High-precision map updating method and device

Abstract

The embodiment of the application discloses a high-precision map updating method and device, the method comprises the following steps: acquiring n-dimensional feature information of a dynamic event in n dimensions, the n dimensions are n factors influencing expression of the dynamic event in a high-precision map, the dynamic event is an event causing dynamic information in the high-precision map to change, and n is an integer greater than 1; and determining an expression mode of the dynamic event in the high-precision map based on the feature information, wherein the expression mode comprises at least one of extended attribute expression or dynamic layer expression. The application provides an effective and feasible method for determining the expression mode of the dynamic event.

Description

Technical Field

[0001] This application relates to the field of intelligent connected vehicle technology, specifically to a high-precision map update method and apparatus. Background Technology

[0002] High-precision maps, as a key capability for achieving autonomous driving, will effectively complement existing sensors in autonomous driving, providing vehicles with more reliable perception capabilities. Compared to traditional navigation maps, high-precision maps serving autonomous driving have higher requirements in all aspects and can work in conjunction with sensors and algorithms to support decision-making.

[0003] Because the external environment dynamically changes and affects vehicle operation during autonomous driving, high-precision maps increasingly require more dynamic information in addition to static layers to meet the evolving needs of the transportation sector. Dynamic information includes a wide range of data, such as real-time traffic flow, road occupancy, traffic control measures, traffic light status, and cooperative driving information. Accurately representing this information in high-precision maps can provide vehicles with timely road information, driving suggestions, and risk warnings, thereby significantly improving the safety of autonomous driving. However, there are currently no unified industry standards or widely implemented products for representing dynamic information in high-precision maps.

[0004] In summary, how to provide a feasible and effective method for representing dynamic events in high-precision maps to better update them is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] This application provides a high-precision map updating method and apparatus, which can provide a feasible and effective high-precision map updating method, thereby improving the event representation of high-precision maps and enhancing the accuracy of high-precision map event representation for better high-precision map updating.

[0006] Firstly, this application provides a high-precision map updating method, which includes:

[0007] The map update device acquires n-dimensional feature information of a dynamic event in n dimensions. These n dimensions are n factors that affect the representation of the dynamic event in the high-precision map. The dynamic event is an event that causes changes in the dynamic information in the high-precision map. Here, n is an integer greater than 1.

[0008] The map updating device determines the representation method of the dynamic event in the high-precision map based on the n-dimensional feature information. The representation method includes at least one of the extended attribute representation method or the dynamic layer representation method. The extended attribute representation method is a way to associate the dynamic event with a static layer in the high-precision map and make it an extended attribute of the static layer element. The dynamic layer representation method is a way to add the dynamic event to a dynamic layer in the high-precision map for representation. Optionally, the dynamic layer in the high-precision map is associated with a static layer.

[0009] The map update device expresses the dynamic event into the high-precision map based on the determined expression method of the dynamic event.

[0010] This application evaluates the representation of dynamic events in high-precision maps from multiple dimensions, thereby accurately determining the representation of each dynamic event and easily automating the process. Compared with existing technologies, this application provides a feasible and effective method for updating high-precision maps, thereby improving the event representation of high-precision maps, enhancing the accuracy and automation of event representation, and updating high-precision maps better and more efficiently.

[0011] In one possible implementation, the n dimensions include at least one of the following dimensions:

[0012] The update frequency of dynamic event states, the probability of event occurrence, the degree of influence of the event on the topology of the high-precision map, the degree of correlation change of the event, the reusability of the geometric representation of the event on the static layer, or the degree of independence of the event from the static layer.

[0013] This application provides several dimensions for evaluating the representation of dynamic events in high-precision maps, and the representation of dynamic events can be determined more accurately and reasonably by using at least one of these dimensions.

[0014] In one possible implementation, the dynamic event is a variety of dynamic events;

[0015] The map update device acquires n-dimensional feature information of dynamic events in n dimensions, including:

[0016] The map updating device acquires n-dimensional feature information of the various dynamic events in the n dimensions;

[0017] The map updating device determines how the dynamic event is represented in the high-precision map based on the n-dimensional feature information, including:

[0018] The map updating device uses a clustering algorithm to determine how the various dynamic events are represented in the high-precision map based on the n-dimensional feature information of these multiple dynamic events in the n dimensions.

[0019] In this application, a clustering algorithm can be used to classify various dynamic events based on the consideration dimensions described above, thereby determining the expression method of each category of dynamic events. Using a clustering algorithm can improve computational efficiency and the accuracy of dynamic event classification, thereby improving the accuracy of dynamic event expression.

[0020] In one possible implementation, the method of determining the representation of the various dynamic events in the high-precision map using a clustering algorithm includes:

[0021] The map updating device uses this clustering algorithm to classify the various dynamic events into a first category of dynamic events and a second category of dynamic events;

[0022] Based on the n-dimensional feature information of the first type of dynamic event and the n-dimensional feature information of the second type of dynamic event, if the correlation between the first type of dynamic event and the static layer in the high-precision map is greater than that between the second type of dynamic event,

[0023] The map update device classifies the first type of dynamic events into events expressed using extended attributes, and the second type of dynamic events into events expressed using dynamic layers.

[0024] In this application, after dividing the dynamic events into two categories, the expression method of each category of dynamic events can be determined by the degree of correlation between these two categories of events and the static layer of the high-precision map, thereby improving the accuracy of the dynamic event expression method. It should be noted that the degree of correlation between the dynamic event and the static layer in the high-precision map is used to indicate the impact of the dynamic event's expression on the high-precision map on that static layer. The greater the correlation, the greater the impact; the smaller the correlation, the smaller the impact. That is, the impact is positively correlated with the degree of correlation.

[0025] In one possible implementation, the dynamic event includes a first dynamic event.

[0026] The map updating device determines how the dynamic event is represented in the high-precision map based on the n-dimensional feature information, including:

[0027] The map updating device determines the expression method judgment result of the first dynamic event in each single dimension based on the feature information in the n-dimensional feature information, and obtains n judgment results. The judgment result includes at least one of the expression method of the first dynamic event being the extended attribute expression or the dynamic layer expression.

[0028] The map update device determines that the dynamic event is represented in the high-precision map in the way that accounts for the largest proportion among the n judgment results.

[0029] In this application, the expression method of dynamic events can be determined through a voting mechanism based on the above n dimensions, which is also an implementation method that can determine the expression method of dynamic events relatively accurately.

[0030] In one possible implementation, after the map updating device determines how the dynamic event is represented in the high-precision map based on the feature information, it further includes:

[0031] The map update device associates the dynamic event and its representation in memory.

[0032] In this application, the determined expression method can be associated with the corresponding dynamic event and stored for subsequent query use, which can avoid repeated calculations each time it is used and save computing resources.

[0033] In one possible implementation, the dynamic event includes a second dynamic event, and the map updating device expresses the dynamic event into the high-precision map based on a determined expression method of the dynamic event, including:

[0034] The map updating device obtains the latest information about the second dynamic event and retrieves the representation of the second dynamic event from the memory;

[0035] The map update device determines that the second dynamic event is expressed as an extended attribute expression method;

[0036] The map updating device creates a new extended attribute table based on the latest information of the second dynamic event, and associates the new extended attribute table with the static layer of the high-precision map;

[0037] Alternatively, the map updating device may modify the existing extended attribute table based on the latest information from the second dynamic event.

[0038] In this application, after determining that a dynamic event is expressed using an extended attribute representation method, the latest attribute information of the dynamic event is associated with a static layer, thereby enabling the latest state of the dynamic event to be expressed in a high-precision map.

[0039] In one possible implementation, the dynamic event includes a third dynamic event, and the map updating device expresses the dynamic event into the high-precision map based on a determined expression method of the dynamic event, including:

[0040] The map updating device obtains the latest information about the third dynamic event and retrieves the representation of the third dynamic event from the memory;

[0041] The map update device determines that the third dynamic event is expressed as a dynamic layer expression.

[0042] The map updating device can create a new dynamic layer based on the latest information of the third dynamic event, or modify an existing dynamic layer based on the latest information of the third dynamic event.

[0043] In this application, after determining that a dynamic event is to be expressed using a dynamic layer, the latest attribute information of the dynamic event is added to the corresponding dynamic layer, so that the latest state of the dynamic event can be expressed in a high-precision map.

[0044] Secondly, this application provides a dynamic event expression device, the device comprising:

[0045] The acquisition unit is used to acquire n-dimensional feature information of a dynamic event in n dimensions. The n dimensions are n factors that affect the expression of the dynamic event in the high-precision map. The dynamic event is an event that causes changes in the dynamic information in the high-precision map. The n is an integer greater than 1.

[0046] The determining unit is used to determine the expression method of the dynamic event in the high-precision map based on the n-dimensional feature information. The expression method includes at least one of the extended attribute expression method or the dynamic layer expression method. The extended attribute expression method is the expression method of associating the dynamic event with a static layer in the high-precision map and becoming an extended attribute of the static layer element. The dynamic layer expression method is the expression method of adding the dynamic event to the dynamic layer of the high-precision map.

[0047] An expression unit is used to express the dynamic event into the high-precision map based on a determined expression method for the dynamic event.

[0048] It should be noted that the dynamic event expression device provided in this application can be a server, a roadside unit (e.g., an RSU, which is short for road side unit), or vehicle-mounted equipment. The vehicle-mounted equipment can include a vehicle or a processing device or unit in the vehicle.

[0049] In one possible implementation, the n dimensions include at least one of the following dimensions:

[0050] The update frequency of dynamic event states, the probability of event occurrence, the degree of influence of the event on the topology of the high-precision map, the degree of correlation change of the event, the reusability of the geometric representation of the event on the static layer, or the degree of independence of the event from the static layer.

[0051] In one possible implementation, the dynamic event includes a variety of dynamic events;

[0052] This acquisition unit is specifically used for:

[0053] Obtain the n-dimensional feature information of these multiple dynamic events across the n dimensions;

[0054] This determining unit is specifically used for:

[0055] Based on the n-dimensional feature information of these multiple dynamic events in the n dimensions, a clustering algorithm is used to determine how these multiple dynamic events are represented in the high-precision map.

[0056] In one possible implementation, the determining unit is specifically used for:

[0057] The clustering algorithm is used to classify the various dynamic events into a first category and a second category of dynamic events.

[0058] Based on the n-dimensional feature information of the first type of dynamic event and the n-dimensional feature information of the second type of dynamic event, if the correlation between the first type of dynamic event and the static layer in the high-precision map is greater than that between the second type of dynamic event,

[0059] The first type of dynamic event is classified as an event expressed using extended attributes, and the second type of dynamic event is classified as an event expressed using dynamic layers.

[0060] In one possible implementation, the dynamic event includes a first dynamic event.

[0061] This determining unit is specifically used for:

[0062] Based on the feature information in each single dimension of the n-dimensional feature information, determine the expression method of the first dynamic event in that single dimension, and obtain n judgment results. The judgment results include at least one of the expression method of the first dynamic event being the extended attribute expression or the dynamic layer expression.

[0063] The dynamic event is determined to be represented in the high-precision map in the way that has the largest proportion among the n judgment results.

[0064] In one possible implementation, the device further includes a storage unit for associating and storing the dynamic event and its representation in a memory after the determining unit determines the representation of the dynamic event in the high-precision map based on the feature information.

[0065] In one possible implementation, the dynamic event includes a second dynamic event, and the expression unit is specifically used for:

[0066] Obtain the latest information about the second dynamic event and retrieve the representation of the second dynamic event from the memory;

[0067] The second dynamic event is determined to be expressed as an extended attribute;

[0068] Create a new extended attribute table based on the latest information of the second dynamic event, and associate the new extended attribute table with the static layer of the high-precision map;

[0069] Alternatively, modify the extended attribute table of the second dynamic event based on the latest information of the second dynamic event.

[0070] In one possible implementation, the dynamic event includes a third dynamic event, and the expression unit is specifically used for:

[0071] Obtain the latest information about the third dynamic event and retrieve the representation of the third dynamic event from the memory;

[0072] The expression method for this third dynamic event is determined to be the dynamic layer expression method;

[0073] Create a new dynamic layer based on the latest information of this third dynamic event;

[0074] Alternatively, modify the dynamic layer to which the third dynamic event belongs based on the latest information of the third dynamic event.

[0075] Thirdly, this application provides a dynamic event expression device, which may include a processor for implementing the high-precision map update method described in the first aspect. The device may also include a memory coupled to the processor. When the processor executes a computer program stored in the memory, it can implement the high-precision map update method described in the first aspect or any possible implementation thereof. The device may also include a communication port for communicating with other devices. Exemplarily, the communication port may be a transceiver, circuit, bus, module, or other type of communication port. It should be noted that the dynamic event expression device provided in this application may be a server, a roadside unit (e.g., an RSU, short for road side unit), or a vehicle-mounted device. The vehicle-mounted device may include a vehicle or processing equipment or units within a vehicle.

[0076] In one possible implementation, the device may include:

[0077] Memory, used to store computer programs;

[0078] The processor is configured to acquire n-dimensional feature information of a dynamic event across n dimensions, where the n dimensions represent n factors influencing the representation of the dynamic event in a high-precision map, and the dynamic event is an event that causes changes in the dynamic information within the high-precision map, where n is an integer greater than 1; determine the representation method of the dynamic event in the high-precision map based on the n-dimensional feature information, where the representation method includes at least one of an extended attribute representation method or a dynamic layer representation method, wherein the extended attribute representation method is a method of associating the dynamic event with a static layer in the high-precision map and making it an extended attribute of the static layer element, and the dynamic layer representation method is a method of adding the dynamic event to a dynamic layer of the high-precision map for representation; and represent the dynamic event in the high-precision map based on the determined representation method of the dynamic event.

[0079] It should be noted that the computer program in the memory of this application can be pre-stored or downloaded from the Internet and stored after use of the device. This application does not specifically limit the source of the computer program in the memory. The coupling in the embodiments of this application is an indirect coupling or connection between devices, units, or modules, which can be electrical, mechanical, or other forms, for information interaction between devices, units, or modules.

[0080] Fourthly, this application provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the method described in any one of the first aspects.

[0081] Fifthly, this application provides a computer program product that, when processed and executed, causes the method described in any one of the first aspects to be performed.

[0082] Sixthly, this application also provides a high-precision map, which includes at least one of a static layer carrying dynamic information or a dynamic layer carrying dynamic information, wherein the expression of the dynamic information in the high-precision map is determined by the method described in any of the first aspects above.

[0083] The solutions provided in the second to sixth aspects above are used to implement or cooperate with the methods provided in the first aspect above, and therefore can achieve the same or corresponding beneficial effects as the first aspect, which will not be elaborated here.

[0084] In summary, this application evaluates the representation of dynamic events in high-precision maps from multiple dimensions, thereby accurately determining the representation of each dynamic event and easily automating the process. Compared with existing technologies, this application provides a feasible and efficient method for updating high-precision maps, which can improve the event representation of high-precision maps and enhance the accuracy and automation of event representation. Attached Figure Description

[0085] The accompanying drawings used in the embodiments of this application will be described below.

[0086] Figure 1 The diagram shown is a schematic representation of the system architecture used in a high-precision map update method provided in this application embodiment.

[0087] Figure 2 The diagram shown is a flowchart of a high-precision map update method provided in an embodiment of this application.

[0088] Figure 3 The diagram shows various ways of expressing dynamic events provided in this application;

[0089] Figure 4 A schematic diagram illustrating the association between an extended attribute table and a static layer, as provided in this application;

[0090] Figure 5 A schematic diagram illustrating the association between dynamic and static layers provided in this application;

[0091] Figure 6 This is a schematic diagram of the logical structure of a device provided in an embodiment of this application;

[0092] Figure 7 A schematic diagram of the hardware structure of the device provided in the embodiments of this application. Detailed Implementation

[0093] The technical solutions in the embodiments of this application are described below with reference to the accompanying drawings.

[0094] To better understand the high-precision map update method provided by the embodiments of the present invention, the applicable scenarios of the embodiments of the present invention will be described exemplarily below.

[0095] For example, the high-precision map updating method provided in this application can be applied to high-precision maps. With the continuous development of autonomous driving, intelligent assisted driving, and transportation networks, high-precision maps have gradually become a tool to better serve these fields. For instance, in the field of autonomous driving, because high-precision maps provide a more accurate, clear, and comprehensive description of roads, and can reflect various dynamic events on the road in real time, they provide vehicles with more room for prediction, enabling them to plan their driving in advance and ensuring smooth and economical driving. Furthermore, high-precision maps can help vehicles reduce computational load. When a vehicle needs to pass through an intersection, it needs to perceive the status of traffic lights ahead in advance. A high-precision map can help it locate the specific area where the traffic lights are located, thereby effectively reducing the computational load of full-range scanning and recognition.

[0096] The high-precision map updating method provided in this application can also be applied to other fields, not limited to the high-precision map field described above.

[0097] To enable high-precision maps to achieve the functions described above, various dynamic events affecting vehicle driving need to be expressed in the high-precision map so that vehicles can perceive these dynamic events. However, there is no unified industry standard or implemented product for expressing dynamic events in high-precision maps. Therefore, this application provides a feasible and effective high-precision map updating method to better express dynamic events affecting driving in high-precision maps, so as to better serve driving and other fields.

[0098] Optionally, the high-precision map updating method provided in this application can be implemented in a server, roadside unit, or vehicle-mounted device (e.g., a vehicle or a processing device or unit in a vehicle), and the device that implements the high-precision map updating method provided in this application is collectively referred to as a map updating device.

[0099] For easier understanding, please refer to Figure 1 , Figure 1 An exemplary system architecture diagram of the high-precision map update method provided in this application is illustrated. This system architecture may include a server 100, a vehicle 101, and a roadside unit 102, etc. The server 100 may include one or more servers, and multiple servers may form a server cluster. The server 100 can communicate with the vehicle 101 and the roadside unit 102 via a network, and the roadside unit 102 can also communicate with the vehicle 101.

[0100] Server 100 can interact and communicate with other devices to obtain the information needed for high-precision maps. For example, server 100 can interact and communicate with servers of transportation bureaus to obtain traffic information, or with servers of meteorological bureaus to obtain weather information, and so on. Vehicle 101 can be an autonomous vehicle, a semi-autonomous vehicle, or a regular vehicle, etc.

[0101] If the high-precision map update method provided in this application is implemented in server 100, then vehicle 101 can interact with server 100 to obtain the latest high-precision map. Alternatively, server 100 can send the latest high-precision map to roadside unit 102, which can then be obtained by vehicle 101 interacting with roadside unit 102.

[0102] If the high-precision map update method provided in this application is implemented in the roadside unit 102, then the roadside unit 102 can obtain the latest information on various dynamic events from the server 100 and update the high-precision map based on this latest information. Then the vehicle 101 can interact with the roadside unit 102 to obtain the latest state of the high-precision map.

[0103] If the high-precision map update method provided in this application is implemented in vehicle 101, then vehicle 101 can obtain the latest information on various dynamic events from server 100 and update the high-precision map based on this latest information for use.

[0104] It should be noted that, Figure 1 The system architecture shown is only an example. Any system architecture that can be applied to the high-precision map update method provided in this application is within the protection scope of this application. This application does not limit the specific system architecture used.

[0105] Based on the above description, the following introduces a feasible and effective high-precision map updating method provided by this application. (See also...) Figure 2 This method is executed by the aforementioned map updating device and may include, but is not limited to, the following steps:

[0106] S201. Obtain the feature information of the dynamic event in n dimensions. The n dimensions are the n factors that affect the expression of the dynamic event in the high-precision map. The dynamic event is the event that causes the dynamic information in the high-precision map to change. The n is an integer greater than 1.

[0107] In a specific embodiment, the above-mentioned dynamic events may include some or all of the following events:

[0108] Weather conditions can include dynamic events such as temperature, air pressure, humidity, sunny, cloudy, windy, foggy, rainy, lightning, snowy, frosty, thunder, or hail.

[0109] Road cover conditions, or road surface environment, can include dynamic events such as water accumulation, snow accumulation, icing, or damage to road cover.

[0110] Road adhesion coefficient: This refers to the adhesion between the road and the vehicle tires. The greater the adhesion, the less likely the vehicle is to slip.

[0111] Road visibility conditions: This can refer to the visible distance caused by fog, haze, or poor lighting.

[0112] Temporary points of interest (POIs) can include non-fixed points of interest, temporary parking spaces, temporary charging stations, or temporary public service points, among other dynamic events.

[0113] Recommendation information can include dynamic events such as recommendations based on user interests or suggested itineraries.

[0114] Road traffic conditions: This can include dynamic events such as traffic accidents, traffic control, road construction, or accident-prone areas.

[0115] Traffic flow conditions: This can include the amount of traffic on each road.

[0116] Traffic light status: This can include dynamic events such as traffic light phase status, semantic information, timing data, or operating status.

[0117] Vehicle obstacles: This can include the type of vehicle causing the obstacle, motion information, headlight and door information, control information, or driving behavior prediction information, etc.

[0118] Other obstacles: This can include all obstacles other than vehicle obstacles.

[0119] Risk warning information may include the type of risk (collision risk in all directions, landslide risk, etc.), risk level, or avoidance suggestions.

[0120] Collaborative driving status: This can refer to vehicle collaborative guidance information, including lane changing collaboration, steering collaboration, special vehicle avoidance, or parking collaboration, etc.

[0121] Route planning: This can refer to the planned route based on existing road conditions.

[0122] Changes in road network topology: This can refer to temporary changes in drivable routes caused by road traffic incidents, manifested as changes in the geometric representation or attributes of road lines and lane lines.

[0123] The above examples exemplify some dynamic events applied to high-precision maps. In practical applications, the granularity of dynamic events can be finer. For instance, the dynamic event of weather conditions can be expressed in a high-precision map as a specific event such as rain, snow, or sunny weather. By updating these dynamic events in the high-precision map in real time, various dynamic conditions on the road can be provided to vehicles and other users of the high-precision map, providing a powerful reference for route planning and behavior prediction. It should be noted that the dynamic events actually used in high-precision maps are not limited to the events mentioned above, and this application does not limit the specific dynamic events or their number.

[0124] Since there are many types of dynamic events, when expressing these various dynamic events in a high-precision map, an appropriate expression method can be selected to express the corresponding dynamic events. In this application, the expression method of dynamic events in a high-precision map may include extended attribute expression method and dynamic layer expression method.

[0125] The aforementioned extended attribute expression method associates dynamic events with static layers in a high-precision map, making them the extended attributes of that static map element. These extended attributes can either override existing attributes of the static map element to express changes in those attributes, or they can extend or add to the static map element's attributes. These static map elements can include lanes, pedestrian crossings, roadside signs, medians, speed limit signs, traffic lights, or roadside phone stands, etc.

[0126] The above dynamic layer representation method involves adding dynamic events to a dynamic layer associated with the static layer. Therefore, it can be seen that dynamic events expressed using the extended attribute method have a higher correlation with the static layer, while dynamic events expressed using the dynamic layer method have a lower correlation with the static layer.

[0127] So, how do we choose an appropriate way to represent a dynamic event? In this application, we can evaluate the specific way of representing a dynamic event by considering several dimensions. The above n dimensions may include at least one of the following dimensions:

[0128] Event state update frequency: This dimension can be used to assess how frequently a dynamic event changes. For example, for a dynamic event like a vehicle obstacle, the change is frequent during vehicle movement, so the change frequency is relatively high; while for a dynamic event like the road adhesion coefficient, the change frequency is relatively low.

[0129] Event occurrence probability: This dimension can be used to assess whether a dynamic event is a frequent event or an occasional event.

[0130] The degree of impact of an event on the topology of the aforementioned high-precision map: This dimension can be used to assess the degree of impact of a dynamic event on the topology of the static layer of the high-precision map. The topology of this static layer is the road network structure within the coverage area of ​​the high-precision map, including the relationships between upper and lower nodes in traversable areas, etc. For example, traffic light status information is only a state or attribute of the traffic light element in the static layer, and its change will not affect the map's topology; however, dynamic events such as road construction or traffic accidents will occupy lanes, affecting traversable areas and traversable lanes, thereby changing the traversable topology and having a significant impact on the map topology.

[0131] The degree of correlation between events: This dimension can be used to assess the extent to which the occurrence or state change of one dynamic event affects the occurrence or state change of another dynamic event. For example, a change in the value of the road adhesion coefficient can be regarded as a state change of road attributes, which will not have a significant impact on other dynamic events or their dynamic changes; however, if a dynamic event such as rain occurs, it will affect the value of the road adhesion coefficient, and the road adhesion coefficient will decrease after rain.

[0132] The reusability of the geometric representation of an event to the static layer: This dimension can be used to evaluate whether the geometric representation of a dynamic event is the same as or corresponds to the geometric representation of the corresponding map element in the static layer. Additionally, this dimension can be used to evaluate whether a dynamic event can directly reuse the geometric representation of a map element at a corresponding location in the static layer, without needing to represent it separately. For example, the dynamic event of traffic light status information can directly reuse the traffic light data in the static layer, without needing to represent it with another geometric entity in the map. As another example, the dynamic event of a vehicle obstacle, if the vehicle obstacle is not present in the static layer, then it needs to be represented in the map in another way.

[0133] The geometric representation of dynamic events refers to the geometric form in which various dynamic events are represented in a high-precision map. For example, dynamic events related to weather conditions such as rain, snow, sunshine, and cloudy weather can be represented in a high-precision map using area-level polygon sets. Similarly, road construction and traffic accidents can generally be represented by irregular shapes composed of vertices and connecting lines of polygons at the road or lane level.

[0134] The aforementioned area-level planar geometric representation can be a polygonal surface or a toroidal surface, etc. The difference between area-level and road-level geometric representation is that area-level events with a large impact range can directly express their geometric location in the map tiles, while road-level events need to express their geometric location on the road. The relative coordinates of the location points in the road geometric representation are determined relative to a certain feature reference point on the road.

[0135] The degree of independence of an event from the static layer: This dimension can be used to assess the degree to which the representation of a dynamic event depends on the static layer. For example, a dynamic event like weather conditions is generally a large-scale event that can be geometrically represented. It does not depend on the road network structure of the static map, therefore, its dependence on the static layer is small, and its layer independence is large. On the other hand, a dynamic event like road construction needs to be represented down to the specific lane location under construction, relying on the road network structure of the static layer. Therefore, its dependence on the static layer is large, and its independence is low.

[0136] The above examples illustrate several considerations that can be used to express dynamic events. It should be noted that the actual considerations are not limited to those described above, and this application does not limit the specific considerations.

[0137] After determining n dimensions for evaluating the specific representation of dynamic events, we can obtain the feature information of the dynamic events in these n dimensions. This feature information characterizes the properties of the dynamic events in each dimension. For ease of understanding, an example is given below.

[0138] Assuming the above n dimensions are the update frequency of event state, the probability of event occurrence, and the degree of independence of the event from the static layer, and assuming that the dynamic events include weather state, traffic accidents, accident-prone road sections, vehicle obstacles, and traffic light state, the feature information of these dynamic events in these three dimensions can be found in Table 1.

[0139] Table 1

[0140]

[0141] In Table 1, the feature information of dynamic events in each dimension was obtained after parameterization and normalization. For the dimension of event state update frequency, the feature information for weather conditions, traffic accidents, accident-prone road sections, vehicle obstacles, and traffic light status are 0.1, 0.5, 0.01, 1, and 0.9, respectively. Alternatively, the update frequencies for these events are 0.1, 0.5, 0.01, 1, and 0.9. The higher the value, the higher the update frequency. It can be seen that vehicle obstacles and traffic light status change frequently, so their update frequencies are very high, almost the highest among all events. Traffic accident status also changes frequently, but not as quickly as vehicle obstacles and traffic light status, so the update frequency is 0.5. Weather conditions and accident-prone road sections change relatively little, hence their lower update frequencies.

[0142] Regarding the probability of events, the characteristic information for weather conditions, traffic accidents, accident-prone road sections, vehicle obstacles, and traffic light status are 1, 0.1, 0.1, 1, and 0.2, respectively. Alternatively, the probabilities of these events are 1, 0.1, 0.1, 1, and 0.2. Similarly, the higher the value, the greater the probability of the event. Weather conditions and vehicle obstacles are certain events, therefore their probability of occurrence is 1. Traffic accidents, accident-prone road sections, and traffic light status are random events, and their probabilities are relatively low.

[0143] Regarding the dimension of independence between events and the static layer, the feature information values ​​for weather conditions, traffic accidents, accident-prone road sections, vehicle obstacles, and traffic light status are 1, 0.8, 0.1, 0.8, and 0.1, respectively. Alternatively, it can be stated that the independence of these events from the static layer is 1, 0.8, 0.1, 0.8, and 0.1, respectively. Similarly, the larger the value, the greater the independence. Specifically, weather conditions, traffic accidents, and vehicle obstacles have less dependence on the static layer, thus exhibiting a higher degree of independence. However, accident-prone road sections and traffic light status depend on lane and traffic light information from the static layer, showing a greater dependency and thus a lower degree of independence.

[0144] It should be noted that the feature information of dynamic events in each dimension can be pre-configured or calculated based on set conditions. The features of each dimension in Table 1 above are exemplarily represented by numerical values, but in the actual implementation, the feature information of dynamic events in each dimension can be represented by levels, etc. This application does not restrict the way feature information is represented.

[0145] S202. Based on the feature information, determine the expression method of the dynamic event in the high-precision map, wherein the expression method includes at least one of extended attribute expression or dynamic layer expression.

[0146] After obtaining the feature information of the dynamic event in n dimensions, it is possible to determine whether the dynamic event is expressed by extended attributes, dynamic layers, or both.

[0147] In the specific implementation process, there are multiple ways to determine the expression method of dynamic events based on this feature information. Several possible implementation methods are introduced below as examples.

[0148] The first implementation method is introduced below: determining the expression method of dynamic events through clustering algorithms.

[0149] In this implementation, the aforementioned dynamic events include m types of dynamic events, where m is an integer greater than 1. Specifically, obtaining the feature information of the dynamic events in n dimensions means obtaining the n-dimensional feature information of each of the m types of dynamic events in those n dimensions.

[0150] After obtaining the n-dimensional feature information of each dynamic event in the n dimensions, the n-dimensional feature information of each dynamic event can be used to construct coordinates in an n-dimensional coordinate system, resulting in m n-dimensional coordinates. Then, a clustering algorithm is used to classify the m dynamic events based on the m n-dimensional coordinates. Based on the classification results, the expression method of each dynamic event in the m dynamic events is determined.

[0151] Specifically, an n-dimensional coordinate system can be created, with the n axes representing the aforementioned n dimensions. Then, the feature information of each of the m dynamic events in these n dimensions can be represented as an n-dimensional coordinate. Thus, the m dynamic events can obtain m n-dimensional coordinates. Then, a clustering algorithm can be used to classify these m n-dimensional coordinates, dividing them into two categories, that is, dividing the m dynamic events into two categories: one category is expressed using extended attributes, and the other category is expressed using dynamic layers.

[0152] In the specific implementation process, clustering algorithms include a variety of algorithms, such as K-Means clustering algorithm, mean-shift clustering algorithm and density-based clustering method, etc. This application does not restrict which clustering algorithm is used for calculation.

[0153] To facilitate understanding how to divide m dynamic events into two categories using a clustering algorithm, the K-Means clustering algorithm is illustrated below. The steps of the K-Means clustering algorithm include: (1) Randomly dividing the above m data points with n-dimensional coordinates into two groups and randomly initializing the center points of each group. (2) Calculating the distance from each data point to the center point, and assigning the data point to the category closest to the center point. (3) Calculating the center point of each category as the new center point. (4) Repeating the above steps until the center point of each category does not change much after each iteration. Alternatively, the center points can be randomly initialized multiple times, and then the above four steps can be performed to calculate the center point, and then the best result can be selected.

[0154] Taking the three dimensions and five events in Table 1 above as an example, a three-dimensional coordinate system can be constructed. The three axes of this coordinate system represent the update frequency of the event state, the probability of the event occurring, and the degree of independence of the event from the static layer. The five events, weather state, traffic accident, accident-prone road section, vehicle obstacle, and traffic light state, are represented as five data points in this three-dimensional coordinate system. The three-dimensional coordinates of these five data points are (0.1,1,1), (0.5,0.1,0.8), (0.01,0.1,0.1), (1,1,0.8), and (0.9,0.2,0.1).

[0155] Then, the five points are classified using the K-Means clustering algorithm steps described above. The final classification results are as follows: data points (0.1,1,1) and (1,1,0.8) belong to one class, i.e., weather conditions and vehicle obstacles belong to one class; data points (0.5,0.1,0.8), (0.01,0.1,0.1), and (0.9,0.2,0.1) belong to another class, i.e., traffic accidents, accident-prone road sections, and traffic light conditions belong to another class.

[0156] In one possible implementation, after dividing the m dynamic events into two categories, the feature information of these two categories of dynamic events in the above n dimensions can be further analyzed. Since these feature information mainly reflects the correlation between the dynamic events and the above static layer, after analysis, the dynamic events with a higher correlation with the static layer can be classified as events expressed using extended attribute expression, while the other category of dynamic events with a lower correlation with the static layer can be classified as events expressed using dynamic layer expression.

[0157] To better understand the relationship between dynamic events and static layers, the following examples will be used to illustrate the relationship between the dimensions described above.

[0158] Regarding the update frequency of event states, dynamic events with lower update frequencies are more closely associated with static layers, while dynamic events with higher update frequencies are less closely associated with static layers.

[0159] Regarding the probability of an event occurring, dynamic events with a lower probability of occurrence are more closely associated with static layers, while dynamic events with a higher probability of occurrence are less closely associated with static layers.

[0160] Regarding the dimension of the degree of influence of events on the topology of the high-precision map, dynamic events with a smaller degree of influence on the topology of the high-precision map are more correlated with static layers, while dynamic events with a larger degree of influence on the topology of the high-precision map are less correlated with static layers.

[0161] Regarding the degree of correlation between events, dynamic events with a smaller degree of correlation change are more correlated with static layers, while dynamic events with a larger degree of correlation change are less correlated with static layers.

[0162] Regarding the reusability of the geometric representation of an event to the static layer, dynamic events with higher reusability of the geometric representation to the static layer have a greater correlation with the static layer, while dynamic events with lower reusability of the geometric representation to the static layer have a smaller correlation with the static layer.

[0163] Regarding the degree of independence between the event and the static layer, dynamic events with a lower degree of independence from the static layer are more correlated with the static layer, while dynamic events with a higher degree of independence from the static layer are less correlated with the static layer.

[0164] To facilitate understanding of how the specific representation of the two types of dynamic events is determined based on the correlation between dynamic events and static layers, an example is provided below. In the example above, the classification results are as follows: the first category includes weather conditions and vehicle obstacles; the second category includes traffic accidents, accident-prone road sections, and traffic light conditions. Analyzing the independence of these two types of dynamic events from the static layers across three dimensions—update frequency of the event conditions, probability of event occurrence, and independence of the events from the static layers—reveals that the first type of dynamic events has a weaker correlation with the static layers compared to the second type. Therefore, the first type of dynamic events is represented using the dynamic layer representation method, while the second type is represented using the extended attribute representation method.

[0165] The second implementation method is described below: determining the expression method of dynamic events through a voting mechanism.

[0166] In this embodiment, a dynamic event is used as an example, which can be referred to as the first dynamic event. Specifically, the above-mentioned acquisition of the feature information of the dynamic event in n dimensions includes acquiring the n-dimensional feature information of the first dynamic event in those n dimensions.

[0167] After obtaining the n-dimensional feature information of the first dynamic event in the n dimensions, the expression method of the first dynamic event in the single dimension is determined based on the feature information of each single dimension in the n-dimensional feature information of the first dynamic event, and n judgment results are obtained. The judgment results include at least one of the expression method of the first dynamic event being the extended attribute expression or the dynamic layer expression; then, the expression method of the dynamic event in the high-precision map is determined to be the expression method with the largest proportion among the n judgment results.

[0168] Specifically, based on a voting mechanism, it is determined that the first dynamic event has p1 dimensions indicating that it should be expressed using extended attributes, and p2 dimensions indicating that it should be expressed using dynamic layers. Then, p1 and p2 are compared. If p1 is greater than p2, the first dynamic event is expressed using extended attributes; if p2 is greater than p1, the first dynamic event is expressed using dynamic layers. Alternatively, p1 and p2 are compared with n / 2 respectively. If p1 is greater than n / 2, the first dynamic event is expressed using extended attributes; if p2 is greater than n / 2, the first dynamic event is expressed using dynamic layers.

[0169] The above description, indicating that the first dynamic event is expressed using extended attributes in a certain dimension, suggests that the first dynamic event has a high degree of correlation with the static layer in that dimension. Conversely, the description, indicating that the first dynamic event is expressed using dynamic layer representations in a certain dimension, suggests that the first dynamic event has a low degree of correlation with the static layer in that dimension.

[0170] To facilitate understanding, let's illustrate with an example, referring to Table 1 above. Taking the weather state event in Table 1 as an example, we can see that the weather state's feature information for the three dimensions—event state update frequency, event occurrence probability, and the degree of independence between the event and the static layer—is 0.1, 1, and 1, respectively. The feature information for the event occurrence probability and the degree of independence between the event and the static layer is both 1, indicating that the weather state is almost unrelated to the static layer in these two dimensions. Therefore, based on these two dimensions, we can determine that the weather state should be represented using a dynamic layer representation. Although the event state update frequency dimension indicates a relatively high correlation between the weather state and the static layer, suggesting the use of extended attribute representation, the number of dimensions indicating the use of a dynamic layer representation is greater than 3 / 2. Therefore, we can determine that the weather state should be represented using a dynamic layer representation.

[0171] The following describes the third implementation method: determining the expression method of dynamic events through a priority mechanism.

[0172] In this embodiment, the first dynamic event described above will also be used as an example. Specifically, it is determined that n dimensions are used to evaluate the expression of the first dynamic event, and these n dimensions have different priorities. For example, the evaluation can be performed using the dimension with the highest priority, that is, the expression indicated by the dimension with the highest priority is the expression of the first dynamic event.

[0173] Taking the weather conditions in Table 1 as an example, Table 1 provides three dimensions for evaluating the representation of dynamic events: the update frequency of the event state, the probability of the event occurring, and the degree of independence of the event from the static layer. However, the priority of these three dimensions, from highest to lowest, is: the degree of independence of the event from the static layer - the update frequency of the event state - the probability of the event occurring. Therefore, we will use the degree of independence of the event from the static layer as the dimension to evaluate the representation of the weather condition. In Table 1, the feature information for the degree of independence of the event from the static layer is 1, indicating that the weather condition is almost unrelated to the static layer. Therefore, we determine that the weather condition will be represented using a dynamic layer representation.

[0174] It should be noted that the above are just examples of several ways to express the dynamic events based on this feature information. In specific embodiments, the implementation methods described above are not limited to those described above.

[0175] The methods described above can be used to determine the expression methods of various dynamic events. For example, see [link to relevant documentation]. Figure 3 , Figure 3 The document lists the various ways to express dynamic events. However, Figure 3The example shown is merely one illustration. In actual implementation, some dynamic events can be expressed using either extended attributes or dynamic layers. Therefore, there is no limitation on using only one method to express a particular dynamic event. Furthermore, different methods of determining the implementation of dynamic events can result in different expressions for those events. The specific expression method for a dynamic event is determined based on the actual method used to determine the expression method.

[0176] In one possible implementation, after determining the expression methods for various dynamic events, the various dynamic events and their corresponding expression methods can be associated and stored in memory for direct retrieval and use later, without recalculating each time they are used, thus saving computing resources. Of course, when a new dynamic event occurs, its expression method can also be determined according to the method described above and stored for later use.

[0177] S203. Based on the defined dynamic event representation method, express the dynamic event into a high-precision map.

[0178] After determining the expression method for the above dynamic events, the dynamic events can be expressed in the high-precision map based on this expression method.

[0179] The following describes the process of expressing the dynamic events in a high-precision map after determining the expression methods for the various dynamic events mentioned above.

[0180] Taking one of the aforementioned dynamic events as an example, this dynamic event can be referred to as the second dynamic event. In a specific embodiment, the high-precision map can run on a server or in a vehicle. Taking the high-precision map running on a server as an example, when vehicles or other devices need to obtain a high-precision map, they can obtain the required area's high-precision map by interacting with the server. The server can obtain information on various dynamic events through monitoring, or through interaction with other servers, roadside devices, or vehicles. For example, it can obtain information on various dynamic events related to weather conditions by interacting with the meteorological bureau's server, or information on various traffic events by interacting with the transportation bureau's server. Then, the obtained dynamic event information is expressed in the high-precision map.

[0181] In a specific embodiment, the server obtains the latest information of the second dynamic event, including the specific type of the second dynamic event, the location where it occurred, and a description of its latest state. Then, the server finds the second dynamic event in the memory and obtains the expression method corresponding to the second dynamic event.

[0182] In one possible implementation, the second dynamic event is expressed as an extended attribute. In this case, if the information of the second dynamic event is obtained for the first time, an extended attribute table can be created for the second dynamic event, and the latest information of the second dynamic event can be added to the extended attribute table. The latest information may include information such as a description of the latest state of the second dynamic event. Then, the extended attribute table is associated with the static layer.

[0183] For example, see Figure 4 The above-mentioned association of the extended attribute table to the static layer can be based on the location information of the second dynamic event, and the extended attribute table can be associated with the map element in the corresponding static layer, and the extended attribute table can be associated with the element attribute table of the map element. Figure 4 The extended attribute event in the map element is the second dynamic event. The element attribute table of the map element includes information such as some static attributes of the map element. For example, if the map element is a lane, then the element attribute table of the lane can include the lane markings and the number of lanes, etc. If the aforementioned second dynamic event is the road adhesion coefficient, and the latest state description is that the road adhesion coefficient is in the range of 0.3 to 0.4, then this latest state description can be added to the extended attribute table established above and associated with the lane in the static layer and the lane's element attribute table. In this way, when the server reads the attribute information in the lane, it can obtain the latest road adhesion coefficient of the lane and display it in the high-precision map.

[0184] If the server has not obtained the second dynamic event for the first time, it can update the extended attribute table of the second dynamic event with the description of the latest state obtained above, so that the information expressed by the server in the high-precision map is the latest state information.

[0185] In another possible implementation, the second dynamic event can be represented as a dynamic layer. In this case, if the second dynamic event does not yet have an associated dynamic layer, a new dynamic layer can be created and associated with it, and then linked to the static layer of the high-precision map. It should be noted that a dynamic layer can include one or more dynamic events, and is not limited to having only one type of dynamic event.

[0186] For example, see Figure 5 , Figure 5The dynamic layer events mentioned above refer to the dynamic events expressed within that dynamic layer. Assuming the second dynamic event is expressed within this dynamic layer, associating this dynamic layer with the static layer of the high-precision map can be achieved by associating the second dynamic event with the corresponding map element in the static layer based on the location information of the second dynamic event. Alternatively, the second dynamic event can also be associated with the element attribute table corresponding to the static layer. Since this is an optional operation, therefore... Figure 5 In the middle layer, the dynamic layer events and the element attribute table are indicated by a dashed line.

[0187] Dynamic events in a dynamic layer can also be associated with an attribute table. Similarly, this attribute table can be used to record information such as the latest state description of the dynamic event. For example, the second dynamic event mentioned above could be a weather state. A dedicated dynamic layer can be created to represent the weather state, and if the location of this weather state is a small town, and the latest state description is moderate rain lasting about half an hour, then the server can describe the weather state of the town area in the dynamic layer as moderate rain lasting about half an hour.

[0188] If, after obtaining the second dynamic event, there is already an associated dynamic layer, then the latest state description of the second dynamic event is directly updated to the corresponding position in the dynamic layer, so that the information expressed by the server in the high-precision map is the latest state information.

[0189] Optionally, high-precision maps typically include multiple dynamic layers. Therefore, for ease of management, these multiple dynamic layers can be coded, and these codes can be associated with the dynamic events in the dynamic layers indicated by the codes. This allows the corresponding layer to be quickly locked based on the corresponding layer code when a dynamic event is updated, and the updated information can be quickly updated to the dynamic layer.

[0190] In summary, this application provides a high-precision map updating method and apparatus, which can provide a feasible and effective high-precision map updating method, thereby improving the event representation of high-precision maps and enhancing the accuracy of high-precision map event representation.

[0191] The foregoing mainly describes the high-precision map update method provided in the embodiments of this application. It is understood that each device, in order to achieve the corresponding functions, includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0192] This application embodiment can divide the device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0193] When dividing each function into modules according to its corresponding function. Figure 6 A schematic diagram of a possible logical structure of the device is shown. This device can be the aforementioned map updating device, a chip within the map updating device, or a processing system within the map updating device, etc. The device 600 includes an acquisition unit 601, a determination unit 602, and an expression unit 603. Wherein:

[0194] The acquisition unit 601 is used to acquire n-dimensional feature information of a dynamic event in n dimensions, where the n dimensions are n factors affecting the representation of the dynamic event in the high-precision map, and the dynamic event is an event that causes changes in the dynamic information in the high-precision map, where n is an integer greater than 1; the acquisition unit 601 can execute Figure 2 The operation described in S201 is shown.

[0195] Determining unit 602 is used to determine the representation of the dynamic event in the high-precision map based on the feature information; the determining unit 602 can perform... Figure 2 The operation described in S202 is shown.

[0196] Expression unit 603 is used to express the dynamic event into the high-precision map based on the determined expression method of the dynamic event; the expression unit 603 can perform... Figure 2 The operation described in S203 is shown.

[0197] In one possible implementation, the n dimensions include at least one of the following dimensions:

[0198] The update frequency of dynamic event states, the probability of event occurrence, the degree of influence of the event on the topology of the high-precision map, the degree of correlation change of the event, the reusability of the geometric representation of the event on the static layer, or the degree of independence of the event from the static layer.

[0199] This dynamic event includes a variety of dynamic events;

[0200] The acquisition unit 601 is specifically used for:

[0201] Obtain the n-dimensional feature information of these multiple dynamic events across the n dimensions;

[0202] The determining unit 602 is specifically used for:

[0203] Based on the n-dimensional feature information of these multiple dynamic events in the n dimensions, a clustering algorithm is used to determine how these multiple dynamic events are represented in the high-precision map.

[0204] In one possible implementation, the determining unit 602 is specifically used for:

[0205] The clustering algorithm is used to classify the various dynamic events into a first category and a second category of dynamic events.

[0206] Based on the n-dimensional feature information of the first type of dynamic event and the n-dimensional feature information of the second type of dynamic event, if it is found that the correlation between the first type of dynamic event and the static layer in the high-precision map is greater than that between the second type of dynamic event, the first type of dynamic event is classified as an event expressed by extended attributes, and the second type of dynamic event is classified as an event expressed by dynamic layers.

[0207] In one possible implementation, the dynamic event includes a first dynamic event, and the determining unit 602 is specifically used for:

[0208] Based on the feature information in each single dimension of the n-dimensional feature information, determine the expression method of the first dynamic event in that single dimension, and obtain n judgment results. The judgment results include at least one of the expression method of the first dynamic event being the extended attribute expression or the dynamic layer expression.

[0209] The dynamic event is determined to be represented in the high-precision map in the way that has the largest proportion among the n judgment results.

[0210] In one possible implementation, the device further includes a storage unit for storing the dynamic event and its representation in a memory after the determining unit 602 determines the representation of the dynamic event in the high-precision map based on the feature information.

[0211] In one possible implementation, the dynamic event includes a second dynamic event, and the expression unit 603 is specifically used for:

[0212] Obtain the latest information about the second dynamic event and retrieve the representation of the second dynamic event from the memory;

[0213] The second dynamic event is determined to be expressed as an extended attribute;

[0214] Create a new extended attribute table based on the latest information of the second dynamic event, and associate the new extended attribute table with the static layer of the high-precision map;

[0215] Alternatively, modify the extended attribute table of the second dynamic event based on the latest information of the second dynamic event.

[0216] In one possible implementation, the dynamic event includes a third dynamic event, and the expression unit 603 is specifically used for:

[0217] Obtain the latest information about the third dynamic event and retrieve the representation of the third dynamic event from the memory;

[0218] The expression method for this third dynamic event is determined to be the dynamic layer expression method;

[0219] Create a new dynamic layer based on the latest information of this third dynamic event;

[0220] Alternatively, modify the dynamic layer to which the third dynamic event belongs based on the latest information of the third dynamic event.

[0221] Figure 6 The specific operation and beneficial effects of each unit in the device 600 shown can be found in the above description. Figure 2 The description of the method and its possible implementations is omitted here.

[0222] Figure 7 The diagram illustrates a possible hardware structure of the device provided in this application, which can be the map updating apparatus described in the above embodiments. The device 700 includes a processor 701, a memory 702, and a communication port 703. The processor 701, communication port 703, and memory 702 can be interconnected or connected to each other via a bus 704.

[0223] For example, memory 702 is used to store computer programs and data of device 700. Memory 702 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0224] In implementation Figure 7 In the case of the illustrated embodiment, execution Figure 7 The software or program code required for the function of all or part of the units is stored in memory 702.

[0225] In implementation Figure 7 In the embodiment, if the software or program code required for the function of some units is stored in memory 702, then in addition to calling the program code in memory 702 to implement some functions, processor 701 can also cooperate with other components (such as communication port 703) to complete the task. Figure 7 Other functions described in the embodiments (such as the function of receiving data).

[0226] There can be multiple communication ports 703, which are used to support device 700 in communication, such as receiving or sending data or signals.

[0227] For example, processor 701 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The processor may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. Processor 701 can be used to read the program stored in the aforementioned memory 702 and execute the aforementioned... Figure 2 The method described herein, and possible implementations thereof. For example, the processor 701 may perform the following operations:

[0228] This involves acquiring n-dimensional feature information of a dynamic event across n dimensions. These n dimensions represent n factors influencing the representation of the dynamic event in a high-precision map. The dynamic event is the event that causes changes in the dynamic information within the high-precision map, where n is an integer greater than 1. This acquisition operation can be... Figure 2 The operation described in step S201 is shown;

[0229] Based on the n-dimensional feature information, the representation of the dynamic event in the high-precision map is determined; this determination operation can be... Figure 2 The operation described in step S202 is shown;

[0230] Based on the determined representation method of the dynamic event, the dynamic event is expressed in the high-precision map; this expression operation can be... Figure 2 The operation described in step S203 is shown.

[0231] Figure 7 The specific operations performed by the device 700 shown and its beneficial effects can be found in the above description. Figure 2 The description of the method and its possible implementations is omitted here.

[0232] This application also provides an apparatus including a processor, a communication port, and a memory, configured to perform the methods described in any of the above embodiments and their possible embodiments.

[0233] In one possible implementation, the device is a chip or a system on a chip (SoC).

[0234] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the methods described in any of the above embodiments and their possible embodiments.

[0235] This application also provides a computer program product, which, when read and executed by a computer, will execute the methods described in any of the above embodiments and their possible embodiments.

[0236] This application also provides a computer program that, when executed on a computer, will enable the computer to implement the methods described in any of the above embodiments and their possible embodiments.

[0237] This application also provides a high-precision map, which includes a static layer and / or a dynamic layer that presents dynamic information. The way the dynamic information is expressed in the static layer and / or the dynamic layer is determined by the high-precision map update method described in any of the above embodiments and their possible embodiments.

[0238] In summary, this application evaluates the representation of dynamic events in high-precision maps from multiple dimensions, thereby accurately determining the representation of each dynamic event and easily automating the process. Compared with existing technologies, this application provides a feasible and efficient high-precision map update method that can improve the event representation of high-precision maps and enhance the accuracy and automation of event representation.

[0239] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items that have substantially the same function and purpose. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor does it limit the quantity or order of execution. It should also be understood that although the following description uses the terms "first," "second," etc., to describe various elements, these elements should not be limited by the terms. These terms are merely used to distinguish one element from another. For example, without departing from the various examples described, a first image can be referred to as a second image, and similarly, a second image can be referred to as a first image. Both the first image and the second image can be images, and in some cases, they can be separate and distinct images.

[0240] It should also be understood that, in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0241] It should also be understood that the term “comprising” (also referred to as “includes”, “including”, “comprises” and / or “comprising”) as used in this specification specifies the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0242] It should also be understood that the phrases "an embodiment," "an embodiment," and "a possible implementation" used throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment or implementation is included in at least one embodiment of this application. Therefore, the phrases "in an embodiment," "an embodiment," or "a possible implementation" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0243] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A high-precision map update method, characterized in that, The method includes: The map update device acquires n-dimensional feature information of dynamic events in n dimensions, where the n dimensions are n factors that affect the expression of the dynamic events in the high-precision map, and the dynamic events are events that cause changes in the dynamic information in the high-precision map, where n is an integer greater than 1. The map updating device determines the representation method of the dynamic event in the high-precision map based on the n-dimensional feature information. The representation method includes at least one of extended attribute representation method or dynamic layer representation method. The extended attribute representation method is a way to associate the dynamic event with a static layer in the high-precision map and make it an extended attribute of the static layer element. The dynamic layer representation method is a way to add the dynamic event to a dynamic layer of the high-precision map for representation. The correlation between the dynamic event expressed by the extended attribute representation method and the static layer is greater than the correlation between the dynamic event expressed by the dynamic layer representation method and the static layer. The map updating device expresses the dynamic events into the high-precision map based on the determined expression method of the dynamic events.

2. The method according to claim 1, characterized in that, The n dimensions include multiples of the following dimensions: The update frequency of dynamic event states, the probability of event occurrence, the degree of influence of the event on the topology of the high-precision map, the degree of correlation change of the event, the reusability of the geometric representation of the event to the static layer, or the degree of independence between the event and the static layer.

3. The method according to claim 1 or 2, characterized in that, The dynamic events are of various types; The map updating device acquires n-dimensional feature information of dynamic events in n dimensions, including: The map updating device acquires n-dimensional feature information of the various dynamic events in the n dimensions; The map updating device determines the representation of the dynamic event in the high-precision map based on the n-dimensional feature information, including: The map updating device determines the representation of the various dynamic events in the high-precision map by using a clustering algorithm based on the n-dimensional feature information of the various dynamic events in the n dimensions.

4. The method according to claim 3, characterized in that, The process of determining the representation of the various dynamic events in the high-precision map using a clustering algorithm includes: The map updating device classifies the various dynamic events using the clustering algorithm to obtain a first type of dynamic event and a second type of dynamic event; If, based on the n-dimensional feature information of the first type of dynamic events and the n-dimensional feature information of the second type of dynamic events, it is determined that the correlation between the first type of dynamic events and the static layer in the high-precision map is greater than that between the second type of dynamic events, then... The map updating device classifies the first type of dynamic events into events expressed using extended attributes, and classifies the second type of dynamic events into events expressed using dynamic layers.

5. The method according to claim 1 or 2, characterized in that, The dynamic events include the first dynamic event. The map updating device determines the representation of the dynamic event in the high-precision map based on the n-dimensional feature information, including: The map updating device determines the expression method judgment result of the first dynamic event in the single dimension based on the feature information in each single dimension of the n-dimensional feature information, and obtains n judgment results. The judgment result includes at least one of the expression method of the first dynamic event being the extended attribute expression or the dynamic layer expression. The map update device determines that the dynamic event is expressed in the high-precision map in the way that accounts for the largest proportion among the n judgment results.

6. The method according to any one of claims 1 to 5, characterized in that, After the map updating device determines the representation of the dynamic event in the high-precision map based on the feature information, it further includes: The map updating device associates and stores the dynamic events and their representations in a memory.

7. The method according to claim 6, characterized in that, The dynamic event includes a second dynamic event. The map updating device expresses the dynamic event into the high-precision map based on a determined expression method for the dynamic event, including: The map updating device obtains the latest information of the second dynamic event and retrieves the expression method of the second dynamic event from the memory; The map update device determines that the expression method of the second dynamic event is the extended attribute expression method; The map updating device creates a new extended attribute table based on the latest information of the second dynamic event, and associates the new extended attribute table with the static layer of the high-precision map; Alternatively, the map updating device may modify the existing extended attribute table based on the latest information from the second dynamic event.

8. The method according to claim 6 or 7, characterized in that, The dynamic events include a third dynamic event. The map updating device expresses the dynamic events into the high-precision map based on a determined expression method for the dynamic events, including: The map updating device obtains the latest information of the third dynamic event and retrieves the expression method of the third dynamic event from the memory; The map updating device determines that the expression method of the third dynamic event is a dynamic layer expression method; The map updating device can create a new dynamic layer based on the latest information of the third dynamic event, or modify an existing dynamic layer based on the latest information of the third dynamic event.

9. A map updating device, characterized in that, The device includes: The acquisition unit is used to acquire n-dimensional feature information of dynamic events in n dimensions, wherein the n dimensions are n factors that affect the expression of the dynamic events in the high-precision map, and the dynamic events are events that cause changes in the dynamic information in the high-precision map, wherein n is an integer greater than 1; A determining unit is configured to determine, based on the n-dimensional feature information, the representation method of the dynamic event in the high-precision map. The representation method includes at least one of an extended attribute representation method or a dynamic layer representation method. The extended attribute representation method associates the dynamic event with a static layer in the high-precision map, making it an extended attribute of the static layer element. The dynamic layer representation method adds the dynamic event to a dynamic layer of the high-precision map for representation. The correlation between the dynamic event expressed using the extended attribute representation method and the static layer is greater than the correlation between the dynamic event expressed using the dynamic layer representation method and the static layer. An expression unit is used to express the dynamic event into the high-precision map based on a determined expression method for the dynamic event.

10. The apparatus according to claim 9, characterized in that, The n dimensions include multiples of the following dimensions: The update frequency of dynamic event states, the probability of event occurrence, the degree of influence of the event on the topology of the high-precision map, the degree of correlation change of the event, the reusability of the geometric representation of the event to the static layer, and the degree of independence of the event or the static layer.

11. The apparatus according to claim 9 or 10, characterized in that, The dynamic events include a variety of dynamic events; The acquisition unit is specifically used for: Obtain n-dimensional feature information of the various dynamic events in the n dimensions; The determining unit is specifically used for: Based on the n-dimensional feature information of the various dynamic events in the n dimensions, a clustering algorithm is used to determine how the various dynamic events are represented in the high-precision map.

12. The apparatus according to claim 11, characterized in that, The determining unit is specifically used for: The clustering algorithm is used to classify the various dynamic events to obtain a first category of dynamic events and a second category of dynamic events; If, based on the n-dimensional feature information of the first type of dynamic events and the n-dimensional feature information of the second type of dynamic events, it is determined that the correlation between the first type of dynamic events and the static layer in the high-precision map is greater than that between the second type of dynamic events, then... The first type of dynamic events are classified as events expressed using extended attributes, and the second type of dynamic events are classified as events expressed using dynamic layers.

13. The apparatus according to claim 9 or 10, characterized in that, The dynamic events include the first dynamic event. The determining unit is specifically used for: Based on the feature information in each single dimension of the n-dimensional feature information, determine the expression method judgment result of the first dynamic event in the single dimension, and obtain n judgment results. The judgment result includes at least one of the expression method of the first dynamic event being the extended attribute expression or the dynamic layer expression. The dynamic event is determined to be represented in the high-precision map in the way that has the largest proportion among the n judgment results.

14. The apparatus according to any one of claims 9 to 13, characterized in that, The device further includes a storage unit, used to associate and store the dynamic event and the expression of the dynamic event in the memory after the determining unit determines the expression of the dynamic event in the high-precision map based on the feature information.

15. The apparatus according to claim 14, characterized in that, The dynamic event includes a second dynamic event, and the expression unit is specifically used for: Obtain the latest information of the second dynamic event, and obtain the expression method of the second dynamic event in the memory; The second dynamic event is determined to be expressed as an extended attribute expression method; Based on the latest information of the second dynamic event, a new extended attribute table is created, and the newly created extended attribute table is associated with the static layer of the high-precision map; Alternatively, modify the extended attribute table of the second dynamic event based on the latest information of the second dynamic event.

16. The apparatus according to claim 14 or 15, characterized in that, The dynamic event includes a third dynamic event, and the expression unit is specifically used for: Obtain the latest information of the third dynamic event, and retrieve the expression method of the third dynamic event from the memory; The expression method for the third dynamic event is determined to be the dynamic layer expression method; Create a new dynamic layer based on the latest information of the third dynamic event; Alternatively, the dynamic layer to which the third dynamic event belongs can be modified based on the latest information of the third dynamic event.

17. A map updating device, characterized in that, The device includes a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, such that the device performs the method as described in any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method of any one of claims 1 to 8.

19. A computer program product, characterized in that, When the computer program product is executed by a processor, the method described in any one of claims 1 to 8 will be executed.

20. A high-precision map, characterized in that, The high-precision map includes at least one of a static layer carrying dynamic information or a dynamic layer carrying dynamic information, wherein the expression of the dynamic information in the high-precision map is determined by the method described in any one of claims 1 to 8.

Images