Map updating method and device

Abstract

The present disclosure provides a map updating method and device, which relate to the field of data processing, and in particular to the field of intelligent transportation. The specific implementation scheme is: obtaining first map data of a preset area, the first map data including the current traffic signs of each intersection in the preset area. Obtaining intersection images obtained by photographing each intersection in the preset area. Obtaining vehicle driving data corresponding to each intersection in the preset area, the vehicle driving data including: the number of vehicles traveling on each type of lane in the intersection within each unit time of a historical period. According to the first map data, the intersection image and the vehicle driving data, the traffic signs of the intersection in the first map data are updated to obtain the second map data. By fusing the intersection image and the driving data to update the traffic signs of each intersection in the first map data, the map updating efficiency can be effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent transportation in data processing, and in particular to a map updating method and device. Background Art

[0002] There are usually some ground guide arrows on the road, wherein the guide arrows can indicate the driving direction of the vehicle, so it is particularly important to include correct guide arrows in the map data.

[0003] When the ground guide arrows in the road are updated, the ground guide arrows in the corresponding map data also need to be updated. In the prior art, when updating the ground guide arrows in the map data, the road is usually imaged, and then the updated ground guide arrows are determined based on image recognition.

[0004] However, ground guide arrows are easily covered and blocked by vehicles, and are prone to wear and tear. Multiple data collection and recognition may be required, so the current implementation method has the problem of low map update efficiency. Summary of the invention

[0005] The present disclosure provides a map updating method and device.

[0006] According to a first aspect of the present disclosure, a map updating method is provided, comprising:

[0007] Acquire first map data of a preset area, wherein the first map data includes current traffic signs at each intersection in the preset area;

[0008] Acquire intersection images obtained by photographing each intersection in the preset area;

[0009] Acquire vehicle driving data corresponding to each intersection in the preset area, wherein the vehicle driving data includes: the number of vehicles traveling on each type of lane at the intersection in each unit time of the historical period;

[0010] According to the first map data, the intersection image and the vehicle driving data, the traffic signs at the intersection in the first map data are updated to obtain the second map data.

[0011] According to a second aspect of the present disclosure, a map updating device is provided, comprising:

[0012] A first acquisition module, used to acquire first map data of a preset area, wherein the first map data includes current traffic signs at each intersection in the preset area;

[0013] A second acquisition module is used to acquire intersection images obtained by photographing each intersection in the preset area;

[0014] A third acquisition module is used to acquire vehicle driving data corresponding to each intersection in the preset area, wherein the vehicle driving data includes: the number of vehicles traveling on each type of lane at the intersection in each unit time of the historical period;

[0015] The processing module is used to update the traffic signs at the intersection in the first map data according to the first map data, the intersection image and the vehicle driving data to obtain the second map data.

[0016] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0020] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect.

[0021] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising: a computer program, wherein the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect.

[0022] The technology according to the present disclosure solves the problem of low map updating efficiency.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0025] Figure 1 A schematic diagram of implementing a ground guide arrow provided in an embodiment of the present disclosure;

[0026] Figure 2 A flowchart of a map updating method provided by an embodiment of the present disclosure;

[0027] Figure 3 A flowchart of a map updating method provided by an embodiment of the present disclosure;

[0028] Figure 4 A schematic diagram of implementing the first map data provided by an embodiment of the present disclosure;

[0029] Figure 5 Implementation diagram of traffic sign update provided by the embodiment of the present disclosure Figure 1 ;

[0030] Figure 6 Implementation diagram of traffic sign update provided by the embodiment of the present disclosure Figure 2 ;

[0031] Figure 7 A schematic diagram of implementing vehicle driving data provided by an embodiment of the present disclosure;

[0032] Figure 8 Implementation diagram of determining change confidence provided by the embodiment of the present disclosure Figure 1 ;

[0033] Fig. 9 Implementation diagram of determining change confidence provided by the embodiment of the present disclosure Figure 2 ;

[0034] Fig.10 is a schematic diagram of the structure of a map updating device according to an embodiment of the present disclosure;

[0035] Fig.11 The block diagram is a block diagram of an electronic device for implementing the map updating method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0037] In order to better understand the technical solution of the present disclosure, the related technologies involved in the present disclosure are further introduced in detail below.

[0038] There are usually ground guide arrows on actual roads, where the ground guide arrows can indicate the direction of vehicle travel. Figure 1 To understand, Figure 1 A schematic diagram of the implementation of the ground guide arrow provided in the embodiment of the present disclosure.

[0039] like Figure 1 As shown, there may be ground guide arrows in the road, wherein the ground guide arrows may be located, for example, at Figure 1 The intersection shown is used to indicate the direction of vehicle travel, for example Figure 1 The arrow shown at 101 in FIG. 1 indicates that the direction of travel of the vehicle is to turn left. Figure 1 The arrow shown at 102 indicates that the driving direction of the vehicle is straight ahead and right turn.

[0040] It is understandable that the ground guide arrows support path planning, voice guidance, and image rendering in the map navigation process, and are one of the most important elements in the map navigation data. If the map is to achieve correct navigation, the map guide arrows included in the map data must be correct. Therefore, when the ground guide arrows on the road are updated, the map data also needs to be updated accordingly.

[0041] The existing method of updating ground guide arrows is mainly to update them by using image recognition and differential discovery of change points. That is to say, the collection vehicle can collect road images on the road, and then perform image recognition based on the collected images, and perform differential processing with the existing map data to determine the change points, and then determine the update of the ground guide arrows.

[0042] However, since the ground guide arrows are mainly located near intersections, they are easily covered and blocked by vehicles, and are easily worn out. They are also affected by special weather conditions. Therefore, the recognition accuracy and recall rate of updating the ground guide arrows based on image recognition and differential discovery of change points are low, affecting the timeliness and completeness of data updates.

[0043] And in another possible implementation, when updating the ground guide arrow, UGC user feedback may be used, where UGC is User Generated Content.

[0044] However, this implementation method relies on user feedback. Locations that users have not reported cannot be recalled. In addition, it is affected by the integrity of the information uploaded by the user. User feedback content may not be completely reliable, so the overall recall rate of changed locations is low.

[0045] Therefore, in the prior art, updating of ground guide arrows has the problems of low recognition accuracy and recall rate, low updating efficiency of ground guide arrows, and low updating completeness.

[0046] In response to the problems in the prior art, the present disclosure proposes the following technical concept: by fusing the results of image recognition and the trajectory flux of each road, the ground guide arrows that have changed in the road can be determined. Based on the fusion of the two parts of data, the recognition accuracy and recall rate of the updated ground guide arrows can be effectively improved, thereby improving the update efficiency and completeness of the ground guide arrows.

[0047] Based on the above introduction, the map updating method provided by the present disclosure is introduced in combination with specific embodiments. It is worth noting that the execution subject of each embodiment in the present disclosure may be, for example, a server, or may also be a processor, microprocessor or other device with data processing function. This embodiment does not limit the specific execution subject, as long as it is a device with data processing function.

[0048] First combine Figure 2 Make an introduction, Figure 2 A flowchart of a map updating method provided in an embodiment of the present disclosure.

[0049] like Figure 2 As shown, the method includes:

[0050] S201. Acquire first map data of a preset area, where the first map data includes current traffic signs at each intersection in the preset area.

[0051] In this embodiment, the preset area can be an area where the map is to be updated. For example, the preset area can be a certain street, or the preset area can be a certain administrative district, or the preset area can be a certain county, or the preset area can also be an area selected in the map, etc. This embodiment does not limit the specific implementation method of the preset area. Any area that needs to update the map data can be used as the preset area in this embodiment.

[0052] For example, first map data of a preset area may be obtained. The first map data of this embodiment includes current traffic signs at various intersections in the preset area. The traffic signs in this embodiment may be understood as the ground guide arrows described above.

[0053] In a possible implementation, for example, there are three intersections in the preset area, namely, intersection 1, intersection 2, and intersection 3, and the current traffic signs of the three intersections may be included in the first map data obtained.

[0054] The map data may be stored in a preset storage unit, which may be a database, a disk, etc. After determining the preset area, the first map data of the preset area may be obtained from the map data stored in the preset storage unit.

[0055] S202: Acquire intersection images obtained by photographing each intersection in a preset area.

[0056] The first map data includes various intersections in a preset area. In this embodiment, intersection images obtained by photographing various intersections in the preset area can also be obtained. In a possible implementation method, one photographed intersection image can be obtained for one intersection, or multiple photographed intersection images can be obtained. This embodiment does not impose any restrictions on this.

[0057] In a possible implementation, for example, a collection vehicle may take at least one photograph of each intersection to obtain an intersection image. The intersection image of each intersection may be stored in a preset storage space. After the first map data is determined, the intersection image corresponding to each intersection in the first map data may be obtained from the preset storage space according to the identifier of each intersection in the first map data.

[0058] Alternatively, in another possible implementation, the intersection images corresponding to each intersection may be obtained from a designated database or data storage system. This embodiment does not impose any particular restriction on the data source for obtaining the intersection images, which may be selected according to actual needs.

[0059] And when acquiring the intersection image, for example, the intersection image taken at any time within the preset time period before the current moment can be acquired, wherein the preset time period can be, for example, a week, half a month, etc. It can be understood that the current acquisition of the intersection image is to determine the latest traffic sign situation at the intersection, so it is necessary to impose certain restrictions on the time of acquiring the intersection image. If the intersection image acquired is a long time ago, such as one year ago or two years ago, then the intersection image acquired at this time may no longer accurately reflect the real intersection situation, that is, the traffic sign at the intersection may have changed. Therefore, in this embodiment, the intersection image taken at any time within the preset time period before the current moment can be acquired, but the preset time period cannot be set too long.

[0060] For any intersection, when obtaining an intersection image taken at any time within a preset time period before the current time, one image or multiple images may be obtained, and this embodiment does not impose any limitation on this, as long as they are images within the preset time period.

[0061] Here, a specific example can be used for illustration. Assume that the collection vehicle collects intersection images of intersections 1 to 100 within one month before the current moment, and then stores the collected intersection images in a preset storage space. And assume that the current first map data includes current traffic signs of intersections 1, 2, and 3 in the preset area.

[0062] Assuming that the preset time period is one week, for example, the image of intersection 1 within one week before the current time can be acquired in the preset storage space, that is, the image of intersection acquired by the acquisition vehicle. The image of intersection 2 within one week before the current time can be acquired in the preset storage space, and the image of intersection 3 within one week before the current time can be acquired in the preset storage space.

[0063] S203: Acquire vehicle driving data corresponding to each intersection in a preset area, where the vehicle driving data includes: the number of vehicles traveling on each type of lane in the intersection in each unit time of a historical period.

[0064] Furthermore, in this embodiment, vehicle driving data corresponding to each intersection in a preset area can also be obtained. The vehicle driving data in this embodiment can include the number of vehicles traveling on each type of lane in the intersection in each unit time of the historical period.

[0065] The various types of lanes may include, for example, left-turn lanes, right-turn lanes, and straight lanes, that is, the driving directions of the lanes, and the historical time period in this embodiment may be, for example, half a year, one month, etc., which is not limited in this embodiment.

[0066] The unit time in this embodiment can be, for example, one day, one hour, half a day, one week, etc. This embodiment also does not limit the specific implementation of the unit time. It is worth noting that the length of the unit time is shorter than the length of the historical period. On this basis, the specific implementation of the historical period and the unit time can be selected and set according to actual needs, and this embodiment does not specifically limit this.

[0067] For example, a specific example can be used to illustrate that it is assumed that the current first map data includes current traffic signs of intersections 1, 2, and 3 in the preset area, and that the historical period is one month and the unit time is one day.

[0068] In this embodiment, the number of vehicles traveling on each type of lane at intersection 1 every day within the month before the current moment can be obtained; and the number of vehicles traveling on each type of lane at intersection 2 every day within the month before the current moment can be obtained; and the number of vehicles traveling on each type of lane at intersection 3 every day within the month before the current moment can be obtained.

[0069] The vehicle driving data may be obtained from a relevant navigation database or a relevant traffic flow statistics database, for example, and this embodiment does not impose any limitation on this.

[0070] It should also be noted that the reason why the vehicle driving data is determined in the present embodiment is to determine the changes in the vehicle driving data in order to determine whether the traffic signs at the intersection have been updated. In order to determine the changes in the vehicle driving data, the above-mentioned historical period can be set to be relatively long. If the historical period is set to be relatively long, it is more likely to cover the vehicle driving data before and after the lane change, so that the update of the traffic sign can be determined according to the changes in the vehicle driving data.

[0071] S204: Update the traffic signs at the intersection in the first map data according to the first map data, the intersection image and the vehicle driving data to obtain second map data.

[0072] After determining the first map data, intersection image and vehicle travel data introduced above, the traffic signs at the intersection in the first map data can be updated according to the first map data, intersection image and vehicle travel data, thereby obtaining the second map data.

[0073] In one possible implementation, for example, image recognition can be performed based on intersection images to obtain traffic signs at each intersection corresponding to the image recognition, and the trajectory flux of the intersection can be determined based on vehicle driving data to obtain traffic signs at each intersection corresponding to the trajectory flux. Then, the traffic signs at each intersection corresponding to the image recognition and the traffic signs at each intersection corresponding to the trajectory flux are fused, and the confidence of the traffic sign update is determined by fusing the two parts of traffic signs, thereby determining the update status of each traffic sign, so as to implement the update of the traffic signs at each intersection in the first map data, thereby obtaining the second map data, which includes the updated traffic signs at each intersection.

[0074] The map updating method provided by the embodiment of the present disclosure includes: obtaining first map data of a preset area, wherein the first map data includes current traffic signs of each intersection in the preset area. Obtaining intersection images obtained by photographing each intersection in the preset area. Obtaining vehicle driving data corresponding to each intersection in the preset area, wherein the vehicle driving data includes: the number of vehicles traveling on each type of lane in the intersection during each unit time of a historical period. According to the first map data, the intersection image and the vehicle driving data, the traffic signs of the intersections in the first map data are updated to obtain second map data. By obtaining intersection images and vehicle driving data corresponding to each intersection in the first map data, and then fusing the intersection images and driving data to update the traffic signs of each intersection in the first map data, the recognition accuracy and recall rate of the updated traffic signs can be effectively improved, thereby effectively improving the map update efficiency.

[0075] Based on the above embodiments, Figures 3 to 9The map updating method provided by the present disclosure is further introduced in detail. Figure 3 A flowchart of a map updating method provided in an embodiment of the present disclosure, Figure 4 A schematic diagram of implementing the first map data provided in an embodiment of the present disclosure, Figure 5 Implementation diagram of traffic sign update provided by the embodiment of the present disclosure Figure 1 , Figure 6 Implementation diagram of traffic sign update provided by the embodiment of the present disclosure Figure 2 , Figure 7 A schematic diagram of implementing vehicle driving data provided by an embodiment of the present disclosure, Figure 8 Implementation diagram of determining change confidence provided by the embodiment of the present disclosure Figure 1 , Fig. 9 Implementation diagram of determining change confidence provided by the embodiment of the present disclosure Figure 2 .

[0076] like Figure 3 As shown, the method includes:

[0077] S301. Acquire first map data of a preset area, where the first map data includes current traffic signs at each intersection in the preset area.

[0078] S302: Obtain intersection images obtained by photographing each intersection in a preset area.

[0079] S303: Obtain vehicle driving data corresponding to each intersection in a preset area, where the vehicle driving data includes: the number of vehicles traveling on each type of lane in the intersection in each unit time of a historical period.

[0080] The implementation of S301 to S303 is similar to the implementation of S201 to S203 described above, and will not be described in detail here.

[0081] S304. Determine a first intersection set and a second intersection set from a plurality of intersections according to the current traffic sign of each intersection in the first map data, wherein the current traffic signs of the intersections in the first intersection set are not empty, and the current traffic signs of the intersections in the second intersection set are empty.

[0082] In this embodiment, the first map data includes current traffic signs at each intersection in a preset area. In a possible implementation, in this embodiment, it is possible to determine whether the current traffic sign at each intersection is empty based on the current traffic sign at each intersection in the first map data, thereby determining a first intersection set and a second intersection set from multiple intersections.

[0083] Among them, the current traffic sign of each intersection in the first intersection set is not empty, and the current traffic sign of each intersection in the second intersection set is empty.

[0084] It can be understood that the above determination of the first intersection set and the second intersection set is actually to divide each intersection in the first map data into two different sets according to whether there is a current traffic sign at each intersection in the first map data.

[0085] For example, the following can be combined Figure 4 To understand, refer to Figure 4 , assuming that the first map data currently includes 5 intersections, namely Figure 4 Junction 1, Junction 2, Junction 3, Junction 4 and Junction 5 are shown. Figure 4 In the first map data, the current traffic signs corresponding to intersection 1 include straight ahead, straight ahead, straight ahead and right turn, there are no corresponding current traffic signs for intersection 2 and intersection 3, and the current traffic signs corresponding to intersection 4 include straight ahead and right turn, and the current traffic signs corresponding to intersection 5 include left turn and execute.

[0086] Then based on Figure 4 The first map data shown can determine the first intersection set whose current traffic signs are not empty, which can be represented by set A, for example. Figure 4 , the first intersection set A includes: intersection 1, intersection 4 and intersection 5. And, a second intersection set with empty current traffic signs can also be determined, for example, it can be represented by set B, see Figure 4 , the second intersection set B includes intersection 2 and intersection 3.

[0087] In the actual implementation process, the specific implementation of the intersections included in the first map data and the current traffic signs corresponding to each intersection may depend on the actual road implementation, and this embodiment does not limit this. Therefore, the specific roads included in the first intersection set and the second intersection set may also depend on the actual situation, as long as the first intersection set includes the intersections where the current traffic signs exist in the first map data, and the second intersection set includes the intersections where the current traffic signs do not exist in the first map data.

[0088] S305: Determine a first set of to-be-selected intersections in the first set of intersections according to current traffic signs and intersection images at each intersection in the first set of intersections.

[0089] The first intersection set in this embodiment includes each intersection where a current traffic sign exists. After the first intersection set is determined, for example, a first intersection set to be selected can be determined in the first intersection set based on the current traffic signs and intersection images of each intersection in the first intersection set.

[0090] In a possible implementation manner, the first traffic sign of each intersection in the first intersection set may be determined according to the intersection image.

[0091] For example, image recognition may be performed on the intersection image of each intersection, so as to determine the first traffic sign of each intersection in the first intersection set.

[0092] For instance, continuing with the above example, the first intersection set currently includes intersection 1, intersection 4, and intersection 5. Then, for example, image recognition can be performed based on the intersection image corresponding to intersection 1 to determine the first traffic sign at intersection 1; and, image recognition can be performed based on the intersection image corresponding to intersection 4 to determine the first traffic sign at intersection 4; and, image recognition can be performed based on the intersection image corresponding to intersection 5 to determine the first traffic sign at intersection 5.

[0093] It should also be noted that, in this embodiment, for any intersection, there may be one intersection image or multiple intersection images. When there is only one intersection image, only one first traffic sign will be determined for the intersection; when there are multiple intersection images, because the intersection images acquired in this embodiment are within a preset time period, the traffic signs on the road generally will not change multiple times in a short period of time, so when there are multiple intersection images, the first traffic signs obtained based on the recognition of the multiple intersection images are usually the same.

[0094] For example, a first set of candidate intersections may be determined in the first set of intersections based on current traffic signs at each intersection in the first set of intersections and first traffic signs corresponding to each intersection in the first set of intersections, wherein the first traffic signs at each intersection in the first set of candidate intersections are different from the current traffic signs.

[0095] Specifically, after determining the first traffic sign corresponding to each intersection in the first intersection set, the first traffic sign of each intersection in the first intersection set can be compared with the corresponding current traffic sign. If the first traffic sign and the current traffic sign of a certain intersection are different, the intersection can be determined as an intersection in the first set of candidate intersections, thereby obtaining the first set of candidate intersections.

[0096] It can be understood that the first traffic sign is a traffic sign obtained by image recognition based on images of the intersection within a preset time period, and the current traffic sign is a traffic sign stored in the current map data. Therefore, when the first traffic sign and the current traffic sign are different, it can be determined that the traffic sign at the intersection may have changed, and such intersections are stored in the first set of candidate intersections. Therefore, the first set of candidate intersections in this embodiment includes intersections where existing traffic signs have changed, which are determined based on image recognition results.

[0097] Based on the above introduction, the following Figure 5 To explain, Figure 5 As shown, it is assumed that the intersection 1 included in the first intersection set A is currently being processed. Figure 5 501 in the figure indicates the current traffic sign of the intersection 1 in the first map data, referring to Figure 5 , the current traffic signs at intersection 1 include straight, straight, straight and right turn.

[0098] as well as Figure 5 502 in the figure shows an intersection image of intersection 1. Based on the intersection image, the first traffic sign of intersection 1 can be determined. Figure 5 , the first traffic signs at intersection 1 include straight ahead and left turn, straight ahead, straight ahead and right turn.

[0099] Therefore, it can be determined that, for intersection 1, the current traffic sign corresponding to intersection 1 is different from the first traffic sign, so intersection 1 can be determined as an intersection in the first set of candidate intersections. For example, A1 can be used to represent the first set of candidate intersections. Figure 5 , the first candidate intersection set A1 includes intersection 1.

[0100] The above operation can be performed for each intersection in the first intersection set, so as to determine at least one intersection where the first traffic sign is different from the current traffic sign, so as to obtain a first set of candidate intersections. In this embodiment, the first set of candidate intersections A1 can be further understood as intersections where the traffic signs obtained by image recognition have changed compared to the traffic signs in the map data.

[0101] S306: Determine a second set of to-be-selected intersections in the second set of intersections according to the current traffic signs and intersection images of each intersection in the second set of intersections.

[0102] The second intersection set in this embodiment includes all intersections where there are no current traffic signs. After determining the second intersection set, the second intersection set to be selected can also be determined in the second intersection set based on the current traffic signs and intersection images of each intersection in the second intersection set.

[0103] In a possible implementation, determining a first traffic sign at each intersection in the second intersection set according to the intersection image;

[0104] According to the first traffic signs corresponding to the intersections in the second intersection set, a second set of intersections to be selected is determined in the second intersection set, and the first traffic signs of the intersections in the second set of intersections to be selected are not empty.

[0105] Among them, determining the first traffic sign of each intersection in the second intersection set based on the intersection image is similar to the implementation method of determining the first traffic sign introduced in the above S305. The difference is that the first traffic sign is currently determined for each intersection in the second intersection set. The specific implementation method of determining the first traffic sign is not repeated in this embodiment.

[0106] After determining the first traffic sign corresponding to each intersection in the second intersection set, the first traffic sign of each intersection in the second intersection set can be compared with the corresponding current traffic sign to determine the second set of selected intersections. In this embodiment, the first traffic sign of each intersection in the second set of selected intersections is not empty.

[0107] It can be understood here that the current traffic signs of each intersection in the second intersection set are empty, that is, each intersection in the second intersection set originally had no traffic signs. If the first traffic sign of a certain intersection in the current second intersection set is not empty, it can be determined that the image recognition result indicates that a new traffic sign has been added to the intersection. Therefore, it is determined that the first traffic sign of the intersection is not empty, and such an intersection is stored in the second intersection set to be selected. Therefore, the second intersection set package to be selected in this embodiment includes the intersection with the new traffic sign determined based on the image recognition result.

[0108] Based on the above introduction, the following Figure 6 To explain, Figure 6 As shown, it is assumed that the intersection 2 included in the second intersection set B is currently being processed. Figure 6 601 in the figure shows the current traffic sign of the intersection 2 in the first map data, referring to Figure 6 , the current traffic sign at intersection 2 is empty.

[0109] as well as Figure 6 602 in FIG. 602 is an intersection image of intersection 2. Based on the intersection image, the first traffic sign of intersection 2 can be determined. Figure 6 , the first traffic signs at intersection 2 include going straight and turning left, going straight and turning right.

[0110] Therefore, it can be determined that for intersection 2, the current traffic sign corresponding to intersection 2 is empty, but the first traffic sign corresponding to intersection 2 is not empty, so intersection 2 can be determined as an intersection in the second set of candidate intersections. For example, B1 can be used to represent the second set of candidate intersections. Figure 6 , the second candidate intersection set B1 includes intersection 2.

[0111] The above operation can be performed for each intersection in the second intersection set, so as to determine at least one intersection where the first traffic sign is not empty, so as to obtain a second set of candidate intersections. The second set of candidate intersections B1 in this embodiment can be further understood as intersections where the traffic sign in the map data is empty but the traffic sign obtained by image recognition is not empty.

[0112] S307: Determine a third set of to-be-selected intersections in the first set of intersections according to the vehicle driving data.

[0113] In this embodiment, the first intersection set includes all intersections where current traffic signs exist. After the first intersection set is determined, a third intersection set to be selected may be determined in the first intersection set based on vehicle travel data.

[0114] In a possible implementation manner, the driving data change amount corresponding to each intersection in the first intersection set may be determined based on the vehicle driving data.

[0115] Based on the above introduction, it can be determined that the vehicle driving data in this embodiment includes the number of vehicles traveling on each type of lane in the intersection in each unit time during the historical period. Therefore, the driving data change corresponding to each intersection in the first intersection set can be determined based on the vehicle driving data.

[0116] For example, you can combine Figure 7 For example, for intersection 1, the vehicle driving data of intersection 1 includes the number of vehicles driving on each type of lane at intersection 1 every day within one month before the current moment. The various types of lanes in this embodiment may include the following three types of lanes: left turn, right turn, and straight. Figure 7 Understanding, such as Figure 7 As shown, assuming that on the first day of this month, there are 0 vehicles turning left at intersection 1 (accounting for 0%), 600 vehicles turning right at intersection 1 (accounting for 37.5%), and 1000 vehicles going straight at intersection 1 (accounting for 62.5%).

[0117] And, refer to Figure 7 On the second day of this month, 400 vehicles turned left at Intersection 1 (accounting for 19%), 500 vehicles turned right at Intersection 1 (accounting for 23.8%), and 1,200 vehicles went straight at Intersection 1 (accounting for 57.2%). The rest may not be listed.

[0118] In the above Figure 7On this basis, when determining the change in driving data corresponding to intersection 1, for example, for each type of lane at intersection 1, the difference in the number of vehicles traveling on two adjacent days can be determined to obtain the change in driving data corresponding to intersection 1. For example, for left-turn lanes, the difference in the number of vehicles traveling on the first day and the second day is 400, and the difference in proportion is 19%. The other lanes are similar, and the difference is determined for every two adjacent days. Therefore, the change in driving data in this embodiment can be multiple values.

[0119] Alternatively, the average value of the difference in the number of vehicles traveling on two adjacent days in a month may be determined as the driving data change amount. Therefore, the driving data change amount in this embodiment may also be a value, and this embodiment does not impose any limitation on this.

[0120] Alternatively, the change in driving data in this embodiment may also be the change in the percentage of the number of vehicles traveling in each lane every two adjacent days, or may also be the average value of the change in percentage. The implementation method is similar to that described above and will not be repeated here.

[0121] After determining the driving change, for example, a third set of candidate intersections can be determined in the first set of intersections based on the driving data change corresponding to each intersection in the first set of intersections, and the driving data change of each intersection in the third set of candidate intersections is greater than or equal to the preset change.

[0122] It is understandable that when the driving data change is greater than or equal to the preset change, it means that the vehicle traffic conditions at the intersection have changed significantly. Figure 7 In the example, the driving data change of the left turn lane reaches 400, and based on Figure 7 It is certain that there are no vehicles in the left-turn trajectory flux on the first day, but there are many vehicles in the left-turn trajectory flux on the second day, which may be because a new left-turn lane has been added to the current intersection. The specific setting of the preset change amount can be selected according to actual needs. For example, when the driving data change amount is for the change in the number of vehicles traveling, it can be a numerical value, and when the driving data change amount is for the change in the proportion of the number of vehicles traveling, it can be a percentage, etc.

[0123] And based on the above introduction, it can be determined that the driving data change in this embodiment can be one value or multiple values. When the driving data change is multiple values, for example, when any value in the driving data change is greater than or equal to the preset change, the intersection is determined as an intersection in the third set of candidate intersections.

[0124] For example, you can combine Figure 5To understand, assuming that the current driving data change is the change in the proportion of the number of driving vehicles, refer to Figure 5 502, for example, for the left turn direction of intersection 1, assuming that the proportion of vehicles traveling in the left turn direction changes from 2% to 40%, it can be determined that the change in driving data reaches 38%. For example, the preset change is 20%, and then, for example, intersection 1 can be determined as an intersection in the third set of candidate intersections. For example, A2 can be used to represent the third set of candidate intersections. Figure 5 , the third candidate intersection set A2 includes intersection 2.

[0125] The above operation can be performed for each intersection in the first intersection set, so as to determine an intersection where the change amount of driving data of at least one vehicle has changed significantly, so as to obtain a third set of intersections to be selected. The third set of intersections to be selected A2 in this embodiment can be further understood as an intersection where the vehicle driving trajectory flux at the intersection has changed significantly, and the trajectory flux in this embodiment can be understood as the proportion of vehicles driving in each type of lane at the current intersection.

[0126] S308. Determine a fourth set of to-be-selected intersections in the second set of intersections according to the vehicle driving data.

[0127] The second intersection set in this embodiment includes all intersections where no current traffic signs exist. After the second intersection set is determined, a fourth intersection set to be selected may be determined in the second intersection set based on vehicle travel data.

[0128] In a possible implementation, a fourth set of candidate intersections may be determined in the second set of intersections based on vehicle driving data corresponding to each intersection in the second set of intersections, and the vehicle driving data of each intersection in the fourth set of candidate intersections may be greater than or equal to a preset threshold.

[0129] It can be understood here that each intersection in the second intersection set has a current empty traffic sign, where the empty traffic sign may exist in a variety of situations, such as the intersection was previously unavailable, or the intersection was previously accessible but no traffic sign was drawn, or the map data is incorrect, etc. In short, each intersection in the second intersection set originally had no traffic sign.

[0130] Because the second intersection set in this embodiment includes intersections where no traffic signs exist, for such intersections, if the traffic signs change, it is either that the intersection that was previously inaccessible is now accessible, or that new traffic signs are drawn. Therefore, for each intersection in the second intersection set, if the traffic signs change, it is only a change from nothing to something, not from one situation to another. Therefore, the trajectory flux of each intersection in the second intersection set is either a change from no trajectory flux to trajectory flux, or the trajectory flux does not change significantly.

[0131] Or it may be that when a new traffic sign is drawn, the traffic plan for the intersection is changed. For example, when there was no traffic sign, vehicles could turn right, but after the new traffic sign was drawn, vehicles were not allowed to turn right. In this case, the trajectory flux will change significantly, but because there was no traffic sign originally, the change of the traffic sign cannot be determined based on the trajectory flux. It can only be determined that a new traffic sign may have been drawn.

[0132] Therefore, when determining the fourth set of intersections to be selected based on the vehicle driving data, as long as the vehicle driving data at the intersection is greater than or equal to a preset threshold, where the preset threshold may be, for example, 1, or the preset threshold may be any other value, which is not limited in this embodiment. That is, as long as the vehicle driving data indicates that there is vehicle traffic at the current intersection, that is, there is track flux, the intersection is determined as an intersection in the fourth set of intersections to be selected.

[0133] Based on the above introduction, the following Figure 6 To explain, based on Figure 6 As shown in 603, there is a trajectory flux in the intersection 2, that is, the vehicle driving data of the intersection 2 is greater than the preset threshold, then the intersection 2 can be determined as an intersection in the fourth set of candidate intersections. For example, B2 can be used to represent the fourth set of candidate intersections. Figure 6 , the fourth candidate intersection set B2 includes intersection 2.

[0134] The above operation can be performed for each intersection in the second intersection set, so as to determine at least one intersection with trajectory flux, and obtain a fourth set of candidate intersections. The fourth set of candidate intersections B2 in this embodiment can be further understood as intersections with trajectory flux.

[0135] S309: Obtain a first weight value of the first set of intersections to be selected, a second weight value of the second set of intersections to be selected, a third weight value of the third set of intersections to be selected, and a fourth weight value of the fourth set of intersections to be selected.

[0136] And in this embodiment, for example, weight values ​​can be set respectively for the first set of intersections to be selected, the second weight value of the second set of intersections to be selected, the third weight value of the third set of intersections to be selected, and the fourth weight value of the fourth set of intersections to be selected.

[0137] For example, a first weight value m1 is set for the first set A1 of intersections to be selected, a second weight value n1 is set for the second set B1 of intersections to be selected, a third weight value m2 is set for the third set A2 of intersections to be selected, and a fourth weight value n2 is set for the fourth set B2 of intersections to be selected. The specific implementation of the first weight value, the second weight value, the third weight value, and the fourth weight value can be selected and set according to actual needs, and this embodiment does not impose any restrictions on this.

[0138] S310, determine a part of the target intersections in the first intersection set based on the first weight value of the first set of intersections to be selected, the third weight value of the third set of intersections to be selected, the corresponding update confidence of each intersection in the first set of intersections to be selected in the first set of intersections to be selected, and the corresponding update confidence of each intersection in the first set of intersections to be selected in the third set of intersections to be selected, and the update confidence is the probability that the traffic signs in the intersections to be selected are updated.

[0139] And in this embodiment, for each of the candidate intersections in the first candidate intersection set, there is a corresponding update confidence, which is used to indicate the probability of the traffic sign in the candidate intersection being updated. For example, when determining whether the intersection is a candidate intersection in the first candidate intersection set, the update confidence of the intersection is synchronously determined. It can be understood that the update confidence depends on the specific intersection situation and the specific determination method of determining whether the intersection is in the first candidate intersection set. That is to say, if a certain intersection is currently determined as an intersection included in the first candidate intersection set, then it is currently considered that the traffic sign at the intersection has been updated, but the current determination of the extent to which the traffic sign at the intersection has been updated is the update confidence in this embodiment. The specific determination method of the update confidence can be selected according to actual needs, as long as it can achieve the probability of the traffic sign in the candidate intersection being updated.

[0140] Similarly, in this embodiment, each candidate intersection in the third set of candidate intersections is also provided with its own updated confidence. The implementation of the updated confidence is similar to that described above, and the updated confidence of the intersection can also be synchronously determined when determining whether the intersection is a candidate intersection in the third set of candidate intersections.

[0141] Therefore, in this embodiment, the updated confidence corresponding to each intersection in the first set of intersections can be determined in the first set of intersections to be selected. Specifically, if an intersection in the first set of intersections exists in the first set of intersections to be selected, then the updated confidence corresponding to the intersection in the first set of intersections to be selected is the confidence obtained when determining that the intersection belongs to the first set of intersections to be selected as introduced above; or, if an intersection in the first set of intersections does not exist in the first set of intersections to be selected, then the updated confidence corresponding to the intersection in the first set of intersections to be selected is 0.

[0142] Similarly, in this embodiment, the updated confidence corresponding to each intersection in the first intersection set in the third set of candidate intersections can be determined. Specifically, if an intersection in the first intersection set exists in the third set of candidate intersections, then the updated confidence corresponding to the intersection in the third set of candidate intersections is the confidence obtained when determining that the intersection belongs to the third set of candidate intersections as introduced above; or, if an intersection in the first intersection set does not exist in the third set of candidate intersections, then the updated confidence corresponding to the intersection in the third set of candidate intersections is 0.

[0143] In this embodiment, a part of the target intersections in the first intersection set can be determined based on the first weight value of the first set of intersections to be selected, the third weight value of the third set of intersections to be selected, the updated confidence corresponding to each intersection in the first set of intersections to be selected in the first set of intersections to be selected, and the updated confidence corresponding to each intersection in the first set of intersections in the third set of intersections to be selected.

[0144] In one possible implementation, for example, the change confidence corresponding to each intersection in the first intersection set can be determined based on the first weight value of the first set of intersections to be selected, the third weight value of the third set of intersections to be selected, the updated confidence corresponding to each intersection in the first set of intersections to be selected in the first set of intersections to be selected, and the updated confidence corresponding to each intersection in the first set of intersections in the third set of intersections to be selected.

[0145] For example, you can combine Figure 8 The change confidence of the intersection t is understood by the following formula 1, wherein the change confidence can satisfy the following formula 1, for example:

[0146] Z(A t )=f(A1 t )×m1+g(A2 t )×n1 Formula 1

[0147] Among them, f(A1 t ) is the updated confidence of intersection t in the first candidate intersection set A1, g(A2 t) is the updated confidence corresponding to the intersection t in the third candidate intersection set A2, m1 is the first weight value of the first candidate intersection set, n1 is the third weight value of the third candidate intersection set, Z(A t ) is the change confidence of the intersection t in the first intersection set A. Wherein, the intersection t is an intersection in the first intersection set A.

[0148] It can be understood that, for any intersection t in the first intersection set, when the image recognition result of intersection t indicates that the traffic sign has changed, the trajectory flux will inevitably change as well. Therefore, the intersections in the first set of candidate intersections and the second set of candidate intersections are actually repeated. That is to say, for intersection t in the first set of candidate intersections, it exists in both the first set of candidate intersections A1 and the third set of candidate intersections A2.

[0149] However, for some special cases, for example, a certain intersection in the first set of intersections only exists in the first set of candidate intersections A1, but not in the third set of candidate intersections A2, then g(A2 t ) is equal to 0. Similarly, for example, if a certain intersection only exists in the third candidate intersection set A2, but not in the first candidate intersection set A1, then f(A1) in the above formula 1 is t ) is equal to 0.

[0150] In determining the change confidence Z(A t ) After that, for example, the change confidence Z(A t ) and the preset confidence. If the change confidence Z(A t ) is greater than or equal to the preset confidence, then, for example, the intersection t in the first intersection set can be determined as the target intersection. The above process is performed for each intersection in the first intersection set A, so that at least one target intersection can be determined to obtain a part of the target intersection. The part of the target intersection here refers to the target intersection where the traffic sign determined in the first intersection set has an updated one.

[0151] And in a possible implementation, before determining the change confidence corresponding to each intersection in the first intersection set, the intersections in the first intersection set can be filtered, for example, based on the updated confidence corresponding to each intersection in the first intersection set in the first set of candidate intersections, and the updated confidence corresponding to each intersection in the first intersection set in the third set of candidate intersections.

[0152] For example, for any intersection p in the first set of intersections, if the update confidence corresponding to intersection p in the first candidate set is less than the target threshold, and / or if the update confidence corresponding to intersection p in the third candidate set is less than the target threshold, then the intersection p can be ignored and no subsequent processing is performed. By filtering according to the update confidence, intersections with a low probability of update can be effectively filtered out, thereby saving subsequent data processing.

[0153] S311. Determine another part of the target intersections in the second intersection set based on the second weight value of the second intersection set to be selected, the fourth weight value of the fourth intersection set to be selected, the updated confidence corresponding to each intersection in the second intersection set in the second intersection set to be selected, and the updated confidence corresponding to each intersection in the second intersection set in the fourth intersection set to be selected.

[0154] In this embodiment, each candidate intersection in the second candidate intersection set has its own updated confidence, and each candidate intersection in the fourth candidate intersection set has its own updated confidence. The implementation of the updated confidence is similar to that described above and will not be repeated here.

[0155] Similarly, in this embodiment, the updated confidence corresponding to each intersection in the second intersection set in the second set of candidate intersections, as well as the updated confidence corresponding to each intersection in the second intersection set in the fourth set of candidate intersections can be determined. The implementation method is similar to that described above and will not be repeated here.

[0156] In this embodiment, another part of the target intersections in the second intersection set can be determined based on the second weight value of the second set of intersections to be selected, the fourth weight value of the fourth set of intersections to be selected, the corresponding updated confidence of each intersection in the second set of intersections to be selected, and the corresponding updated confidence of each intersection in the second set of intersections to be selected in the fourth set of intersections to be selected.

[0157] In one possible implementation, for example, the change confidence corresponding to each intersection in the second intersection set can be determined based on the second weight value of the second set of intersections to be selected, the fourth weight value of the fourth set of intersections to be selected, the updated confidence corresponding to each intersection in the second set of intersections to be selected, and the updated confidence corresponding to each intersection in the second set of intersections to be selected in the fourth set of intersections to be selected.

[0158] For example, you can combine Fig. 9 The change confidence of the intersection w can be understood by the following formula 2, where the change confidence can satisfy the following formula 2, for example:

[0159] Z(B w )=f(B1 w )×m2+g(B2w )×n2 Formula 1

[0160] Among them, f(B1 w ) is the updated confidence of the intersection w in the second candidate intersection set B1, g(B2 w ) is the updated confidence corresponding to the intersection w in the fourth candidate intersection set B2, m2 is the second weight value of the second candidate intersection set, n2 is the fourth weight value of the fourth candidate intersection set, Z(B w ) is the change confidence of the intersection w in the second intersection set B. Wherein, the intersection w is an intersection in the second intersection set B.

[0161] In determining the change confidence Z(B w ) After that, for example, the change confidence Z(B w ) and the preset confidence. If the change confidence Z(B w ) is greater than or equal to the preset confidence, then, for example, the intersection w in the second intersection set can be determined as the target intersection. The above process is performed for each intersection in the second intersection set B, so that at least one target intersection can be determined to obtain a part of the target intersection. The part of the target intersection here refers to the target intersection where the traffic sign determined in the second intersection set has an updated one.

[0162] And in a possible implementation, before determining the change confidence corresponding to each intersection in the second intersection set, the intersections in the second intersection set can be filtered, for example, based on the updated confidence corresponding to each intersection in the second intersection set in the second set of candidate intersections, and the updated confidence corresponding to each intersection in the second intersection set in the fourth set of candidate intersections.

[0163] For example, for any intersection q in the second intersection set, if the update confidence of intersection q in the second candidate set is less than the target threshold, and / or if the update confidence of intersection q in the fourth candidate set is less than the target threshold, then the intersection q can be ignored and no subsequent processing is performed. By filtering according to the update confidence, intersections with a low probability of update can be effectively filtered out, thereby saving subsequent data processing.

[0164] S312: Update the traffic sign of the target intersection in the first map data to obtain second map data.

[0165] After the target intersection is determined, it can be determined that the target intersection is an intersection where traffic signs need to be updated, and the traffic signs of the target intersection in the first map data can be updated to obtain the second map data.

[0166] In a possible implementation, for example, the target intersection can be input to an operator, who can review and update the map to obtain the second map data. Alternatively, the traffic sign of the target intersection can be updated based on the image recognition result of the intersection image corresponding to the target intersection to obtain the second map data. This embodiment does not limit the implementation method of updating the traffic sign of the target intersection, which can be selected and set according to actual needs.

[0167] And in this embodiment, after the second map data is updated, for example, a map display can be performed based on the second map data; or, the second map data can also be sent to a preset device, where the preset device can be, for example, a user's device, or it can also be an operator's device, and this embodiment does not impose any restrictions on this.

[0168] The map updating method provided by the embodiment of the present disclosure determines, for each intersection in a first intersection set including traffic signs, a first set of candidate intersections where traffic signs indicated by image recognition have been modified based on the recognition results of the intersection images and the traffic signs; and determines, based on the changes in the vehicle driving conditions at the intersections, a third set of candidate intersections where traffic signs indicated by vehicle driving data have been modified, and then merges the two sets, determines the change confidence of the changes in the intersections in the first intersection set based on the update confidence and weight values, thereby determining the target intersections where the traffic signs have been modified; and, for each intersection in a second intersection set that does not include traffic signs, determines, based on the recognition results of the intersection images and the traffic signs, a third set of candidate intersections where traffic signs indicated by image recognition have been modified. a second set of candidate intersections where new traffic signs have been added; and, based on changes in vehicle driving conditions at the intersections, determining a fourth set of candidate intersections where new traffic signs indicated by vehicle driving data have been added, and then fusing the two sets, determining the change confidence of changes in intersections in the second set of intersections based on update confidence and weight values, thereby determining the target intersections where new traffic signs have been added, and then updating the traffic signs at the target intersections, so that map data can be updated quickly and accurately. Because the above implementation integrates the intersections that need to be updated by determining the contents of image recognition and trajectory flux, it can effectively improve the recognition accuracy and recall rate of updated traffic signs, and thus effectively improve the update efficiency of maps.

[0169] Fig.10 FIG. 1 is a schematic diagram of the structure of a map updating device according to an embodiment of the present disclosure. Fig.10 As shown, the map updating device 1000 of this embodiment may include: a first acquisition module 1001 , a second acquisition module 1002 , a third acquisition module 1003 , and a processing module 1004 .

[0170] A first acquisition module 1001 is used to acquire first map data of a preset area, wherein the first map data includes current traffic signs at each intersection in the preset area;

[0171] The second acquisition module 1002 is used to acquire the intersection image obtained by photographing each intersection in the preset area;

[0172] The third acquisition module 1003 is used to acquire vehicle driving data corresponding to each intersection in the preset area, wherein the vehicle driving data includes: the number of vehicles traveling on each type of lane at the intersection in each unit time of the historical period;

[0173] The processing module 1004 is used to update the traffic signs at the intersection in the first map data according to the first map data, the intersection image and the vehicle driving data to obtain the second map data.

[0174] In a possible implementation, the processing module 1004 is specifically configured to:

[0175] Determining a target intersection among a plurality of intersections in the preset area according to the first map data, the intersection image and the vehicle driving data;

[0176] The traffic sign of the target intersection in the first map data is updated.

[0177] In a possible implementation, the processing module 1004 is specifically configured to:

[0178] Determine a first intersection set and a second intersection set from the plurality of intersections according to the current traffic sign of each intersection in the first map data, wherein the current traffic signs of the intersections in the first intersection set are not empty, and the current traffic signs of the intersections in the second intersection set are empty;

[0179] A target intersection is determined from among multiple intersections in the preset area according to current traffic signs at each intersection in the first intersection set, current traffic signs at each intersection in the second intersection set, the intersection image and the vehicle travel data.

[0180] In a possible implementation, the processing module 1004 is specifically configured to:

[0181] Determining a first set of to-be-selected intersections in the first set of intersections according to current traffic signs at each intersection in the first set of intersections and the intersection image;

[0182] Determining a second set of to-be-selected intersections in the second set of intersections according to current traffic signs at each intersection in the second set of intersections and the intersection image;

[0183] Determining a third set of to-be-selected intersections from the first set of intersections according to the vehicle travel data;

[0184] Determining a fourth set of to-be-selected intersections from the second set of intersections according to the vehicle travel data;

[0185] The target intersection is determined according to the first set of intersections to be selected, the second set of intersections to be selected, the third set of intersections to be selected, and the fourth set of intersections to be selected.

[0186] In a possible implementation, the processing module 1004 is specifically configured to:

[0187] Determining, according to the intersection image, a first traffic sign for each intersection in the first intersection set;

[0188] The first set of candidate intersections is determined in the first set of intersections according to the current traffic signs at each intersection in the first set of intersections and the first traffic signs corresponding to each intersection in the first set of intersections, wherein the first traffic signs at each intersection in the first set of candidate intersections are different from the current traffic signs.

[0189] In a possible implementation, the processing module 1004 is specifically configured to:

[0190] Determining, according to the intersection image, a first traffic sign for each intersection in the second intersection set;

[0191] The second set of to-be-selected intersections is determined in the second set of to-be-selected intersections according to the first traffic signs corresponding to the intersections in the second set of to-be-selected intersections, and the first traffic signs of the intersections in the second set of to-be-selected intersections are not empty.

[0192] In a possible implementation, the processing module 1004 is specifically configured to:

[0193] Determine, based on the vehicle driving data, a driving data change amount corresponding to each intersection in the first intersection set;

[0194] The third set of candidate intersections is determined in the first set of intersections according to the change in driving data corresponding to each intersection in the first set of intersections, and the change in driving data of each intersection in the third set of candidate intersections is greater than or equal to a preset change.

[0195] In a possible implementation, the processing module 1004 is specifically configured to:

[0196] The fourth set of candidate intersections is determined in the second set of candidate intersections according to the vehicle driving data corresponding to each intersection in the second set of candidate intersections, and the vehicle driving data of each intersection in the fourth set of candidate intersections is greater than or equal to a preset threshold.

[0197] In a possible implementation, the processing module 1004 is specifically configured to:

[0198] Obtaining a first weight value of the first set of intersections to be selected, a second weight value of the second set of intersections to be selected, a third weight value of the third set of intersections to be selected, and a fourth weight value of the fourth set of intersections to be selected;

[0199] According to the first weight value of the first set of candidate intersections, the third weight value of the third set of candidate intersections, the update confidence corresponding to each intersection in the first set of candidate intersections, and the update confidence corresponding to each intersection in the first set of candidate intersections in the third set of candidate intersections, a part of the target intersections is determined in the first set of candidate intersections, wherein the update confidence is the probability that the traffic signs in the candidate intersections are updated;

[0200] According to the second weight value of the second set of intersections to be selected, the fourth weight value of the fourth set of intersections to be selected, the updated confidence corresponding to each intersection in the second set of intersections to be selected, and the updated confidence corresponding to each intersection in the second set of intersections to be selected in the fourth set of intersections to be selected, another part of the target intersections in the second set of intersections is determined.

[0201] In a possible implementation, the processing module 1004 is further configured to:

[0202] After updating the traffic signs at the intersection in the first map data according to the first map data, the intersection image and the vehicle driving data to obtain the second map data, displaying the map according to the second map data; or sending the second map data to a preset device.

[0203] The present disclosure provides a map updating method and device, which are applied to the field of intelligent transportation in data processing to achieve the purpose of improving the updating efficiency of maps.

[0204] It should be noted that the head model in this embodiment is not a head model for a specific user and cannot reflect the personal information of a specific user. It should be noted that the two-dimensional face image in this embodiment comes from a public data set.

[0205] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0206] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0207] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0208] Fig.11 A schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0209] like Fig.11 As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0210] A number of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0211] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1101 performs the various methods and processes described above, such as a map update method. For example, in some embodiments, the map update method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the map update method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the map update method in any other appropriate manner (e.g., by means of firmware).

[0212] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0213] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0214] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0215] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0216] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0217] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0218] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0219] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A map updating method, comprising: Acquire first map data of a preset area, wherein the first map data includes current traffic signs at each intersection in the preset area; Acquire an intersection image obtained by photographing each intersection in the preset area, so as to determine the traffic signs at each intersection in the preset area according to the intersection image; Acquire vehicle driving data corresponding to each intersection in the preset area, the vehicle driving data including: the number of vehicles traveling on each type of lane in the intersection in each unit time of the historical period, so as to determine whether the traffic signs of each intersection are updated according to the changes of the vehicle driving data corresponding to each intersection in the preset area; According to the first map data, the intersection image and the vehicle driving data, the traffic signs at the intersections in the first map data are updated to obtain the second map data; wherein the intersection image and the vehicle driving data are used to determine the update confidence of the current traffic signs at each intersection in the preset area, and the update confidence is the probability of the traffic signs at each intersection being updated.

2. The method according to claim 1, wherein: The updating of the traffic sign at the intersection in the first map data according to the first map data, the intersection image and the vehicle driving data comprises: Determining a target intersection among a plurality of intersections in the preset area according to the first map data, the intersection image and the vehicle driving data; The traffic sign of the target intersection in the first map data is updated.

3. The method according to claim 2, wherein: The step of determining a target intersection among a plurality of intersections in the preset area according to the first map data, the intersection image and the vehicle driving data comprises: Determine a first intersection set and a second intersection set from the plurality of intersections according to the current traffic sign of each intersection in the first map data, wherein the current traffic signs of the intersections in the first intersection set are not empty, and the current traffic signs of the intersections in the second intersection set are empty; A target intersection is determined from among multiple intersections in the preset area according to current traffic signs at each intersection in the first intersection set, current traffic signs at each intersection in the second intersection set, the intersection image and the vehicle travel data.

4. The method according to claim 3, wherein: The determining of a target intersection among a plurality of intersections in the preset area according to the current traffic signs of each intersection in the first intersection set, the current traffic signs of each intersection in the second intersection set, the intersection image and the vehicle driving data comprises: Determining a first set of to-be-selected intersections in the first set of intersections according to current traffic signs at each intersection in the first set of intersections and the intersection image; Determining a second set of to-be-selected intersections in the second set of intersections according to current traffic signs at each intersection in the second set of intersections and the intersection image; Determining a third set of to-be-selected intersections from the first set of intersections according to the vehicle travel data; Determining a fourth set of to-be-selected intersections from the second set of intersections according to the vehicle travel data; The target intersection is determined according to the first set of intersections to be selected, the second set of intersections to be selected, the third set of intersections to be selected, and the fourth set of intersections to be selected.

5. The method according to claim 4, wherein: The step of determining a first set of to-be-selected intersections in the first set of intersections according to the current traffic signs of each intersection in the first set of intersections and the intersection image comprises: Determining, according to the intersection image, a first traffic sign for each intersection in the first intersection set; The first set of candidate intersections is determined in the first set of intersections according to the current traffic signs at each intersection in the first set of intersections and the first traffic signs corresponding to each intersection in the first set of intersections, wherein the first traffic signs at each intersection in the first set of candidate intersections are different from the current traffic signs.

6. The method according to claim 4, wherein: The determining a second set of to-be-selected intersections in the second set of intersections according to the current traffic signs of each intersection in the second set of intersections and the intersection image comprises: Determining, according to the intersection image, a first traffic sign for each intersection in the second intersection set; The second set of to-be-selected intersections is determined in the second set of to-be-selected intersections according to the first traffic signs corresponding to the intersections in the second set of to-be-selected intersections, and the first traffic signs of the intersections in the second set of to-be-selected intersections are not empty.

7. The method according to claim 4, wherein: The step of determining a third set of to-be-selected intersections from the first set of intersections according to the vehicle travel data comprises: Determine, based on the vehicle driving data, a driving data change amount corresponding to each intersection in the first intersection set; The third set of candidate intersections is determined in the first set of intersections according to the change in driving data corresponding to each intersection in the first set of intersections, and the change in driving data of each intersection in the third set of candidate intersections is greater than or equal to a preset change.

8. The method according to claim 4, wherein: The step of determining a fourth set of to-be-selected intersections from the second set of intersections according to the vehicle travel data comprises: The fourth set of candidate intersections is determined in the second set of candidate intersections according to the vehicle driving data corresponding to each intersection in the second set of candidate intersections, and the vehicle driving data of each intersection in the fourth set of candidate intersections is greater than or equal to a preset threshold.

9. The method according to any one of claims 4 to 8, wherein: The step of determining the target intersection according to the first set of to-be-selected intersections, the second set of to-be-selected intersections, the third set of to-be-selected intersections, and the fourth set of to-be-selected intersections includes: Obtaining a first weight value of the first set of intersections to be selected, a second weight value of the second set of intersections to be selected, a third weight value of the third set of intersections to be selected, and a fourth weight value of the fourth set of intersections to be selected; According to the first weight value of the first set of candidate intersections, the third weight value of the third set of candidate intersections, the update confidence corresponding to each intersection in the first set of candidate intersections, and the update confidence corresponding to each intersection in the first set of candidate intersections in the third set of candidate intersections, a part of the target intersections is determined in the first set of candidate intersections, wherein the update confidence is the probability that the traffic signs in the candidate intersections are updated; According to the second weight value of the second set of intersections to be selected, the fourth weight value of the fourth set of intersections to be selected, the updated confidence corresponding to each intersection in the second set of intersections to be selected, and the updated confidence corresponding to each intersection in the second set of intersections to be selected in the fourth set of intersections to be selected, another part of the target intersections in the second set of intersections is determined.

10. The method according to any one of claims 1 to 9, wherein: After the traffic signs at the intersection in the first map data are updated according to the first map data, the intersection image and the vehicle driving data to obtain the second map data, the method further includes: Displaying a map according to the second map data; or, The second map data is sent to a preset device.

11. A map updating device, comprising: A first acquisition module, used to acquire first map data of a preset area, wherein the first map data includes current traffic signs at each intersection in the preset area; A second acquisition module is used to acquire an intersection image obtained by photographing each intersection in the preset area, so as to determine the traffic signs of each intersection in the preset area according to the intersection image; A third acquisition module is used to acquire vehicle driving data corresponding to each intersection in the preset area, wherein the vehicle driving data includes: the number of vehicles traveling on each type of lane at the intersection in each unit time of the historical period, so as to determine whether the traffic signs at each intersection are updated according to the changes of the vehicle driving data corresponding to each intersection in the preset area; A processing module, used to update the traffic signs at the intersections in the first map data according to the first map data, the intersection image and the vehicle driving data, to obtain second map data; wherein the intersection image and the vehicle driving data are used to determine the update confidence of the current traffic signs at each intersection in the preset area, and the update confidence is the probability of the traffic signs at each intersection being updated.

12. The device according to claim 11, wherein The processing module is specifically used for: Determining a target intersection among a plurality of intersections in the preset area according to the first map data, the intersection image and the vehicle driving data; The traffic sign of the target intersection in the first map data is updated.

13. The device according to claim 12, wherein: The processing module is specifically used for: Determine a first intersection set and a second intersection set from the plurality of intersections according to the current traffic sign of each intersection in the first map data, wherein the current traffic signs of the intersections in the first intersection set are not empty, and the current traffic signs of the intersections in the second intersection set are empty; A target intersection is determined from among multiple intersections in the preset area according to current traffic signs at each intersection in the first intersection set, current traffic signs at each intersection in the second intersection set, the intersection image and the vehicle travel data.

14. The device according to claim 13, wherein: The processing module is specifically used for: Determining a first set of to-be-selected intersections in the first set of intersections according to current traffic signs at each intersection in the first set of intersections and the intersection image; Determining a second set of to-be-selected intersections in the second set of intersections according to current traffic signs at each intersection in the second set of intersections and the intersection image; Determining a third set of to-be-selected intersections from the first set of intersections according to the vehicle travel data; Determining a fourth set of to-be-selected intersections from the second set of intersections according to the vehicle travel data; The target intersection is determined according to the first set of intersections to be selected, the second set of intersections to be selected, the third set of intersections to be selected, and the fourth set of intersections to be selected.

15. The device according to claim 14, wherein: The processing module is specifically used for: Determining, according to the intersection image, a first traffic sign for each intersection in the first intersection set; The first set of candidate intersections is determined in the first set of intersections according to the current traffic signs at each intersection in the first set of intersections and the first traffic signs corresponding to each intersection in the first set of intersections, wherein the first traffic signs at each intersection in the first set of candidate intersections are different from the current traffic signs.

16. The device according to claim 14, wherein: The processing module is specifically used for: Determining, according to the intersection image, a first traffic sign for each intersection in the second intersection set; The second set of to-be-selected intersections is determined in the second set of to-be-selected intersections according to the first traffic signs corresponding to the intersections in the second set of to-be-selected intersections, and the first traffic signs of the intersections in the second set of to-be-selected intersections are not empty.

17. The device according to claim 14, wherein: The processing module is specifically used for: Determine, based on the vehicle driving data, a driving data change amount corresponding to each intersection in the first intersection set; The third set of candidate intersections is determined in the first set of intersections according to the change in driving data corresponding to each intersection in the first set of intersections, and the change in driving data of each intersection in the third set of candidate intersections is greater than or equal to a preset change.

18. The device according to claim 14, wherein: The processing module is specifically used for: The fourth set of candidate intersections is determined in the second set of candidate intersections according to the vehicle driving data corresponding to each intersection in the second set of candidate intersections, and the vehicle driving data of each intersection in the fourth set of candidate intersections is greater than or equal to a preset threshold.

19. The device according to any one of claims 14 to 18, wherein: The processing module is specifically used for: Obtaining a first weight value of the first set of intersections to be selected, a second weight value of the second set of intersections to be selected, a third weight value of the third set of intersections to be selected, and a fourth weight value of the fourth set of intersections to be selected; According to the first weight value of the first set of candidate intersections, the third weight value of the third set of candidate intersections, the update confidence corresponding to each intersection in the first set of candidate intersections, and the update confidence corresponding to each intersection in the first set of candidate intersections in the third set of candidate intersections, a part of the target intersections is determined in the first set of candidate intersections, wherein the update confidence is the probability that the traffic signs in the candidate intersections are updated; According to the second weight value of the second set of intersections to be selected, the fourth weight value of the fourth set of intersections to be selected, the updated confidence corresponding to each intersection in the second set of intersections to be selected, and the updated confidence corresponding to each intersection in the second set of intersections to be selected in the fourth set of intersections to be selected, another part of the target intersections in the second set of intersections is determined.

20. The device according to any one of claims 11 to 19, wherein: The processing module is also used for: After updating the traffic signs at the intersection in the first map data according to the first map data, the intersection image and the vehicle driving data to obtain the second map data, displaying the map according to the second map data; or sending the second map data to a preset device.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

Images