Map data testing method and device, electronic equipment and storage medium

Abstract

Embodiments of the present disclosure disclose a map data testing method and device, electronic equipment and a storage medium. The method comprises: obtaining target road data of a target road in at least one map data; based on the target road data, simulating a walking motion of a particle swarm on the target road by using a particle swarm algorithm, and not performing the walking motion again when a stop condition is met; wherein the walking direction of the particle swarm on the target road is related to the road direction of the target road; obtaining motion information of the particle swarm on the target road; and testing the target road data based on the motion information. This technical solution can quickly test problems existing in the target road data. In addition, the particle swarm is used for simulation, without additional labor cost and matching work of new and old maps, thereby saving the testing cost of map data.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, specifically to a map data testing method, apparatus, electronic device, and storage medium. Background Technology

[0002] Most map data is vector-based. To meet the need for rapid updates and iterations, map data needs to be evaluated, such as its topological relationships and completeness. Existing technologies, such as target evaluation and evaluation of newer, lower-precision maps based on existing, higher-precision maps, cannot meet the practical needs of rapid map data updates and iterations due to high evaluation costs, long cycles, and inability to evaluate the latest areas.

[0003] Therefore, there is a need to propose a map evaluation solution that is time-efficient and has fewer restrictions on both new and old maps. Summary of the Invention

[0004] This disclosure provides a map data testing method, apparatus, electronic device, and storage medium.

[0005] In a first aspect, this disclosure provides a map data testing method, which includes: Obtain target road data for the target road from at least one map dataset; Based on the target road data, the particle swarm algorithm is used to simulate the walking motion of the particle swarm on the target road, and the walking motion is stopped when the stopping condition is met; wherein, the walking direction of the particle swarm on the target road is related to the road travel direction of the target road; Obtain the motion information of the particle swarm on the target road; The target road data is tested based on the motion information.

[0006] Secondly, embodiments of the present invention provide a map data testing device, comprising: The first acquisition module is configured to acquire target road data of the target road in at least one map dataset. The walking simulation module is configured to simulate the walking motion of a particle swarm on the target road using a particle swarm algorithm based on the target road data, and to stop walking motion when a stopping condition is met; wherein, the walking direction of the particle swarm on the target road is related to the road travel direction of the target road; The second acquisition module is configured to acquire motion information of the particle swarm on the target road; The testing module is configured to test the target road data based on the motion information.

[0007] The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above function.

[0008] In one possible design, the above-described device includes a memory and a processor. The memory stores one or more computer instructions that support the device in performing the corresponding methods described above, and the processor is configured to execute the computer instructions stored in the memory. The device may also include a communication interface for communicating with other devices or communication networks.

[0009] Thirdly, embodiments of this disclosure provide an electronic device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in any of the above aspects.

[0010] Fourthly, embodiments of this disclosure provide a computer-readable storage medium for storing computer instructions used by any of the above-described devices, which, when executed by a processor, are used to implement the methods described in any of the above aspects.

[0011] Fifthly, embodiments of this disclosure provide a computer program product comprising computer instructions which, when executed by a processor, are used to implement the methods described in any of the preceding aspects.

[0012] The technical solutions provided in this disclosure may have the following beneficial effects: In this embodiment of the disclosure, when testing target road data, a particle swarm algorithm is used to simulate the movement of a particle swarm on the target road based on the target road data. The movement ceases when a stopping condition is met, and the movement information of the particle swarm on the target road is statistically obtained. The target road data is then tested based on this movement information. In this way, the particle swarm algorithm is used to simulate the movement of a particle swarm on the target road on the map. By statistically analyzing the movement characteristics of the particle swarm after its movement ends, problems in the target road data can be quickly identified. Furthermore, using particle swarm optimization for simulation eliminates the need for additional manual labor and matching between old and new maps, saving on map data testing costs.

[0013] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0014] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments, taken in conjunction with the accompanying drawings. In the drawings: Figure 1A flowchart illustrating a map data testing method according to an embodiment of the present disclosure is shown; Figure 2 A schematic diagram of a lane-level road according to an embodiment of the present disclosure is shown; Figure 3 Showing according to Figure 1 A flowchart of step S102 in the illustrated embodiment; Figure 4 A schematic diagram showing the effect of particle movement direction on a target road according to an embodiment of the present disclosure; Figure 5 This diagram illustrates the current position of each particle in a particle swarm on a target path at a certain moment, according to an embodiment of the present disclosure. Figures 6A-6B A schematic diagram showing the final aggregation position of the particle swarm on the target road in the target road data before and after the update according to an embodiment of the present disclosure; Figure 7 A structural block diagram of a map data testing apparatus according to an embodiment of the present disclosure is shown; Figure 8 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown; Figure 9 This is a schematic diagram of the structure of a computer system suitable for implementing a map data testing method according to an embodiment of the present disclosure. Detailed Implementation

[0015] In the following, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement them. Furthermore, for clarity, portions unrelated to the description of the exemplary embodiments have been omitted from the drawings.

[0016] In this disclosure, it should be understood that terms such as “comprising” or “having” are intended to indicate the presence of features, figures, steps, behaviors, components, parts or combinations thereof disclosed in this specification, and do not preclude the possibility of the presence or addition of one or more other features, figures, steps, behaviors, components, parts or combinations thereof.

[0017] It should also be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] The user information (including but not limited to user device information such as location information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals shall be provided for users to choose to authorize or refuse.

[0019] The details of the embodiments of this disclosure are described in detail below through specific examples.

[0020] Figure 1 A flowchart illustrating a map data testing method according to an embodiment of this disclosure is shown. Figure 1 As shown, the map data testing method includes the following steps: In step S101, at least one set of target road data for the target road in the map data is obtained; In step S102, based on the target road data, the particle swarm algorithm is used to simulate the walking motion of the particle swarm on the target road, and the walking motion is stopped when the stopping condition is met; wherein, the walking direction of the particle swarm on the target road is related to the road travel direction of the target road; In step S103, the motion information of the particle swarm on the target road is obtained; In step S104, the target road data is tested based on the motion information.

[0021] In this embodiment, the executing entity of the map data testing method can be a terminal device or a server. This map data testing method tests the target road data of a target road in the map data, aiming to expose potential problems in the map data so that relevant personnel can update the target road data to meet the needs of rapid map data updates and iterations. In some embodiments, this map data testing method can be used to test the target road data of a target road in a set of map data to evaluate the topological connectivity, map completeness, etc. This map data testing method can also be used to evaluate the differences between old and new map data. If the target road data for the same target road has been updated, this map data testing method can be used to test the target road data in the updated old and new map data to compare the differences before and after the target road update.

[0022] Map data, also known as vector maps, refers to digital maps that use points, lines, and polygons to depict key map elements such as lane lines, ground markings, road boundaries, and traffic signs / poles, and define the categories of each map element by editing its attributes.

[0023] Figure 2 A schematic diagram of a lane-level road according to an embodiment of the present disclosure is shown. Figure 2 As shown, the target road in the map data can be a lane-level road, defined by insurmountable road boundaries (represented by thick solid lines in the figure), insurmountable lane dividing lines (represented by thin solid lines in the figure), surmountable lane dividing lines (represented by dashed lines in the figure), and impassable lane ends (represented by road ends). In some embodiments, the target road in the map data can also be a road-level road, defined by insurmountable road boundaries and impassable lane ends. This embodiment only uses lane-level roads as an example for illustrative purposes; unless otherwise specified, the target road refers to a lane-level road. It is understood that the data testing method proposed in this embodiment is also applicable to the testing of road data for road-level roads.

[0024] In some embodiments, target road data may include, but is not limited to, the uncrossable road boundaries of the target road, the uncrossable solid lane dividing lines between different lanes of the target road, the crossable dashed lane dividing lines, and the impassable lane ends and / or road ends, as described above. Furthermore, the target road data may also include the road travel direction, such as... Figure 2 As shown by the middle arrow, in lane-level roads, the direction of travel can be the direction of travel of the lane, and the direction of travel of the road can indicate the direction of travel of the object.

[0025] The particle swarm optimization algorithm, also known as the random walk algorithm of particles, is applied to the test application of target road data in this embodiment. Unlike the classic particle swarm optimization algorithm, the walking direction of the particle swarm on the target road in this embodiment is not random, but related to the road travel direction of the target road, which can be directly obtained from the target road data.

[0026] In some embodiments, particles in a particle swarm cease movement if a stopping condition is met during their movement. In some embodiments, the stopping condition can be preset, including but not limited to: a particle reaching the end of a target road or lane, and / or any particle exceeding the map coverage area, and / or exceeding a preset movement time. Exceeding the map coverage area can be understood as the particle's location being outside the coverage area of ​​the target road data. This may occur when the map data does not depict the end of a road or lane, or when the road boundaries on the target road are not fully defined, causing the particle to exceed the coverage area of ​​the target road data. Furthermore, a preset particle movement time period can be established. Particles in the particle swarm can begin movement at random times within this time period, and after the end time of this time period, particles that have not yet stopped will cease movement.

[0027] By using the particle swarm optimization algorithm to simulate the movement of a swarm of particles on a target road, and stopping the movement when a stopping condition is met, the particles in the swarm simulate vehicles, thus simulating the process of a swarm of vehicles actually using the map, in order to expose problems with the map data.

[0028] In order to statistically analyze the motion information of the particle swarm on the target road after the particles cease their walking motion, the number of particles in the particle swarm needs to be large enough to be statistically significant. Then, the motion information of the particle swarm is correlated with the evaluation indicators of the target road data, and the target road data is evaluated based on the evaluation indicators of the target road data.

[0029] In some embodiments, motion information of particles on a target path can be obtained after the particles in the particle swarm cease their walking motion. This motion information may include, but is not limited to, the distribution of the number of steps taken by the particles in the particle swarm, the distribution of the movement directions of the particle swarm, the final aggregation position of the particles in the particle swarm, and the time when the particles in the particle swarm cease their movement.

[0030] In some embodiments, if the distribution of the number of steps of particles in the particle swarm is relatively stable, for example, if there are particles with few steps, a medium number of steps, and particles with many steps, and the proportion of particles with few steps, a medium number of steps, and particles with many steps is also in line with the norm, then the connectivity of the target road in the map data can be considered to be good. However, if the distribution of the number of steps of particles in the particle swarm is unstable, for example, most particles have few steps, only a small number of particles have medium or many steps, or there are no particles with medium or many steps, since the initial position of the particle swarm is a random position selected from the target road, having few steps means either reaching the end of the road after taking very few steps or encountering a dead end. If a large number of particles have this problem, then the connectivity of the target road in the map data can be considered to be abnormal, and further judgment is required.

[0031] In some embodiments, the distribution of particle movement directions in the particle swarm is usually consistent with the road travel direction on the map. By counting the number of particles whose particle movement direction differs from the road travel direction on the map, if the number of such particles exceeds a set threshold, it indicates that there may be abnormal turning points, forks, etc. in the target road.

[0032] In some embodiments, the final aggregation location of particles in a particle swarm is typically an impassable location, such as the end of a road, the end of a lane, and / or a location beyond the map's coverage area. By statistically analyzing this final aggregation location, it can be determined whether the particle aggregation location is reasonable, i.e., whether it is the actual end of the target road and / or the actual end of a lane. The final aggregation location can also be used to evaluate the rationality of the topological relationship of the target road before and after the update in the old and new maps. By comparing the differences in the final aggregation locations of the particle swarm in the old and new maps, the area where the target road has changed in the old and new maps can be determined. For example, by counting the number of particles within this changed area, if the number of particles exceeds a threshold, it can be considered that the proportion of impassable parts in the target road is large, and the topological relationship of the target road is unreasonable.

[0033] In some embodiments, the end-movement time of particles in a particle swarm can be used to evaluate the complexity of the target road before and after updating the old and new maps. For example, by comparing the end-movement times of particles in the particle swarm in the old and new maps, a longer end-movement time indicates a more complex target road. For instance, by simulating the movement of a particle swarm on a target road in two map datasets according to the method described in this embodiment, after the movement ends, the end-movement time of the particle swarm in the two map datasets can be counted. If the average end-movement time of the particle swarm in one map dataset is much longer than that in the other map dataset, it can be preliminarily determined that the target roads in the two map datasets are different in length. One possibility is that the target road in the map dataset with the longer average end-movement time may be longer than the target road in the other map dataset. Another possibility is that the target road in the map dataset with the shorter average end-movement time has a break in the road at some point, thus requiring further judgment. However, if the average end-movement times of the particle swarm on the target road in the two map datasets are not significantly different, it can be determined that there is no difference between the target roads in the two map datasets, and no further judgment is required.

[0034] In this embodiment of the disclosure, when testing target road data, a particle swarm algorithm is used to simulate the movement of a particle swarm on the target road based on the target road data. The movement ceases when a stopping condition is met, and the movement information of the particle swarm on the target road is statistically obtained. The target road data is then tested based on this movement information. In this way, the particle swarm algorithm is used to simulate the movement of a particle swarm on the target road on the map. By statistically analyzing the movement characteristics of the particle swarm after its movement ends, problems in the target road data can be quickly identified. Furthermore, using particle swarm optimization for simulation eliminates the need for additional manual labor and matching between old and new maps, saving on map data testing costs.

[0035] In an optional implementation of this embodiment, the initial position of the particle swarm as it travels on the target road is a random position on the target road.

[0036] In this optional implementation, the particle swarm optimization algorithm itself possesses statistical characteristics, reflected in the randomness of particle movement. Based on target road data, the particle swarm optimization algorithm is used to simulate vehicle movement on the target road. Particles simulate vehicles, and parameters such as the total number of particles, their initial positions, and their step length can be set. All particles are scattered onto the target road at the same time or at different times within a set time period. The initial position of a particle on the target road can be a random position on the target road to better reflect the actual vehicle situation on a real road. The step length of a particle can be a random step length, and a range of step lengths can be preset for this range. It should be noted that for each step a particle takes, a random step length can be selected from the range as the step length for the next movement. It can be understood that the initial position of a particle is a random position on the target road, while the next position is determined based on the next movement direction and the random step length.

[0037] In one optional implementation of this embodiment, such as Figure 3 As shown, step S102, which is the step of simulating the movement of a particle swarm on the target road using the particle swarm algorithm based on the target road data, and ceasing the movement when the stopping condition is met, further includes the following steps: In step S301, the road travel direction corresponding to the current position of the particles in the particle swarm on the target road is obtained from the target road data; In step S302, the next travel direction of the particle is determined within a preset angle range where the road travel direction is located; In step S303, the next position to which the particle will move is determined based on the current position and the next moving direction; In step S304, after setting the next position as the current position, proceed to step S301 and continue execution until the stop condition is met.

[0038] In this optional implementation, the direction of travel on the target road can include the direction of travel corresponding to different positions on the target road. To ensure that the particles travel on the target road, the direction of each particle's movement can be randomly selected within a preset angle range corresponding to the direction of travel on the road at the particle's current position. That is, the randomness of the particle's movement is reflected by the randomness of the direction of each step during the particle's movement. At the same time, the particles will not go beyond the target road and will always stay on the target road. In this way, when the particle meets the stopping condition, it will no longer perform walking motion. The statistical distribution of the particle movement directions can reflect the possible abnormal turning points, forks, etc. on the target road. In some embodiments, the preset angle range can be set such that the current position and the next position of the particle are not opposite to the direction of travel on the road. For example, the preset angle range can be an angle range less than ±90 degrees. This disclosure does not limit this.

[0039] Figure 4 A schematic diagram illustrating the effect of particle movement direction on a target road according to an embodiment of the present disclosure is shown. Figure 4 As shown, the particle's current position is at the gray dot. The direction of travel on the road at the current position is as indicated by the arrow. The next direction of travel can be any random direction within an angle α to the left or right of the direction of travel on the road indicated by the arrow. After the particle moves to the next position, it takes the next position as its current position and selects any random direction within an angle α to the left or right of the direction of travel on the road at the new current position as its next direction of travel. The particle continues to move until the stopping condition is met, at which point it stops moving.

[0040] In an optional implementation of this embodiment, the step of determining the next position to which the particle will move based on the current position and the next moving direction further includes the following steps: Get the random walking step length; The next candidate position is determined based on the current position, the next walking direction, and the random walking step size; If the next candidate position does not exceed the target road range in the target road data, then the next candidate position is determined as the next position to which the particle travels.

[0041] In this optional implementation, the next position a particle moves from its current position should not exceed the range of the target road. If it does, the motion information of this part of the particle will not play an effective role in the test results of this disclosure, but will instead generate noise and affect the accuracy of the test results.

[0042] Therefore, we can first determine the possible next candidate position based on the parameters of the current position, the next walking direction, and the random walking step size. Then, we determine whether the determined next candidate position exceeds the target road range. If it does not exceed the target road range, we determine it as the next position for the particle to walk. This process is repeated until the particle meets the stopping condition and stops walking.

[0043] In some embodiments, the target road range includes the area within the solid lane lines and the area within the road boundary lines of the target road. The area within the solid lane lines can be understood as follows: when the target road includes solid lane lines, the line connecting the particle's current position and its next position should not intersect with the solid lane lines. Similarly, the area within the road boundary lines can be understood as follows: the line connecting the particle's current position and its next position should not intersect with the road boundary lines of the target road.

[0044] Within the range of the solid lane lines and the road boundary lines of the target road, the particle can move. Therefore, if the next candidate position obtained based on the current position, the next direction of movement, and the random step size falls within the above range, the next candidate position can be determined as the next position to which the particle moves.

[0045] Accordingly, particles cannot move outside the solid lane lines and road boundary lines of the target road. Therefore, if the next candidate position obtained based on the current position, the next direction of movement, and the random step size falls outside the above range, the next candidate position cannot be used as the next position to which the particle moves, and the next position needs to be recalculated.

[0046] In other embodiments, there may be special cases where map data is not created or the end of the target road is not created. In such cases, it can be determined whether the next candidate position exceeds the target road range by judging whether there are lane lines or road boundary lines of the target road on both sides. If it is determined in this way that the next candidate position exceeds the target road range, then the next candidate position cannot be used as the next position for the particle to move to. The next position can be re-determined by shortening the random step size and / or changing the next movement direction.

[0047] In an optional implementation of this embodiment, the method further includes the following steps: If the next candidate location is outside the target road range, then the next walking direction and / or the random walking step size are re-determined; Based on the redefined next walking direction and / or the random walking step length, the next position to be reached will be determined to be within the target road range.

[0048] In this optional implementation, if the next candidate location is outside the target road range, the next walking direction can be redefined, and the next location can be determined within the target road range based on the current location and the redefined next walking direction.

[0049] For example, the next walking direction can be randomly selected again, and the next candidate position can be recalculated based on the newly selected next walking direction. If the next candidate position is still outside the target road range, the above steps of randomly selecting the next walking direction can be repeated until the next candidate position is within the target road range, and then the next candidate position is determined as the next position.

[0050] For example, the next walking direction can be updated by reducing the angle between the current next walking direction and the road travel direction at the current position, and the next candidate position can be recalculated. If the next candidate position is still outside the target road range, the above steps of reducing the next walking direction can be repeated until the next candidate position is within the target road range, and then the next candidate position is determined as the next position.

[0051] In other embodiments, the random walking step length can be regenerated. If the next candidate position recalculated based on the current position and the regenerated random walking step length is still outside the target road range, the above steps of randomly generating the walking step length can be repeated until the next candidate position falls within the target road range.

[0052] In some embodiments, the next walking direction and random walking step length can be updated by re-determining the next walking direction and random walking step length as mentioned above, and the next candidate position can be determined based on the updated next walking direction and random walking step length. If the next candidate position is still outside the target road range, the above steps of re-determining the next walking direction and random walking step length can be repeated until the next candidate position falls within the target road range.

[0053] In an optional implementation of this embodiment, the method further includes the following steps: If the next candidate position is outside the target road range, the random walking step size is re-determined so that the random walking step size is less than the distance from the current position along the next walking direction to the boundary of the target road range; The next position is determined based on the redefined random walk step size.

[0054] In this optional implementation, if the next candidate position exceeds the target road range, the random walking step size can be redefined. This redefined random walking step size can be less than the distance from the current position to the boundary of the target road range. The boundary of the target road range can be a solid lane line or a boundary lane line intersecting the line connecting the current position and the next candidate position. It should be noted that when redefined, the distance from the current position to the boundary of the target road range can be calculated first, and the new random walking step size can be set to a value less than that distance. The next candidate position determined based on this redefined random walking step size should be within the target road range and can then be used as the next position the particle moves to.

[0055] In an optional implementation of this embodiment, step S104, namely the step of testing the target road data based on the motion information, further includes the following steps: The target road data corresponding to the target road itself is tested based on the motion information of the particle swarm on the target road in the same map data; Based on the motion information of particle swarms associated with the target road in different map data, the differences in the target road data corresponding to the target road are tested.

[0056] In this optional implementation, the target road data can come from an updated map dataset. Using the method described in this embodiment, a swarm of particles can be scattered onto the target road in the map dataset. The scattered particles can move along the target road according to the above method and cease moving when a stopping condition is met. Subsequently, the target road data in the map dataset can be tested based on the movement information of the particle swarm on the target road, such as the distribution of the number of steps taken by the particles, the distribution of the movement direction of the particles, and the final aggregation position of the particles, to evaluate the update effect of the new map data.

[0057] In some embodiments, testing the target road data based on the movement step distribution of particles in the particle swarm involves comparing the test results with the movement step distribution of particles in the particle swarm of a target road with normal topological connectivity. For target roads with normal topological connectivity, the movement step distribution of particles in the particle swarm is relatively stable. For example, the particle swarm contains particles with few steps, particles with a medium number of steps, and particles with a large number of steps, and the proportion of these particles is also consistent with normal conditions. If the movement step distribution of particles in the particle swarm is unstable in the test results, such as most particles having few steps, only a small number of particles having medium or large numbers of steps, or even no particles having medium or large numbers of steps, since the initial position of the particle swarm is a random position selected from the target road, a few steps either means that the particle has reached the end of the road after taking very few steps or encountered a dead end. If a large number of particles exhibit this problem, it can be considered that the connectivity of the target road in the new map data is abnormal, and further judgment is required.

[0058] In some embodiments, testing the target road data based on the distribution of particle swarm movement directions involves counting the number of particles in the map whose movement direction differs from the road's direction of travel. If the number of such particles exceeds a set threshold, it indicates that there may be abnormal turning points, forks, etc., in the target road in the new map data.

[0059] In some embodiments, testing the target road data based on the final aggregation position of particles in the particle swarm involves comparing the test results of the final aggregation position of particles with the impassable road ends or lane ends in the target road data. If there are particle aggregation positions other than the road ends or lane ends, the particle data is further counted. If the number of particles exceeds a set threshold, it indicates that the topological relationship of the target road in the new map data is unreasonable.

[0060] In addition, the differences in target road data of related target roads in two or more sets of new and old map data can be tested to evaluate the effectiveness of the new map data update.

[0061] In some embodiments, the area where the target road has changed in the new and old maps is determined by comparing the differences in the final aggregation positions of particle swarms in the new and old maps. For example, the number of particles in this changed area is counted. If the number of particles exceeds a threshold, it can be considered that the proportion of impassable parts in the target road is large, indicating that the topological relationship of the target road in the new map data is unreasonable.

[0062] In an optional implementation of this embodiment, the differences between different target road data corresponding to the target road are tested based on the motion information of particle groups associated with the target road in different map data, including at least one of the following: Based on the motion duration of the particle swarm in the motion information, the differences in complexity of the different map data are compared; Based on the distribution of the number of movement steps of the particle swarm in the motion information, it is determined whether the road connectivity in the different map data is consistent. Based on the motion direction characteristics of the particle swarm in the motion information, it is determined whether the road direction of the target road in the different map data is consistent; Based on the aggregation position of the particle swarm in the motion information, it is determined whether the end of the target road is consistent in the different map data.

[0063] In this optional implementation, by comparing the completion times of particles in the particle swarm in different map data, if the completion time of particles in the new map is longer, it indicates that the target road in the new map data is more complex, and the new map data has an updating effect. For example, according to the method in this embodiment, the movement of particle swarms on the target road is simulated in two map data. After the movement ends, the completion time of particle swarms in the two map data can be counted. If the average completion time of particle swarms in one map data is much longer than that in the other map data, it can be preliminarily determined that the target roads in the two map data are different in length. One possibility is that the target road in the map data with the longer average completion time may be longer than the target road in the other map data, that is, the complexity of the map data is greater than that of the other map data. Another possibility is that the target road in the map data with the shorter average completion time has a break in the road, so further judgment is needed. However, if the average completion time of particle swarms on the target road in the two map data is not much different, it can be determined that there is no difference between the target roads in the two map data, and no further judgment is needed.

[0064] In some embodiments, the consistency of road connectivity in different map data can also be determined based on the distribution of movement steps of particle swarms in motion information. As mentioned above, if the movement step distribution of most particles in the map data is stable, for example, the number of particles with few, medium, and many steps is relatively even, or the number of particles with few, medium, and many steps in the two map data is not significantly different, then the road connectivity of the different map data can be determined to be relatively consistent; otherwise, the road connectivity of the different map data can be determined to be inconsistent.

[0065] In some embodiments, the movement direction of the particle swarm is normally consistent with the direction of travel of the road in the map data. For example, if the direction of travel of the target road in one map data is north-south, then the distribution of the movement direction of the particle swarm should also be north-south. If the movement direction of some particles is abnormal, it can be considered that the target road in the map data has an abnormal turning point or fork. By comparing the movement direction of most particles in two map data, it can also be determined whether the road direction of the target road in the two map data is consistent.

[0066] In some embodiments, based on the aggregation positions of the particle swarm in the motion information, it can also be determined whether the ends of the target roads are consistent in different map data. Normally, after the particle swarm finishes its motion, most particles will aggregate at the end of the target road. If the aggregation positions of most particles on the target road are inconsistent in the two sets of map data, then the ends of the target roads can be considered inconsistent.

[0067] The threshold values ​​mentioned above can be set according to actual statistical needs, and this disclosure does not limit them.

[0068] Figure 5 This diagram illustrates the current position of each particle in a particle swarm on a target path at a certain moment, according to an embodiment of the present disclosure. Figure 5 As shown, each gray dot represents a particle, and the meaning of the lines in the diagram can be found by referring to... Figure 2 As shown, thick solid lines represent road boundaries that particles cannot cross, thin solid lines represent lane dividing lines that particles cannot cross, dashed lines represent lane dividing lines that particles can cross, and the ends of the road represent the ends of lanes that are impassable. Figure 5 The diagram shows two target paths. The scattered particles travel in the direction indicated by the arrows in the diagram, from... Figure 5 It can be seen that particles in the particle swarm can be at any position on the target road at any time, and their positions are random, but they do not exceed the coverage area of ​​the target road.

[0069] Figures 6A-6B This diagram illustrates the final aggregation positions of particle swarms on a target road in target road data before and after an update, according to an embodiment of this disclosure. By comparison... Figure 6A and Figure 6B The final aggregation position of each particle in the swarm can be determined. Figure 6B In the updated target road data shown, the end of one of the target roads is... Figure 6A The location of the end of the target road before the update is different. The location of the end of the target road after the update is farther away. In other words, the target road has been lengthened compared to before the update.

[0070] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein.

[0071] Figure 7 A structural block diagram of a map data testing apparatus according to an embodiment of the present disclosure is shown. This apparatus can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 7 As shown, the map data testing device includes: The first acquisition module 701 is configured to acquire target road data of the target road in at least one piece of map data; The walking simulation module 702 is configured to simulate the walking motion of a particle swarm on the target road using a particle swarm algorithm based on the target road data, and to stop walking motion when a stopping condition is met; wherein, the walking direction of the particle swarm on the target road is related to the road travel direction of the target road; The second acquisition module 703 is configured to acquire motion information of the particle swarm on the target road; Test module 704 is configured to test the target road data based on the motion information.

[0072] In this embodiment, the map data testing device tests the target road data of a target road in the map data. The purpose is to expose potential problems in the map data so that relevant personnel can update the target road data to meet the needs of rapid map data updates and iterations. In some embodiments, the map data testing device can be used to test the target road data of a target road in a set of map data to evaluate the topological connectivity, map completeness, etc. The map data testing device can also be used to evaluate the differences between old and new map data. If the target road data for the same target road has been updated, the map data testing device can be used to test the target road data in the updated old and new map data to compare the differences before and after the target road update.

[0073] Map data, also known as vector maps, refers to digital maps that use points, lines, and polygons to depict key map elements such as lane lines, ground markings, road boundaries, and traffic signs / poles, and define the categories of each map element by editing its attributes.

[0074] The target road in the map data can be a lane-level road, defined by insurmountable road boundaries, insurmountable solid lane dividers, traversable dashed lane dividers, and impassable lane ends. In some embodiments, the target road in the map data can also be a road-level road, defined by insurmountable road boundaries and impassable lane ends. This embodiment only uses a lane-level road as an example for illustrative purposes; unless otherwise specified, the target road refers to a lane-level road. It is understood that the data testing device proposed in this embodiment is also applicable to testing road data of road-level roads.

[0075] In some embodiments, target road data may include, but is not limited to, the uncrossable road boundaries of the target road, the uncrossable solid lane dividing lines of different lanes of the target road, the crossable dashed lane dividing lines, and the impassable lane ends and / or road ends, etc., as described above. In addition, target road data may also include road travel direction, which may be the lane travel direction in lane-level roads, and the road travel direction may represent the travel direction of the driving object.

[0076] The particle swarm optimization algorithm, also known as the random walk algorithm of particles, is applied to the test application of target road data in this embodiment. Unlike the classic particle swarm optimization algorithm, the walking direction of the particle swarm on the target road in this embodiment is not random, but related to the road travel direction of the target road, which can be directly obtained from the target road data.

[0077] In some embodiments, particles in a particle swarm cease movement if a stopping condition is met during their movement. In some embodiments, the stopping condition can be preset, including but not limited to: a particle reaching the end of a target road or lane, and / or any particle exceeding the map coverage area, and / or exceeding a preset movement time. Exceeding the map coverage area can be understood as the particle's location being outside the coverage area of ​​the target road data. This may occur when the map data does not depict the end of a road or lane, or when the road boundaries on the target road are not fully defined, causing the particle to exceed the coverage area of ​​the target road data. Furthermore, a preset particle movement time period can be established. Particles in the particle swarm can begin movement at random times within this time period, and after the end time of this time period, particles that have not yet stopped will cease movement.

[0078] By using the particle swarm optimization algorithm to simulate the movement of a swarm of particles on a target road, and stopping the movement when a stopping condition is met, the particles in the swarm simulate vehicles, thus simulating the process of a swarm of vehicles actually using the map, in order to expose problems with the map data.

[0079] In order to statistically analyze the motion information of the particle swarm on the target road after the particles cease their walking motion, the number of particles in the particle swarm needs to be large enough to be statistically significant. Then, the motion information of the particle swarm is correlated with the evaluation indicators of the target road data, and the target road data is evaluated based on the evaluation indicators of the target road data.

[0080] In some embodiments, motion information of particles on a target path can be obtained after the particles in the particle swarm cease their walking motion. This motion information may include, but is not limited to, the distribution of the number of steps taken by the particles in the particle swarm, the distribution of the movement directions of the particle swarm, the final aggregation position of the particles in the particle swarm, and the time when the particles in the particle swarm cease their movement.

[0081] In some embodiments, if the distribution of the number of steps of particles in the particle swarm is relatively stable, for example, if there are particles with few steps, a medium number of steps, and particles with many steps, and the proportion of particles with few steps, a medium number of steps, and particles with many steps is also in line with the norm, then the connectivity of the target road in the map data can be considered to be good. However, if the distribution of the number of steps of particles in the particle swarm is unstable, for example, most particles have few steps, only a small number of particles have medium or many steps, or there are no particles with medium or many steps, since the initial position of the particle swarm is a random position selected from the target road, having few steps means either reaching the end of the road after taking very few steps or encountering a dead end. If a large number of particles have this problem, then the connectivity of the target road in the map data can be considered to be abnormal, and further judgment is required.

[0082] In some embodiments, the distribution of particle movement directions in the particle swarm is usually consistent with the road travel direction on the map. By counting the number of particles whose particle movement direction differs from the road travel direction on the map, if the number of such particles exceeds a set threshold, it indicates that there may be abnormal turning points, forks, etc. in the target road.

[0083] In some embodiments, the final aggregation location of particles in a particle swarm is typically an impassable location, such as the end of a road, the end of a lane, and / or a location beyond the map's coverage area. By statistically analyzing this final aggregation location, it can be determined whether the particle aggregation location is reasonable, i.e., whether it is the actual end of the target road and / or the actual end of a lane. The final aggregation location can also be used to evaluate the rationality of the topological relationship of the target road before and after the update in the old and new maps. By comparing the differences in the final aggregation locations of the particle swarm in the old and new maps, the area where the target road has changed in the old and new maps can be determined. For example, by counting the number of particles within this changed area, if the number of particles exceeds a threshold, it can be considered that the proportion of impassable parts in the target road is large, and the topological relationship of the target road is unreasonable.

[0084] In some embodiments, the end-movement time of particles in a particle swarm can be used to evaluate the complexity of the target road before and after updating the old and new maps. For example, by comparing the end-movement times of particles in the particle swarm in the old and new maps, a longer end-movement time indicates a more complex target road. For instance, by simulating the movement of a particle swarm on a target road in two map datasets according to the method described in this embodiment, after the movement ends, the end-movement time of the particle swarm in the two map datasets can be counted. If the average end-movement time of the particle swarm in one map dataset is much longer than that in the other map dataset, it can be preliminarily determined that the target roads in the two map datasets are different in length. One possibility is that the target road in the map dataset with the longer average end-movement time may be longer than the target road in the other map dataset. Another possibility is that the target road in the map dataset with the shorter average end-movement time has a break in the road at some point, thus requiring further judgment. However, if the average end-movement times of the particle swarm on the target road in the two map datasets are not significantly different, it can be determined that there is no difference between the target roads in the two map datasets, and no further judgment is required.

[0085] In this embodiment of the disclosure, when testing target road data, a particle swarm algorithm is used to simulate the movement of a particle swarm on the target road based on the target road data. The movement ceases when a stopping condition is met, and the movement information of the particle swarm on the target road is statistically obtained. The target road data is then tested based on this movement information. In this way, the particle swarm algorithm is used to simulate the movement of a particle swarm on the target road on the map. By statistically analyzing the movement characteristics of the particle swarm after its movement ends, problems in the target road data can be quickly identified. Furthermore, using particle swarm optimization for simulation eliminates the need for additional manual labor and matching between old and new maps, saving on map data testing costs.

[0086] In an optional implementation of this embodiment, the initial position of the particle swarm as it travels on the target road is a random position on the target road.

[0087] In this optional implementation, the particle swarm optimization algorithm itself possesses statistical characteristics, reflected in the randomness of particle movement. Based on target road data, the particle swarm optimization algorithm is used to simulate vehicle movement on the target road. Particles simulate vehicles, and parameters such as the total number of particles, their initial positions, and their step lengths can be set. All particles are scattered onto the target road at the same time or at different times within a set time period. The initial position of a particle on the target road can be a random position to better reflect the actual vehicle situation on a road. The step length of a particle can be random, and a range of step lengths can be preset, from which random step lengths can be obtained. It should be noted that for each step a particle takes, a random step length can be selected from the range as the step length for the next movement. It can be understood that the initial position of a particle is a random position on the target road, while the next position is determined based on the next movement direction and the random step length.

[0088] In an optional implementation of this embodiment, the walking simulation module includes: The first acquisition submodule is configured to acquire the road travel direction corresponding to the current position of the particles in the particle swarm on the target road from the target road data; The first determining submodule is configured to determine the next travel direction of the particle within a preset angle range of the road travel direction; The second determining submodule is configured to determine the next position to which the particle will move based on the current position and the next moving direction; The second acquisition submodule is configured to take the next position as the current position and then transfer to the first acquisition submodule to continue execution until the stop condition is met.

[0089] In this optional implementation, the direction of travel on the target road can include the direction of travel corresponding to different positions on the target road. To ensure that the particles travel on the target road, the direction of each particle's movement can be randomly selected within a preset angle range corresponding to the direction of travel on the road at the particle's current position. That is, the randomness of the particle's movement is reflected by the randomness of the direction of each step during the particle's movement. At the same time, the particles will not go beyond the target road and will always stay on the target road. In this way, when the particle meets the stopping condition, it will no longer perform walking motion. The statistical distribution of the particle movement directions can reflect the possible abnormal turning points, forks, etc. on the target road. In some embodiments, the preset angle range can be set such that the current position and the next position of the particle are not opposite to the direction of travel on the road. For example, the preset angle range can be an angle range less than ±90 degrees. This disclosure does not limit this.

[0090] In an optional implementation of this embodiment, the second determining submodule includes: The third acquisition submodule is configured to acquire random walking step length; The third determination submodule is configured to determine the next candidate position based on the current position, the next walking direction, and the random walking step size; The fourth determination submodule is configured to determine the next candidate position as the next position to which the particle travels if the next candidate position does not exceed the target road range in the target road data.

[0091] In this optional implementation, the next position a particle moves from its current position should not exceed the range of the target road. If it does, the motion information of this part of the particle will not play an effective role in the test results of this disclosure, but will instead generate noise and affect the accuracy of the test results.

[0092] Therefore, we can first determine the possible next candidate position based on the parameters of the current position, the next walking direction, and the random walking step size. Then, we determine whether the determined next candidate position exceeds the target road range. If it does not exceed the target road range, we determine it as the next position for the particle to walk. This process is repeated until the particle meets the stopping condition and stops walking.

[0093] In some embodiments, the target road range includes the area within the solid lane lines and the area within the road boundary lines of the target road. The area within the solid lane lines can be understood as follows: when the target road includes solid lane lines, the line connecting the particle's current position and its next position should not intersect with the solid lane lines. Similarly, the area within the road boundary lines can be understood as follows: the line connecting the particle's current position and its next position should not intersect with the road boundary lines of the target road.

[0094] Within the range of the solid lane lines and the road boundary lines of the target road, the particle can move. Therefore, if the next candidate position obtained based on the current position, the next direction of movement, and the random step size falls within the above range, the next candidate position can be determined as the next position to which the particle moves.

[0095] Accordingly, particles cannot move outside the solid lane lines and road boundary lines of the target road. Therefore, if the next candidate position obtained based on the current position, the next direction of movement, and the random step size falls outside the above range, the next candidate position cannot be used as the next position to which the particle moves, and the next position needs to be recalculated.

[0096] In other embodiments, there may be special cases where map data is not created or the end of the target road is not created. In such cases, it can be determined whether the next candidate position exceeds the target road range by judging whether there are lane lines or road boundary lines of the target road on both sides. If it is determined in this way that the next candidate position exceeds the target road range, then the next candidate position cannot be used as the next position for the particle to move to. The next position can be re-determined by shortening the random step size and / or changing the next movement direction.

[0097] In an optional implementation of this embodiment, the apparatus further includes: The first determining module is configured to redetermine the next walking direction and / or the random walking step size if the next candidate position exceeds the target road range; The second determining module is configured to determine the next position reached by walking within the target road range based on the re-determined next walking direction and / or the random walking step length.

[0098] In this optional implementation, if the next candidate location is outside the target road range, the next walking direction can be redefined, and the next location can be determined within the target road range based on the current location and the redefined next walking direction.

[0099] For example, the next walking direction can be randomly selected again, and the next candidate position can be recalculated based on the newly selected next walking direction. If the next candidate position is still outside the target road range, the above steps of randomly selecting the next walking direction can be repeated until the next candidate position is within the target road range, and then the next candidate position is determined as the next position.

[0100] For example, the next walking direction can be updated by reducing the angle between the current next walking direction and the road travel direction at the current position, and the next candidate position can be recalculated. If the next candidate position is still outside the target road range, the above steps of reducing the next walking direction can be repeated until the next candidate position is within the target road range, and then the next candidate position is determined as the next position.

[0101] In other embodiments, the random walking step length can be regenerated. If the next candidate position recalculated based on the current position and the regenerated random walking step length is still outside the target road range, the above steps of randomly generating the walking step length can be repeated until the next candidate position falls within the target road range.

[0102] In some embodiments, the next walking direction and random walking step length can be updated by re-determining the next walking direction and random walking step length as mentioned above, and the next candidate position can be determined based on the updated next walking direction and random walking step length. If the next candidate position is still outside the target road range, the above steps of re-determining the next walking direction and random walking step length can be repeated until the next candidate position falls within the target road range.

[0103] In an optional implementation of this embodiment, the apparatus further includes: The third determining module is configured to redetermine the random walking step size if the next candidate position exceeds the target road range, such that the random walking step size is less than the distance from the current position along the next walking direction to the boundary of the target road range; The fourth determining module is configured to determine the next position based on the redefined random walking step size.

[0104] In this optional implementation, if the next candidate position exceeds the target road range, the random walking step size can be redefined. This redefined random walking step size can be less than the distance from the current position to the boundary of the target road range. The boundary of the target road range can be a solid lane line or a boundary lane line intersecting the line connecting the current position and the next candidate position. It should be noted that when redefined, the distance from the current position to the boundary of the target road range can be calculated first, and the new random walking step size can be set to a value less than that distance. The next candidate position determined based on this redefined random walking step size should be within the target road range and can then be used as the next position the particle moves to.

[0105] In an optional implementation of this embodiment, the test module includes: The first test submodule is configured to test the target road data corresponding to the target road itself based on the motion information of the particle group on the target road in the same map data; The second testing submodule is configured to test the differences between different target road data corresponding to the target road based on the motion information of particle groups associated with the target road in different map data.

[0106] In this optional implementation, the target road data can come from an updated map dataset. Using the apparatus described in this embodiment, a swarm of particles can be scattered onto the target road in the map dataset. The scattered particles can move along the target road according to the apparatus and cease moving when a stopping condition is met. Subsequently, the target road data in the map dataset can be tested based on the movement information of the particle swarm on the target road, such as the distribution of the number of steps taken by the particles, the distribution of the movement direction of the particles, and the final aggregation position of the particles, to evaluate the update effect of the new map data.

[0107] In some embodiments, testing the target road data based on the movement step distribution of particles in the particle swarm involves comparing the test results with the movement step distribution of particles in the particle swarm of a target road with normal topological connectivity. For target roads with normal topological connectivity, the movement step distribution of particles in the particle swarm is relatively stable. For example, the particle swarm contains particles with few steps, particles with a medium number of steps, and particles with a large number of steps, and the proportion of these particles is also consistent with normal conditions. If the movement step distribution of particles in the particle swarm is unstable in the test results, such as most particles having few steps, only a small number of particles having medium or large numbers of steps, or even no particles having medium or large numbers of steps, since the initial position of the particle swarm is a random position selected from the target road, a few steps either means that the particle has reached the end of the road after taking very few steps or encountered a dead end. If a large number of particles exhibit this problem, it can be considered that the connectivity of the target road in the new map data is abnormal, and further judgment is required.

[0108] In some embodiments, testing the target road data based on the distribution of particle swarm movement directions involves counting the number of particles in the map whose movement direction differs from the road's direction of travel. If the number of such particles exceeds a set threshold, it indicates that there may be abnormal turning points, forks, etc., in the target road in the new map data.

[0109] In some embodiments, testing the target road data based on the final aggregation position of particles in the particle swarm involves comparing the test results of the final aggregation position of particles with the impassable road ends or lane ends in the target road data. If there are particle aggregation positions other than the road ends or lane ends, the particle data is further counted. If the number of particles exceeds a set threshold, it indicates that the topological relationship of the target road in the new map data is unreasonable.

[0110] In addition, the differences in target road data of related target roads in two or more sets of new and old map data can be tested to evaluate the effectiveness of the new map data update.

[0111] In some embodiments, the area where the target road has changed in the new and old maps is determined by comparing the differences in the final aggregation positions of particle swarms in the new and old maps. For example, the number of particles in this changed area is counted. If the number of particles exceeds a threshold, it can be considered that the proportion of impassable parts in the target road is large, indicating that the topological relationship of the target road in the new map data is unreasonable.

[0112] In an optional implementation of this embodiment, the second test submodule is implemented as at least one of the following: Based on the motion duration of the particle swarm in the motion information, the differences in complexity of the different map data are compared; Based on the distribution of the number of movement steps of the particle swarm in the motion information, it is determined whether the road connectivity in the different map data is consistent. Based on the motion direction characteristics of the particle swarm in the motion information, it is determined whether the road direction of the target road in the different map data is consistent; Based on the aggregation position of the particle swarm in the motion information, it is determined whether the end of the target road is consistent in the different map data.

[0113] In this optional implementation, by comparing the completion times of particles in the particle swarm in different map data, if the completion time of particles in the new map is longer, it indicates that the target road in the new map data is more complex, and the new map data has an updating effect. For example, according to the method in this embodiment, the movement of particle swarms on the target road is simulated in two map data. After the movement ends, the completion time of particle swarms in the two map data can be counted. If the average completion time of particle swarms in one map data is much longer than that in the other map data, it can be preliminarily determined that the target roads in the two map data are different in length. One possibility is that the target road in the map data with the longer average completion time may be longer than the target road in the other map data, that is, the complexity of the map data is greater than that of the other map data. Another possibility is that the target road in the map data with the shorter average completion time has a break in the road, so further judgment is needed. However, if the average completion time of particle swarms on the target road in the two map data is not much different, it can be determined that there is no difference between the target roads in the two map data, and no further judgment is needed.

[0114] In some embodiments, the consistency of road connectivity in different map data can also be determined based on the distribution of movement steps of particle swarms in motion information. As mentioned above, if the movement step distribution of most particles in the map data is stable, for example, the number of particles with few, medium, and many steps is relatively even, or the number of particles with few, medium, and many steps in the two map data is not significantly different, then the road connectivity of the different map data can be determined to be relatively consistent; otherwise, the road connectivity of the different map data can be determined to be inconsistent.

[0115] In some embodiments, the movement direction of the particle swarm is normally consistent with the direction of travel of the road in the map data. For example, if the direction of travel of the target road in one map data is north-south, then the distribution of the movement direction of the particle swarm should also be north-south. If the movement direction of some particles is abnormal, it can be considered that the target road in the map data has an abnormal turning point or fork. By comparing the movement direction of most particles in two map data, it can also be determined whether the road direction of the target road in the two map data is consistent.

[0116] In some embodiments, based on the aggregation positions of the particle swarm in the motion information, it can also be determined whether the ends of the target roads are consistent in different map data. Normally, after the particle swarm finishes its motion, most particles will aggregate at the end of the target road. If the aggregation positions of most particles on the target road are inconsistent in the two sets of map data, then the ends of the target roads can be considered inconsistent.

[0117] The threshold values ​​mentioned above can be set according to actual statistical needs, and this disclosure does not limit them.

[0118] This disclosure also discloses an electronic device. Figure 8 This diagram illustrates a structural block diagram of an electronic device according to an embodiment of the present disclosure, such as... Figure 8 As shown, the electronic device 800 includes a memory 801 and a processor 802; wherein, The memory 801 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 802 to implement the above method steps.

[0119] Figure 9 This is a schematic diagram of the structure of a computer system suitable for implementing a map data testing method according to an embodiment of the present disclosure.

[0120] like Figure 9 As shown, the computer system 900 includes a processing unit 901, which can be implemented as a CPU, GPU, FPGA, NPU, or other processing unit. The processing unit 901 can execute various processes according to any of the above-described methods of this disclosure, based on a program stored in the read-only memory (ROM) 902 or a program loaded from the storage portion 908 into the random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the computer system 900. The processing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0121] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 910 as needed so that computer programs read from it can be installed into storage section 908 as needed.

[0122] In particular, according to embodiments of this disclosure, any of the methods described above in the embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program containing program code for performing any of the methods in the embodiments of this disclosure. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911.

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0124] The units or modules described in the embodiments of this disclosure can be implemented in software or hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0125] In another aspect, this disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the apparatus described in the above embodiments; or it may be a standalone computer-readable storage medium not assembled into a device. The computer-readable storage medium stores one or more programs that are used by one or more processors to perform the methods described in this disclosure.

[0126] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A map data testing method, wherein, include: Obtain target road data for the target road from at least one map dataset; Based on the target road data, the particle swarm algorithm is used to simulate the walking motion of the particle swarm on the target road, and the walking motion is stopped when the stopping condition is met; wherein, the walking direction of the particle swarm on the target road is related to the road travel direction of the target road; Obtain the motion information of the particle swarm on the target road; The target road data is tested based on the motion information; Specifically, based on the target road data, a particle swarm algorithm is used to simulate the movement of a particle swarm on the target road, and the movement stops when a stopping condition is met, including: Obtain the road travel direction corresponding to the current position of the particles in the particle swarm on the target road from the target road data; The next travel direction of the particle is determined within a preset angle range where the road travel direction is located; The next position to which the particle will move is determined based on the current position and the next direction of movement; After setting the next position as the current position, proceed to the step of obtaining the road travel direction corresponding to the current position of the particle in the particle swarm on the target road from the target road data, and continue execution until the stopping condition is met.

2. The method according to claim 1, wherein, The initial position of the particle swarm as it travels along the target road is a random position on the target road.

3. The method according to claim 1, wherein, Determining the next position of the particle based on the current position and the next walking direction includes: Get the random walking step length; The next candidate position is determined based on the current position, the next walking direction, and the random walking step size; If the next candidate position does not exceed the target road range in the target road data, then the next candidate position is determined as the next position to which the particle travels.

4. The method according to claim 3, wherein, The target road range includes the area within the solid lane lines and the area within the road boundary lines of the target road.

5. The method according to claim 3 or 4, wherein, The method further includes: If the next candidate location is outside the target road range, then the next walking direction and / or the random walking step size are re-determined; Based on the redefined next walking direction and / or the random walking step size, the next position to be reached will be determined to be within the target road range.

6. The method according to claim 3 or 4, wherein, The method further includes: If the next candidate position exceeds the target road range, the random walking step size is re-determined so that the random walking step size is less than the distance from the current position along the next walking direction to the boundary of the target road range; The next position is determined based on the redefined random walk step size.

7. The method according to claim 3 or 4, wherein, Testing the target road data based on the motion information includes: The target road data corresponding to the target road itself is tested based on the motion information of the particle swarm on the target road in the same map data; Based on the motion information of particle swarms associated with the target road in different map data, the differences in the target road data corresponding to the target road are tested.

8. The method according to claim 7, wherein, Based on the motion information of particle swarms associated with the target road in different map data, the differences between different target road data corresponding to the target road are tested, including at least one of the following: Based on the motion duration of the particle swarm in the motion information, the differences in complexity of the different map data are compared; Based on the distribution of the number of movement steps of the particle swarm in the motion information, it is determined whether the road connectivity in the different map data is consistent. Based on the motion direction characteristics of the particle swarm in the motion information, it is determined whether the road direction of the target road in the different map data is consistent; Based on the aggregation position of the particle swarm in the motion information, it is determined whether the end of the target road is consistent in the different map data.

9. A map data testing device, wherein, include: The first acquisition module is configured to acquire target road data of the target road in at least one map dataset. The walking simulation module is configured to simulate the walking motion of a particle swarm on the target road using a particle swarm algorithm based on the target road data, and to stop walking motion when a stopping condition is met; wherein, the walking direction of the particle swarm on the target road is related to the road travel direction of the target road; The second acquisition module is configured to acquire motion information of the particle swarm on the target road; The testing module is configured to test the target road data based on the motion information; The walking simulation module includes: The first acquisition submodule is configured to acquire the road travel direction corresponding to the current position of the particles in the particle swarm on the target road from the target road data; The first determining submodule is configured to determine the next travel direction of the particle within a preset angle range of the road travel direction; The second determining submodule is configured to determine the next position to which the particle will move based on the current position and the next moving direction; The second acquisition submodule is configured to take the next position as the current position and then transfer to the first acquisition submodule to continue execution until the stop condition is met.

10. An electronic device, wherein, The method includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of any one of claims 1-8.

11. A computer-readable storage medium having computer instructions stored thereon, wherein, When executed by a processor, the computer instructions implement the method described in any one of claims 1-8.

Images