JIANGXIA ECOLOGICAL CONSTR CO LTD

Patent Information

Application Number
CN202411120763.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-15
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional traffic data visualization methods lack the ability to process data and user interaction, and cannot make full use of historical data and real-time data, resulting in inaccurate traffic flow prediction and low timeliness, neglecting user personalized needs, affecting the decision-making efficiency and safety of traffic management. .

Method used

By identifying vehicle density and traffic speed, analyzing the trend of traffic characteristics, combining historical data to predict traffic peak periods and congestion areas, dynamically adjusting the data view refresh frequency and information display level, evaluating the ease of use of the user interface and optimizing the interface design, matching users use habits and cognitive abilities.

Benefits of technology

It improves the accuracy and user experience of traffic forecasting, reduces users' cognitive load, improves the quality of traffic data processing and visualization, and ensures the accuracy and efficiency of traffic information application.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119049278A_ABST
    Figure CN119049278A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent traffic, in particular to a visualization processing method and system for displaying traffic big data, and the method comprises the following steps: recognizing the vehicle density and traffic flow speed of a plurality of regions based on traffic image data, analyzing the traffic flow feature change trend of a plurality of time periods, and generating an image feature data set. According to the method, traffic image data and historical traffic data are analyzed, traffic flow features and congestion time modes are analyzed and recognized, the accuracy of traffic prediction is improved, user demand preferences are analyzed in combination with user query feedback data, data views are dynamically adjusted according to user behaviors, the user experience and decision-making efficiency are improved, and the user experience and the decision-making efficiency are improved. By evaluating the operation accuracy and the information acquisition speed of the user interface and optimizing the interface design, the cognitive load of the user is reduced, the usability and the efficiency of a visual interface are improved, the traffic big data processing and visualization quality is improved, and the accuracy and the efficiency of traffic information application are optimized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a visualization processing method and system for displaying traffic big data. Background Art

[0002] The field of intelligent transportation technology utilizes modern information technology, communication technology, data processing technology, control technology, and computer technology and applies it to road traffic management. It aims to improve road use efficiency, enhance traffic safety, reduce traffic congestion, and enhance the quality of transportation services and environmental sustainability. It includes traffic signal control systems, electronic toll collection systems, and automatic vehicle navigation. It monitors traffic conditions in real time, optimizes traffic flow distribution, and provides rapid response and services to emergencies.

[0003] Among them, the visualization processing method for displaying traffic big data aims to integrate and display traffic data. By collecting batch traffic data and converting traffic data into graphics and images using data visualization technology, users can intuitively understand and analyze traffic conditions, helping traffic managers and decision makers to quickly and accurately obtain key information and make effective management decisions when dealing with complex traffic conditions. By realizing the visualization of traffic data, the monitoring, analysis and optimization capabilities of the traffic system can be enhanced, thereby improving traffic flow and safety.

[0004] Traditional traffic data visualization methods have poor capabilities in data processing and user interaction, lack flexibility in integrating multiple types of data, and cannot fully utilize the combination of historical data and real-time data, resulting in inaccurate and low timeliness in traffic flow predictions. They ignore user personalized needs, and data display and user interface design cannot be adjusted according to user behavior and preferences, which limits user experience and operational efficiency. As a result, decision makers are unable to quickly obtain key information when dealing with complex traffic situations, affecting traffic safety and circulation efficiency. They fail to evaluate ease of use and user cognitive load, optimize information display, increase the difficulty for users to process information in emergency situations, lead to misoperation or delayed processing time, and affect the effectiveness of traffic management. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a visualization processing method and system for displaying traffic big data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, a visualization processing method for displaying traffic big data, comprising the following steps:

[0007] S1: Based on traffic image data, identify the vehicle density and traffic speed in multiple areas, analyze the changing trend of traffic characteristics in multiple time periods, and generate image feature data sets;

[0008] S2: Based on the image feature dataset, combined with historical traffic data, analyze the time pattern of vehicle flow and accident occurrence, predict traffic peak hours and congested areas, and generate a traffic prediction model;

[0009] S3: Based on the traffic prediction model and in combination with the user's query feedback data, identify the user's common query types and parameters, evaluate the user's task mode and demand preference, and generate a view demand analysis result;

[0010] S4: according to the view demand analysis result, combined with user behavior data and external traffic data, predict the change of user information demand, adjust the refresh frequency and information display level of the data view, and generate view refresh parameters;

[0011] S5: Based on the view refresh parameters and in combination with user feedback, analyze various user interfaces, record the accuracy and speed of user operations, evaluate the usability and information acquisition efficiency of various interfaces, and generate cognitive load evaluation information;

[0012] S6: According to the cognitive load assessment information, the interface layout and information display method are adjusted, the interface design is optimized to match the user's usage habits and cognitive abilities, and a traffic data visualization result is generated.

[0013] As a further solution of the present invention, the image feature data set includes a vehicle density index, a vehicle speed distribution diagram, and time period traffic change curve information; the traffic prediction model includes peak traffic prediction data, congestion area location prediction information, and accident probability analysis results; the view demand analysis results include user query frequency statistics, preferred view type information, and demand priority sorting results; the view refresh parameters include refresh frequency setting parameters, information display level parameters, and dynamic adjustment logic results; the cognitive load assessment information includes interface operation error rate, task completion time, and user satisfaction score; the traffic data visualization results include interface layout optimization parameters, information display method adjustment results, and user cognitive ability analysis results.

[0014] As a further solution of the present invention, based on traffic image data, the vehicle density and traffic speed of multiple areas are identified, and the trend of traffic flow characteristics in multiple time periods is analyzed. The steps of generating an image feature data set are specifically as follows:

[0015] S101: Based on the traffic image data, image data captured by traffic monitoring cameras is collected and analyzed, vehicle density and traffic speed information within the monitoring areas of multiple cameras are evaluated, and traffic flow data records are generated;

[0016] S102: Based on the traffic flow data record, evaluating the change trend of vehicle density and traffic flow speed in multiple time periods, and generating trend analysis results;

[0017] S103: Analyze the traffic flow characteristics of multiple areas based on the trend analysis results and in combination with the time information and geographical locations of multiple image data to generate an image feature data set.

[0018] As a further solution of the present invention, based on the image feature data set, combined with historical traffic data, analyzing the time pattern of vehicle flow and accident occurrence, predicting traffic peak hours and congested areas, and generating a traffic prediction model are specifically as follows:

[0019] S201: Based on the image feature data set and in combination with historical traffic flow data, analyzing changes in traffic flow in multiple time periods to generate traffic flow pattern analysis results;

[0020] S202: Based on the traffic flow pattern analysis result, analyzing the time information of multiple traffic accidents, evaluating the time characteristics of the traffic accidents, and analyzing the relationship with the traffic flow, and generating correlation evaluation information;

[0021] S203: Based on the correlation evaluation information and in combination with historical traffic flow data, the traffic flow of multiple areas is predicted, the time and location of multiple congested areas are analyzed, and a traffic prediction model is generated.

[0022] As a further solution of the present invention, based on the traffic prediction model, combined with the user's query feedback data, identifying the user's common query types and parameters, evaluating the user's task mode and demand preference, and generating the view demand analysis results are specifically as follows:

[0023] S301: Based on the traffic prediction model, combined with the user's query feedback data, analyzing and recording the query type, including the query route and congestion time, and generating a user query type record;

[0024] S302: Analyze the user query type record, analyze the usage frequency of multiple parameters and options in the user query, identify the user's demand preferences for multiple traffic information, and generate a user demand identification record;

[0025] S303: According to the user demand identification record, combined with the user's task execution frequency, evaluate the user's demand for view type, analyze and record the view adjustment demand, and generate a view demand analysis result.

[0026] As a further solution of the present invention, according to the view demand analysis result, combined with user behavior data and external traffic data, predicting the change of user information demand, adjusting the refresh frequency of the data view and the information display level, the step of generating the view refresh parameter is specifically as follows:

[0027] S401: Based on the view demand analysis result, analyzing the user's behavior data in multiple time periods and task types, recording the data access frequency and duration, and generating a user behavior data record;

[0028] S402: Based on the user behavior data records and in combination with real-time traffic data, an exponential smoothing method is used to predict changes in information demand, calculate the information refresh frequency required for multiple time periods, and generate a refresh demand calculation result;

[0029] S403: According to the refresh demand calculation result, the refresh frequency and information display level of the data view are adjusted, view parameters are set, including refresh interval and data level, and view refresh parameters are generated.

[0030] As a further solution of the present invention, the exponential smoothing method is according to the formula:

[0031] S t =αY t +(1-α)(βT t-1 +γD t-1 +δP t-1 +S t-1 )

[0032] Calculate the information refresh frequency, where S t is the predicted value of information refresh frequency in time period t, Y t is the traffic data actually observed in time period t, t is the time period currently being evaluated and calculated, t-1 refers to the time point before the current time point t, T t-1 is the traffic trend data of the previous period, D t-1 is the data delay factor of the previous time period, P t-1 is the impact of special events in the previous period, S t-1 is the prediction result of the previous time period, and α is used to adjust the real-time data Y t The smoothing parameter that affects the prediction, β is used to adjust the traffic trend data T in the previous time period t-1 The weight of γ is used to adjust the data delay factor D in the previous time period. t-1 The weight of δ is used to adjust the impact of special events in the previous time period P t-1 The weight of .

[0033] As a further solution of the present invention, based on the view refresh parameters and in combination with user feedback, multiple user interfaces are analyzed, the accuracy and speed of user operations are recorded, the usability and information acquisition efficiency of multiple interfaces are evaluated, and the steps of generating cognitive load evaluation information are specifically as follows:

[0034] S501: Based on the view refresh parameters, collect and analyze the operation data of the user in various interfaces, evaluate the accuracy and speed of the user operation, and generate a user operation data record;

[0035] S502: Based on the user operation data records, measuring the user operation error rates and average task completion times of multiple user interfaces, calculating efficiency scores of the multiple user interfaces, and generating interface performance evaluation results;

[0036] S503: Based on the interface performance evaluation results, evaluate the usability and information acquisition efficiency of various interfaces, consider the user's satisfaction and feedback on the interface, analyze the user's cognitive load on various user interfaces, and generate cognitive load evaluation information.

[0037] As a further solution of the present invention, according to the cognitive load assessment information, the interface layout and information display method are adjusted to optimize the interface design to match the user's usage habits and cognitive abilities, and the steps of generating traffic data visualization results are specifically as follows:

[0038] S601: Based on the cognitive load evaluation information, identifying factors affecting user cognitive efficiency in information display mode and interface layout, and generating cognitive efficiency influencing factors;

[0039] S602: Apply the cognitive efficiency influencing factors to adjust the interface layout and information display method to match the user's usage habits and cognitive abilities, optimize the visibility and accessibility of interface elements, and generate an interface configuration optimization record;

[0040] S603: Based on the interface configuration optimization record, a traffic data visualization interface is constructed to display various traffic data to the user, record user operations and feedback information, and generate traffic data visualization results.

[0041] A visualization processing system for displaying traffic big data, the visualization processing system for displaying traffic big data is used to execute the visualization processing method for displaying traffic big data, the system comprises:

[0042] The data feature analysis module identifies the vehicle density and traffic speed in multiple areas based on traffic image data, analyzes traffic flow trends in multiple time periods in combination with historical data, predicts traffic peaks and congestion areas, and generates traffic information analysis records;

[0043] The user demand analysis module collects user query feedback data based on the traffic information analysis record, analyzes common query types and parameters, evaluates the user's task mode and demand preference, and generates a task mode recognition record;

[0044] The information refresh evaluation module predicts changes in information needs based on the task mode recognition records, combines user behavior and traffic data, adjusts the refresh frequency of the data view and the information display level, and generates update frequency parameters;

[0045] The user interface evaluation module analyzes user feedback on various interfaces based on the update frequency parameters, records operation accuracy and speed, evaluates the ease of use and information acquisition efficiency of the interface, and generates an interface efficiency evaluation result;

[0046] The visualization interface optimization module adjusts the interface layout and information display method according to the interface efficiency evaluation results, optimizes the design to match the user's usage habits and cognitive abilities, and generates traffic data visualization results.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are:

[0048] In the present invention, by analyzing traffic image data and historical traffic data, the vehicle flow characteristics and congestion time patterns are analyzed and identified to improve the accuracy of traffic forecasts, and the user query feedback data is combined to analyze user demand preferences, and the data view is dynamically adjusted according to user behavior to improve user experience and decision-making efficiency. By evaluating the operation accuracy and information acquisition speed of the user interface, the interface design is optimized, the user's cognitive load is reduced, the usability and efficiency of the visualization interface are improved, and the quality of traffic big data processing and visualization is improved, thereby ensuring the accuracy and efficiency of traffic information applications and improving traffic management and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0050] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0051] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0052] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0053] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0054] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0055] Figure 7 This is a detailed flow chart of S6 of the present invention;

[0056] Figure 8 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0058] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0059] See also Figure 1 The present invention provides a technical solution, a visualization processing method for displaying traffic big data, comprising the following steps:

[0060] S1: Based on traffic image data, identify the vehicle density and traffic speed in multiple areas, analyze the changing trend of traffic characteristics in multiple time periods, and generate image feature data sets;

[0061] S2: Based on the image feature dataset and combined with historical traffic data, analyze the time pattern of vehicle flow and accidents, predict traffic peak hours and congested areas, and generate a traffic prediction model;

[0062] S3: Based on the traffic prediction model and combined with the user's query feedback data, identify the user's common query types and parameters, evaluate the user's task mode and demand preference, and generate view demand analysis results;

[0063] S4: Based on the view demand analysis results, combined with user behavior data and external traffic data, predict the change of user information demand, adjust the refresh frequency of the data view and the information display level, and generate view refresh parameters;

[0064] S5: Based on the view refresh parameters and combined with user feedback, analyze various user interfaces, record the accuracy and speed of user operations, evaluate the usability and information acquisition efficiency of various interfaces, and generate cognitive load assessment information;

[0065] S6: According to the cognitive load assessment information, adjust the interface layout and information display method, optimize the interface design to match the user's usage habits and cognitive ability, and generate traffic data visualization results.

[0066] The image feature data set includes vehicle density index, vehicle speed distribution map, and time period traffic change curve information. The traffic prediction model includes peak traffic prediction data, congested area location prediction information, and accident probability analysis results. The view demand analysis results include user query frequency statistics, preferred view type information, and demand priority sorting results. View refresh parameters include refresh frequency setting parameters, information display level parameters, and dynamic adjustment logic results. Cognitive load assessment information includes interface operation error rate, task completion time, and user satisfaction score. Traffic data visualization results include interface layout optimization parameters, information display method adjustment results, and user cognitive ability analysis results.

[0067] See also Figure 2 Based on traffic image data, the vehicle density and traffic speed of multiple areas are identified, and the changing trend of traffic characteristics in multiple time periods is analyzed. The specific steps of generating image feature data sets are as follows:

[0068] S101: Based on the traffic image data, the image data captured by the traffic monitoring camera is collected and analyzed, and the vehicle density and traffic speed information in the monitoring area of ​​multiple cameras are evaluated to generate the traffic data record. The specific process is as follows;

[0069] In sub-step S101, based on traffic image data, the image data captured by the traffic monitoring camera is collected and analyzed. By setting data collection nodes, high-frequency sampling is performed on the road section covered by each monitoring point, and the vehicle flow and speed are recorded every minute. The position and speed information of the vehicle are extracted through the image processing algorithm, and the average speed and vehicle density of multiple monitoring points are calculated. The vehicle density evaluation model is adopted, and the formula is: Where D represents the vehicle density, c i is the number of vehicles captured by the i-th monitoring point, A is the total area of ​​the monitoring area, the vehicle density in the monitoring area is evaluated, and the traffic data record is generated.

[0070] S102: Based on the traffic flow data records, the change trends of vehicle density and traffic flow speed in multiple time periods are evaluated, and the process of generating trend analysis results is specifically as follows;

[0071] In sub-step S102, based on the traffic data records, the changing trends of vehicle density and traffic speed in multiple time periods are evaluated. The vehicle density and speed data are seasonally adjusted and outliers are processed using time series analysis methods. Moving average and exponential smoothing methods are applied to smooth the data series to identify long-term and short-term changing trends. The trend analysis formula is V t =αX t-1 +(1-α)V t-1 , where V t is the trend value at time t, X t-1is the actual observation value at time t-1, and α is the smoothing coefficient, which is used to control the sensitivity of the model to historical data, evaluate the trend changes of traffic speed and density, and generate trend analysis results.

[0072] S103: According to the trend analysis result, the time information and geographical location of the multiple image data are combined to analyze the traffic flow characteristics of the multiple regions, and the process of generating the image feature data set is as follows;

[0073] In sub-step S103, based on the trend analysis results, combined with the time information and geographic location of multiple image data, the traffic flow characteristics of multiple regions are analyzed, the traffic flow data are partitioned by cluster analysis method, multiple traffic flow patterns are identified, and the statistical characteristics of each pattern are calculated, including the average speed and vehicle density during peak hours. The traffic flow characteristic formula is used, and the formula is: Among them, F k represents the characteristic value of the kth traffic pattern, N k is the number of data points in the target mode, S k is the sample set belonging to the kth mode, v j The vehicle speed of sample j is analyzed, and the traffic flow characteristics of various geographical locations and time periods are generated to generate an image feature dataset.

[0074] See also Figure 3 ,Based on the image feature dataset, combined with historical traffic data,,analyze the time pattern of vehicle flow and accidents, predict traffic peak hours and congested areas, and generate the,traffic prediction model in the following steps:

[0075] S201: Based on the image feature data set and in combination with the historical traffic flow data, the traffic flow changes in multiple time periods are analyzed to generate the traffic flow pattern analysis results. Specifically, the process is as follows;

[0076] In sub-step S201, based on the image feature data set and combined with historical traffic flow data, the traffic flow changes in multiple time periods are analyzed. The current traffic flow feature data and the traffic flow records of the same period in the past are integrated through the data integration algorithm. The increase and decrease of traffic flow in multiple time periods are determined by the data comparison analysis method. The traffic flow change analysis model is used, and the formula is: Among them, Q Δ is the percentage change of traffic flow, Q c is the currently observed traffic flow, Q h For the traffic volume in the same period of history, evaluate the changing trend of traffic volume within the time period and generate traffic flow pattern analysis results.

[0077] S202: Based on the traffic flow pattern analysis results, the time information of multiple traffic accidents is analyzed, the time characteristics of the traffic accidents are evaluated, and the relationship with the traffic flow is analyzed to generate the correlation evaluation information. The specific process is as follows;

[0078] In sub-step S202, based on the traffic pattern analysis results, the time information of multiple traffic accidents is analyzed, the time characteristics of traffic accidents are evaluated, and the relationship with traffic flow is analyzed. The correlation between the time period with high accident rate and traffic flow is identified by cross-analysis of accident time tags and traffic density data. The time correlation evaluation model is adopted, and the formula is: Among them, C ta is the time characteristic value of the traffic accident, T i is the time of the accident, V i For the traffic flow at the corresponding time, the weighted average of accident time and traffic flow is calculated, the relationship between the probability of accident occurrence and traffic density is analyzed, and correlation evaluation information is generated.

[0079] S203: Based on the correlation evaluation information and in combination with the historical traffic flow data, the traffic flow of multiple areas is predicted, the time and location of multiple congested areas are analyzed, and the specific process of generating a traffic prediction model is as follows;

[0080] In sub-step S203, based on the correlation evaluation information and combined with the historical traffic flow data, the traffic flow of multiple areas is predicted, the time and location of multiple congested areas are analyzed, and the linear regression model is applied to establish a traffic flow prediction model through the training data set to predict the traffic flow status. The formula is P flow =β0+β1T+β2L, where P flow is the predicted traffic flow, β0 is the model intercept, β1 is the time variable coefficient, β2 is the location variable coefficient, T is the time variable, and L is the geographic location variable. By adjusting the coefficients β1 and β2, the traffic flow conditions at various times and locations can be predicted to generate a traffic prediction model.

[0081] See also Figure 4 ,Based on the traffic prediction model, combined with the user's query feedback data, ,identify the user's common query types and parameters, evaluate the user's task mode and demand preference, ,and generate the view demand analysis results in the following steps:

[0082] S301: Based on the traffic prediction model, combined with the user's query feedback data, the query type is analyzed and recorded, including the query route and congestion time, and the specific process of generating the user query type record is as follows;

[0083] In sub-step S301, based on the traffic prediction model and combined with the user's query feedback data, the user's query type is analyzed and recorded, and the query information input by the user, including the selected route and the query congestion time, is collected through the data capture system. The data classification algorithm is applied to classify and mark the collected query types, analyze the user behavior pattern, and adopt the query record model, the formula is Among them, Qr Represents the comprehensive index of user query records, t i is the time specified in the i-th query, l i For the corresponding route identification, the user's query preference is recorded and quantified, and a user query type record is generated.

[0084] S302: Analyze the user query type record, analyze the usage frequency of multiple parameters and options in the user query, identify the user's demand preferences for various traffic information, and generate the user demand identification record. The specific process is as follows;

[0085] In sub-step S302, the user query type records are analyzed to identify the user's demand preferences for various traffic information. The usage frequency of various query types is calculated through statistical analysis methods, and the user's behavior trend analysis is performed. The demand identification model is used, and the formula is: Among them, U p is the user demand preference value, f j is the usage frequency of the jth query type, p j is the preference weight of the query type, m is the total number of query types, and the query preferences of users under various traffic conditions are analyzed to generate user demand identification records.

[0086] S303: According to the user demand identification record, combined with the user's task execution frequency, the user's demand for view type is evaluated, and the view adjustment demand is analyzed and recorded. The specific process of generating the view demand analysis result is as follows;

[0087] In sub-step S303, based on the user demand identification records and the user's task execution frequency, the user's demand for view types is evaluated. Through the user interface usage data analysis, the frequently used view functions and unmet needs are identified. The view demand evaluation model is used, and the formula is: Among them, V d is the view demand, v k is the usage frequency of the kth view type, w k is the user's demand weight for the view type, and q is the total number of view types. In this way, the user's demand for multiple view adjustments is analyzed and recorded to generate view demand analysis results.

[0088] See also Figure 5 ,According to the results of view demand analysis, combined with user behavior data and external traffic data, the changes in user information demand are predicted, and the refresh frequency and information display level of the data view are adjusted. The specific steps for generating view refresh parameters are as follows:

[0089] S401: Based on the view demand analysis results, analyze the user's behavior data under multiple time periods and task types, record the data access frequency and duration, and generate the user behavior data record. The specific process is as follows;

[0090] In sub-step S401, based on the view demand analysis results, the user's behavior data in multiple time periods and task types are analyzed, the data access frequency and duration are collected through the user activity monitoring system, and various data are classified and summarized to identify high-frequency access time periods and task types. The behavior data recording model is adopted, and the formula is Among them, B freq Represents the frequency index of user behavior data, f h is the data access frequency in the hth time period, d h is the continuous access time of the corresponding time period, t represents the total number of time periods considered, and the user's behavior pattern is analyzed to generate user behavior data records.

[0091] S402: Based on the user behavior data records and in combination with the real-time traffic data, the exponential smoothing method is used to predict the change of information demand, calculate the information refresh frequency required for multiple time periods, and generate the refresh demand calculation result. The specific process is as follows;

[0092] In sub-step S402, based on user behavior data records and combined with real-time traffic data, the exponential smoothing method is used to predict changes in information demand. By analyzing the correlation between past data access patterns and real-time traffic conditions, the exponential smoothing method is used to predict data access demand in future time periods, calculate the information refresh frequency required for multiple time periods, and generate refresh demand calculation results.

[0093] Exponential smoothing method, according to the formula:

[0094] S t =αY t +(1-α)(βT t-1 +γD t-1 +δP t-1 +S t-1 )

[0095] Calculate the information refresh frequency, where S t is the predicted value of information refresh frequency in time period t, Y t is the traffic data actually observed in time period t, t is the time period currently being evaluated and calculated, t-1 refers to the time point before the current time point t, T t-1 is the traffic trend data of the previous period, D t-1 is the data delay factor of the previous time period, P t-1 is the impact of special events in the previous period, S t-1is the prediction result of the previous time period, and α is used to adjust the real-time data Y t The smoothing parameter that affects the prediction, β is used to adjust the traffic trend data T in the previous time period t-1 The weight of γ is used to adjust the data delay factor D in the previous time period. t-1 The weight of δ is used to adjust the impact of special events in the previous time period P t-1 The weight of .

[0096] The specific execution process of the formula is as follows:

[0097] Collect traffic data Y from historical traffic monitoring system t ,Traffic trend dataT t-1 ,Data delay factor D t-1 , and special events affect P t-1 , use the historical data set to perform regression analysis of parameters α, β, γ, and δ, evaluate the contribution of the target parameters to the prediction accuracy, use linear regression to adjust the weight coefficient to minimize the prediction error, substitute the parameters into the formula, and calculate the prediction information refresh frequency S for each time period t .

[0098] S403: According to the refresh demand calculation result, the refresh frequency and information display level of the data view are adjusted, and the view parameters are set, including the refresh interval and the data level. The specific process of generating the view refresh parameters is as follows;

[0099] In sub-step S403, according to the refresh demand calculation result, the refresh frequency and information display level of the data view are adjusted, and the view parameters, including the refresh interval and data level, are set to match the needs and behavior patterns of differentiated users. The model is adjusted using the view parameters. The formula is V set =β0+β1I+β2L, where V set is the view setting value, β0 is the basic setting value, β1 is the refresh interval coefficient, β2 is the data level coefficient, I is the set refresh interval, and L is the data level. By adjusting β1 and β2, the view is configured to maximize user satisfaction and generate view refresh parameters.

[0100] See also Figure 6 ,Based on the view refresh parameters and combined with user feedback,,multiple user interfaces are analyzed, the accuracy and speed of user operations are recorded,,and the usability and information acquisition efficiency of various interfaces are evaluated.,The specific steps for generating cognitive load evaluation information are as follows:

[0101] S501: Based on the view refresh parameters, collect and analyze the user's operation data in various interfaces, evaluate the accuracy and speed of the user's operation, and generate the user operation data record. The specific process is as follows;

[0102] In sub-step S501, based on the view refresh parameters, the user's operation data on various interfaces is collected and analyzed, and the user's operation information, including click accuracy and response speed, is recorded through interface interaction tracking technology to evaluate the accuracy and speed of user operations. The operation data analysis model is adopted, and the formula is: Among them, O data Represents the comprehensive score of user operation data, a i Score the accuracy of the i-th operation, t i is the completion time of the corresponding operation, n represents the number of data points and the number of cycles, analyzes and calculates the user's operation efficiency and accuracy, and generates user operation data records.

[0103] S502: Based on the user operation data records, the user operation error rates and average task completion times of multiple user interfaces are measured, the efficiency scores of multiple user interfaces are calculated, and the process of generating interface performance evaluation results is specifically as follows;

[0104] In sub-step S502, based on the user operation data records, the user operation error rate and average task completion time of multiple user interfaces are measured, the user operation data of multiple interfaces are analyzed, and the error rate and average time are calculated by applying statistical analysis methods, and then the efficiency scores of multiple interfaces are calculated. The performance evaluation model is adopted, and the formula is: Among them, P eff is the interface efficiency score, ∈ j is the error rate of the jth interface, τ j is the average task completion time, and m is used to represent the total number of multiple categories, reflecting the performance of multiple user interfaces and generating interface performance evaluation results.

[0105] S503: Based on the interface performance evaluation results, the usability and information acquisition efficiency of various interfaces are evaluated, the user's satisfaction and feedback on the interface are considered, and the cognitive load of the user on various user interfaces is analyzed. The specific process of generating cognitive load evaluation information is as follows;

[0106] In sub-step S503, based on the interface performance evaluation results, the usability and information acquisition efficiency of various interfaces are evaluated. Combined with user feedback and satisfaction survey data, the cognitive load of users on various interfaces is analyzed. The cognitive load evaluation model is applied to consider the psychological and perceptual reactions of users when using the interface. The formula is: Among them, C load is the cognitive load value, u k is the user satisfaction score of the kth interface, v k is the information acquisition efficiency, s k To determine the user's subjective difficulty level on the target interface, analyze the user's cognitive load on various user interfaces and generate cognitive load assessment information.

[0107] See also Figure 7 ,According to the cognitive load assessment information, the interface layout and information display method are adjusted, and the interface design is optimized to match the user's usage habits and cognitive abilities. The specific steps for generating traffic data visualization results are as follows:

[0108] S601: Based on cognitive load assessment information, identifying factors affecting user cognitive efficiency in information display mode and interface layout, and generating cognitive efficiency influencing factors in detail as follows;

[0109] In sub-step S601, based on the cognitive load assessment information, the factors affecting the user's cognitive efficiency in the information display method and interface layout are identified, and the user's behavior data on the interface, including click rate, dwell time, and error rate, are analyzed to determine the interface elements that cause excessive cognitive load. The factor analysis method is used to extract the key factors affecting cognitive efficiency from the batch of user interaction data, using the following factor analysis formula: F = V -1 (b-μ), where F represents the factor score, V -1 is the inverse matrix of the extracted factor loadings, b represents the observed behavioral data vector, μ is the mean of the behavioral data, and identifies the interface elements that need to be adjusted in the interface design to generate the factors affecting cognitive efficiency.

[0110] S602: Apply cognitive efficiency influencing factors, adjust the interface layout and information display method to match the user's usage habits and cognitive abilities, optimize the visibility and accessibility of interface elements, and generate interface configuration optimization records. The specific process is as follows;

[0111] In sub-step S602, the factors affecting cognitive efficiency are applied to adjust the interface layout and information display method to match the user's usage habits and cognitive abilities, adjust the position and size of interface elements, optimize the visibility and accessibility of information, and test the interface efficiency by simulating user interaction. The formula is: Where R represents the interface responsiveness score, w i is the weight of each interface element, e i Score the efficiency of target elements in user testing, optimize the usability and user satisfaction of the interface, and generate interface configuration optimization records.

[0112] S603: Based on the interface configuration optimization record, a traffic data visualization interface is constructed to display various traffic data to the user, and user operations and feedback information are recorded to generate a traffic data visualization result. Specifically, the process is as follows;

[0113] In sub-step S603, based on the interface configuration optimization record, a variety of traffic data are displayed to users by building a traffic data visualization interface, presenting traffic data in various forms such as charts, maps and dynamic indicators, designing and implementing a user interaction recording framework, recording user operations and feedback information, tracking and optimizing user experience, and the formula is Among them, U represents the user satisfaction score, f i Represents the target user feedback type, u i is the cumulative number of target feedback types, N is the total number of feedbacks, and the visualization interface is adjusted and optimized in real time to generate traffic data visualization results.

[0114] See also Figure 8 A visualization processing system for displaying traffic big data is provided. The visualization processing system for displaying traffic big data is used to execute the visualization processing method for displaying traffic big data. The system includes:

[0115] The data feature analysis module identifies the vehicle density and traffic speed in multiple areas based on traffic image data, analyzes traffic flow trends in multiple time periods in combination with historical data, predicts traffic peaks and congestion areas, and generates traffic information analysis records;

[0116] The user demand analysis module collects user query feedback data based on traffic information analysis records, analyzes common query types and parameters, evaluates user task modes and demand preferences, and generates task mode recognition records;

[0117] The information refresh evaluation module predicts changes in information needs based on task mode recognition records, combined with user behavior and traffic data, adjusts the refresh frequency of data views and information display levels, and generates update frequency parameters;

[0118] The user interface evaluation module analyzes user feedback on various interfaces based on update frequency parameters, records operation accuracy and speed, evaluates interface usability and information acquisition efficiency, and generates interface efficiency evaluation results;

[0119] The visualization interface optimization module adjusts the interface layout and information display method according to the interface efficiency evaluation results, optimizes the design to match the user's usage habits and cognitive abilities, and generates traffic data visualization results.

[0120] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A visualization processing method for displaying traffic big data, characterized in that: The following steps are involved: Based on traffic image data, the vehicle density and traffic speed in multiple areas are identified, the changing trend of traffic characteristics in multiple time periods is analyzed, and an image feature data set is generated; Based on the image feature data set and in combination with historical traffic data, the time pattern of vehicle flow and accident occurrence is analyzed, traffic peak hours and congested areas are predicted, and a traffic prediction model is generated; Based on the traffic prediction model, combined with the user's query feedback data, identify the user's common query types and parameters, evaluate the user's task mode and demand preference, and generate a view demand analysis result; According to the view demand analysis results, combined with user behavior data and external traffic data, predict changes in user information demand, adjust the refresh frequency and information display level of the data view, and generate view refresh parameters; Based on the view refresh parameters and in combination with user feedback, multiple user interfaces are analyzed, the accuracy and speed of user operations are recorded, the usability and information acquisition efficiency of multiple interfaces are evaluated, and cognitive load evaluation information is generated; According to the cognitive load assessment information, the interface layout and information display method are adjusted, the interface design is optimized to match the user's usage habits and cognitive abilities, and traffic data visualization results are generated.

2. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: The image feature data set includes vehicle density index, vehicle speed distribution map, and time period traffic change curve information; the traffic prediction model includes peak traffic prediction data, congestion area location prediction information, and accident probability analysis results; the view demand analysis results include user query frequency statistics, preferred view type information, and demand priority sorting results; the view refresh parameters include refresh frequency setting parameters, information display level parameters, and dynamic adjustment logic results; the cognitive load assessment information includes interface operation error rate, task completion time, and user satisfaction score; the traffic data visualization results include interface layout optimization parameters, information display method adjustment results, and user cognitive ability analysis results.

3. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: Based on traffic image data, the vehicle density and traffic speed of multiple areas are identified, and the changing trend of traffic characteristics in multiple time periods is analyzed. The specific steps for generating image feature data sets are as follows: Based on traffic image data, collect and analyze image data captured by traffic monitoring cameras, evaluate vehicle density and traffic speed information within the monitoring area of ​​multiple cameras, and generate traffic data records; Based on the traffic flow data records, evaluating the changing trends of vehicle density and traffic flow speed in multiple time periods, and generating trend analysis results; According to the trend analysis results, combined with the time information and geographical locations of multiple image data, the traffic flow characteristics of multiple areas are analyzed to generate an image feature data set.

4. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: Based on the image feature data set, combined with historical traffic data, the time pattern of vehicle flow and accident occurrence is analyzed, and the traffic peak period and congestion area are predicted. The specific steps of generating a traffic prediction model are as follows: Based on the image feature data set and in combination with historical traffic flow data, traffic flow changes in multiple time periods are analyzed to generate traffic flow pattern analysis results; Based on the traffic flow pattern analysis results, the time information of multiple traffic accidents is analyzed, the time characteristics of the traffic accidents are evaluated, and the relationship with the traffic flow is analyzed to generate correlation evaluation information; Based on the correlation evaluation information and in combination with historical traffic flow data, the traffic flow in multiple areas is predicted, the time and location of multiple congested areas are analyzed, and a traffic prediction model is generated.

5. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: Based on the traffic prediction model, combined with the user's query feedback data, the steps of identifying the user's common query types and parameters, evaluating the user's task mode and demand preference, and generating the view demand analysis results are as follows: Based on the traffic prediction model, combined with the user's query feedback data, the query type is analyzed and recorded, including the query route and congestion time, and a user query type record is generated; Analyze the user query type record, analyze the usage frequency of multiple parameters and options in the user query, identify the user's demand preferences for multiple traffic information, and generate a user demand identification record; According to the user demand identification record, combined with the user's task execution frequency, the user's demand for view type is evaluated, the view adjustment demand is analyzed and recorded, and the view demand analysis result is generated.

6. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: According to the view demand analysis results, combined with user behavior data and external traffic data, predict the change of user information demand, adjust the refresh frequency and information display level of the data view, and generate the view refresh parameters in the following steps: Based on the view demand analysis results, analyze the user's behavior data under multiple time periods and task types, record the data access frequency and duration, and generate user behavior data records; Based on the user behavior data records and in combination with real-time traffic data, an exponential smoothing method is used to predict changes in information demand, calculate the information refresh frequency required for multiple time periods, and generate a refresh demand calculation result; According to the refresh demand calculation result, the refresh frequency and information display level of the data view are adjusted, and the view parameters, including the refresh interval and the data level, are set to generate the view refresh parameters.

7. The visualization processing method for displaying traffic big data according to claim 6 is characterized in that: The exponential smoothing method is according to the formula: S t =αY t +(1-α)(βT t-1 +γD t-1 +δP t-1 +S t-1 ) Calculate the information refresh frequency, where S t is the predicted value of information refresh frequency in time period t, Y t is the traffic data actually observed in time period t, t is the time period currently being evaluated and calculated, t-1 refers to the time point before the current time point t, T t-1 is the traffic trend data of the previous period, D t-1 is the data delay factor of the previous time period, P t-1 is the impact of special events in the previous period, S t-1 is the prediction result of the previous time period, and α is used to adjust the real-time data Y t The smoothing parameter that affects the prediction, β is used to adjust the traffic trend data T in the previous time period t-1 The weight of γ is used to adjust the data delay factor D in the previous time period. t-1 The weight of δ is used to adjust the impact of special events in the previous time period P t-1 The weight of .

8. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: Based on the view refresh parameters and in combination with user feedback, the steps of analyzing various user interfaces, recording the accuracy and speed of user operations, evaluating the usability and information acquisition efficiency of various interfaces, and generating cognitive load evaluation information are as follows: Based on the view refresh parameters, collect and analyze the user's operation data in various interfaces, evaluate the accuracy and speed of the user's operation, and generate user operation data records; Based on the user operation data records, measuring the user operation error rates and average task completion time of multiple user interfaces, calculating the efficiency scores of the multiple user interfaces, and generating interface performance evaluation results; Based on the interface performance evaluation results, the usability and information acquisition efficiency of various interfaces are evaluated, the user's satisfaction and feedback on the interface are considered, the user's cognitive load on various user interfaces is analyzed, and cognitive load evaluation information is generated.

9. The visualization processing method for displaying traffic big data according to claim 1 is characterized in that: According to the cognitive load assessment information, the interface layout and information display method are adjusted to optimize the interface design to match the user's usage habits and cognitive abilities. The specific steps for generating traffic data visualization results are: Based on the cognitive load assessment information, identifying factors affecting user cognitive efficiency in information display mode and interface layout, and generating cognitive efficiency influencing factors; Apply the cognitive efficiency influencing factors, adjust the interface layout and information display method to match the user's usage habits and cognitive abilities, optimize the visibility and accessibility of interface elements, and generate interface configuration optimization records; Based on the interface configuration optimization record, a traffic data visualization interface is constructed to display various traffic data to users, record user operations and feedback information, and generate traffic data visualization results.

10. A visualization processing system for displaying traffic big data, characterized in that: According to the visualization processing method for displaying traffic big data according to any one of claims 1 to 9, the system comprises: The data feature analysis module identifies the vehicle density and traffic speed in multiple areas based on traffic image data, analyzes traffic flow trends in multiple time periods in combination with historical data, predicts traffic peaks and congestion areas, and generates traffic information analysis records; The user demand analysis module collects user query feedback data based on the traffic information analysis record, analyzes common query types and parameters, evaluates the user's task mode and demand preference, and generates a task mode recognition record; The information refresh evaluation module predicts changes in information needs based on the task mode recognition records, combines user behavior and traffic data, adjusts the refresh frequency of the data view and the information display level, and generates update frequency parameters; The user interface evaluation module analyzes user feedback on various interfaces based on the update frequency parameters, records operation accuracy and speed, evaluates the ease of use and information acquisition efficiency of the interface, and generates an interface efficiency evaluation result; The visualization interface optimization module adjusts the interface layout and information display method according to the interface efficiency evaluation results, optimizes the design to match the user's usage habits and cognitive abilities, and generates traffic data visualization results.

Citation Information

Patent Citations

  • Urban road traffic flow state estimation method and system based on block chain

    CN117671961A

  • Intelligent traffic management method and system based on traffic flow

    CN117746626A

  • Expressway running state studying and judging method fusing intercommunication and main line data

    CN117809454A

  • Traffic information publishing system and method, computer equipment and storage medium

    CN117975729A

  • Man-machine interaction system and man-machine interaction method

    CN118151763A

Cited By

  • Multidimensional data analysis method and device based on holography

    CN119719657A

  • Self-adaptive adjustment method and system for monitoring interface of power monitoring system

    CN120891943A

  • Adaptive adjustment method and system for power monitoring system monitoring interface

    CN120891943B

  • Intelligent report data visual management method and system, medium and product

    CN121144574A