User dynamic activity calculation method, device and system based on ETC data

Abstract

The application discloses a user dynamic activity degree calculation method, device and system based on ETC data, and belongs to the technical field of data analysis. The method comprises the following steps: obtaining toll data and associated consumption data corresponding to a unique identifier of a user under an ETC account of the user; aligning the two in time and space through a preset time-space correlation condition, constructing a toll-consumption event chain, and calculating a current dynamic activity degree value of a geographic node based on a time-space decay dynamic weight model; dividing the activity degree into levels according to double thresholds, rendering the levels in a differentiated visual style, and superimposing a consumption feature icon to realize visual dynamic updating. The application breaks through the limitation of single-dimensional analysis, integrates toll and consumption data, realizes accurate quantification of the activity degree through a time-space decay model, intuitively presents user behavior characteristics, improves the application value of ETC data, and provides data support for expressway operation analysis, high-activity-degree area identification and accurate decision-making.

Description

Technical Field

[0001] This application belongs to the field of data analysis technology, and in particular relates to a method, device and system for calculating user dynamic activity based on ETC data. Background Technology

[0002] Electronic Toll Collection (ETC) systems, as the mainstream technology for highway toll collection, have been fully implemented nationwide, accumulating massive amounts of user traffic flow data and related consumption data. ETC data not only includes basic traffic information such as vehicle entrance and exit toll stations, travel time, and vehicle type, but also correlates with multi-dimensional consumption behavior data such as service area spending, parking lot payments, and third-party commercial points, providing core data support for understanding user travel patterns, consumption preferences, and regional activity levels.

[0003] However, existing technologies for analyzing user activity using ETC data have significant limitations. Traditional solutions only count user activity at each toll station / area based on the number of passages, completely ignoring ETC-related consumption data. This fails to reflect the actual consumption activity and contribution of users within the area, making it difficult to accurately characterize high-activity users and high-activity areas. Existing activity calculations mostly use static weights, failing to consider the time decay effect and unable to distinguish between "recent high-frequency travel" and "historical low-frequency travel." As a result, the activity results cannot truly reflect the user's current travel activity and regional stickiness, and do not conform to the natural memory of user travel behavior and the pattern of activity decline. Passage data and consumption data are disconnected, failing to achieve accurate spatiotemporal alignment through unique user identifiers. This makes it impossible to construct a complete "passage-consumption" behavior chain, resulting in insufficient data value mining and difficulty in supporting refined operational decisions. Some solutions only use activity data for static heatmap display, failing to achieve deep linkage between activity calculation and visualization rendering. This fails to intuitively present the dynamic changes in user activity and consumption characteristics, making it difficult to meet the real-time perception needs of operations personnel for user behavior.

[0004] Existing technologies cannot accurately calculate user activity levels across two dimensions—"traffic + consumption"—and with dynamic decay over time and space, making it difficult to meet the core needs of highway operators for in-depth analysis of user behavior, identification of high-activity areas, and precise marketing. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, and system for calculating user dynamic activity based on ETC data. By using a unique user identifier, the method achieves spatiotemporal alignment of passage data and consumption data, constructs a passage-consumption event chain, and accurately quantifies the dynamic activity of users at geographical nodes based on a spatiotemporal decay dynamic weight model. This overcomes the shortcomings of existing technologies, such as single dimension, static memorylessness, and data fragmentation, and provides reliable support for highway operation analysis and accurate decision-making.

[0006] To achieve the above objectives, the solution proposed in this application is: In a first aspect, embodiments of this application provide a method for calculating user dynamic activity based on ETC data, including: Obtain the passage data and associated consumption data corresponding to the user's unique identifier under the user's ETC account; Using the user's unique identifier as the primary key, the passage data that meets the preset spatiotemporal association conditions is matched and aligned with the associated consumption data to generate passage-consumption events for the corresponding geographical nodes, and then linked together in chronological order to form a passage-consumption event chain. Based on the passage-consumption event chain, the dynamic activity value of the target geographic node at the current moment is calculated through a spatiotemporal decay dynamic weight model.

[0007] The method described in the embodiments of this application may also have the following additional technical features: Furthermore, the formula for the spatiotemporal decay dynamic weight model is as follows:

[0008] in, Indicates the target geographic node at the current time. The dynamic activity value; This represents the total number of access-consumption events corresponding to the target geographic node; This represents the base passage weight corresponding to a single passage event; Indicates the first The consumption contribution value corresponding to each pass-consumption event, consumption contribution value The pass event is assigned a value based on a preset segmented range of the user's consumption value at the target geographic node. The pass event with no consumption value corresponds to... ; This represents the consumption weighting factor; Represents the time decay constant; Indicates the first The timing of each transit-consumption event.

[0009] Furthermore, the preset spatiotemporal correlation conditions include: Under the same unique user identifier, the difference between the consumption time and the corresponding passage time is within a preset time window, and the straight-line distance between the consumption location and the corresponding ETC entrance / exit location is less than a preset distance threshold.

[0010] Furthermore, the consumption weighted coefficient Time decay coefficient All are adaptively adjusted based on one or more of the following: user type, vehicle type, and travel frequency; the dynamic activity value decays exponentially over time and is updated with the recording of new travel-consumption events.

[0011] Furthermore, a first threshold and a second threshold are preset. Based on the relationship between the dynamic activity value and the first and second thresholds, the geographic nodes are divided into activity levels, and differentiated visuals are used for hierarchical visualization rendering based on different activity levels.

[0012] Furthermore, the activity levels include dormant, active, and core states; When the dynamic activity value is less than the first threshold, the geographic node is classified as dormant. When the dynamic activity value is greater than or equal to the first threshold and less than the second threshold, the geographic node is classified as active. When the dynamic activity value is greater than the second threshold, the geographic node is classified as the core state.

[0013] Secondly, embodiments of this application provide a user dynamic activity calculation device based on ETC data, comprising: The data acquisition module is configured to acquire the passage data and associated consumption data corresponding to the user's unique identifier under the user's ETC account; The event association module is configured to use the user's unique identifier as the association primary key to match and align the access data and associated consumption data that meet the preset spatiotemporal association conditions, generate access-consumption events for the corresponding geographical nodes, and string them together in chronological order to form an access-consumption event chain; The active calculation module is configured to calculate the dynamic activity value of the target geographic node at the current moment based on the passage-consumption event chain and through a spatiotemporal decay dynamic weight model.

[0014] Furthermore, it also includes a visual rendering module, which is configured to preset a first threshold and a second threshold, divide geographic nodes into activity levels according to the relationship between the dynamic activity value and the first and second thresholds, and perform hierarchical visual rendering based on different activity levels using differentiated visuals.

[0015] Thirdly, embodiments of this application provide a user dynamic activity calculation system based on ETC data. The system includes a processor and a memory. The memory stores a computer program, which is loaded and executed by the processor to implement the user dynamic activity calculation method provided in the first aspect of embodiments of this application.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it is used to implement the user dynamic activity calculation method provided in the first aspect of embodiments of this application.

[0017] The user dynamic activity calculation method based on ETC data provided in this application has the following advantages compared with the prior art: This application's embodiments do not calculate activity solely based on the number of passages. Instead, they achieve spatiotemporal alignment of passage data and consumption data through unique user identifiers, integrating consumption contribution values ​​into a spatiotemporal decay dynamic weighting model. This allows dynamic activity to simultaneously reflect the combined impact of user passage and consumption behaviors, solving the problem of limited analytical dimensions in existing technologies that rely solely on passage data. Furthermore, the spatiotemporal decay dynamic weighting model introduces a time decay coefficient, assigning differentiated weights to passage-consumption events occurring at different times. This accurately distinguishes the impact of recent and historical events on current activity, truly reflecting the user's current state and overcoming the deficiency of existing static weights in reflecting time decay. The dynamic activity value calculated in this application's embodiments is a result of integrating passage conditions and consumption contributions, providing objective and quantifiable data support for highway operation analysis.

[0018] The model in this application supports real-time recording and updating of new access-consumption events, enabling dynamic activity levels to increase instantly with user behavior and reflect changes in user area activity in a timely manner. The model performs natural decay on geographical nodes that have not been accessed for a long time, which can realistically simulate the fading process of user behavior memory, making the activity calculation results closer to the actual user behavior state.

[0019] This application embodiment divides dynamic activity into different activity levels by pre-setting two thresholds (a first threshold and a second threshold), providing accurate and stable calculation data for hierarchical visualization with differentiated visual styles, enabling the visualization effect to accurately reflect the true level of user area activity. The visualization based on dynamic activity not only distinguishes different activity levels but also achieves visual effect mapping through consumption contribution values, improving the intuitiveness and effectiveness of the visualized information.

[0020] The dynamic activity data in this application can accurately identify high-frequency travel and high-consumption areas for users, providing important data for the layout of highway service areas and the operation and management of toll stations, thereby improving the accuracy of operational decisions. By combining the travel-consumption event chain with dynamic activity data, user travel patterns can be comprehensively analyzed, providing highway operators with accurate user service data and improving operational efficiency and service quality. Attached Figure Description

[0021] Figure 1A flowchart illustrating the user dynamic activity calculation method based on ETC data according to an embodiment of this application is shown. Figure 2 This paper shows a structural block diagram of a user dynamic activity calculation device based on ETC data according to an embodiment of this application; Figure 3 A structural block diagram of a computer device according to an embodiment of this application is shown; Figure 4 A structural block diagram of a user dynamic activity calculation device based on ETC data according to another embodiment of this application is shown; Figure 5 A flowchart illustrating another embodiment of the method for calculating user dynamic activity based on ETC data is shown. Detailed Implementation

[0022] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, it should be noted that, for ease of description, only the parts relevant to this application are shown in the accompanying drawings, not the entire structure. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0023] The terms “comprising” and “having”, and any variations thereof, used in this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0024] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0025] like Figure 1 As shown in the figure, this application provides a method for calculating user dynamic activity based on ETC data, including the following steps: Step 101: Obtain the passage data and associated consumption data corresponding to the user's unique identifier under the user's ETC account.

[0026] In this embodiment, the user's unique identifier is used as the globally unique association primary key. The passage data and associated consumption data under the corresponding user's ETC account are uniformly collected and extracted from the highway ETC clearing and settlement system, toll lane system, service area consumption system, parking management system and third-party commercial cooperation platform. This ensures that the multi-source heterogeneous data of the same user can be clearly attributed and correspond one-to-one, avoiding data disorder, loss or duplicate matching caused by inconsistent user identifiers. This provides a real, complete and reliable original data foundation for subsequent spatiotemporal alignment and dynamic activity calculation.

[0027] Specifically, the traffic data in this embodiment includes: entrance toll station ID, exit toll station ID, travel time, and vehicle type. The entrance and exit toll station IDs uniquely identify the location nodes where a vehicle enters or exits the highway, clarifying the user's starting and ending points and providing a basic positioning basis for subsequent spatial location matching and geographical node division. Travel time records the precise time when a user arrives at or leaves the corresponding geographical node, providing a temporal basis for time-diminishing calculations. Vehicle type distinguishes vehicle types, ensuring that the behavioral data of different types of users can be reasonably differentiated, thus ensuring the accuracy and consistency of subsequent activity calculations.

[0028] Specifically, the associated consumption data includes: service area consumption records and parking payment records linked to the ETC card, or associated third-party commercial consumption points data. Service area consumption records, parking payment records, and third-party commercial consumption points data are all real consumption behavior data generated by users within highway travel scenarios, objectively reflecting users' consumption behavior and intensity at corresponding geographical nodes. Simultaneously acquiring the above consumption data with toll data breaks through the traditional single-dimensional analysis model that relies solely on toll data. This allows the subsequent construction of dynamic activity metrics to integrate both toll behavior and consumption contributions, achieving a more comprehensive, realistic, and accurate measurement of user activity and avoiding evaluation bias caused by ignoring consumption behavior.

[0029] This step uses unique user identifiers to achieve unified collection and cleaning of multi-source data, ensuring that the data source is legitimate, the fields are complete, the time sequence is continuous, and the attribution is accurate. This provides stable and standardized data input for the subsequent spatiotemporal alignment of passage-consumption events and the calculation of the spatiotemporal decay dynamic weight model.

[0030] Step 102: Using the user's unique identifier as the primary key, match and align the access data and related consumption data that meet the preset spatiotemporal association conditions to generate access-consumption events for the corresponding geographical nodes, and string them together in chronological order to form an access-consumption event chain.

[0031] In this embodiment of the application, the user's unique identifier is used as the global association primary key. The passage data and associated consumption data obtained in step 101 are spatiotemporally matched and aligned to generate the passage-consumption events of the corresponding geographical nodes, and are connected in time order to form a passage-consumption event chain. Then, based on the passage-consumption event chain, the dynamic activity value of the target geographical node at the current time is calculated through the spatiotemporal decay dynamic weight model.

[0032] This application embodiment uses preset spatiotemporal association conditions to accurately link the passage behavior and consumption behavior of the same user as the same event, avoiding mismatches caused by data fragmentation. The preset spatiotemporal association conditions include temporal association conditions and spatial association conditions. Specifically, the temporal association condition includes ensuring that, under the same user's unique identifier, the difference between the consumption time and the corresponding passage time is within a preset time window, such as 15 or 30 minutes before or after the passage, guaranteeing that the consumption behavior occurs within a reasonable timeframe for this passage. The spatial association condition includes ensuring that the straight-line distance between the consumption location and the corresponding ETC entrance / exit location is less than a preset distance threshold, such as 1 km or 2 km, guaranteeing that the consumption behavior occurs near the geographical node of this passage.

[0033] When a passage record and one or more consumption records simultaneously meet the above-mentioned time association and spatial association conditions, they are matched and aligned to generate a passage-consumption event corresponding to the geographic node; all passage-consumption events of the same user under the same geographic node are sorted in chronological order of occurrence and linked together to form a passage-consumption event chain for that geographic node, providing time-series structured data input for subsequent dynamic activity calculation.

[0034] Specifically, all data is grouped according to the user's unique identifier to ensure that the passage records and consumption records of the same user are collected in the same dataset, avoiding confusion or mismatch between data from different users. For each passage record, the user's unique identifier, passage time, and entrance / exit toll station ID (location) are recorded; for each consumption record, the user's unique identifier, consumption time, and consumption location (latitude and longitude or POI) are recorded. An index is built according to the user's unique identifier, and matching and alignment are only performed within the dataset of the same user to ensure the accuracy of data attribution.

[0035] Within the same user's dataset, for each passage record, all of the user's consumption records are traversed to determine if the aforementioned time-related and spatial-related conditions are simultaneously met. When a passage record and one or more consumption records simultaneously meet these conditions, they are associated as a complete passage-consumption event. The core attributes of this event include: user unique identifier, geographic node (entrance / exit toll station ID), event time (based on passage time), and consumption contribution value (calculated from the associated consumption amount). If a passage record has no associated consumption records, a passage-consumption event containing only the passage behavior is still generated, in which case the consumption contribution value is 0. Subsequently, all passage-consumption events of the same user under the same geographic node are sorted according to the chronological order of the events and linked together to form a passage-consumption event chain for that geographic node, providing time-seriesd and structured data input for subsequent dynamic activity calculations.

[0036] Step 103: Based on the passage-consumption event chain, calculate the dynamic activity value of the target geographic node at the current moment through the spatiotemporal decay dynamic weight model.

[0037] Based on the constructed access-consumption event chain, the spatiotemporal decay dynamic weight model shown in the following formula is used to calculate the target geographic node at the current time. Dynamic activity value:

[0038] The formula calculates the contribution of each passage-consumption event at the target geographic node to the current activity level, and then sums up the contributions of all events to obtain the final dynamic activity value. It is primarily composed of the "basic contribution" of a single event. and time decay correction term Composition, multiplication of the two, and then processing of all events. Summation yields... .

[0039] in, Indicates the target geographic node at the current time. The dynamic activity value, It is the final output of the model, a numerical value used to quantify the level of user activity at that geographic node, providing a basis for subsequent classification, visualization, or operational decisions.

[0040] This represents the total number of passage-consumption events corresponding to the target geographic node; it also represents how many times the user has engaged in matching passage-consumption behavior at that node, which determines the range of the summation and directly reflects the user's passage frequency at that node.

[0041] This represents the basic pass weight corresponding to a single pass event; this weight is a fixed value, meaning that "as long as a user passes through once, it will contribute a basic value to the activity score," which is the basic threshold for activity score, ensuring that pass behavior without consumption can also be included in the activity score.

[0042] Indicates the first The consumption contribution value corresponding to each pass-consumption event, consumption contribution value The pass event is assigned a value based on a preset segmented range of the user's consumption value at the target geographic node. The pass event with no consumption value corresponds to... ; This represents the consumption-weighted coefficient, used to adjust the strength of the impact of consumption on activity level. The larger the value, the stronger the amplifying effect of consumption contribution on activity level; The smaller the size, the more emphasis is placed on the passage itself.

[0043] This represents the time decay constant, used to control the rate at which activity decays over time. The larger the value, the faster the decay, and the faster the impact of historical events on current activity disappears; The smaller the value, the slower the decay, and the longer the impact of historical behavior lasts.

[0044] Indicates the first The occurrence time of a passage-consumption event is typically taken as the midpoint between the passage time and the associated consumption time, and is used as the timestamp for calculating the time difference between the event and the current time. .

[0045] The term represents an exponential decay, simulating the natural fading pattern of user behavioral memory. The closer the event occurred (…), the more pronounced the decay. The smaller the value, the closer it is to 1, and the contribution hardly diminishes; the further back in time the event occurred ( The larger the value, the closer it is to 0, and the contribution becomes almost zero, thus achieving the effect of "great impact of short-term behavior and small impact of long-term behavior".

[0046] The basic contribution of each event is This is calculated as "basic pass weight + amplified consumption contribution". The contribution of a pass event without consumption is... Even if a user makes a purchase, their activity level will still be counted; the contribution from a popular event will be recorded as [amount]. The activity level will be higher than that of simple passage, reflecting the activity level of consumption.

[0047] To better adapt the model to the behavioral characteristics of different user groups and improve the accuracy and rationality of activity calculation, the consumption weighting coefficient in this application embodiment... Time decay coefficient All support adaptive adjustments based on one or more of the following: user type, vehicle model, and travel frequency.

[0048] User types are categorized based on "vehicle type + travel frequency." Travel frequency is calculated from the passage data in step 101, using passage time and entrance / exit toll station IDs to count the number of times a user passes through a given period. For example, a user who passes through ≥10 times within 30 days is considered a high-frequency user; this is a direct statistical result of the passage data.

[0049] Specifically, in this embodiment, users are divided into two categories: high-frequency users and low-frequency users, or non-commercial passenger vehicle users and commercial vehicle users. For commercial vehicle users (such as trucks and buses), whose travel frequency is high and whose single-transaction spending is typically low, the consumption weighting coefficient can be appropriately reduced. This avoids a single small purchase having an excessive impact on activity levels; it also increases the time decay coefficient. This accelerates the decay rate of historical event activity, more accurately reflecting the changes in activity levels under high-frequency travel by commercial vehicles.

[0050] For non-commercial passenger vehicle users, their travel frequency is relatively low, and the contribution of a single consumption behavior to the regional activity level is relatively significant. Therefore, the consumption weighting coefficient can be appropriately increased. This reflects the role of consumer behavior in boosting activity levels; it can also reduce the time decay coefficient. This slows down the decay rate of historical events and prevents activity levels from rapidly dropping to zero due to low-frequency travel.

[0051] Users of different vehicle types exhibit significantly different travel characteristics. Different settings can be implemented based on the vehicle type field in the traffic data. For commercial vehicles such as large trucks and buses, adjustments should be made according to the rules for commercial vehicles. and For non-commercial passenger vehicles, the rules for non-commercial passenger vehicles shall apply. and This adjustment process can be achieved through a pre-configured vehicle model-parameter mapping table, which automatically matches the corresponding parameter values ​​based on the vehicle model identifier under the user's ETC account, without requiring manual intervention.

[0052] Travel frequency can be obtained by counting the number of times a user travels within a preset statistical period (such as 30 days or 90 days). For example, if a user's average monthly number of travels exceeds a preset high-frequency threshold, they are identified as a high-frequency user, and the corresponding increase is applied. If a user's average monthly number of visits is lower than a preset low-frequency threshold, they are classified as a low-frequency user, and their usage is reduced accordingly. It can also periodically (e.g., daily, weekly) update users' travel frequency levels based on their historical travel data and simultaneously adjust the corresponding model parameters to achieve dynamic adaptation.

[0053] The above parameter adjustment rules can be implemented through a preset configuration table or an adaptive algorithm. Before each activity calculation, the user's unique identifier is used to query the corresponding user type, vehicle type, and travel frequency level, and then the corresponding parameters are automatically matched. and This ensures that the model parameters are always adapted to user behavior characteristics, thereby improving the rationality of the calculation results.

[0054] The dynamic activity value in this application embodiment also supports two dynamic update modes, fully covering the change process of user behavior. With the real-time update of new events, when the system receives a new access-consumption event and adds it to the event chain, the basic access weight corresponding to the event is updated. With consumption contribution value This information is directly added to the activity calculation of the corresponding geographic node, causing an instantaneous increase in the node's activity value. This process can be triggered during event entry, without waiting for a scheduled task, ensuring that the activity level reflects changes immediately after user behavior occurs.

[0055] It can also traverse all geographic nodes according to a preset time step (such as hourly or daily), based on the current time. The decay term for each event is recalculated, and the activity value is updated. Alternatively, an incremental update method can be used, performing decay calculations only on nodes whose activity values ​​have not returned to zero, reducing the system's computational load. This decay process simulates the natural fading of user behavior memories, ensuring that the activity value always reflects the user's current true state, rather than historical states.

[0056] By combining the two update modes described above, this application embodiment achieves full-cycle dynamic tracking of user activity, which can respond to new behaviors in real time and accurately reflect the time decay of behaviors, making the activity calculation results closer to the actual changes in user behavior.

[0057] In addition, such as Figure 5 As shown, the embodiment of this application includes step 104, which involves setting a first threshold and a second threshold, dividing the geographic nodes into activity levels based on the relationship between the dynamic activity value and the first and second thresholds, and performing hierarchical visualization rendering based on different activity levels using differentiated visuals.

[0058] This application embodiment uses a preset first threshold (low threshold) and a second threshold (high threshold). The setting of the two thresholds is based on the distribution characteristics of user behavior at geographical nodes and business operation needs. They are determined jointly through statistical analysis and business rules. Specifically, based on the historical dynamic activity value distribution of the target user group at each geographical node, reasonable hierarchical nodes are determined through statistical analysis to ensure a balanced distribution of users at different levels and avoid the proportion of a certain level being too high or too low. The hierarchical results need to match the highway operation scenario and be able to effectively distinguish between "areas with no long-term interaction", "areas with stable interaction" and "high-activity core activity areas", providing effective support for operational decisions. The thresholds also support differentiated configuration according to different user groups and different regional characteristics, and can be periodically iterated and optimized based on the latest user behavior data to adapt to changes in user behavior.

[0059] This application embodiment classifies geographic nodes into three activity levels—dormant, active, and core—based on the relationship between dynamic activity values ​​and two thresholds. The first threshold serves as the boundary between dormant and active states. When the dynamic activity value is less than the first threshold, the geographic node is classified as dormant. The goal is to distinguish between "areas with no long-term interaction" and "areas with stable interaction." Using historical dynamic activity values ​​of users at each geographic node as samples, their distribution characteristics are statistically analyzed. A lower percentile (e.g., 10%~20% percentile) is selected as the initial threshold to ensure that most nodes without recent interaction are classified as dormant. Based on operational experience, a minimum activity threshold is set, such as the upper limit of node activity for nodes that have only had a single pass without consumption and the time exceeds 3 months, to ensure that user interaction behavior at dormant nodes has indeed subsided over a long period. The first threshold can be set as the 20th percentile of the user activity distribution, or a fixed activity value (e.g., 0.5) based on business needs, ensuring that only nodes below this value are classified as dormant.

[0060] The second threshold serves as the dividing line between active and core states. When the dynamic activity value is greater than or equal to the first threshold but less than the second threshold, the geographic node is classified as active; when the dynamic activity value is greater than the second threshold, the geographic node is classified as core. Its goal is to distinguish between "areas with stable interactions" and "high-activity core activity areas." Based on historical activity distribution, a higher percentile (e.g., 80%~90% percentile) is selected as the initial threshold to ensure that only a few high-frequency, high-activity nodes are classified as core states, highlighting the distinctiveness of high-activity areas. Combining the operational definition of "high-activity users / areas," the lower limit of activity corresponding to "high-frequency access + high consumption" behavior is used as a reference value. For example, the lowest activity value corresponding to a node where a user has accessed the site ≥ 5 times within 30 days and has accumulated a consumption amount ≥ a preset value can be used as a reference for the second threshold. Alternatively, the second threshold can be set to the 80th percentile of the user activity distribution, or a fixed activity value (e.g., 3.0), ensuring that nodes above this value are high-activity core activity areas for the user.

[0061] To adapt to dynamic changes in user behavior, the two thresholds in this application support periodic iterative optimization: the distribution of user activity can be recalculated according to a preset period (such as monthly or quarterly), and the first and second thresholds can be updated; differentiated threshold configurations can be set for different user types (non-commercial passenger cars / commercial vehicles) and different regions (service areas / toll stations), for example, the second threshold can be appropriately increased for users of commercial vehicles to reflect the high activity judgment standard under their high frequency of passage; and operations personnel can fine-tune the thresholds according to actual business needs to ensure that the classification results are consistent with business objectives.

[0062] By setting the above rules, the first threshold and the second threshold can reasonably classify the activity level of users at geographical nodes, so that the division of dormant, active and core states not only conforms to the actual user behavior, but also meets the business needs of operation analysis.

[0063] This application embodiment also renders geographic nodes on the map using differentiated visual styles based on the divided activity levels, so that different activity levels can be intuitively distinguished.

[0064] Specifically, dormant nodes are displayed as gray or dashed outlines to reduce their visual presence. This is used to represent areas that have been visited in the past but have not seen any new visits or consumption over a long period. The purpose is to present areas where users have been inactive for a long time with a low-contrast, low-saturation style, avoiding a large amount of invalid information occupying the user's visual focus, allowing operators to quickly focus on the user's current active behavior. Through the weakened visual style, the signal that "this area is no longer the user's focus" is intuitively conveyed, forming a clear contrast with active and core states, helping users quickly understand the time decay characteristics of activity.

[0065] Active nodes are displayed as solid highlighted nodes, with the node color gradually changing from cool tones (such as blue) to warm tones (such as red) as the dynamic activity value increases, intuitively reflecting the changes in activity level. The solid highlighted style quickly attracts visual attention on the map, clearly indicating the user's current main activity area. Through continuous color gradient, the dynamic activity value is transformed into a color change that the user can perceive, allowing them to intuitively judge the strength of activity without having to look at the numerical value. The gradient effect conveys quantitative information about activity level without increasing interface complexity, ensuring the simplicity and efficiency of the map interface.

[0066] Core nodes are displayed with dynamic effects, such as breathing lights and halo effects, with the halo radius positively correlated with the node's recent consumption contribution value, highlighting areas of high user activity. Dynamic effects like breathing lights and halos create strong visual focal points on static maps, intuitively identifying the core areas with the highest user activity, providing key targets for operational decisions. The positive correlation between the halo radius and the node's recent consumption contribution value directly translates this key indicator of consumption activity into visual dimensions, allowing operations personnel to instantly identify areas of concentrated user spending. The dynamic effects themselves visually echo the "high-frequency access + high consumption" activity attributes of core nodes, creating a clear visual distinction from dormant and active states.

[0067] This hierarchical rendering method essentially transforms abstract dynamic activity data into a layered, ordered, and highly information-dense visual language. Dormant nodes hide invalid information; active nodes present the main activities; and core nodes highlight key high-activity areas. Ultimately, this achieves intuitive identification of user activity and allows for rapid location of visual targets in core activity areas, significantly improving the analytical efficiency of operations personnel.

[0068] To further intuitively reflect the intensity and contribution of users' consumption behavior at geographical nodes, this application embodiment, based on the basic visualization rendering completed based on activity level, overlays consumption feature icons on the map trajectory line or corresponding geographical node, transforming abstract consumption data into intuitive visual information through graphical marking.

[0069] Specifically, by traversing each passage-consumption event chain, it is determined whether the consumption contribution value corresponding to the current event reaches a preset threshold. If the consumption contribution value is greater than or equal to the preset threshold, it is determined that the passage includes a large consumption behavior in the service area. A fixed style supply point icon is overlaid and displayed in the middle of the map trajectory segment corresponding to the passage, or next to the corresponding entrance / exit toll station node, to mark that high-activity consumption has occurred at this location. The icon is bound to the trajectory line and node position and moves synchronously with map zooming and panning to maintain accurate spatial position correspondence.

[0070] By statistically analyzing the number of consumptions and cumulative consumption contribution values ​​of nodes in the same city or geographical area within a preset period (such as the past 30 days), if a node repeatedly generates high consumption behavior and the cumulative consumption contribution value reaches a preset high contribution threshold, then the node is determined to be a high-contribution user area. The geographical area corresponding to the node is filled with a gold texture to cover the original base color, forming a visual effect that is clearly different from ordinary nodes. The display range of the gold texture is consistent with the geographical range of the node, and the brightness and saturation of the texture are positively correlated with the cumulative consumption contribution value; the higher the consumption, the more prominent the visual effect.

[0071] Dynamic activity levels already reflect both traffic and consumption, but they cannot directly distinguish between high traffic and low consumption versus low traffic and high consumption. By independently overlaying consumption feature icons, consumption behavior can be specifically highlighted without changing the activity rendering logic, making consumption contributions independently identifiable and visually apparent, thus achieving a layered display of traffic activity and consumption activity.

[0072] Supply point icons are used to accurately locate the location of a single large-amount transaction. They can accurately mark the specific trajectory segment or node where the large-amount transaction occurred, enabling operators to quickly identify the location where the user's transaction took place. The icons are simple and clear, do not obscure basic map information, and are highly recognizable. They are also convenient for analyzing users' consumption habits, consumption preferences, and the distribution of high-activity consumption points during their travels.

[0073] Gold texture fill is used to identify areas with consistently high contributions. Gold is a highly recognizable and active color, which can significantly highlight important areas with continuous high consumption and create a strong visual distinction from ordinary nodes. Using a surface texture fill instead of dot icons can intuitively reflect high contributions at the regional level, rather than single consumption, making it easier to identify core user activity areas. This allows operators to quickly identify high-activity service areas, high-activity road sections, and high-activity city nodes, providing an intuitive basis for business layout and marketing resource allocation.

[0074] In summary, the layered visualization of this application significantly improves the efficiency of information expression. Node color / halo represents activity level; supply point icons represent single large-amount consumption; and gold textures represent long-term high-consumption contributions in a given area. These three elements do not interfere with each other and are clearly layered, achieving a multi-dimensional visualization of "activity level + single-time consumption + cumulative regional contribution." This fully presents the complete picture of user behavior within a single interface, greatly improving analysis efficiency and intuitiveness.

[0075] This application embodiment can also capture the two core changes of time passage and new data generation simultaneously through a dynamic update mechanism, linking the dynamic activity calculation model and the front-end visualization interface to achieve real-time and accurate dynamic updates of the visualization effect, ensuring that the visualization display is completely synchronized with the user's actual behavior status and activity changes. This dynamic update mechanism includes two parts: a natural decay effect and an instant activation effect, corresponding to the exponential decay process of activity over time, and the instantaneous boost and animation feedback process triggered by new behavior, respectively.

[0076] Specifically, the natural decay effect corresponds to the exponential decay of the dynamic activity value over time. Its visualization update is achieved through a linkage mechanism of "background timed calculation + front-end real-time rendering". By presetting a fixed time step (such as hourly or daily, which can be adjusted according to business needs), a timed monitoring task is launched. This task is only executed for geographical nodes where "there are currently no new passage-consumption events", reducing the system's computational load. After the timed task is triggered, the spatiotemporal decay dynamic weight model is invoked, and for each eligible geographical node, the weight is adjusted according to the current time. With the time of the event The difference is used to recalculate the dynamic activity value of the node. Due to time difference Continuously increasing, exponentially decaying term Continuous reduction, leading to The activity level decreases automatically according to an exponential law; the latest dynamic activity value after recalculation is pushed to the front-end visualization interface in real time. The front-end adjusts the visual effects of the corresponding nodes synchronously based on the new activity value. If the activity value is still higher than the first threshold (active state), the node color saturation is gradually reduced and the halo effect is weakened, and the node continues to darken as the activity level decreases. If the activity value drops below the first threshold (entering the dormant state), the node is switched to a gray or dashed outline, and its visual presence is gradually weakened. If the activity value continues to decay to near 0, the node visual effects gradually disappear, leaving only faint historical traces (such as light gray dots), completing the visualization of the "forgetting" process. The timed monitoring task is triggered cyclically according to a preset step size to continuously capture the impact of time on the activity level, ensuring the continuity and authenticity of the natural decay effect.

[0077] The instant activation effect corresponds to the momentary increase in activity after a new passage-consumption event occurs. Its visual update is achieved through a "real-time data capture + instant trigger rendering" mechanism. By building a data monitoring interface, new passage and consumption data pushed by the ETC backend management system, toll collection system, and consumption system are captured in real time and quickly linked to the corresponding geographical node using the user's unique identifier. Once new data is captured, the backend immediately triggers a dynamic activity recalculation process, adding the new passage-consumption event to the event chain of the corresponding node and recalculating the node's dynamic activity value. Due to the contribution of newly added events Instantaneous superposition, and the event time Approaching the current moment The decay term approaches 1, leading to Instantaneous boost; the updated activity value and new event markers are simultaneously pushed to the front end, which immediately triggers preset lighting or revival animation effects. If the node was previously dormant (gray / dashed line), a revival animation is triggered, gradually transitioning from gray to a solid highlight in the active state, accompanied by a brief flashing effect, intuitively demonstrating the activation process from nothing to something. If the node was previously active, a lighting animation is triggered, instantly brightening the node color and instantly enhancing the halo effect. If it reaches the core state after the boost, a breathing light effect is activated simultaneously, highlighting the significant increase in activity. If the new event involves a large amount of consumption, a supply point marker is simultaneously superimposed on the corresponding trajectory segment. If the cumulative consumption reaches a high contribution threshold, a gold texture fill is triggered simultaneously in the corresponding area, ensuring that consumption characteristics and activity updates are synchronized.

[0078] The natural decay effect aligns with the forgetting curve of user behavior. A user's activity level at a particular geographic node naturally declines over time, much like the forgetting process of behavioral memory. By gradually weakening the effect through activity index decay and visual effects, this natural law is realistically simulated, making the visualization more closely match actual user behavior and avoiding the distortion problem of "historical behavior influencing current visualization over a long period." It also ensures the real-time accuracy of the visualization. Without natural decay updates, dormant nodes would retain their original visual style for a long time, leading to misjudgments of the user's current activity area by operations personnel. Regularly updating the decay effect ensures that the visualization perfectly matches the user's current activity level, providing accurate data for operational decisions. Furthermore, it balances system performance and user experience by employing "timed step size + targeted calculation" (only performed on nodes without new events). This ensures the continuity of the decay effect while avoiding the system load pressure caused by real-time recalculation of all nodes, balancing performance and the smoothness of the visualization.

[0079] Instant activation effects provide a direct feedback on the impact of user behavior. When a user generates a new activity or purchase, their activity level instantly increases. By activating a revival animation, this "behavior-activity" relationship is visually presented, allowing operations personnel to quickly perceive the impact of user behavior on activity levels. This eliminates the need for manual data queries to capture the latest user behavior dynamics. Furthermore, it highlights real-time information on high activity levels. New activities and purchases often reflect current user needs, and instant activation effects quickly highlight this information, helping operations personnel identify new active areas and consumption preferences, supporting timely operational decisions (such as real-time marketing pushes). Finally, it enhances the interactivity and readability of visualizations. Static visualizations cannot reflect dynamic changes in activity levels. Instant animation effects make the entire visualization interface more interactive, transforming abstract activity level changes into intuitive visual feedback, reducing the analysis costs for operations personnel and improving information retrieval efficiency.

[0080] In summary, this application's embodiment achieves a three-in-one synchronization of visualization effects, dynamic activity values, and user behavior through a dual dynamic update mechanism of "natural decay + instant activation." This not only solves the problem that traditional static visualization cannot reflect changes over time, but also clearly distinguishes between the two scenarios of natural decay of activity and activation of new behaviors through differentiated animation effects. Ultimately, it achieves the goal of real-time, realistic, and intuitive visualization, providing more accurate and timely support for user behavior analysis and operational decision-making.

[0081] like Figure 2 As shown, this application embodiment provides a user dynamic activity calculation device based on ETC data, including a data acquisition module 201, an event association module 202, and an activity calculation module 203, wherein: The data acquisition module 201 is configured to acquire the passage data and associated consumption data corresponding to the user's unique identifier under the user's ETC account; The event association module 202 is configured to use the user's unique identifier as the association primary key to match and align the access data and associated consumption data that meet the preset spatiotemporal association conditions, generate access-consumption events for the corresponding geographical nodes, and connect them in chronological order to form an access-consumption event chain; The active calculation module 203 is configured to calculate the dynamic activity value of the target geographic node at the current moment based on the passage-consumption event chain and through a spatiotemporal decay dynamic weight model.

[0082] In addition, such as Figure 4As shown, the user dynamic activity calculation device in this application embodiment further includes a visual rendering module 204, which is configured to preset a first threshold and a second threshold, divide the geographic nodes into activity levels according to the relationship between the dynamic activity value and the first threshold and the second threshold, and perform hierarchical visual rendering based on different activity levels using differentiated visuals.

[0083] The user dynamic activity calculation device based on ETC data in this application embodiment can be a computer device or a component within a computer device, such as an integrated circuit or a chip. The computer device can be a terminal or other devices besides a terminal. For example, the computer device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle computer device, mobile internet device (MID), ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., and can also be a server, network attached storage (NAS), personal computer (PC), etc. This application embodiment does not specifically limit the specific implementation.

[0084] The user dynamic activity calculation device based on ETC data provided in this application embodiment can achieve... Figure 1 The various processes implemented in the embodiment of the user dynamic activity calculation method based on ETC data will not be described again here to avoid repetition.

[0085] This application also provides a computer device, such as... Figure 3 As shown, the computer device includes a processor 301 and a memory 302. The memory 302 stores programs or instructions that can run on the processor 301. When the processor 301 executes the program or instructions, it implements the various steps of the above-described user dynamic activity calculation method based on ETC data and achieves the same technical effect. To avoid repetition, it will not be described again here. It should be noted that the computer device in this application embodiment includes the above-described mobile computer device and non-mobile computer device.

[0086] The memory 302 can be used to store software programs and various data. The memory 302 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 302 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 302 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0087] Processor 301 may include one or more processing units; optionally, processor 301 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 301.

[0088] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of the user dynamic activity calculation method based on ETC data and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0089] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described embodiment of the user dynamic activity calculation method based on ETC data, and can achieve the same technical effect. To avoid repetition, it will not be described again here. It should be understood that the chip mentioned in this application embodiment can also be called a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0090] This application also provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described embodiment of the user dynamic activity calculation method based on ETC data, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0091] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0092] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for calculating user dynamic activity based on ETC data, characterized in that, include: Obtain the passage data and associated consumption data corresponding to the user's unique identifier under the user's ETC account; Using the user's unique identifier as the primary key, the passage data that meets the preset spatiotemporal association conditions is matched and aligned with the associated consumption data to generate passage-consumption events for the corresponding geographical nodes, and then linked together in chronological order to form a passage-consumption event chain. Based on the aforementioned access-consumption event chain, the dynamic activity value of the target geographical node at the current moment is calculated using a spatiotemporal decay dynamic weight model.

2. The user dynamic activity calculation method according to claim 1, characterized in that, The formula for the spatiotemporal decay dynamic weight model is as follows: in, Indicates the target geographic node at the current time. The dynamic activity value; This represents the total number of access-consumption events corresponding to the target geographic node; This represents the base passage weight corresponding to a single passage event; Indicates the first The consumption contribution value corresponding to each pass-consumption event, the consumption contribution value The pass event is assigned a value based on a preset segmented range of the user's consumption value at the target geographic node. The pass event with no consumption value corresponds to... ; This represents the consumption weighting factor; Represents the time decay constant; Indicates the first The timing of each transit-consumption event.

3. The user dynamic activity calculation method according to claim 1, characterized in that, The preset spatiotemporal correlation conditions include: Under the same unique user identifier, the difference between the consumption time and the corresponding passage time is within a preset time window, and the straight-line distance between the consumption location and the corresponding ETC entrance / exit location is less than a preset distance threshold.

4. The user dynamic activity calculation method according to claim 2, characterized in that, The consumption weighting coefficient Time decay coefficient All are adaptively adjusted based on one or more of the following: user type, vehicle type, and travel frequency; the dynamic activity value decays exponentially over time and is updated with the recording of new passage-consumption events.

5. The user dynamic activity calculation method according to claim 1, characterized in that, A first threshold and a second threshold are preset. Based on the relationship between the dynamic activity value and the first and second thresholds, the geographic nodes are divided into activity levels, and differentiated visuals are used for hierarchical visualization rendering based on different activity levels.

6. The user dynamic activity calculation method according to claim 5, characterized in that, The activity levels include dormant state, active state, and core state; When the dynamic activity value is less than the first threshold, the geographic node is classified as dormant. When the dynamic activity value is greater than or equal to the first threshold and less than the second threshold, the geographic node is classified as active. When the dynamic activity value is greater than the second threshold, the geographic node is classified as the core state.

7. A user dynamic activity calculation device based on ETC data, characterized in that, include: The data acquisition module is configured to acquire the passage data and associated consumption data corresponding to the user's unique identifier under the user's ETC account; The event association module is configured to use the user's unique identifier as the association key to match and align the passage data that meets the preset spatiotemporal association conditions with the associated consumption data, generate passage-consumption events for the corresponding geographical nodes, and connect them in chronological order to form a passage-consumption event chain. The active calculation module is configured to calculate the dynamic activity value of the target geographic node at the current moment based on the passage-consumption event chain and through a spatiotemporal decay dynamic weight model.

8. The user dynamic activity calculation device according to claim 7, characterized in that, It also includes a visual rendering module, which is configured to preset a first threshold and a second threshold, divide geographic nodes into activity levels according to the relationship between the dynamic activity value and the first threshold and the second threshold, and perform hierarchical visual rendering based on different activity levels using differentiated visuals.

9. A user dynamic activity calculation system based on ETC data, the system comprising a processor and a memory, wherein the memory stores a computer program, characterized in that, The computer program is loaded and executed by the processor to implement the user dynamic activity calculation method as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the user dynamic activity calculation method as described in any one of claims 1 to 6.

Images