Honeycomb grid and circular thermal dynamic interaction visualization method for designated driving scene

Abstract

The invention relates to the technical field of designated driving services, in particular to a honeycomb grid and circular thermal dynamic interaction visualization method for a designated driving scene, and the method comprises the steps: obtaining the data of a designated driving order and the position information of a driver; a double-model fusion framework is constructed, the double-model fusion framework comprises a honeycomb grid layer and a circular thermal layer, the grid resolution and the order grabbing radius are dynamically adjusted based on the city level, and dynamic rendering is conducted on multi-dimensional data through a step rule engine; an order making probability is calculated based on the order making probability model to generate an intelligent prompt, the order making possibility of a preset point location is visually fed back through graphic animations, and the graphic animations comprise a pulse graphic animation, a gradual change graphic animation and a static graphic animation; and grading the moving speed of the driver, and updating the position information of the driver by adopting different frequencies according to grading. Therefore, the problems that in the prior art, grid division is fixed, the order grabbing range is rigid, and the visualization level is single are solved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of chauffeur service, in particular to a honeycomb grid and circular heat dynamic interaction visualization method for a chauffeur service scene. BACKGROUND

[0002] With the development of mobile Internet, chauffeur service has become an important part of urban transportation. In order to improve the efficiency of drivers taking orders, chauffeur platforms usually use heat maps to display order distribution. However, the traditional technology has the following limitations: 1. Using uniform grid to display order heat, which cannot dynamically adjust the precision according to the size of the city (such as first-tier cities and third-tier cities), resulting in information overload in large cities and insufficient precision in small cities. 2. The radius of driver's order grabbing is fixed, and it is not dynamically optimized combined with real-time order taking rate. The order grabbing range of high order taking rate drivers is not reasonably contracted, and the range of low order taking rate drivers is not timely expanded. 3. Only real-time order distribution is displayed, and there is a lack of fusion analysis of historical data and real-time demand, making it difficult for drivers to predict high potential areas. SUMMARY

[0003] The application provides a honeycomb grid and circular heat dynamic interaction visualization method for a chauffeur service scene to solve the problems of fixed grid division, rigid order grabbing range, and single visualization level in the prior art.

[0004] The first aspect of the application provides a honeycomb grid and circular heat dynamic interaction visualization method for a chauffeur service scene, comprising the following steps: obtaining chauffeur order data and driver location information, wherein the order data includes historical orders and real-time orders, and the driver location information includes real-time positioning of the driver and moving speed of the driver; constructing a double model fusion architecture based on the chauffeur order data and driver location information, the double model fusion architecture including a honeycomb grid layer and a circular heat layer, dynamically adjusting the grid resolution and the order grabbing radius based on the city level, and dynamically rendering multi-dimensional data through a ladder rule engine; calculating the order probability based on the order probability model, generating an intelligent prompt based on the order probability, and intuitively feeding back the order possibility of the preset point through a graphic animation, the graphic animation including a pulse graphic animation, a gradient graphic animation, and a static graphic animation; classifying the driver moving speed, and updating the driver location information at different frequencies according to the classification.

[0005] Optionally, the honeycomb grid layer comprises: dividing the city level according to the daily order volume of the city, the city level including first-tier cities, second-tier cities, and third-tier cities; setting the initial grid resolution according to the city level based on the H3 geographic index system, wherein the first-tier cities use H7 resolution, the second-tier cities use H8 resolution, and the third-tier cities use H9 resolution; automatically upgrading the resolution by 1 level when the daily order volume in the grid exceeds the target threshold; and reducing the resolution by 1 level when it is lower than the target threshold.

[0006] Optionally, the circular heat layer comprises: presetting a basic order-picking radius according to city levels; generating a dynamic order-picking range according to the basic order-picking radius, and combining the real-time scaling radius of the driver order-picking rate, wherein the order-picking radius calculation formula is: R=R_base x (1+αx(1-rate)), wherein R is the order-picking radius, R_base is the basic radius, α is a system configuration parameter, and rate is the order-picking rate, which is the ratio of the order-picking amount to the order-picking opportunity in the last 30 minutes.

[0007] Optionally, the ladder rule engine comprises: defining order quantity thresholds and corresponding colors for each heat ladder according to city configuration x-y level heat ladders, wherein the corresponding colors include red, yellow, and green, representing order density from high to low; and updating the ladder parameters in real time through a JSON configuration file.

[0008] Optionally, the dynamic rendering of multi-dimensional data by the ladder rule engine comprises: aggregating order heat values through a honeycomb grid layer, superimposing the driver order-picking range of the circular heat layer, and forming a layered visual interface, wherein the heat value aggregation is obtained by using a MapReduce model to batch calculate the weighted decay value of orders in the grid.

[0009] Optionally, the formula of the order probability model is:

[0010] wherein, is the order probability, the historical order-picking rate is the ratio of the past 7-day same-period order-picking amount to the total order amount in the grid, and the real-time demand rate is the ratio of the un-picked order amount to the number of online drivers in the current grid.

[0011] Optionally, the intelligent prompt generated according to the order probability visually feeds back the order possibility of the preset point through a graphic animation, and the graphic animation comprises a pulse graphic animation, a gradient graphic animation, and a static graphic animation, comprising: when the order probability is greater than 0.7, triggering the pulse graphic animation; when the order probability is greater than or equal to 0.3 and less than or equal to 0.7, triggering the gradient graphic animation; and when the order probability is less than 0.3, triggering the static graphic animation.

[0012] Optionally, the driver moving speed is classified into low speed, medium speed, and high speed.

[0013] The second aspect embodiment of the application provides an electronic device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are configured to execute a honeycomb grid and circular heat dynamic interaction visualization method for a chauffeur scene as described in the above embodiments.

[0014] A third aspect of the present application provides a computer readable storage medium having stored thereon a computer program, which is executed by a processor to implement a method for dynamic interaction visualization of a cellular grid and circular heat map in a driving scenario as described in the above embodiments.

[0015] The present application has the following beneficial effects: The embodiment of the present application constructs a double model fusion architecture of cellular grid and circular heat map, ensures the number of grids in different scale cities to be in a ladder distribution through dynamic grading of the cellular grid, avoids data overload, guides drivers to move to high probability areas through dynamic order grabbing radius combined with real-time order taking rate, improves the order taking probability of drivers, realizes multi-dimensional data dynamic rendering combined with ladder rule engine, generates intelligent prompts containing pulse, gradual change and static graphic animation by means of order taking probability model to feedback order taking possibility, and updates position information at different frequencies according to the grading of driver moving speed, effectively improves the matching efficiency of driving orders and drivers, enhances the scientific nature of driver decision-making, adapts to the differentiated needs of multiple cities, and improves the intelligent level of platform operation. Thus, the problems of fixed grid division, rigid order grabbing range and single visualization level in the prior art are solved.

[0016] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which: Figure 1 A flowchart of a method for dynamic interaction visualization of a cellular grid and circular heat map in a driving scenario according to an embodiment of the present application is shown in FIG. 1; Figure 2 A flowchart of a method for superimposition of a cellular grid layer and a circular heat map layer according to an embodiment of the present application is shown in FIG. 2; Figure 3 A schematic diagram of a hierarchical visualization interface according to an embodiment of the present application is shown in FIG. 3; Figure 4 A structural schematic diagram of an electronic device according to an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0018] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0019] A dynamic interactive visualization method of a cellular grid and a circular heat map for a driving service scenario is described below with reference to the accompanying drawings. In view of the fixed grid division, rigid order pickup range, and single visualization level mentioned in the background art, the present application provides a dynamic interactive visualization method of a cellular grid and a circular heat map for a driving service scenario. In this method, a dual-model fusion architecture of a cellular grid and a circular heat map is constructed, the number of grids in different size cities is ensured to be distributed in a ladder shape through dynamic grading of the cellular grid to avoid data overload, the dynamic order pickup radius is combined with the real-time order pickup rate to guide drivers to move to high-probability areas and improve the order pickup probability of drivers, multi-dimensional data is dynamically rendered by a ladder rule engine, intelligent prompts containing pulse, gradient, and static graphic animations are generated by an order probability model to feedback the order probability, and the position information is updated at different frequencies according to the driver's moving speed, which effectively improves the matching efficiency of driving orders and drivers, enhances the scientific nature of driver decision-making, adapts to the differentiated needs of multiple cities, and improves the intelligent level of platform operation. Thus, the problems of fixed grid division, rigid order pickup range, and single visualization level in the prior art are solved.

[0020] Specifically, Figure 1 A flowchart of the dynamic interactive visualization method of a cellular grid and a circular heat map for a driving service scenario provided by the embodiments of the present application is shown in FIG. 1.

[0021] As Figure 1 shown, the dynamic interactive visualization method of a cellular grid and a circular heat map for a driving service scenario includes the following steps: In step S101, driving order data and driver location information are obtained, wherein the order data includes historical orders and real-time orders, and the driver location information includes real-time positioning of the driver and moving speed of the driver.

[0022] Specifically, historical orders can be used to analyze regional order rules to assist in order probability prediction, real-time orders can reflect the current demand distribution to dynamically adjust the heat map display, real-time positioning of the driver is the core basis for determining the order pickup range, and the moving speed provides a key parameter for optimizing the position information update frequency and balancing system performance and real-time performance.

[0023] It can be understood that the embodiments of the present application lay a data foundation for precise matching and efficient scheduling of transportation capacity.

[0024] In step S102, a dual-model fusion architecture is constructed according to the driving order data and the driver location information, the dual-model fusion architecture includes a cellular grid layer and a circular heat map layer, the grid resolution and the order pickup radius are dynamically adjusted based on the city level, and multi-dimensional data is dynamically rendered by a ladder rule engine, as shown in Figure 2 .

[0025] It can be understood that, by dynamically adjusting the grid resolution and order grabbing radius based on the city level, the embodiments of the present application can adapt the grid display to the order density of different city sizes and the order grabbing range to the driver's order grabbing ability. In combination with the dynamic rendering of the multi-dimensional data by the ladder rule engine, the precise visualization of order distribution and the intelligent guidance of driver order grabbing can be realized, which not only avoids the problems of information overload or insufficient precision, but also improves the efficiency of transport capacity matching, while meeting the differentiated needs of different cities.

[0026] In the embodiments of the present application, the cellular grid layer comprises: dividing the city level according to the daily order quantity of the city, the city level comprising a first-level city, a second-level city and a third-level city; setting an initial grid resolution based on the H3 geographic index system according to the city level, wherein the first-level city adopts H7 resolution, the second-level city adopts H8 resolution, and the third-level city adopts H9 resolution; when the daily order quantity in the grid exceeds the target threshold, the resolution is automatically increased by one level; when it is lower than the target threshold, the resolution is decreased by one level.

[0027] The daily order quantity of the city refers to the total number of driving orders generated in a city in one day, which is a core indicator for measuring the demand size of driving service in the city. The statistical range covers all orders initiated and successfully submitted by users through the driving platform within 24 hours, including real-time orders, reservation orders and various driving service demands.

[0028] The H3 geographic index system is a geographic spatial index framework based on hexagonal grid developed by Uber. Its core feature is to divide the earth's surface into layers using hexagonal grids. Each grid (called "H3 index") has a unique identifier and supports multi-level resolution from coarse to fine. Currently, it provides 16 levels of resolution. The higher the level, the smaller the grid area and the higher the precision. For example, the side length of a single grid with H7 resolution is about 1.2 kilometers, H8 is about 0.5 kilometers, and H9 is about 0.2 kilometers.

[0029] It can be understood that, by dividing the level according to the daily order quantity of the city and matching the initial resolution of the H3 system, and dynamically increasing or decreasing the resolution according to the comparison between the daily order quantity in the grid and the target threshold, the embodiments of the present application can avoid information overload in the first-level city with high order density by using coarse grid, ensure the display precision in the third-level city with low order density by using fine grid, and accurately adapt the resolution of a single grid to the actual order quantity by real-time adjustment, so as to realize efficient presentation of spatial information in different size cities and different order density areas, and provide a flexible and accurate basic framework for subsequent heat rendering and transport capacity analysis.

[0030] In the embodiments of the present application, the circular heat layer comprises: presetting a basic order grabbing radius according to the city level; The dynamic order grabbing range is generated according to the basic order grabbing radius with the real-time position of the driver as the center, and the radius is scaled in real time in combination with the order grabbing rate of the driver, wherein the order grabbing radius calculation formula is: R = R_base x (1 + a x (1 - rate)) wherein R is the order grabbing radius, R_base is the basic radius, a is a system configuration parameter, and rate is the order grabbing rate, and the order grabbing rate is the ratio of the order grabbing quantity to the order grabbing opportunity in the last 30 minutes.

[0031] For example, taking a secondary city as an example, the preset basic order grabbing radius R_base is 3.5 km, and the system configuration parameter a is 0.3 by default. Assuming that the driver Li has 10 order grabbing opportunities in the last 30 minutes, and successfully grabs 3 orders, the order grabbing rate rate = 3 / 10 = 0.3. According to the formula, the real-time order grabbing radius is calculated as R = 3.5 x (1 + 0.3 x (1 - 0.3)) = 3.5 x (1 + 0.3 x 0.7) = 3.5 x 1.21 = 4.235 km. At this time, the dynamic order grabbing range of Li is a circular area with a radius of 4.235 km and with the real-time position of Li as the center, which is about 21% larger than the basic radius, helping Li to expand the order grabbing range because of the low order grabbing rate.

[0032] It can be understood that the circular heat layer of the embodiment of the application presets the basic order grabbing radius according to the city level, and scales the order grabbing range in real time in combination with the order grabbing rate of the driver in the last 30 minutes, which can adapt the initial order grabbing radius of different scale cities to the regional order density, automatically expand the order grabbing range of the driver with a low order grabbing rate to obtain more opportunities, keep a reasonable range of the driver with a high order grabbing rate to avoid resource waste, realize the personalized dynamic adjustment of the order grabbing range, effectively improve the order grabbing efficiency of the driver and the order matching accuracy, and balance the order grabbing fairness of drivers with different abilities.

[0033] In the embodiment of the application, the ladder rule engine includes: configuring x-y level heat ladders according to cities, defining order quantity thresholds and corresponding colors for each heat ladder, wherein the corresponding colors include red, yellow and green, indicating order density from high to low; and updating the ladder parameters in real time through a JSON configuration file.

[0034] For example, taking a first-tier city as an example, the ladder rule engine is configured as a 5-level heat ladder, and the specific parameters are defined through a JSON file. Among them, the rules corresponding to the 5-level ladder are as follows: level 1 (highest density): the number of real-time orders in the grid is greater than or equal to 80, display deep red (#FF3333), prompt the driver that the area order is highly dense; level 2: order quantity 50~79, display orange red (#FF9933), indicating that the order is dense; level 3: order quantity 30~49, display yellow (#FFFF66), representing the order quantity is moderate; level 4: order quantity 15~29, display light green (#99FF66), indicating that the order is less; level 5 (lowest density): order quantity ≤5, display deep green (#33CC33), prompt the order is sparse.

[0035] If there is a surge of orders during the late peak, the platform can adjust the level 1 threshold to 100 orders by modifying the JSON file, and change the level 2 color to #FF6633. After updating, there is no need to restart the system, and the driver's interface will synchronize the new heat ladder display rule in real time, ensuring that the visualization effect accurately matches the actual order changes.

[0036] It can be understood that the embodiments of the application can not only accurately match the heat display of cities of different sizes with their own order density characteristics, but also help drivers quickly identify high demand areas through intuitive color gradients, while supporting flexible adjustment of thresholds and colors to respond to order fluctuations, improving the adaptability, readability and dynamic response ability of heat visualization, and providing clear and timely reference for driver order grabbing decisions.

[0037] In the embodiments of the application, dynamic rendering of multi-dimensional data by the ladder rule engine includes: aggregating order heat values through a honeycomb grid layer, superimposing a driver order grabbing range of a circular heat layer, and forming a layered visualization interface, wherein the heat value aggregation is obtained by using a MapReduce model to batch calculate the weighted decay value of orders in the grid.

[0038] Specifically, relying on the MapReduce distributed computing model, the order data in the honeycomb grid layer is batch processed—combined with the time decay factor of historical orders (such as the weight of orders in the last 1 hour 0.8, the weight of orders in the last 24 hours 0.2) and the instant weight of real-time orders, the weighted decay value (i.e. comprehensive heat value) of each grid is calculated, realizing the fusion and aggregation of multi-period order data, and ensuring that the heat value can reflect the real activity of the area order.

[0039] In the front-end interface, such as Figure 3As shown, first, the aggregated grid heat value is rendered into a red-yellow-green color gradient (corresponding to heat value from high to low) according to the preset ladder by the ladder rule engine, forming the underlying honeycomb grid heat map; then the driver's order grabbing range of the circular heat layer (centered on the real-time position of the driver, and a semi-transparent circle is drawn according to the dynamically calculated order grabbing radius) is superimposed thereon, forming a layered interface of "grid heat + order grabbing range".

[0040] It can be understood that, by means of the ladder rule engine, the embodiment of the application dynamically renders multi-dimensional data, and by means of the MapReduce model, the weighted decay value of orders in the grid is batch calculated to realize heat value aggregation, and the order grabbing range of the circular heat layer is superimposed to form a layered visual interface, which can not only fuse historical and real-time order data through weighted decay processing to accurately reflect the real activity of orders in the grid, but also enable the driver to simultaneously grasp the global order heat distribution (honeycomb grid layer) and the personal order grabbing boundary (circular heat layer) through layered display, so as to realize the coordinated perception of macroscopic situation and microscopic range.

[0041] In step S103, the order placing probability is calculated based on the order placing probability model, and an intelligent prompt is generated according to the order placing probability, and the order placing possibility of the preset point is intuitively fed back through a graphic animation, and the graphic animation includes a pulse graphic animation, a gradient graphic animation, and a static graphic animation.

[0042] It can be understood that, the embodiment of the application calculates the order placing probability based on the order placing probability model, and generates an intelligent prompt through a pulse, a gradient, and a static graphic animation according to the probability, so as to intuitively feed back the order placing possibility of the preset point, which can not only help the driver quickly identify a high-potential area and reduce decision-making time, but also accurately convey the gradient difference of the order placing possibility through different animation forms, avoid information confusion, and at the same time enable the driver to clearly predict the order potential of different areas, improve the targeting and success rate of order grabbing, and enhance the practicality and guidance of visual interaction.

[0043] In the embodiment of the application, the formula of the order placing probability model is as follows:

[0044] wherein, is the order placing probability, the historical order placing rate is the ratio of the same period order placing quantity in the past 7 days to the total order quantity in the grid, and the real-time demand rate is the ratio of the unaccepted order quantity to the number of online drivers in the current grid.

[0045] In the embodiment of the present application, the intelligent prompt is generated according to the order-out probability, and the order-out possibility of the preset point is intuitively fed back through the graphic animation, the graphic animation includes a pulse graphic animation, a gradient graphic animation and a static graphic animation, and the graphic animation includes: when the order-out probability is greater than 0.7, the pulse graphic animation is triggered; when the order-out probability is greater than or equal to 0.3 and less than or equal to 0.7, the gradient graphic animation is triggered; and when the order-out probability is less than 0.3, the static graphic animation is triggered.

[0046] For example, taking a city commercial circle grid as an example, the total order quantity of the grid in the same period (such as Friday 19:00-20:00) in the past 7 days is 100 orders, and the order-out quantity in the same period is 70 orders, so the historical order-out rate = 70 / 100 = 0.7; the unaccepted order quantity in the current grid is 15 orders, the number of online drivers is 20, and the real-time demand rate = 15 / 20 = 0.75. According to the order-out probability model formula P = 0.7 x historical order-out rate + 0.3 x real-time demand rate, the order-out probability P = 0.7 x 0.7 + 0.3 x 0.75 = 0.49 + 0.225 = 0.715 can be calculated. Since 0.715>0.7, the system triggers the pulse graphic animation: the zoom-in and zoom-out effect every 2 seconds is displayed at the grid position, and the “high potential area” prompt is attached, which intuitively informs the driver that the order-out possibility of this place is high in the short term.

[0047] It can be understood that, in the embodiment of the present application, the intelligent prompt is generated according to the order-out probability through the pulse, gradient and static graphic animations, which can not only convert the abstract probability value into the visual signal easy to be perceived by the driver, so that the high potential area quickly attracts attention through the dynamic pulse, the medium potential area maintains attention through the gradient, and the low potential area reduces interference through the static, but also helps the driver to instantly judge the order-out possibility gradient of different point positions through the clear animation difference, reduces the decision hesitation time, and at the same time, the intuitive visual feedback strengthens the pre-judgment ability of the driver to the high value area, improves the accuracy and efficiency of order grabbing, and makes the complex data decision simple and easy to understand.

[0048] In step S104, the driver's moving speed is classified, and the driver's position information is updated at different frequencies according to the classification.

[0049] It can be understood that, in the embodiment of the present application, the driver's moving speed is classified and the position information is updated at different frequencies, which can not only ensure the real-time of the position information by updating the position information at a high frequency when the driver is in a driving state, avoiding the deviation between the order grabbing range and the actual position, but also reduce the system data transmission and processing pressure by updating the position information at a low frequency when the driver is in a waiting state, balancing the accuracy of the position information and the system performance consumption.

[0050] In the embodiment of the present application, classifying the driver's moving speed includes: low speed, medium speed and high speed.

[0051] For example, in low-speed state, the driver position information is updated every 15 seconds, which ensures the accuracy of the position data and reduces the invalid update in static or slow motion; in medium-speed state, the update interval is shortened to every 8 seconds, balancing the real-time performance and system load; in high-speed state, the update interval is further shortened to every 3 seconds, ensuring the accurate synchronization of the driver position and the order-picking range in fast motion.

[0052] According to the method for dynamic interaction visualization of a cellular grid and a circular heat map in a chauffeur scenario provided in the embodiments of the present application, a double-model fusion architecture of a cellular grid and a circular heat map is constructed, dynamic grading of the cellular grid is performed, the number of grids in different cities is ensured to be in a ladder distribution, and data overload is avoided; a dynamic order-picking radius is combined with a real-time order-picking rate to guide drivers to move to a high-probability area and improve the order-picking probability of the drivers; a multi-dimensional data dynamic rendering is realized in combination with a ladder rule engine, intelligent prompts containing pulse, gradual change, and static graphic animations are generated by means of an order-picking probability model to feed back the order-picking possibility, and position information is updated at different frequencies according to the grading of the moving speed of the drivers, which effectively improves the matching efficiency of chauffeur orders and drivers, enhances the scientific nature of the decision-making of the drivers, adapts to the differentiated needs of different cities, and improves the intelligent level of platform operation. Thus, the problems of fixed grid division, rigid order-picking range, and single visualization level in the prior art are solved.

[0053] FIG. 4 is a structural schematic diagram of a vehicle provided in the embodiments of the present application. The electronic device can include: a memory 401, a processor 402, and a computer program stored in the memory 401 and executable on the processor 402.

[0054] The processor 402 implements the method for dynamic interaction visualization of a cellular grid and a circular heat map in a chauffeur scenario provided in the above embodiments when executing the program.

[0055] Further, the electronic device further includes: a communication interface 403 for communication between the memory 401 and the processor 402.

[0056] The memory 401 is used to store the computer program executable on the processor 402.

[0057] The memory 401 can include a high-speed RAM memory and can also include a non-volatile memory, such as at least one disk memory.

[0058] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For convenience of representation, Figure 4 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0059] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can complete communication between each other through an internal interface.

[0060] The processor 402 can be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0061] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method for cellular grid and circle heat dynamic interaction visualization in a hailing scene as described above.

[0062] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0063] Furthermore, the terms "first", "second", etc. are used herein only to describe different steps or features and do not imply a relative importance or a specific order of steps or features. Thus, features defined with "first", "second" etc. can include one or more of the features implicitly or explicitly. In the description of the application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise expressly specified.

[0064] Any process or method descriptions or blocks in flow charts described herein and elsewhere can be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process. Alternate implementations are included within the scope of the preferred embodiments of the present application in which the functions performed by the various processes described herein and elsewhere are allocated differently among the components of the preferred embodiments, such as according to the functions performed by the various components, in a substantially simultaneous manner, or according to a different order.

[0065] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware and in another embodiment, the steps or methods can be implemented with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0066] Those of skill in the art would understand that information and signals can be represented using any of a variety of technologies and techniques. Further, those of skill in the art would understand that the preferred embodiments of the present application can be implemented by a variety of means, including as a process, an apparatus, a machine, or a combination thereof. In another embodiment, the information, instructions, or commands can be downloaded over the Internet or over another network by way of data signals embodied in carrier waves.

Claims

1. A method for visualizing the dynamic interaction between honeycomb grids and circular thermal dynamics in a designated driver scenario, characterized in that: The following steps are involved: Obtaining designated driver order data and driver location information, wherein the order data includes historical orders and real-time orders, and the driver location information includes the driver's real-time location and driver movement speed; A dual-model fusion architecture is constructed based on the designated driver order data and driver location information. The dual-model fusion architecture includes a honeycomb grid layer and a circular thermal layer. The grid resolution and order grabbing radius are dynamically adjusted based on the city level. The multi-dimensional data is dynamically rendered using a ladder rule engine. Calculate the order probability based on the order probability model, generate intelligent prompts based on the order probability, and intuitively feedback the order possibility of the preset point through graphic animation. The graphic animation includes pulse graphic animation, gradient graphic animation, and static graphic animation; The driver's moving speed is graded, and the driver's position information is updated at different frequencies according to the grades.

2. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The honeycomb grid layer comprises: Cities are classified into three levels based on their daily order volume, including first-tier cities, second-tier cities, and third-tier cities. Based on the H3 geographic index system, the initial grid resolution is set according to the city level, among which the first-tier cities use H7 resolution, the second-tier cities use H8 resolution, and the third-tier cities use H9 resolution; When the daily order volume within the grid exceeds the target threshold, the resolution is automatically increased by one level; when it is lower than the target threshold, the resolution is reduced by one level.

3. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The circular thermodynamic layer comprises: Preset the basic order grabbing radius based on the city level; With the driver's real-time location as the center, a dynamic order grabbing range is generated according to the basic order grabbing radius. The radius is scaled in real time based on the driver's order acceptance rate. The order grabbing radius is calculated using the following formula: ； Among them, R is the order grabbing radius, R_base is the basic radius, α is the system configuration parameter, rate is the order acceptance rate, and the order acceptance rate is the ratio of the number of orders received in the past 30 minutes to the order grabbing opportunities.

4. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The ladder rule engine includes: Configure x- to y-level thermal ladders for each city, and define order volume thresholds and corresponding colors for each thermal ladder. The corresponding colors include red, yellow, and green, indicating order density from high to low. Update ladder parameters in real time via JSON configuration files.

5. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The dynamic rendering of multi-dimensional data through the ladder rule engine includes: aggregating order thermal values ​​through the honeycomb grid layer, superimposing the driver's order grabbing range of the circular thermal layer, and forming a layered visualization interface, wherein the thermal value aggregation is obtained by batch calculating the weighted attenuation value of the orders in the grid using the MapReduce model.

6. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The formula of the order probability model is: ； in, The historical order rate is the ratio of the number of orders placed in the same period of the past 7 days in the grid to the total number of orders. The real-time demand rate is the ratio of the number of unreceived orders in the current grid to the number of online drivers.

7. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The intelligent prompt is generated according to the order placement probability, and the possibility of placing an order at a preset point is intuitively fed back through graphic animation. The graphic animation includes pulse graphic animation, gradient graphic animation, and static graphic animation, including: When the order probability is greater than 0.7, the pulse graphic animation is triggered; When the order probability is greater than or equal to 0.3 and less than or equal to 0.7, the gradient graphic animation is triggered; When the order probability is less than 0.3, a static graphic animation is triggered.

8. The method for interactive visualization of honeycomb grid and circular thermal dynamics in a designated driver scenario according to claim 1, characterized in that: The grading of the driver's moving speed includes: low speed, medium speed, and high speed.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for visualizing the interactive cellular grid and circular thermal dynamics of a designated driver scenario as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a honeycomb grid and circular thermal dynamic interaction visualization method for a designated driver scenario as described in any one of claims 1 to 8.

Images