An intelligent update method and system for an autonomous driving navigation map

Abstract

The present invention relates to the technical field of automotive navigation, and particularly relates to an intelligent update method and system for an autonomous driving navigation map. Based on the change of navigation path planning, the spatial influence of each congested area on the target area is obtained, and combined with the time difference of congestion occurrence between each congested area and the target area, the correlation of the congestion phenomenon between each congested area and the target area is obtained. From the correlation, the time influence is obtained, so as to determine the time influence of each congested area on the target area. According to the spatial influence and time influence, the initial traffic flow of the target area is corrected, and the accurate and real traffic flow of the target area can be obtained, improving the accuracy of traffic flow acquisition, and thus improving the accuracy of obtaining the map update priority.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive navigation, and particularly to an intelligent update method and system for an autonomous driving navigation map. Background Art

[0002] Autonomous driving technology highly depends on high-precision maps to achieve functions such as precise positioning, path planning, and environmental perception. Map update is crucial for autonomous driving because the environment is constantly changing, such as road construction, traffic sign adjustment, etc. If these changes are not reflected on the map in a timely manner, it may affect the safety and reliability of autonomous driving vehicles. Therefore, continuously updating map data is the key to ensuring the efficient operation of the autonomous driving system.

[0003] The existing update method for autonomous driving maps is to update the maps of each region according to the map update priority of each region. Among them, the higher the map update priority, the more priority for updating. Currently, the way to obtain the map update priority of each region is directly obtained from the traffic flow of each region. The larger the traffic flow, the higher the map update priority. However, the traffic flow of a single region is usually affected by other surrounding related regions, resulting in the traffic flow not being its true traffic flow, thus affecting the accuracy of obtaining the map update priority. Summary of the Invention

[0004] In order to solve the technical problem of inaccurate traffic flow acquisition in the existing regions, the purpose of the present invention is to provide an intelligent update method and system for an autonomous driving navigation map, and the specific technical solutions adopted are as follows:

[0005] In the first aspect of the present invention, an intelligent update method for an autonomous driving navigation map is provided, including:

[0006] Based on the change in navigation path planning, obtain the spatial influence of each congested region on the target region, where the congested region is a region with vehicle congestion within the preset neighborhood of the target region;

[0007] Combine the time difference between the occurrence of congestion in each congested region and the target region to obtain the correlation of the congestion phenomenon between each congested region and the target region;

[0008] Determine the time influence of each congested region on the target region, where the time influence is obtained from the correlation;

[0009] According to the spatial influence and time influence, correct the initial traffic flow of the target region.

[0010] In an exemplary embodiment, the process of obtaining the congested region includes:

[0011] Obtain the associated area, where the associated area is the area within the preset neighborhood of the target area;

[0012] Obtain the average speed of the autonomous vehicle in each associated area during the target period and compare it with the preset average speed threshold;

[0013] If the average speed is less than the preset average speed threshold, determine that the corresponding associated area is a congested area.

[0014] In an exemplary embodiment, the obtaining of the spatial influence of each congested area on the target area based on the change in navigation path planning includes:

[0015] Obtain the first quantity of autonomous vehicles whose original navigation path passes through the first congested area and does not pass through the target area during the target period; the first congested area is any one of the congested areas;

[0016] Obtain the second quantity of autonomous vehicles that change the original navigation path to the actual navigation path during the target period; the actual navigation path is the navigation path that passes through the target area and does not pass through the first congested area;

[0017] Obtain the ratio of the second quantity to the first quantity as the spatial influence factor of the first congested area on the target area.

[0018] In an exemplary embodiment, the obtaining process of the time difference between the occurrence of congestion in each congested area and the target area includes:

[0019] Obtain the historical traffic volumes of the first congested area and the target area; the first congested area is any one of the congested areas;

[0020] Construct a linear regression model according to the relationship between the historical traffic volumes of the first congested area and the target area and time;

[0021] Solve the linear regression model to obtain the time difference between the occurrence of congestion in the first congested area and the target area.

[0022] In an exemplary embodiment, the linear regression model is:

[0023] ;

[0024] Wherein, represents the historical traffic volume of the target area at time, represents the historical traffic volume of the o-th congested area at time, represents the time difference between the occurrence of congestion in the o-th congested area and the target area, represents the regression coefficient, Represents the error term of the linear regression model.

[0025] In an exemplary embodiment, the process of obtaining the correlation between each congestion area and the congestion phenomenon in the target area includes:

[0026] Obtain the first traffic flow sequence of the first congestion period in the target period for the first congestion area; the first congestion area is any congestion area, and the first congestion period is the congestion period of the first congestion area in the target period;

[0027] According to the first congestion period and the time difference, obtain the second congestion period, which is the congestion period of the target area;

[0028] Obtain the second traffic flow sequence of the target area in the second congestion period;

[0029] Obtain the correlation coefficient between the first traffic flow sequence and the second traffic flow sequence.

[0030] In an exemplary embodiment, determining the time impact of each congestion area on the target area includes:

[0031] Use the result of normalizing the correlation coefficient corresponding to the first congestion area as the time impact factor of the first congestion area on the target area.

[0032] In an exemplary embodiment, correcting the initial traffic flow of the target area according to the spatial impact and time impact includes:

[0033] According to the spatial impact and time impact, obtain the comprehensive impact factor of each congestion area on the target area;

[0034] Fuse the comprehensive impact factors of all congestion areas on the target area to obtain the final impact factor;

[0035] Determine the correction factor, which is negatively correlated with the final impact factor;

[0036] Multiply the correction factor by the initial traffic flow of the target area to obtain the corrected traffic flow of the target area.

[0037] In an exemplary embodiment, the spatial impact is specifically the spatial impact factor, and the time impact is specifically the time impact factor;

[0038] The process of obtaining the comprehensive impact factor of each congestion area on the target area according to the spatial impact and time impact includes:

[0039] Obtain the third quantity of autonomous driving vehicles whose driving paths pass through the first congestion area within the target time period, and the fourth quantity of autonomous driving vehicles whose driving paths pass through the target area; the first congestion area is any congestion area;

[0040] Obtain the ratio of the third quantity to the total quantity as the weight of the time impact corresponding to the first congestion area; the total quantity is the sum of the third quantity and the fourth quantity;

[0041] According to the weight, perform a weighted sum of the spatial impact factor and the time impact factor to obtain the comprehensive impact factor of the first congestion area on the target area.

[0042] In the second aspect of the present invention, there is provided an intelligent update system for an autonomous driving navigation map, including: a memory and a processor; the memory is connected to the processor; the memory is used to store program instructions; the processor is used to implement the above-mentioned intelligent update method of the autonomous driving navigation map when the program instructions are executed.

[0043] The present invention has the following beneficial effects: Since the areas with vehicle congestion within the preset neighborhood of the target area will affect the traffic flow of the target area, therefore, based on the change of the navigation path planning, obtain the spatial impact of each congestion area on the target area, and according to the time difference between the congestion occurrence in each congestion area and the target area, as well as the correlation between the congestion phenomena in each congestion area and the target area, determine the time impact of each congestion area on the target area, obtain the impact of each congestion area on the traffic flow of the target area from the two dimensions of spatial impact and time impact, and finally correct the initial traffic flow of the target area according to the spatial impact and time impact, so as to obtain the accurate and real traffic flow of the target area, improve the accuracy of traffic flow acquisition, and thus improve the accuracy of obtaining the map update priority. Description of the Drawings

[0044] Figure 1 is a flowchart of an intelligent update method for an autonomous driving navigation map provided by an embodiment of the present invention;

[0045] Figure 2 is a flowchart for obtaining a congestion area provided by an embodiment of the present invention;

[0046] Figure 3 is a flowchart for obtaining the spatial impact provided by an embodiment of the present invention;

[0047] Figure 4 is a flowchart for obtaining the time difference provided by an embodiment of the present invention;

[0048] Figure 5 is a flowchart for obtaining the correlation provided by an embodiment of the present invention;

[0049] Figure 6 Figure 6 is a correction flowchart for correcting the initial traffic flow of a target area provided by an embodiment of the present invention;

[0050] Figure 7 Figure 7 is a flowchart for obtaining a comprehensive influence factor provided by an embodiment of the present invention. Detailed implementation manners

[0051] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The data information collected in this application is obtained with full consent and authorization, and the collection, use, and processing of relevant information need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0053] This embodiment provides an intelligent update method for an autonomous driving navigation map, as Figure 1 shown, including the following steps:

[0054] Step 1: Based on the change in navigation path planning, obtain the spatial influence of each congested area on the target area, where the congested area is an area with vehicle congestion within the preset neighborhood of the target area;

[0055] Step 2: Combine the time difference between the occurrence of congestion in each congested area and the target area to obtain the correlation between the congestion phenomena in each congested area and the target area;

[0056] Step 3: Determine the time influence of each congested area on the target area, where the time influence is obtained from the correlation;

[0057] Step 4: Correct the initial traffic flow of the target area according to the spatial influence and the time influence.

[0058] The following, in conjunction with the accompanying drawings, specifically describes each step.

[0059] Step 1: Based on the change in navigation path planning, obtain the spatial influence of each congested area on the target area, where the congested area is an area with vehicle congestion within the preset neighborhood of the target area.

[0060] Since this application is to correct the initial traffic flow in the target area, it is necessary to divide the original map into multiple areas in advance. The division method for each area is set according to the actual situation. For example, it can be divided according to administrative regions, or the map can be evenly divided into multiple areas.

[0061] In an exemplary embodiment, first, the grid division method is adopted to convert the map into a grid data structure, and the map is divided into multiple grid units of equal size. Then, according to the road topology information, the grid units are merged or adjusted to form areas of equal size, and the road coherence and integrity within the area are ensured as much as possible. Specifically: 1. Convert the map data into a grid format and determine an appropriate grid size. At the same time, extract the road topology information in the map, including the nodes, edges of the road, and their connection relationships. 2. Evenly divide the map according to the set grid size to obtain a series of grid units. 3. Traverse each grid unit to determine whether it contains a road. For the grid unit containing a road, analyze its connection with the roads in adjacent grid units. 4. According to the road coherence, merge the adjacent grid units with closely connected roads into one area. For some isolated grid units with fewer connections to the roads in other areas, merge them with adjacent units. Finally, the original map can be divided into areas. It should be understood that this embodiment is not limited to the area division method.

[0062] Determine the target area from the divided areas. The target area is the area used for traffic flow correction. Then, determine the map update priority according to the corrected traffic flow, so as to realize the map update of the target area. Among them, the target area can be the area with a large traffic flow among the areas. An area with a large traffic flow means that users have a more urgent need for real-time traffic information. Updating the map information of these areas in a timely manner can provide more accurate navigation services.

[0063] This invention is based on the in-vehicle terminal in an autonomous vehicle obtaining the real-time positioning information (i.e., coordinate information, specifically including longitude and latitude) of the autonomous vehicle. For example, the in-vehicle terminal is equipped with a GPS positioning system. Moreover, the in-vehicle terminal can also record relevant information such as the driving trajectory, real-time driving speed, and timestamp of the autonomous vehicle. It should be understood that the technologies such as the autonomous driving control of autonomous vehicles are all conventional technologies and are not the focus of this invention, so they will not be elaborated.

[0064] Each autonomous vehicle sends its own positioning information and other relevant data information to the background system. The background system processes the data according to the positioning information of each autonomous vehicle and each area in the divided map to obtain the corrected traffic flow in the target area.

[0065] In this embodiment, the target area is analyzed to obtain the corrected traffic flow in the target time period of the target area. The length of the target time period and its position in a day are set according to actual needs. In an exemplary embodiment, the target time period is selected as the morning rush hour of a representative day, and the duration of the target time period is 2 hours, such as 7:00 - 9:00 in the morning.

[0066] For the current day, this embodiment also presets a historical time period, which includes several consecutive days in the past. The last day in the historical time period is the day before the current day. The target time period in each past day is the same time period in a day as that of the current day.

[0067] For any area, count the number of autonomous vehicles entering the area during the target time period. The number of autonomous vehicles entering the area can be determined by the positioning information of each autonomous vehicle and the boundary coordinates of each area, and this number is used as the traffic flow of the area. Among them, the traffic flow in the target time period of each day in the historical time period is used as the historical traffic flow of this area on each day in the historical time period. The traffic flow in the target time period of the current day is used as the initial traffic flow of this area.

[0068] The traffic flow in urban traffic has the characteristic of dynamic propagation, that is, the change in the traffic flow of a certain area will affect the traffic flow of adjacent or nearby areas. For example, an accident occurs on the main road of an area, resulting in a sharp increase in the traffic flow on this road, causing congestion in this area, and may also lead to an increase in the traffic flow of surrounding areas, ultimately spreading to more roads and areas. Therefore, when analyzing the traffic flow between individual areas, the mutual influence between areas also needs to be considered. Therefore, for the target area, it is necessary to obtain the congested area of the target area, and the congested area is the area with vehicle congestion within the preset neighborhood of the target area. In an exemplary embodiment, as Figure 2 shown, a specific process for obtaining the congested area is given as follows:

[0069] Step 1-1: Obtain the associated area, and the associated area is the area within the preset neighborhood of the target area.

[0070] Centered on the target area, obtain other areas within the preset neighborhood of the target area. The preset neighborhood is specifically a circular area with the center point of the target area as the center and within the preset radius range. The size of the preset radius is set according to the actual situation, such as determined by the area size of each area. If the preset radius is set too small, there will be too few associated areas, resulting in ineffective associated areas. If the preset radius is set too large, areas with weak relevance will be included, affecting the accuracy and efficiency of data processing. In an exemplary embodiment, the setting of the preset radius needs to ensure that at least all other areas in contact with the target area are included as the associated areas of the target area.

[0071] Step 1-2: Obtain the average speed of the autonomous vehicles in each associated area during the target period, and compare it with a preset average speed threshold.

[0072] When congestion occurs in a certain area, the driving speed of the autonomous vehicles in that area during the target period is relatively low. Therefore, the area with congestion can be determined by the magnitude of the driving speed of the autonomous vehicles in that area.

[0073] Specifically, for any associated area, obtain the average speed of each autonomous vehicle in that associated area on the same day during the target period, and then calculate the average value of the average speeds of all the autonomous vehicles in that associated area during the target period as the average speed corresponding to that associated area. Thus, the average speeds corresponding to each associated area are obtained.

[0074] Preset an average speed threshold. The purpose of setting this preset average speed threshold is to compare it with the average speeds corresponding to each associated area. If it is less than this preset average speed threshold, it means the average speed is relatively low, and there is a congestion phenomenon in the corresponding associated area. Therefore, this preset average speed threshold can be obtained from the overall level of the driving speeds of the autonomous vehicles in the area when there is a congestion phenomenon in a large number of historical areas.

[0075] Step 1-3: If the average speed is less than the preset average speed threshold, then determine that the corresponding associated area is a congested area.

[0076] Compare the average speeds corresponding to each associated area with the preset average speed threshold, obtain the associated areas with average speeds less than the preset average speed threshold, and determine the associated areas with average speeds less than the preset average speed threshold as congested areas. Thus, the congested areas of the target area are obtained.

[0077] After obtaining the congested areas of the target area, obtain the impacts of each congested area on the target area from the spatial and temporal dimensions respectively.

[0078] When there is congestion in the congestion area during the target time period, the autonomous vehicle may choose another route. If the route selected by the autonomous vehicle passes through the target area, the traffic flow in the target area may increase at this time. However, the traffic flow in the target area on that day is more affected by the congestion area, rather than the real traffic flow in the target area. Suppose area A is congested and the autonomous vehicle changes its route to pass through area B, resulting in an increase in the traffic flow in area B. But the increase in the traffic flow in area B is due to the congestion in area A, rather than the normal traffic flow in area B itself. Therefore, the route-changing behavior of the autonomous vehicle, that is, the change in the navigation path planning of the autonomous vehicle, will cause the traffic flow in the target area to change, specifically, the traffic flow is inflated. Therefore, based on the change in the navigation path planning, obtain the spatial influence of each congestion area on the target area.

[0079] The route-changing behavior of the autonomous vehicle, that is, the change in the navigation path planning of the autonomous vehicle, is used to represent the influence of the congestion area on the target area. When the autonomous vehicle originally planned to pass through area A changes its route to area B, and the more autonomous vehicles that originally planned to pass through area A actually pass through area B, it means that the influence degree of area A on area B is greater.

[0080] In an exemplary embodiment, as Figure 3 shown, the following gives a specific implementation process for obtaining the spatial influence of each congestion area on the target area based on the change in the navigation path planning:

[0081] Steps 1-4: Obtain the first quantity of autonomous vehicles whose original navigation path passes through the first congestion area and does not pass through the target area during the target time period.

[0082] For the convenience of description, define the first congestion area as any congestion area of the target area.

[0083] Obtain the original navigation paths of each autonomous vehicle during the target time period of that day. The original navigation path is the pre-planned and unadjusted navigation path, and specifically, the original navigation path is the navigation path that passes through the first congestion area and does not pass through the target area. Thus, obtain the quantity of autonomous vehicles with such an original navigation path during the target time period of that day as the first quantity.

[0084] Steps 1-5: Obtain the second quantity of autonomous vehicles whose original navigation path is changed to the actual navigation path during the target time period.

[0085] Due to the existence of congestion, some autonomous vehicles will change from passing through the first congested area to passing through the target area, that is, the autonomous vehicles do not follow the original navigation path, and the actual driving path changes, thus becoming the actual navigation path and realizing a lane change. The actual navigation path is the real driving path of the autonomous vehicle, and moreover, the actual navigation path is the navigation path that passes through the target area and does not pass through the first congested area. Therefore, obtain the number of autonomous vehicles whose original navigation path changes to the actual navigation path during the target time period of the day as the second quantity.

[0086] Therefore, the second quantity is determined from the first quantity. The first quantity includes the second quantity, and the first quantity is greater than the second quantity.

[0087] Step 1-6: Obtain the ratio of the second quantity to the first quantity as the spatial influence factor of the first congested area on the target area.

[0088] The spatial influence of the first congested area on the target area can be represented by the lane change rate. The lane change rate refers to the proportion of autonomous vehicles that should have passed through the first congested area but changed lanes to the target area. Therefore, calculate the ratio of the second quantity to the first quantity, and this ratio is used as the lane change rate, indicating the spatial influence degree of the congestion in the first congested area on the increase in traffic flow in the target area. The larger this ratio, the more significant the spatial influence of the congestion in the first congested area on the target area. Therefore, this ratio is used as the spatial influence factor of the first congested area on the target area. Since the first quantity is greater than the second quantity, the value range of this ratio is 0-1. Thus, the spatial influence factors of each congested area on the target area are obtained.

[0089] Step 2: Combine the time differences between the occurrences of congestion in each congested area and the target area to obtain the correlation of the congestion phenomena between each congested area and the target area.

[0090] When there is congestion in each congested area, there may be a more obvious congestion phenomenon in the target area after a period of time. At this time, the traffic flow in the target area may be caused by the propagation effect of the congested area, that is, when congestion occurs in a certain area, the phenomenon of traffic congestion spreading from one area to another area. This propagation effect makes the traffic flow in the target area possibly affected by the congested area.

[0091] However, this inter-regional propagation effect may have a time lag, that is, the congestion in the congested area will not immediately affect the target area, and the influence may take some time to be transmitted to the target area through the traffic network. Therefore, when analyzing the time influence between regions, it is first necessary to determine the lag time of the congested area causing congestion in the target area, that is, to determine the time difference between the occurrences of congestion in each congested area and the target area.

[0092] In an exemplary embodiment, as Figure 4 shown, a process for obtaining the time difference between the occurrences of congestion in each congested area and the target area is given as follows:

[0093] Step 2-1: Obtain the historical traffic flows of the first congested area and the target area.

[0094] Taking the first congested area as an example, according to the above description, obtain the historical traffic flows of the first congested area and the target area at the target time period of each day within the historical time period.

[0095] Step 2-2: Construct a linear regression model based on the relationship between the historical traffic flows of the first congested area and the target area and time.

[0096] Denote the historical traffic flow of the target area at time in the target time period as , and the historical traffic flow of the o-th congested area at time in the target time period as . Set to represent the time difference between the occurrences of congestion in the o-th congested area and the target area. Then, the historical traffic flow of the o-th congested area at time in the target time period is .

[0097] Conduct a cross-analysis of the traffic flow changes in the o-th congested area and the traffic flow changes in the target area to find the time delay between the two. Correspondingly, the linear regression model is:

[0098] ;

[0099] where represents the regression coefficient, represents the error term of the linear regression model, and the least squares method (OLS) is used to estimate the model parameters.

[0100] Step 2-3: Solve the linear regression model to obtain the time difference between the occurrences of congestion in the first congested area and the target area.

[0101] Conduct a cross-analysis of the traffic flow changes between the first congested area and the target area. According to the relationship between the inter-regional traffic flow and time given by the linear regression model, solve the linear regression model to obtain the time difference between the occurrences of congestion in the o-th congested area and the target area It should be understood that for the o-th congested area, since the time difference is obtained from the historical traffic flow during the target time period of each day within the historical time period, if the time differences corresponding to each day within the historical time period are obtained, the average value of the time differences can be calculated to obtain the final time difference corresponding to the o-th congested area. By adopting the above process, the time differences between each congested area and the target area when congestion occurs can be obtained.

[0102] As other implementation manners, in addition to the above manner of obtaining the time difference, the following manner of obtaining the time difference can also be adopted: For example, obtain the traffic flow of the first congested area and the target area on the same day, and according to the traffic flow on the same day, adopt the analysis process of the above linear regression model to obtain the time difference corresponding to the first congested area. Or: During the target time period of each day within the historical time period, start timing when congestion begins to occur in the first congested area, and then start timing when congestion begins to occur in the target area, and calculate the time interval between the two moments as the time difference between the first congested area and the target area when congestion occurs within each day of the historical time period, and then calculate the average value of the obtained time differences as the final time difference between the first congested area and the target area when congestion occurs.

[0103] To determine the mutual influence between regions, time series analysis can be used. When congestion occurs in the congested area, the target area will show congestion characteristics similar to those of the congested area when the obtained time difference arrives. When the congestion characteristics of the congested area are more correlated with the characteristics of the target area over time, it indicates that the influence degree of the congested area on the target area is greater. Therefore, according to the obtained time difference, the correlation between the congestion phenomena of each congested area and the target area is obtained. In an exemplary embodiment, as Figure 5 shown, the following gives a specific process for obtaining the correlation:

[0104] Step 2-4: Obtain the first traffic flow sequence of the first congested time period of the first congested area during the target time period.

[0105] Determine the moment when the first congested area starts to be congested and the moment when the congestion in the first congested area is relieved during the target time period of the same day. The time period between these two moments is the congested time period, defined as the first congested time period. Then, the first congested time period is the congested time period of the first congested area during the target time period.

[0106] Preset an acquisition period, and the time length of the acquisition period is determined by the length of the first congested time period, so as to ensure that the first congested time period includes multiple acquisition periods.

[0107] Obtain the traffic flow of each acquisition period in the first congestion area during the first congestion time period of the day, so as to obtain multiple traffic flows during the first congestion time period. Then arrange them in the order of the acquisition periods, and obtain a traffic flow sequence, which is defined as the first traffic flow sequence of the first congestion area.

[0108] Step 2-5: Obtain the second congestion time period according to the first congestion time period and the time difference.

[0109] Set the second congestion time period as the congestion time period of the target area. Since there is a time lag between the congestion phenomenon in the first congestion area and the target area, and the lag time is the time difference of the first congestion area obtained above. Therefore, add the time difference corresponding to the first congestion area to the moment when the first congestion area starts to be congested as the moment when the target area starts to be congested, and add the time difference corresponding to the first congestion area to the moment when the congestion in the first congestion area is relieved as the moment when the congestion in the target area is relieved. The time period between these two moments is the congestion time period of the target area, which is defined as the second congestion time period.

[0110] Step 2-6: Obtain the second traffic flow sequence of the target area during the second congestion time period.

[0111] After obtaining the second congestion time period, in the same way as the acquisition method of the first traffic flow sequence in the first congestion area, according to the same preset acquisition period, obtain the traffic flow of each acquisition period in the target area during the second congestion time period of the day, so as to obtain multiple traffic flows during the second congestion time period. Then arrange them in the order of the acquisition periods, and obtain a traffic flow sequence, which is defined as the second traffic flow sequence of the target area.

[0112] Step 2-7: Obtain the correlation coefficient between the first traffic flow sequence and the second traffic flow sequence.

[0113] Obtain the correlation coefficient between the first traffic flow sequence and the second traffic flow sequence. The correlation coefficient can be cosine similarity, Pearson correlation coefficient, etc. In this embodiment, the Pearson correlation coefficient algorithm is used to obtain the Pearson correlation coefficient between the first traffic flow sequence and the second traffic flow sequence as the correlation between the congestion phenomena of the first congestion area and the target area. The greater the correlation, the greater the time impact of the first congestion area on the target area.

[0114] Using the above process, obtain the correlation between the congestion phenomena of each congestion area and the target area.

[0115] Step 3: Determine the time impact of each congestion area on the target area, and the time impact is obtained from the correlation.

[0116] According to the correlation between the congestion phenomena of each congestion area and the target area, obtain the time impact of each congestion area on the target area.

[0117] Taking the first congested area as an example, normalize the Pearson correlation coefficient corresponding to the first congested area, and use the normalized result as the time impact factor of the first congested area on the target area. The normalization method here can be: obtain the maximum Pearson correlation coefficient and the minimum Pearson correlation coefficient from the Pearson correlation coefficients corresponding to each congested area, and use the maximum-minimum normalization method to normalize the Pearson correlation coefficient corresponding to the first congested area. Thus, the time impact factors of each congested area on the target area are obtained. It should be understood that the above normalization method is applicable to the case where there are multiple congested areas. If the number of congested areas is relatively small, the following normalization method can be used: , represents the object to be processed, and exp represents the exponential function with the natural constant e as the base.

[0118] Step 4: Correct the initial traffic flow of the target area according to the spatial impact and the time impact.

[0119] The spatial impact and the time impact are the impacts of each congested area on the traffic flow of the target area from two dimensions of space and time. Then, comprehensively consider the spatial impact and the time impact to correct the initial traffic flow of the target area. In an exemplary embodiment, as Figure 6 shown, a specific correction process is given:

[0120] Step 4-1: Obtain the comprehensive impact factor of each congested area on the target area according to the spatial impact and the time impact.

[0121] The impact of the congested area on the target area is manifested jointly in space and time. According to the spatial impact factor and the time impact factor, obtain the comprehensive impact factor of each congested area on the target area.

[0122] In an exemplary embodiment, different congested areas may be affected by space or time to different degrees. For example, if the congested area is a transportation hub area, the possibility of an autonomous vehicle changing lanes is low (i.e., the spatial impact is weak), but the congestion propagation is strong (i.e., the time impact is strong). If the congested area is a branch road area, the possibility of an autonomous vehicle bypassing is relatively high (i.e., the spatial impact is strong), but the congestion propagation range is limited (i.e., the time impact is weak). Therefore, it is necessary to determine the weights of the spatial impact and the time impact according to the actual situation of each congested area, so as to determine the dominant degree of the time impact factor and the spatial impact factor through the weights.

[0123] In an exemplary embodiment, as Figure 7 shown, a specific acquisition process of the comprehensive impact factor is given as follows:

[0124] Step 4-1-1: Obtain the third quantity of autonomous vehicles whose driving routes pass through the first congestion area during the target time period, and the fourth quantity of autonomous vehicles whose driving routes pass through the target area.

[0125] Since when a certain congestion area is a frequently selected area for users, the vehicle route dependence of frequently selected roads (such as main roads) is strong, and even if there is congestion, it tends to stick to the original route, resulting in more significant congestion propagation, that is, a higher degree of time influence.

[0126] Taking the first congestion area as an example, during the target time period of each day in the historical time period, obtain the driving routes of each autonomous vehicle (the driving route is the actual driving route of the autonomous vehicle), and obtain the number of autonomous vehicles whose driving routes pass through the first congestion area as the third quantity. Then calculate the sum value of the corresponding third quantity for each day in the historical time period as the final third quantity. The larger the final third quantity, the more the first congestion area belongs to the frequently selected area for users.

[0127] Similarly, during the target time period of each day in the historical time period, obtain the number of autonomous vehicles whose driving routes pass through the target area as the fourth quantity. Then calculate the sum value of the corresponding fourth quantity for each day in the historical time period as the final fourth quantity.

[0128] Step 4-1-2: Obtain the ratio of the third quantity to the total quantity as the weight of the time influence corresponding to the first congestion area.

[0129] Calculate the sum value of the final third quantity and the final fourth quantity as the total quantity. Then calculate the ratio of the final third quantity to the total quantity, and use this ratio as the weight of the time influence corresponding to the first congestion area. The larger this ratio, the more likely the first congestion area is a frequently selected area for the public. At this time, the spatial influence factor of the user's route-changing behavior is small, and the time influence factor is large, that is, the time influence of the first congestion area dominates.

[0130] Using the above method, obtain the weights of the time influence corresponding to each congestion area.

[0131] Step 4-1-3: According to the weight, perform weighted summation on the spatial influence factor and the time influence factor to obtain the comprehensive influence factor of the first congestion area on the target area.

[0132] The obtained weight is the weight of the time influence factor of the first congestion area. According to this weight, obtain the weight of the spatial influence factor of the first congestion area. Among them, the weight of the spatial influence factor is the value 1 minus this weight.

[0133] In an exemplary embodiment, the calculation formula of the comprehensive influence factor is as follows:

[0134] ;

[0135] Wherein, is the comprehensive influence factor of the o-th congestion area on the target area, is the spatial influence factor of the o-th congestion area on the target area, is the time influence factor of the o-th congestion area on the target area, is the weight of the time influence factor obtained in Steps 4-1-1 and 4-1-2.

[0136] In the above manner, the comprehensive influence factors of each congestion area on the target area are obtained.

[0137] As another implementation manner, if the situation that different congestion areas are affected by space or time to different degrees is not considered, the average value of the spatial influence factor and the time influence factor can also be directly calculated as the comprehensive influence factor.

[0138] Step 4-2: Integrate the comprehensive influence factors of all congestion areas on the target area to obtain the final influence factor.

[0139] Based on the comprehensive influence factors of each congestion area on the target area, integrate the comprehensive influence factors of all congestion areas on the target area to obtain the final influence factor. In an exemplary embodiment, the average value of the comprehensive influence factors of each congestion area on the target area is calculated as the final influence factor.

[0140] Step 4-3: Determine the correction factor, and the correction factor is negatively correlated with the final influence factor.

[0141] The final influence factor represents the influence of all congestion areas on the traffic flow of the target area. The larger the final influence factor, the more serious the influence on the traffic flow of the target area, that is, the more serious the overestimation degree of the traffic flow of the target area, and the greater the gap between the actual traffic flow and the initial traffic flow of the target area, and the more necessary it is to reduce the initial traffic flow of the target area. Then, according to the obtained final influence factor, the correction factor is obtained, and the correction factor is negatively correlated with the final influence factor. In an exemplary embodiment, the difference between the value 1 and the final influence factor is calculated, and this difference is the correction factor.

[0142] Step 4-4: Multiply the correction factor by the initial traffic flow of the target area to obtain the corrected traffic flow of the target area.

[0143] Calculate the product of the correction factor and the initial traffic flow of the target area to obtain the corrected traffic flow of the target area. The corrected traffic flow is the real traffic flow of the target area on that day, thereby achieving accurate acquisition of the traffic flow of the target area.

[0144] According to the data processing process provided in this embodiment, the real traffic volume of each area on the same day can be obtained. The greater the traffic volume, the higher the map update priority. Then, the map update priority of each area can be obtained based on the real traffic volume of each area, so as to implement the navigation map update according to the map update priority of each area.

[0145] This embodiment also provides an intelligent update system for an autonomous driving navigation map, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-mentioned embodiment of the intelligent update method for the autonomous driving navigation map when the program instructions are executed.

[0146] In an exemplary embodiment, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned embodiment of the intelligent update method for the autonomous driving navigation map are implemented.

[0147] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0148] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A method for intelligently updating an autonomous driving navigation map, characterized in that: include: Based on the change of the navigation path planning, the spatial impact of each congested area on the target area is obtained, and the congested area is an area with vehicle congestion within a preset neighborhood of the target area; Combined with the time difference between the occurrence of congestion in each congested area and the target area, the correlation between the congestion phenomenon in each congested area and the target area is obtained; determining a time impact of each congested area on the target area, the time impact being obtained from the correlation; According to the spatial influence and the temporal influence, the initial traffic flow of the target area is corrected, including: according to the spatial influence and the temporal influence, obtaining the comprehensive influence factor of each congested area on the target area; integrating the comprehensive influence factors of all congested areas on the target area to obtain the final influence factor; determining a correction factor, wherein the correction factor is negatively correlated with the final influence factor; and multiplying the correction factor by the initial traffic flow of the target area to obtain the corrected traffic flow of the target area.

2. The intelligent updating method of the autonomous driving navigation map according to claim 1, characterized in that: The process of obtaining the congested area includes: Acquire a related area, where the related area is an area within a preset neighborhood of the target area; Obtain the average speed of the autonomous driving vehicles in each associated area during the target period and compare it with the preset average speed threshold; If the average speed is less than a preset average speed threshold, the corresponding associated area is determined to be a congested area.

3. The intelligent updating method of the autonomous driving navigation map according to claim 1, characterized in that: The obtaining of the spatial impact of each congested area on the target area based on the change of the navigation path planning includes: Acquire a first number of autonomous driving vehicles whose original navigation paths pass through a first congested area and do not pass through the target area during a target time period; the first congested area is any congested area; Acquire a second number of autonomous driving vehicles that change an original navigation path into an actual navigation path during the target time period; the actual navigation path is a navigation path that passes through the target area and does not pass through the first congested area; A ratio of the second number to the first number is obtained as a spatial impact factor of the first congested area on the target area.

4. The intelligent updating method of an autonomous driving navigation map according to claim 1, characterized in that: The process of obtaining the time difference between the occurrence of congestion in each congested area and the target area includes: Obtaining historical vehicle flow in a first congestion area and a target area; the first congestion area is any congestion area; According to the relationship between the historical traffic volume and time in the first congestion area and the target area, a linear regression model is constructed; The linear regression model is solved to obtain the time difference between the occurrence of congestion in the first congested area and the target area.

5. The intelligent updating method of the autonomous driving navigation map according to claim 4, characterized in that: The linear regression model is: ； in, Indicates that the target area is Historical traffic volume over time, Indicates that the oth congested area is Historical traffic volume over time, represents the time difference between the congestion in the oth congested area and the target area, represents the regression coefficient, represents the error term of the linear regression model.

6. The intelligent updating method of an autonomous driving navigation map according to claim 1, characterized in that: The process of obtaining the correlation between the congestion phenomena of each congested area and the target area includes: Acquire a first vehicle flow sequence of a first congestion time period in a first congestion area in a target time period; the first congestion area is any congestion area, and the first congestion time period is a congestion time period in the first congestion area in the target time period; According to the first congestion time period and the time difference, a second congestion time period is obtained, where the second congestion time period is a congestion time period of a target area; Acquire a second traffic flow sequence of the target area in the second congestion time period; Obtain a correlation coefficient between the first vehicle flow sequence and the second vehicle flow sequence.

7. The intelligent updating method of the autonomous driving navigation map according to claim 6, characterized in that: The determining of the time impact of each congested area on the target area includes: A result of normalizing the correlation coefficient corresponding to the first congested area is used as a time influence factor of the first congested area on the target area.

8. The intelligent updating method of an autonomous driving navigation map according to claim 1, characterized in that: The spatial impact is specifically a spatial impact factor, and the temporal impact is specifically a temporal impact factor; The comprehensive impact factor of each congested area on the target area is obtained according to the spatial impact and the temporal impact, including: Obtaining a third number of autonomous driving vehicles whose driving paths pass through a first congestion area during a target period, and a fourth number of autonomous driving vehicles whose driving paths pass through a target area; the first congestion area being any congestion area; Obtaining a ratio of the third number to the total number as a weight of the time impact corresponding to the first congested area; the total number is the sum of the third number and the fourth number; According to the weights, the spatial impact factor and the temporal impact factor are weighted and summed to obtain a comprehensive impact factor of the first congested area on the target area.

9. An intelligent updating system for an autonomous driving navigation map, characterized in that it includes: Memory and processor; The memory is connected to the processor; The memory is used to store program instructions; The processor is used to implement the intelligent update method of the autonomous driving navigation map according to any one of claims 1 to 8 when the program instructions are executed.

Images