Urban road network automatic driving complexity evaluation method and system based on POI data

Abstract

The invention relates to an urban road network automatic driving complexity evaluation method and system based on POI data, and belongs to the technical field of automatic driving. The urban road network automatic driving complexity evaluation method based on the POI data is based on the POI data and road network topological data, a universal quantitative evaluation model is established, and the complexity of the urban road network automatic driving is evaluated. Quantitative evaluation of the automatic driving complexity of all the roads of the road network is realized in a unified manner based on a GIS platform, the problems of normalization and coverage of the evaluation method are solved, and the method and the evaluation method can complement each other. Considering that the core of the method is to solve the problems of universality and breadth and has certain limitations in evaluation precision and accuracy, in practical application, the prior automatic driving complexity of all roads in a road network can be obtained through modeling by using the method, and then the forward evaluation method is used for performing special correction on road sections with medium and high complexity, so that the accuracy of the road network is improved. And finally, the overall road network automatic driving complexity with relatively high reliability is obtained.

Description

Technical Field

[0001] This disclosure belongs to the field of autonomous driving technology, and in particular relates to a method and system for evaluating the complexity of autonomous driving in urban road networks based on POI data. Background Technology

[0002] The intelligent vehicle industry is developing rapidly. Relying on the iterative updates of autonomous driving technology, the commercialization and widespread adoption of advanced intelligent driving assistance functions have become a reality. This has also led to a rapid increase in the number of advanced intelligent driving vehicles equipped with highway and city NOA (Navigate On Autopilot). As the number of intelligent vehicles continues to grow, improving the user experience and satisfaction of car users with advanced intelligent driving functions has become an important after-sales aspect that major automakers are increasingly focusing on. Therefore, research and technologies related to autonomous driving operations are gradually being developed within the industry.

[0003] Autonomous driving route operation is one of the core components of autonomous driving operation. It aims to establish an evaluation method for the complexity and reliability of autonomous driving on different roads by studying and analyzing the dynamic and static characteristics of different roads and the performance of vehicle NOA functions. In this way, combined with the characteristics of autonomous driving technology, targeted and personalized operation strategies can be formulated for roads with different levels of complexity to ensure the driver and passenger experience when using advanced intelligent driving functions such as NOA on highways and in cities.

[0004] Currently, industry methods for analyzing and evaluating the complexity of autonomous driving routes largely rely on large amounts of user-generated NOA (Noise, Automation, and Access) driving data and accident data transmitted back to the backend. This is achieved by statistically analyzing indicators reflecting NOA performance, such as interruption rate or takeover frequency, and by analyzing accident causes, to derive the route complexity evaluation result. Generally, poor NOA performance is considered to indicate high autonomous driving complexity on a road segment, and vice versa. The advantage of this method is that it is based on forward analysis and uses evaluation indicators that directly represent complexity, resulting in relatively accurate analysis of road complexity. However, its main drawbacks are: first, NOA interruption rate and takeover frequency are quantitative indicators, while accident causes are qualitative indicators, making it difficult to normalize them into a unified quantitative indicator for evaluation; second, because it is a forward analysis, it requires a large amount of data, making it impossible to scientifically evaluate road segments with limited or no driving data, meaning it cannot achieve full network coverage and cannot guarantee a satisfactory NOA experience on certain roads.

[0005] Therefore, it is necessary to provide a new method and system for evaluating the complexity of autonomous driving in urban road networks based on POI data to solve the above-mentioned technical problems. Summary of the Invention

[0006] The purpose of this disclosure is to provide a method and system for evaluating the complexity of autonomous driving in urban road networks based on POI data in order to solve the above-mentioned problems.

[0007] This disclosure achieves the above objectives through the following technical solutions: A method for evaluating the complexity of autonomous driving in urban road networks based on POI data includes the following steps: Obtain the full GIS data of POIs and the road network topology GIS data of the area to be evaluated, and perform data cleaning and filtering to obtain the processed GIS data of POIs and the processed road network topology GIS data, respectively. Construct a gravity-like model to describe the quantitative impact of POIs on road segment complexity; Based on the processed POI GIS data and the processed road network topology GIS data, the autonomous driving complexity of all roads in the overall road network is obtained within the GIS platform through the gravity-like model. The numerical values ​​of autonomous driving complexity of all roads in the overall road network are classified by clustering algorithm, and finally the classified autonomous driving complexity quantification evaluation results of all roads are obtained.

[0008] As a further optimization of this disclosure, the processed POI GIS data includes POI category, AOI area, operating hours, and entrance / exit coordinates; the processed road network topology GIS data includes road grade, road length, direction, origin / endpoint coordinates, number of lanes, whether there is a median strip, and whether there is an organic non-discrete strip.

[0009] As a further optimization of this disclosure, a gravity-like model is constructed to describe the quantitative impact of POIs on road segments, including: The impact of POI entrances and exits on the autonomous driving complexity of this road segment is defined as being directly proportional to the type and area of ​​the parent POI corresponding to the POI entrance / exit, correlated with the road attributes of the road segment, and inversely proportional to the distance correlation coefficient between the POI entrance / exit and the road segment, thus constructing a gravity-like model.

[0010] As a further optimization of this disclosure, based on the processed POI GIS data and the processed road network topology GIS data, the autonomous driving complexity of all roads in the overall road network is obtained within the GIS platform using the gravity-like model, including: Based on the gravity-like model, using the processed POI GIS data and the processed road network topology GIS data, full-scale rapid calculation is achieved on the GIS software platform, and the GIS spatial computing capabilities are used to obtain the quantified values ​​of the autonomous driving complexity of all roads in the overall road network.

[0011] As a further optimization of this disclosure, the quantification value of the autonomous driving complexity of all roads in the overall road network is a numerical range.

[0012] As a further optimization of this disclosure, a clustering algorithm is used to classify the numerical values ​​of autonomous driving complexity for all roads in the overall road network, ultimately obtaining a categorized quantitative evaluation result of autonomous driving complexity for all roads, including: The clustering algorithm is used to classify the quantitative values ​​of autonomous driving complexity of all roads in the overall road network into five categories: high complexity, relatively high complexity, medium complexity, relatively low complexity, and low complexity. Finally, the categorized autonomous driving complexity quantification evaluation results of all roads are obtained.

[0013] As a further optimization of this disclosure, the clustering algorithm includes the mean method and the geometric method.

[0014] A system for evaluating the complexity of autonomous driving in urban road networks based on Points of Interest (POI) data includes: The data acquisition module is used to acquire the full GIS data of POIs and the road network topology GIS data of the area to be evaluated, and to perform data cleaning and filtering to obtain the processed GIS data of POIs and the processed road network topology GIS data, respectively. The model building module is used to build a gravity-like model that describes the complex quantitative impact of POIs on road segments; The driving complexity calculation module is used to obtain the autonomous driving complexity of all roads in the overall road network within the GIS platform based on the processed POI GIS data and the processed road network topology GIS data, through the gravity-like model. The classification module is used to classify the numerical values ​​of autonomous driving complexity of all roads in the overall road network through clustering algorithms, and finally obtain the classified autonomous driving complexity quantification evaluation results of all roads.

[0015] An electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to execute the program stored in the memory to implement the urban road network autonomous driving complexity evaluation method based on POI data.

[0016] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for evaluating the complexity of autonomous driving in urban road networks based on POI data.

[0017] The beneficial effects of this disclosure are as follows: This disclosure can effectively supplement the quantitative evaluation results of autonomous driving complexity for road segments with insufficient or no driving data, and can complement other evaluation methods. Furthermore, based on modeling algorithms and GIS platform capabilities, it can quickly generalize to obtain the autonomous driving complexity of all roads in a city-level road network. After parameter adjustments for different cities, it can be replicated to other cities, greatly assisting in the development and efficiency improvement of autonomous driving route operations. In practical applications, this disclosure can first be used to model and obtain the prior autonomous driving complexity of all roads in the road network. Then, the aforementioned positive evaluation method can be used to specifically correct road segments with medium to high complexity, ultimately obtaining a highly reliable overall road network autonomous driving complexity. Attached Figure Description

[0018] Figure 1 This is a flowchart of a method in an embodiment of this disclosure; Figure 2 This is a system structure block diagram of an embodiment of this disclosure; Figure 3 This is a block diagram of the device structure in an embodiment of this disclosure. Detailed Implementation

[0019] The present application will now be described in further detail with reference to the accompanying drawings. It should be noted that the following specific embodiments are only used to further illustrate the present application and should not be construed as limiting the scope of protection of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application based on the above application content.

[0020] like Figure 1 As shown, a method for evaluating the complexity of autonomous driving in urban road networks based on POI (Interest Point Query) data includes the following steps: S1. Obtain the full GIS (Geographic Information System) data and road network topology GIS data of the POIs in the area to be evaluated, and perform data cleaning and filtering to obtain the processed GIS data of the POIs and the processed road network topology GIS data, specifically including: Acquire full GIS data of POIs at the city or district level, perform data cleaning and filtering, and extract key indicator data needed to build an evaluation model, including POI category, AOI area, business hours, entrance and exit coordinates, etc.

[0021] Generally, a city-level or area-level full POI data can be obtained from an online map provider and imported into GIS software for display. Alternatively, free API interfaces can be used to crawl POI data for relevant areas. The initial full POI data typically includes fields such as POI ID, name, category (multi-level classification), address, administrative division (country, province, city, district, etc.), coordinates, area, operating status (yes / no), operating hours, and coordinates of affiliated entrances / exits. The main POI indicators required for establishing the complex quantitative evaluation model in this invention are category (accurate to three levels of classification), area, operating status and time, and coordinates of affiliated entrances / exits. Therefore, the initial full POI data needs to be cleaned and filtered to remove invalid and erroneous data, extract the required field information, and be transformed according to the entrance / exit target. That is, the final processed POI data displayed on the GIS should be a set of points corresponding to all POI entrances / exits, with each entrance / exit point containing fields such as coordinates, parent POI category, area, and operating hours.

[0022] Road network topology GIS data can also be obtained from internet map providers and can be imported into GIS software for display. The road segments provided by the map providers are divided into nodes by intersections through steps such as merging and breaking. Each road segment contains attribute fields such as the road class (expressway, arterial road, secondary arterial road, local road, etc.), road length, direction, origin and destination coordinates, number of lanes, and whether there is a median strip and a non-motorized vehicle separation strip.

[0023] Simultaneously, it is necessary to determine the spatial extent affected by surrounding POI entrances and exits for each road segment for subsequent calculations. Considering that roads of different grades generally have different building setbacks, with higher grades having larger setbacks, and referring to relevant urban planning standards of different cities, different setback values ​​can be matched to each road segment based on the road grade data in the road attributes. On this basis, using a GIS platform, a double-sided buffer zone is established for each road segment, with the buffer length taken as the setback value. Simultaneously, a circular buffer zone with a radius of 500m is established with the start and end points of the road segment as the center. POI entrances and exits within all of the above buffer zones are selected as the POIs affecting the calculation of the road segment's complexity.

[0024] S2. Construct a gravity-like model to describe the complex quantitative impact of POIs on road segments, specifically including: This step is the core step of this disclosure. The focus is on establishing a quantitative evaluation method for calculating the complexity of autonomous driving on road segments, based on the GIS data of the processed POIs and the processed road network topology GIS data selected above, and using a feature model that can describe the interaction relationship.

[0025] The First Law of Geography is a fundamental concept in geography, its core idea being that things closer together have a stronger mutual influence and connection. Similarly, this law can describe the relationship between Points of Interest (POIs) and roads to some extent; that is, the closer a POI is to a road, the greater its impact on road complexity. Extending this concept, in traffic engineering, gravity models are often used to describe the degree of interaction between a pair of Origin and Outer Points (ODs). These models assume that the traffic intensity between ODs is directly proportional to the traffic volume generated by the OD itself and inversely proportional to a power of the traffic impedance between the two points. Named for its resemblance to Newton's law of gravity, this paper proposes a gravity-like model that can quantify the impact of POIs on road segment complexity. The core idea is that the impact of a POI entrance / exit on the autonomous driving complexity of a road segment is directly proportional to the type and area of ​​the parent POI corresponding to that POI entrance / exit, correlated with the road attributes of the road segment, and inversely proportional to a power of the distance between the POI entrance / exit and the road segment. The specific expression is as follows: ; in, This represents the impact of the i-th POI entrance / exit point on the autonomous driving complexity of road segment j; This represents the indicator data of the i-th POI entrance / exit point itself, including its type, area, business hours, etc. This refers to the indicator data of road segment j itself, including its road grade, whether it has a median strip and a separation strip between motor vehicles and non-motor vehicles, etc. This represents the distance between the i-th POI entrance / exit point and road segment j, calculated as the perpendicular distance from the point to the line segment, with n being the power. These are the normalization coefficients; for ,have: ; in, This represents the type index of the parent POI corresponding to the i-th POI entrance / exit point. Different weight values ​​are assigned according to different categories. Generally, for commercial POIs such as shopping malls and supermarkets, office POIs such as office buildings and parks, and residential POIs such as schools, hospitals, and residential communities, they are usually considered to have a greater impact on roads, so the weight value is correspondingly higher. For leisure POIs such as parks and squares, and industrial POIs such as factories, they are usually considered to have a smaller impact on roads, so the weight value is correspondingly lower.

[0026] This represents the area index of the parent POI corresponding to the i-th POI entrance / exit point. It is generally believed that the larger the area, the larger the corresponding volume, the greater the traffic demand, and the greater the impact on the road. Therefore, corresponding weight values ​​can be assigned according to the area size. This represents the business status indicator of the parent POI corresponding to the i-th POI entrance / exit point. If it is within business hours, it is assigned a weight value of 1; otherwise, it is assigned 0. for ,have: ; in, This represents the road grade index for road segment j, with different weight values ​​assigned to different road grades. Generally, the higher the road grade, the higher the degree of road structure, and the more orderly and regular the traffic flow, which is usually considered to result in relatively lower complexity for autonomous driving. Therefore, the weight values ​​should increase progressively from expressway, arterial road, secondary arterial road to local road. This indicator indicates whether road segment j has a median strip. It primarily characterizes the impact of opposite-side POIs on the road segment. Generally, it's considered that for road segments with a median strip, traffic from opposite-side POI entrances / exits has a smaller impact on the segment. Therefore, when calculating the impact of opposite-side POI entrances / exits on road segment j, if road segment j has a median strip, the weight value is correspondingly smaller, and vice versa; same-side POIs are not affected by this indicator. This index indicates whether road segment j has a median strip (or non-motorized vehicle lane). This index primarily characterizes the degree of influence of the presence or absence of a median strip on the road segment. It is generally believed that for road segments with a median strip, vehicles traveling in the motorized lane are less affected by pedestrians and non-motorized vehicles on the outer side; therefore, in the calculation, if road segment j has a median strip, the weight value is correspondingly smaller, and vice versa.

[0027] Ultimately, we have the autonomous driving complexity value for road segment j under the influence of all surrounding POIs. for:

[0028] S3. Based on the processed POI GIS data and the processed road network topology GIS data, the autonomous driving complexity of all roads in the overall road network is obtained within the GIS platform using the gravity-like model, specifically including: This step is based on the gravity-like model described in step S2. It uses the processed POI GIS data and processed road network topology GIS data obtained after steps S1 and S2 to perform full-scale and rapid calculations on the GIS software platform. Through the powerful spatial computing capabilities of GIS, it obtains the quantified values ​​of the autonomous driving complexity of all roads in the overall road network.

[0029] S4. Classify the numerical values ​​of autonomous driving complexity for all roads in the overall road network using a GIS clustering algorithm, ultimately obtaining a categorized quantitative evaluation result of autonomous driving complexity for all roads, specifically including: The complexity values ​​of all roads in the road network are classified into five categories—high complexity, relatively high complexity, medium complexity, relatively low complexity, and low complexity—using clustering algorithms. This yields a quantified evaluation result of the autonomous driving complexity of all roads. The GIS platform provides a rich set of clustering algorithms, including the mean method and geometric method, allowing for the selection of a suitable algorithm based on the numerical range of complexity values, resulting in a relatively scientific and reasonable distribution. After classification, the results are assigned to all road segments in the road network, and the classification results are visualized using GIS software, ultimately yielding usable quantified results of the road network's autonomous driving complexity.

[0030] The quantified values ​​of autonomous driving complexity for all roads in the overall road network obtained in step S3 should fall within a large numerical range. However, the complexity value of a specific road segment does not directly reflect its level within the overall road network. Therefore, a clustering algorithm is needed to classify all the above values, ultimately categorizing the complexity of each road into one of five levels: high, relatively high, medium, relatively low, and low complexity, and visualizing this classification. This allows for intuitive subsequent analysis and processing.

[0031] like Figure 2 As shown, embodiments of this disclosure provide a system for evaluating the complexity of autonomous driving in urban road networks based on Points of Interest (POI) data, including: The data acquisition module 11 is used to acquire the full GIS data of POIs and the road network topology GIS data of the area to be evaluated, and to perform data cleaning and filtering to obtain the processed GIS data of POIs and the processed road network topology GIS data, respectively. Model building module 12 is used to build a gravity-like model that describes the quantitative impact of POIs on road segment complexity. The driving complexity calculation module 13 is used to obtain the autonomous driving complexity of all roads in the overall road network within the GIS platform based on the processed POI GIS data and the processed road network topology GIS data, through the gravity-like model. The classification module 14 is used to classify the numerical values ​​of autonomous driving complexity of all roads in the overall road network using a GIS clustering algorithm, and finally obtain the classified autonomous driving complexity quantification evaluation results of all roads.

[0032] The implementation process of the functions and roles of each module in the above system is detailed in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0033] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0034] In the above embodiments, any number of modules can be combined into one module, or any one module can be split into multiple modules. Alternatively, at least some of the functionality of one or more of these modules can be combined with at least some of the functionality of other modules and implemented in one module. At least one of all modules can be at least partially implemented as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of all modules can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0035] See Figure 3 The electronic device provided in the embodiments of this disclosure includes a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120 and the memory 1130 communicate with each other through the communication bus 1140. Memory 1130 is used to store computer programs; When the processor 1110 executes the program stored in the memory 1130, it implements the above-described method for evaluating the complexity of autonomous driving in urban road networks based on POI data. The aforementioned communication bus 1140 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, it is represented by only one thick line in the figure, but this does not indicate that there is only one bus or one type of bus.

[0036] The communication interface 1120 is used for communication between the above-mentioned electronic device and other devices.

[0037] The memory 1130 may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1130 may also be at least one storage device located remotely from the aforementioned processor 1110.

[0038] The processor 1110 mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0039] Embodiments of this disclosure also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the urban road network autonomous driving complexity evaluation method based on POI data as described above.

[0040] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs, which, when executed, implement the urban road network autonomous driving complexity evaluation method based on POI data according to embodiments of this disclosure.

[0041] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0042] The embodiments described above are merely examples of several implementations of this disclosure, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent disclosure. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this disclosure, and these modifications and improvements all fall within the protection scope of this disclosure.

Claims

1. A method for evaluating the complexity of autonomous driving in urban road networks based on POI data, characterized in that, Includes the following steps: Obtain the full GIS data of POIs and the road network topology GIS data of the area to be evaluated, and perform data cleaning and filtering to obtain the processed GIS data of POIs and the processed road network topology GIS data, respectively. Construct a gravity-like model to describe the quantitative impact of POIs on road segment complexity; Based on the processed POI GIS data and the processed road network topology GIS data, the autonomous driving complexity of all roads in the overall road network is obtained within the GIS platform through the gravity-like model. The numerical values ​​of autonomous driving complexity of all roads in the overall road network are classified by clustering algorithm, and finally the classified autonomous driving complexity quantification evaluation results of all roads are obtained.

2. The method for evaluating the complexity of autonomous driving in urban road networks based on POI data according to claim 1, characterized in that, The processed POI GIS data includes POI category, AOI area, operating hours, and entrance / exit coordinates; the processed road network topology GIS data includes road grade, road length, direction, origin / end point coordinates, number of lanes, presence of median strip, and presence of organic / non-organic median strip.

3. The method for evaluating the complexity of autonomous driving in urban road networks based on POI data according to claim 1, characterized in that, Construct a gravity-like model to describe the complex quantitative impact of POIs on road segments, including: The impact of POI entrances and exits on the autonomous driving complexity of this road segment is defined as being directly proportional to the type and area of ​​the parent POI corresponding to the POI entrance / exit, correlated with the road attributes of the road segment, and inversely proportional to the distance correlation coefficient between the POI entrance / exit and the road segment, thus constructing a gravity-like model.

4. The method for evaluating the complexity of autonomous driving in urban road networks based on POI data according to claim 1, characterized in that, Based on the processed POI GIS data and the processed road network topology GIS data, the autonomous driving complexity of all roads in the overall road network is obtained within the GIS platform using the gravity-like model, including: Based on the gravity-like model, using the processed POI GIS data and the processed road network topology GIS data, full-scale rapid calculation is achieved on the GIS software platform, and the GIS spatial computing capabilities are used to obtain the quantified values ​​of the autonomous driving complexity of all roads in the overall road network.

5. The method for evaluating the complexity of autonomous driving in urban road networks based on POI data according to claim 4, characterized in that, The quantification values ​​for the complexity of autonomous driving on all roads of the overall road network are within a numerical range.

6. The method for evaluating the complexity of autonomous driving in urban road networks based on POI data according to claim 1, characterized in that, The autonomous driving complexity values ​​of all roads in the overall road network are classified using a clustering algorithm, ultimately yielding a categorized quantitative evaluation result of the autonomous driving complexity of all roads, including: The clustering algorithm is used to classify the quantitative values ​​of autonomous driving complexity of all roads in the overall road network into five categories: high complexity, relatively high complexity, medium complexity, relatively low complexity, and low complexity. Finally, the categorized autonomous driving complexity quantification evaluation results of all roads are obtained.

7. The method for evaluating the complexity of autonomous driving in urban road networks based on POI data according to claim 1, characterized in that, The clustering algorithms include the mean method and the geometric method.

8. A system for evaluating the complexity of autonomous driving in urban road networks based on POI data, characterized in that, include: The data acquisition module is used to acquire the full GIS data of POIs and the road network topology GIS data of the area to be evaluated, and to perform data cleaning and filtering to obtain the processed GIS data of POIs and the processed road network topology GIS data, respectively. The model building module is used to build a gravity-like model that describes the complex quantitative impact of POIs on road segments; The driving complexity calculation module is used to obtain the autonomous driving complexity of all roads in the overall road network within the GIS platform based on the processed POI GIS data and the processed road network topology GIS data, through the gravity-like model. The classification module is used to classify the numerical values ​​of autonomous driving complexity of all roads in the overall road network using a GIS clustering algorithm, and finally obtain the classified autonomous driving complexity quantification evaluation results of all roads.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor is used to execute a program stored in a memory to implement the method for evaluating the complexity of autonomous driving in urban road networks based on POI data, as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for evaluating the complexity of autonomous driving in urban road networks based on POI data, as described in any one of claims 1-7.

Images