Lottery terminal data visualization method and system

Abstract

The invention discloses a lottery terminal data visualization method and system, and relates to the technical field of lottery data visualization. According to the method, multi-element terminal operation parameters and user interaction data flow are collected in real time, and a dynamic user state evaluation model is fused with a time sequence behavior analysis and participation degree scoring algorithm, so that the user interaction stage and the cognitive load level are accurately recognized. Based on a staged adaptive strategy library, a content priority rule, a layout template and a visual parameter adjustment range are dynamically matched, and a real-time feedback analysis engine is used for performing windowing processing and effect evaluation on a microscopic interaction signal, so that dynamic fine adjustment of visual parameters is realized. Through multi-dimensional data fusion and a real-time adaptive mechanism, the user interaction fluency and the key information reaching precision are remarkably improved, meanwhile, the rendering stability of the terminal in a resource limited scene is guaranteed, and the user decision-making efficiency and the terminal marketing conversion rate are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of lottery data visualization, and in particular to a lottery terminal data visualization method and method. Background Art

[0002] In the field of lottery terminal data visualization, existing technologies often rely on static or semi-dynamic interface designs. Their visualization strategies are typically based on fixed templates or simple rules, lacking in-depth perception and dynamic response to users' real-time behavior and terminal operating status. For example, traditional systems often use a unified information display layout, failing to adjust content priorities based on the user's current interaction stage. This can lead to information overload or the burying of key promotional information, impacting user decision-making efficiency. Furthermore, existing technologies often limit user engagement assessments to single dimensions such as click frequency or dwell time, ignoring fine-grained interaction signals such as eye movement trajectories and touch operation sequences. This leads to biased engagement judgments and makes it difficult to accurately match user cognitive load.

[0003] On the other hand, existing visualization feedback mechanisms suffer from significant lags. Most systems rely on offline data analysis and adjustment strategies, failing to capture real-time micro-interaction feedback and dynamically optimize interface parameters. Furthermore, existing technologies fail to fully consider the constraints imposed by the terminal's operating state on visualization rendering. When resources are limited, lags or incomplete information display can occur, further degrading the user experience. Summary of the Invention

[0004] In response to the above technical problems, the present invention provides a lottery terminal data visualization method and system for solving the problem of lottery terminal sales data visualization.

[0005] A lottery terminal data visualization method comprises the following steps: Step S1: Real-time monitoring and collection of multiple operating status parameters and user interaction data streams of the lottery sales terminal, wherein the operating status parameters include at least terminal load, network conditions, and current promotional information, and the user interaction data stream includes at least touch operation sequences, eye tracking data, and voice commands; and signal preprocessing and feature normalization operations are performed on the collected raw data.

[0006] Step S2: Based on the pre-processed data, a dynamic user state evaluation model is used to infer the current user's interaction stage and engagement level in real time; and combined with the terminal operation state parameters, a unified real-time situational portrait is generated.

[0007] Step S3: Based on the real-time situation portrait and a preset or dynamically adjusted phased adaptive visualization strategy library, select and execute the visualization presentation task of the current stage; the strategy library is a combination of different user interaction stages and participation levels, and predefines content priority rules, layout template constraints, interaction guidance mechanisms, and dynamic adjustment ranges of visualization parameters; the visualization parameters include at least information density, animation effect intensity, and relevance thresholds of recommended content.

[0008] Step S4: During the presentation of the visual content, continuously collect the user's micro-interaction feedback signals, and use the real-time feedback analysis engine to process the signals to evaluate the immediate effect of the current visual presentation.

[0009] Step S5: Based on the instant effect evaluation result and in accordance with the parameter dynamic adjustment rules defined in the policy library, fine-tune at least one visualization parameter of the currently presented visualization content within an allowable range.

[0010] Furthermore, in step S2, the dynamic user state evaluation model includes a time series behavior analysis module for processing interaction sequence data, the time series behavior analysis module uses a neural network to analyze touch operation and sight trajectory time series data; an engagement scoring module for quantifying user engagement, the engagement scoring module calculates a comprehensive engagement score , which is calculated as follows: ,in is the overall engagement score; is the number of characteristic indicators selected; For the A set of characteristics related to engagement; For the A function to process and normalize a feature set; For the The preset weights of the characteristic indicators.

[0011] Furthermore, in step S3, the specific steps of the phased adaptive visualization strategy library include: Step S301 : setting content priority rules to define display priorities or conditional probabilities of different types of content for each interaction stage.

[0012] Step S302 : constraining the layout templates to limit the set of available layout templates for each stage or participation level.

[0013] Step S303: formulate an interaction guidance mechanism to dynamically adjust the visibility of interactive elements or recommended terms on the interface according to the inferred user intention and the current stage to guide the user to the next step.

[0014] Step S304 : dynamically adjust the range of visualization parameters, and set upper and lower limits and adjustment steps for information density and animation intensity parameters.

[0015] Furthermore, in step S4, the operations of the real-time feedback analysis engine for processing micro-interaction feedback signals include signal windowing processing and immediate effect index calculation, wherein the signal windowing processing is to intercept the user's interaction signal sequence with a preset time window; the immediate effect index calculation calculates at least one immediate effect index among visual focus stability and interaction flow degree within the time window; and the calculated immediate effect index is compared with the expected effect baseline defined in the current stage strategy library.

[0016] Furthermore, in step S5, the operation of fine-tuning the visualization parameters based on the immediate effect evaluation result includes adjusting one or more visualization parameters within an allowable range according to a preset negative feedback adjustment rule when the calculated immediate effect index is significantly lower than the expected effect baseline; and adjusting the parameters within an allowable range according to a preset positive feedback adjustment rule when the calculated immediate effect index is significantly higher than the expected effect baseline. Furthermore, the micro-interaction feedback signal refers to a data stream obtained in real time or quasi-real time by sensors configured on the terminal, which can reflect in fine-grained terms the physiological or behavioral details of the user's interaction with the visual interface. The data stream includes at least one or more of the following data combinations: gaze point coordinate sequence, gaze duration, scanning path parameters, and pupil diameter change data from an eye tracking sensor; and fine touch operation data beyond simple clicks from a touch screen sensor.

[0017] A lottery terminal data visualization system includes: The data acquisition and scenario generation unit is used to monitor and collect the multivariate operating status parameters and user interaction data streams of the lottery sales terminal in real time, and perform signal preprocessing and feature normalization operations to generate a real-time scenario portrait.

[0018] The user state evaluation and decision-making unit is used to infer the user interaction stage and participation level based on the real-time situation portrait using a dynamic user state evaluation model, and select or decide the visualization presentation tasks and parameters of the current stage according to the staged adaptive visualization strategy library.

[0019] The visualization content presentation unit is configured to generate and adaptively adjust the presentation of the first type of data visualization content on the consumer interface of the lottery sales terminal according to the decision result of the user status evaluation and decision-making unit.

[0020] The interaction feedback collection unit is used to continuously collect the user's micro-interaction feedback signals during the presentation of visual content.

[0021] A feedback signal analysis and adjustment unit is used to process the micro-interaction feedback signal to evaluate the immediate effect of the visualization presentation, and based on the evaluation results and policy rules, fine-tune the visualization parameters being presented by the visualization content presentation unit, or trigger the user status evaluation and decision unit to re-evaluate the status when conditions are met.

[0022] The background policy management unit provides an administrator background interface with permission control, which is used for authorized administrators to configure and manage the phased adaptive visualization policy library, content library, test plan and permissions.

[0023] Compared with the prior art, the present invention has the following advantages: (1) The present invention optimizes the visual interface presentation in real time through dynamic user status evaluation and phased adaptive strategy, significantly improving the user interaction fluency and information acquisition efficiency, thereby enhancing the lottery purchasing experience and terminal marketing conversion rate; (2) The present invention realizes the dynamic matching of visual content and user cognitive load based on the real-time parameter fine-tuning mechanism of micro-interaction feedback, reduces the operation learning cost and maximizes the accuracy of promotion information reach. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The figure is a flowchart of an exemplary step of the data visualization method of the present invention.

[0025] Figure 2 The figure is a flowchart of an exemplary step of the phased adaptive visualization strategy library of the present invention.

[0026] Figure 3 A schematic block diagram of the system of the present invention. DETAILED DESCRIPTION

[0027] like Figure 3 The figure shows a schematic block diagram of the system structure of a lottery terminal data visualization system provided by this embodiment, which includes a data acquisition and scenario generation unit for real-time monitoring and acquisition of multiple operating status parameters and user interaction data streams of the lottery sales terminal, and performing signal preprocessing and feature normalization operations to generate a real-time scenario portrait.

[0028] This unit utilizes the terminal's sensors and system interfaces to monitor and collect terminal operating status parameters and user interaction data streams in real time. The unit's built-in preprocessing module performs preliminary signal processing, such as denoising, format conversion, and timestamp alignment of raw sensor data. The feature normalization module converts features from different sources and dimensions to a unified or comparable scale, ultimately generating structured, real-time contextual profile data.

[0029] The user state assessment and decision-making unit is used to infer the user's interaction stage and engagement level based on real-time contextual profiling using a dynamic user state assessment model. It then selects or decides on the visualization tasks and parameters for the current stage based on a phased adaptive visualization strategy library. This unit receives contextual profiling data from the data acquisition unit and internally incorporates a dynamic user state assessment model. Exemplarily, this model can be a time series model based on a recurrent neural network, which analyzes user interaction sequences to infer the user's current interaction stage and engagement level.

[0030] The visualization content presentation unit is responsible for generating and adaptively adjusting the presentation of the first type of data visualization content on the lottery sales terminal's consumer interface based on the user status assessment and the decision-making unit's decision results. Following instructions from the decision-making unit, this unit is responsible for generating and displaying data visualization content on the lottery sales terminal's consumer interface. For example, it might adjust the interface layout, select the data content to be displayed (lottery information, historical lottery results, recommended numbers, etc.), set information density, apply specific animation effects (such as scrolling numbers and animated charts), and adjust the relevance threshold of recommended content. Importantly, this unit is able to adaptively adjust these presentation parameters, rather than being fixed.

[0031] The interaction feedback collection unit is used to continuously collect micro-interaction feedback signals from the user during the presentation of visual content. During the presentation of visual content, this unit continuously operates, collecting micro-interaction feedback signals between the user and the currently presented content through terminal sensors. For example, these signals may include the user's gaze path across different interface elements, subtle changes in pupil diameter, touch pressure, or sliding speed / trajectory, all of which go beyond simple click events.

[0032] The feedback signal analysis and adjustment unit processes micro-interaction feedback signals to evaluate the immediate effectiveness of the visualization. Based on the evaluation results and policy rules, it fine-tunes the visualization parameters currently being presented by the visualization content presentation unit or, if conditions are met, triggers the user state evaluation and decision-making unit to reassess the state. This unit receives the micro-interaction signal stream from the interaction feedback collection unit. It contains a real-time feedback analysis engine. In one embodiment, this engine first performs windowed processing on the signals (for example, analyzing gaze data from the past two seconds) and then calculates immediate effectiveness metrics, such as "visual focus stability" or "interaction fluency" for the user within the window. These calculated metrics are then compared with the "expected effectiveness baseline" preset in the policy library for the current user state and visualization task. Based on the comparison results and predefined policy rules, the unit fine-tunes the parameters of the visualization content currently being presented. For example, negative feedback may result in reducing information density or increasing button contrast; positive feedback (such as very smooth interaction) may result in accelerating animation speed or recommending more in-depth information. When specific conditions are met, this unit can also trigger the user state evaluation and decision-making unit to conduct a comprehensive state reassessment.

[0033] The backend policy management unit provides an administrator backend interface with permission control, which is used for authorized administrators to configure and manage the phased adaptive visualization policy library, content library, test plans and permissions.

[0034] This embodiment provides a lottery terminal data visualization method, such as Figure 1 FIG. 1 is a flowchart of an exemplary step of the data visualization method of this embodiment, which includes the following steps: Step S1: Real-time monitoring and collection of multiple operating status parameters and user interaction data streams of the lottery sales terminal. The operating status parameters include at least terminal load, network conditions, and current promotional information. The user interaction data stream includes at least touch operation sequences, eye tracking data, and voice commands. Signal preprocessing and feature normalization operations are performed on the collected raw data.

[0035] In one embodiment, after the system is started, the data acquisition unit continuously monitors the terminal status, for example, using the system API to obtain CPU load and network latency data once per second, and syncing the latest promotional information from the backend. Simultaneously, it collects user interaction data at a high frequency, such as recording touch point sequences on the touch screen at a frequency of 60Hz, recording gaze point coordinates and pupil diameter data output by the eye tracker at a frequency of 30Hz or higher, and processing the audio stream input from the microphone in real time to identify potential voice commands.

[0036] For example, preprocessing is performed on the collected raw data: de-jittering and smoothing are performed on the touch point sequence; invalid fixations caused by blinking or rapid saccades are filtered out from the eye movement data; and noise reduction and endpoint detection are performed on the speech data. The processed data is then feature normalized, for example, by mapping both CPU load and fixation duration to the [0, 1] range using minimum-maximum scaling.

[0037] Step S2: Based on the preprocessed data, a dynamic user state evaluation model is used to infer the current user's interaction stage and engagement level in real time; and combined with the terminal operation state parameters, a unified real-time situational portrait is generated.

[0038] Based on the data stream processed in step S1, the user state evaluation and decision-making unit uses its dynamic user state evaluation model (LSTM model) to make real-time inferences. For example, based on the behavior sequence of the user's gaze jumping between different color areas and a small number of clicks in the last 5 seconds, the model may infer that the user is in the "browsing and exploration" stage. At the same time, the engagement scoring module calculates a lower score based on the low interaction frequency and distracted attention during this period. The score is used to determine the engagement level as "low". Combining the inferred user stage and engagement level with the terminal status obtained from S1, a unified real-time context profile is generated, such as "{User stage: Browsing and Exploration, Engagement: Low, Terminal Load: Normal, Network: Good, Current Activity: New User Offer}".

[0039] Step S3: Based on the real-time situational portrait and a preset or dynamically adjusted phased adaptive visualization strategy library, select and execute the visualization presentation task of the current stage; the strategy library predefines content priority rules, layout template constraints, interaction guidance mechanisms, and dynamic adjustment ranges of visualization parameters for different user interaction stages and engagement levels; visualization parameters include at least information density, animation effect intensity, and relevance thresholds for recommended content.

[0040] like Figure 2 FIG. 1 is a flowchart of an exemplary step of the phased adaptive visualization strategy library of this embodiment. The specific steps of the phased adaptive visualization strategy library include: Step S301 sets content priority rules, defining the display priority or conditional probability of different types of content for each interaction phase. These rules can be dynamically generated or selected based on the user's historical behavior, immediate needs inferred from the current contextual profile, or preset business logic. For example, during the user's "browsing" phase, promotional information may take precedence over detailed rules for specific gameplay, while during the user's "number selection" phase, prompt information directly related to the number selection operation has the highest priority. Conditional probability means that the system will display a certain recommended content with a certain probability based on a comprehensive evaluation, such as within a specific time period or under a specific user profile.

[0041] Step S302 constrains the layout templates, limiting the set of available layout templates for each stage or engagement level. A layout template is a pre-designed layout of various interface elements, such as "focused," "information overview," or "guided steps." Constraints mean that the system selects the most appropriate templates from a pre-set template library, or a single template, based on the user's current interaction stage and the engagement level assessed in S2.

[0042] Step S303: Develop an interaction guidance mechanism to dynamically adjust the visibility of interactive elements or recommended terms on the interface based on the inferred user intent and the current stage, to guide the user to the next step. User intent is derived by analyzing the interaction data stream collected by the user in S1 and combining it with the user state assessment model in S2. Adjusting the visibility of interactive elements can include changing the size and color of buttons, adding visual emphasis such as breathing light effects or micro-animations, and dynamically generating or selecting appropriate text prompts based on the current scenario and the user's potential needs. For example, when the user remains on an interface for a long time without performing any operation, guiding text such as "Need help?" or "Try this function?" can pop up.

[0043] Step S304 dynamically adjusts the range of visualization parameters, setting upper and lower limits and adjustment steps for information density and animation intensity parameters. The dynamic adjustment here ensures that even during the adaptive change process, these parameters will not exceed the preset reasonable range, thereby ensuring the consistency and usability of the user experience. For example, the upper limit of information density can prevent the interface from being too crowded and difficult to identify, while the lower limit ensures the presentation of necessary information; the upper limit of animation intensity avoids the performance consumption or user disgust that may be caused by overly cool animations, while the lower limit ensures the necessary dynamic feedback effect. The adjustment step size defines the amplitude of each adjustment, making the changes smoother or more controllable.

[0044] Based on the real-time situational portrait generated in step S2, the user status assessment and decision-making unit queries the phased adaptive visualization strategy library. In one embodiment, the strategy library presets rules for the "browsing and exploration" stage and the "low engagement" state: corresponding to S301 content priority, "hot lottery types" and "newcomer discounts" information are prioritized, followed by gameplay introductions; corresponding to S302 layout constraints, layout template C is selected, which features a large image area, minimal text, and a prominent entry button; corresponding to S303 interactive guidance, a slight breathing light animation effect is used to draw attention to the "newcomer discount" area; corresponding to S304 parameter range, information density is set to "low", animation intensity is set to "medium", and the recommended content relevance threshold is set to "0.6".

[0045] Step S4: During the presentation of visual content, the user's micro-interaction feedback signals are continuously collected, and the real-time feedback analysis engine is used to process the signals to evaluate the immediate effect of the current visual presentation. During the presentation of visual content, the interactive feedback collection unit continuously collects the user's micro-interactions. For example, it is detected that the user's eyes stay in the "Double Color Ball" area for a long time, followed by a click operation, but then the eyes quickly move away and wander in other areas. The real-time feedback analysis engine of the feedback signal analysis and adjustment unit processes these signals. In one embodiment, it analyzes with a window of 2 seconds and calculates that the visual focus stability index in the window is 0.4, and the interactive fluency index is also low.

[0046] Step S5: Based on the immediate effect evaluation result and in accordance with the parameter dynamic adjustment rules defined in the policy library, fine-tune at least one visualization parameter of the currently presented visualization content within an allowable range.

[0047] Based on the immediate effect evaluation result of step S4, the feedback signal analysis and adjustment unit operates according to the adjustment rules defined in the policy library. For example, the rules may indicate: for negative feedback in the "browsing exploration" stage, try to reduce the information density. Then, the system fine-tunes the visualization parameters, and the instruction presentation unit removes a secondary recommendation position on the interface and slightly enhances the visual contrast of the "Double Color Ball" area. Alternatively, if the negative feedback persists, or it is detected that the user has issued a clear voice instruction, which meets the conditions for triggering state re-evaluation defined in the policy library, the unit will trigger the user state evaluation and decision-making unit to perform a comprehensive state update and decision-making. In step S2, the dynamic user state evaluation model includes a time series behavior analysis module for processing interaction sequence data, which uses a neural network to analyze touch operation and eye trajectory time series data; an engagement scoring module for quantifying user engagement, which calculates a comprehensive engagement score. , which is calculated as follows: ,in is the overall engagement score; is the number of characteristic indicators selected; For the A set of features related to engagement; for example, it may include "number of effective interactions per unit time", "percentage of time the gaze stays in key information areas", "task completion", etc. For the A function to process and normalize a feature set; For the The preset weights of various feature indicators are used; for example, the weight of "eye retention" may be higher in the "information search" stage than in the "browsing and exploration" stage.

[0048] In step S4, the operations of the real-time feedback analysis engine for processing micro-interaction feedback signals include signal windowing processing and immediate effect index calculation. Signal windowing processing is to intercept the user's interaction signal sequence in a preset time window; immediate effect index calculation is to calculate at least one immediate effect index including visual focus stability and interaction flow degree within the time window; and the calculated immediate effect index is compared with the expected effect baseline defined in the current stage strategy library.

[0049] In step S5, the operation of fine-tuning the visualization parameters based on the immediate effect evaluation result includes adjusting one or more visualization parameters within an allowable range according to a preset negative feedback adjustment rule when the calculated immediate effect index is significantly lower than the expected effect baseline; and adjusting the parameters within an allowable range according to a preset positive feedback adjustment rule when the calculated immediate effect index is significantly higher than the expected effect baseline. Micro-interaction feedback signals refer to data streams acquired in real time or quasi-real time by sensors configured on the terminal, which can reflect in fine-grained terms the physiological or behavioral details of the user's interaction with the visual interface. The data streams contain at least one or more of the following data combinations: gaze point coordinate sequence, gaze duration, scanning path parameters, and pupil diameter change data from eye tracking sensors; and fine touch operation data beyond simple clicks from touch screen sensors.

[0050] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in similar ways. As long as they do not deviate from the scope defined by the invention, they should all fall within the scope of protection of the present invention.

Claims

1. A lottery terminal data visualization method, characterized in that: The steps include: Step S1: Real-time monitoring and collection of multiple operating status parameters and user interaction data streams of the lottery sales terminal, wherein the operating status parameters include at least terminal load, network conditions, and current promotional information, and the user interaction data stream includes at least touch operation sequences, eye tracking data, and voice commands; and performing signal preprocessing and feature normalization operations on the collected raw data; Step S2: Based on the pre-processed data, a dynamic user state evaluation model is used to infer the current user's interaction stage and engagement level in real time; and combined with the terminal operation state parameters, a unified real-time situation profile is generated; Step S3: Based on the real-time situational portrait and a preset or dynamically adjusted phased adaptive visualization strategy library, a visualization presentation task for the current phase is selected and executed; the strategy library predefines content priority rules, layout template constraints, interaction guidance mechanisms, and dynamic adjustment ranges of visualization parameters for different user interaction phases and engagement levels; the visualization parameters include at least information density, animation effect intensity, and a relevance threshold for recommended content; Step S4: During the presentation of the visual content, continuously collect the user's micro-interaction feedback signals, and process the signals using a real-time feedback analysis engine to evaluate the immediate effect of the current visual presentation; Step S5: Based on the instant effect evaluation result and in accordance with the parameter dynamic adjustment rules defined in the policy library, fine-tune at least one visualization parameter of the currently presented visualization content within an allowable range.

2. A lottery terminal data visualization method according to claim 1, characterized in that In step S2, the dynamic user state evaluation model includes a time series behavior analysis module for processing interaction sequence data, which uses a neural network to analyze touch operation and sight trajectory time series data; an engagement scoring module for quantifying user engagement, which calculates a comprehensive engagement score. , which is calculated as follows: ,in is the overall engagement score; is the number of characteristic indicators selected; For the A set of characteristics related to engagement; For the A function to process and normalize a feature set; For the The preset weights of the characteristic indicators.

3. A lottery terminal data visualization method according to claim 1, characterized in that: In step S3, the specific steps of the phased adaptive visualization strategy library include: Step S301 , setting content priority rules to define the display priority or conditional probability of different types of content for each interaction stage; Step S302 , constraining the layout templates to limit the set of available layout templates for each stage or participation level; Step S303: developing an interaction guidance mechanism to dynamically adjust the visibility of interactive elements or recommended terms on the interface based on the inferred user intent and the current stage, so as to guide the user to the next step; Step S304 : dynamically adjust the range of visualization parameters, and set upper and lower limits and adjustment steps for information density and animation intensity parameters.

4. A lottery terminal data visualization method according to claim 1, characterized in that In step S4, the operations of the real-time feedback analysis engine for processing micro-interaction feedback signals include signal windowing processing and immediate effect index calculation, wherein the signal windowing processing is to intercept the user's interaction signal sequence in a preset time window; the immediate effect index calculation calculates at least one immediate effect index of visual focus stability and interaction flow degree within the time window; and the calculated immediate effect index is compared with the expected effect baseline defined in the current stage strategy library.

5. A lottery terminal data visualization method according to claim 1, characterized in that In step S5, the operation of fine-tuning the visualization parameters based on the immediate effect evaluation result includes: when the calculated immediate effect index is significantly lower than the expected effect baseline, adjusting one or more visualization parameters within the allowable range according to the preset negative feedback adjustment rules; when the calculated immediate effect index is significantly higher than the expected effect baseline, adjusting the parameters within the allowable range according to the preset positive feedback adjustment rules.

6. A lottery terminal data visualization method according to claim 1, characterized in that: The micro-interaction feedback signal refers to a data stream obtained in real time or quasi-real time by sensors configured on the terminal, which can reflect the physiological or behavioral details of the user's interaction with the visual interface in a fine-grained manner. The data stream includes at least one or more of the following data combinations: gaze point coordinate sequence, gaze duration, scanning path parameters and pupil diameter change data from eye tracking sensors; and fine touch operation data beyond simple clicks from touch screen sensors.

7. A lottery terminal data visualization system, characterized in that: include: The data collection and scenario generation unit, as the starting point of the system, is responsible for real-time monitoring and collection of multiple operating status parameters and user interaction data streams of lottery sales terminals; After signal preprocessing and feature normalization, the collected raw data is integrated into a real-time situational profile, providing a basis for subsequent user status assessment; The User State Assessment and Decision-Making Unit receives and, based on the real-time contextual portraits generated by the Data Collection and Context Generation Unit, utilizes a dynamic user state assessment model to infer the current user's interaction stage and engagement level in real time. In this model, the comprehensive engagement score is a key metric for quantifying user engagement. Combining the inferred user interaction stage and constructed user state, the unit further selects and determines the most appropriate visualization presentation tasks and related parameters for the current stage based on a preset or dynamically adjusted "Phase-Based Adaptive Visualization Strategy Library." The visualization content presentation unit, based on the decision results of the "user status assessment and decision-making unit," is responsible for generating and adaptively adjusting the specific presentation of the first type of data visualization content on the consumer interface of the lottery sales terminal; An interaction feedback collection unit, used to continuously collect micro-interaction feedback signals from users during the presentation of visual content; A feedback signal analysis and adjustment unit, configured to process the micro-interaction feedback signal to evaluate the immediate effect of the visualization presentation, and fine-tune the visualization parameters being presented by the visualization content presentation unit based on the evaluation result and policy rules, or trigger the user status evaluation and decision unit to re-evaluate the status when conditions are met; The background policy management unit provides an administrator background interface with permission control, which is used for authorized administrators to configure and manage the phased adaptive visualization policy library, content library, test plan and permissions.

Images