Experience speed and experience speed limit acquisition method and device, vehicle, medium and equipment

Abstract

The application discloses an experience speed and experience speed limit acquisition method and device, a vehicle, a medium and equipment, and belongs to the field of data processing. The method comprises the following steps: acquiring a plurality of speed values of a plurality of trajectories at a road center point in a section of road; clustering and Gaussian distribution fitting are performed on the plurality of speed values to obtain a preset number of Gaussian fitting speed distribution curves, and the speed at the road center point is divided into a low-speed interval, a normal interval and a high-speed interval according to the Gaussian fitting speed distribution curves, wherein the preset number of Gaussian fitting speed distribution curves correspond to the low-speed interval, the normal interval and the high-speed interval one by one; the experience speed at the road center point is acquired by using the speed values in the normal interval and the high-speed interval; and the experience speed limit at the road center point is acquired by using the speed values in the high-speed interval. The application effectively identifies the low-speed interval, has intuitiveness, optimizes the calculation of the experience speed and the experience speed limit, and makes the results more accurate.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a method, apparatus, vehicle, medium and equipment for obtaining empirical speed and empirical speed limit. Background Technology

[0002] Existing technical methods do not effectively distinguish between the experience speed and the experience speed limit for a given road. The experience speed limit is generally determined based on speed limit signs, which is a mechanical method and not applicable to road sections without speed limit signs. In addition, the result of the experience speed limit is easily affected by low-speed zones.

[0003] The existing methods for obtaining empirical speed and empirical speed limit are to take the quantile after weighting the speed values ​​of the trajectory. This method is fast and can solve the influence of low-speed samples on the speed results to a certain extent. However, it has the problems of not being able to effectively identify low-speed intervals and poor intuitiveness. Summary of the Invention

[0004] To address the problem that the distinction between empirical speed and empirical speed limit is not clear and that low-speed ranges cannot be effectively identified, this application mainly provides a method, apparatus, vehicle, medium, and equipment for obtaining empirical speed and empirical speed limit.

[0005] In a first aspect, embodiments of this application provide a method for obtaining empirical speed and empirical speed limit, which includes:

[0006] Obtain multiple velocity values ​​at the center point of multiple trajectories along a road segment;

[0007] Clustering and Gaussian distribution fitting are performed on multiple speed values ​​to obtain a preset number of Gaussian fitted speed distribution curves. Based on the Gaussian fitted speed distribution curves, the speed at the center point of the road is divided into low speed range, normal range and high speed range. The preset number of Gaussian fitted speed distribution curves correspond one-to-one with the low speed range, normal range and high speed range.

[0008] By using the speed values ​​of the normal and high-speed sections, the empirical speed at the center point of the road can be obtained;

[0009] By using the speed values ​​in the high-speed section, the empirical speed limit at the center point of the road can be obtained.

[0010] Secondly, embodiments of this application provide an experience speed and experience speed limit acquisition device, which includes:

[0011] The trajectory point speed acquisition module is used to acquire multiple speed values ​​of multiple trajectories passing through the center point of a road segment;

[0012] The speed clustering module is used to cluster and fit Gaussian distributions to multiple speed values, and obtain a preset number of Gaussian-fitted speed distribution curves. Based on the Gaussian-fitted speed distribution curves, the speed at the center point of the road is divided into low-speed interval, normal interval, and high-speed interval. The preset number of Gaussian-fitted speed distribution curves correspond one-to-one with the low-speed interval, normal interval, and high-speed interval.

[0013] The empirical speed acquisition module is used to obtain the empirical speed at the center point of the road using the speed values ​​of the normal range and the high-speed range.

[0014] The experience-based speed limit acquisition module is used to obtain the experience-based speed limit at the center point of the road using the speed values ​​of the high-speed section.

[0015] Thirdly, embodiments of this application provide a vehicle, wherein the vehicle includes the experience speed and experience speed limit acquisition device of Scheme 2.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which, when executed, cause the computer to perform the experience speed and experience speed limit acquisition method in Scheme 1.

[0017] Fifthly, embodiments of this application provide a computer device including a processor and a memory, the memory storing computer instructions, which, when executed by the processor, implement the empirical speed and empirical speed limit acquisition method in Scheme 1.

[0018] The technical solution of this application embodiment calculates the probability density distribution of the speed values ​​of trajectory points on each trajectory on the road using Gaussian distribution, and clusters multiple different Gaussian fitted speed distribution curves. Based on the expected value of the Gaussian distribution data, the Gaussian fitted speed distribution curves are divided into low-speed intervals, normal intervals, and high-speed intervals. The low-speed intervals are filtered out in a timely manner, and the empirical speed and empirical speed limit are calculated based on the normal interval and the high-speed interval. This not only effectively identifies the low-speed interval and is intuitive, but also optimizes the calculation of empirical speed and empirical speed limit, making the results more accurate. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description exemplarily illustrate some embodiments of this application.

[0020] Figure 1 This is a schematic diagram illustrating a specific implementation of a method for obtaining experience speed and experience speed limit according to this application;

[0021] Figure 2This is a schematic diagram of a specific example of a method for obtaining experience speed and experience speed limit according to this application;

[0022] Figure 3 This is a schematic diagram of a specific embodiment of an experience speed and experience speed limit acquisition device according to this application.

[0023] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0024] The optional embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby making a clearer and more explicit definition of the scope of protection of this application.

[0025] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0026] Under good road conditions, such as without adverse weather, accidents, peak traffic jams, etc., the speed at which most drivers are traveling can be used as the experience speed; the speed at which drivers traveling at relatively high speeds are traveling under the speed limit of traffic signs can be used as the experience speed limit; and the low-speed range is defined as the section of the road where many speeds are significantly lower than the average speed due to various natural or external factors.

[0027] In this application, the base map refers to the layer placed at the bottom of multiple layers during the map drawing process, which constitutes the basic framework of the base map. The base map contains many geographical features that identify geographical locations, such as transportation, roads, landforms, etc.

[0028] In this application, the road center point refers to a series of location points on the base map used to mark roads. The road center point is collected from the location points on the center line of each road.

[0029] This application first requires statistically analyzing multiple speed values ​​associated with each road center point. This necessitates acquiring multiple trajectories and calculating the speed value at each trajectory point. Then, the trajectory points are matched with the road center points in the base map to associate them, thus statistically analyzing the multiple speed values ​​associated with each road center point. Based on these speed values ​​associated with each center point, Gaussian curve fitting is performed. Since it's necessary to divide the area into low-speed, high-speed, and normal speed ranges, three Gaussian-fitted speed distribution curves are clustered based on each road center point. This effectively filters out the low-speed range. Furthermore, the normal and high-speed ranges are used to calculate empirical speeds and speed limits, optimizing the calculation process and resulting in more accurate results.

[0030] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. The specific embodiments described below can be combined with each other to form new embodiments. The same or similar ideas or processes described in one embodiment may not be repeated in other embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0031] Figure 1 This paper illustrates a specific implementation of a method for obtaining experience speed and experience speed limit according to this application.

[0032] exist Figure 1 In the specific implementation shown, a method for obtaining empirical speed and empirical speed limit mainly includes:

[0033] Step S101: Obtain multiple speed values ​​of multiple trajectories passing through the center point of a road segment.

[0034] In this embodiment, there are multiple tracks in a road segment, and each track consists of several track points. The timestamp information and location information of each track point can be obtained through vehicle-mounted sensors, road network equipment, or other means. Based on the timestamp information and location information, the speed value of each track point can be calculated, and the speed value of the track point provides the basis for the statistical analysis of the speed value of each road center point.

[0035] In one specific embodiment of this application, obtaining the speed values ​​of multiple trajectories passing through the center point of a road segment includes: obtaining a first number of trajectories in a road segment, obtaining a second number of trajectory points in each trajectory and the speed value of each trajectory point; associating each trajectory point with the nearest road center point, wherein each road center point is associated with multiple trajectory points; and using the speed values ​​of the associated multiple trajectory points as the speed value at the road center point.

[0036] In this embodiment, multiple trajectory points in each trajectory of a road segment are obtained, and the speed value of each trajectory point is obtained by calculating the timestamp information and location information of each trajectory point; the first quantity and the second quantity are determined according to the length of the road and the sampling interval of the trajectory points.

[0037] In a specific example of this application, each trajectory point in each trajectory is bound to a road center point. The trajectory point ID associated with the nearest road center point for each trajectory point is recorded. That is, the road center point closest to each trajectory point is found, and each trajectory point is treated as an associated trajectory point of that nearest road center point, with its trajectory point ID recorded. Through this association method, each road center point can be associated with multiple trajectory points, and the speed values ​​of these multiple associated trajectory points are used as the speed value at the road center point. Therefore, a road center point can obtain multiple speed values. The speed value of the trajectory point corresponding to the associated trajectory point ID is retrieved. While a trajectory point has only one nearest road center point, a road center point can be associated with more than one trajectory point. Each time a road center point is associated with a trajectory point, a trajectory point ID is recorded to represent that trajectory point. Based on the trajectory point ID, the corresponding trajectory point can be retrieved conveniently and promptly, facilitating the statistical analysis of speed samples for each road center point, and thus facilitating subsequent speed sample estimation of the road center point.

[0038] exist Figure 1 In the specific implementation shown, a method for obtaining experience speed and experience speed limit further includes:

[0039] Step S102: Cluster and Gaussian distribution fitting are performed on multiple speed values ​​to obtain a preset number of Gaussian fitted speed distribution curves. Based on the Gaussian fitted speed distribution curves, the speed at the center point of the road is divided into low speed range, normal range and high speed range. The preset number of Gaussian fitted speed distribution curves correspond one-to-one with the low speed range, normal range and high speed range.

[0040] In this embodiment, a Gaussian distribution is applied to multiple speed values ​​associated with each road center point. Since it's necessary to divide multiple speeds at a given location into low-speed, normal, and high-speed intervals, the preset number is set to 3 during cluster fitting. Although the three curves generated by cluster fitting have some overlap, these three curves are more realistic, resulting in higher calculation accuracy.

[0041] In one specific embodiment of this application, the speed at the center point of the road is divided into a low-speed interval, a normal interval, and a high-speed interval based on the Gaussian-fitted speed distribution curve. This includes: sorting the mean values ​​of the Gaussian-fitted speed distribution curves in ascending order to obtain a first mean, a second mean, and a third mean; using the probability density distribution of the corresponding Gaussian-fitted speed distribution curve based on the first mean as the low-speed interval; using the probability density distribution of the corresponding Gaussian-fitted speed distribution curve based on the second mean as the normal interval; and using the probability density distribution of the corresponding Gaussian-fitted speed distribution curve based on the third mean as the high-speed interval, wherein the low-speed interval, the normal interval, and the high-speed interval include overlapping intervals.

[0042] In this embodiment, the first mean, the second mean, and the third mean are used as the axes of symmetry of the curve, respectively. Based on the calculated probability density distribution, the low-speed interval, the normal interval, and the high-speed interval are obtained respectively. The intervals distinguished by probability do not have accurate dividing points, which is more in line with the real situation.

[0043] In one specific embodiment of this application, multiple speed values ​​are clustered and fitted with a Gaussian distribution to obtain a preset number of Gaussian-fitted speed distribution curves. This includes: using the speed values ​​of multiple trajectory points associated with the road center point, counting the number of multiple trajectory points in different speed ranges, and calculating the probability in different speed ranges; and calculating the mean and standard deviation based on the number and probability in different speed ranges, thereby obtaining a preset number of Gaussian-fitted speed distribution curves respectively.

[0044] In this embodiment, the number of samples within each range of fluctuation of each integer value of speed is counted, that is, the number of speed values ​​of the trajectory points. After the speed value samples corresponding to each road center point are counted, curve fitting and clustering are performed to calculate the probability of each speed value and fit three Gaussian curves. This method is highly intuitive, facilitates the filtering out of low-speed intervals, and has a better effect of reducing the influence of low-speed intervals.

[0045] exist Figure 1 In the specific implementation shown, a method for obtaining experience speed and experience speed limit further includes:

[0046] Step S103, the empirical speed acquisition module is used to obtain the empirical speed at the center point of the road by using the speed values ​​of the normal interval and the high-speed interval. The empirical speed at the location of the center point of the road is obtained by using the mean and weighted value of the normal interval and the mean and weighted value of the high-speed interval.

[0047] In this embodiment, the empirical speed is extracted based on the normal range and the high-speed range. The average of the two ranges is weighted by the area covered by each range and considered as the normal speed without the influence of various factors. This empirical speed result is more accurate and less susceptible to the influence of the low-speed range.

[0048] In one specific embodiment of this application, the empirical speed at the center point of the road is calculated using the speed values ​​of the normal interval and the high-speed interval, including: calculating the weighted value corresponding to the normal interval and the high-speed interval respectively using the mean and standard deviation of the normal interval and the high-speed interval respectively; and adding the corresponding weighted values ​​extracted from the mean of the normal interval and the mean of the high-speed interval to obtain the empirical speed.

[0049] In this embodiment, the weighted values ​​for the normal and high-speed intervals are calculated using the mean and standard deviation of each interval. The weighted values ​​for the mean of the normal and high-speed intervals are extracted and summed to obtain the empirical speed. The area of ​​each interval is calculated separately, and the proportion of the area in each interval is used as the weighted value for each interval. The weighted values ​​for the mean of the normal and high-speed intervals are then summed to obtain the empirical speed, making the result more accurate.

[0050] exist Figure 1 In the specific implementation shown, a method for obtaining experience speed and experience speed limit further includes:

[0051] Step S104: Using the speed values ​​of the high-speed section, obtain the empirical speed limit at the center point of the road. Using the mean and standard deviation of the high-speed section, obtain the empirical speed limit at the location of the center point of the road.

[0052] In this embodiment, the first standard deviation to the right of the mean of the high-speed section is taken as the new empirical speed limit. Driving at this empirical speed limit can ensure that, under normal circumstances, one can drive faster than fast-driving people.

[0053] In one specific embodiment of this application, the empirical speed limit at the center point of the road is calculated using the speed values ​​of the high-speed section, including: adding the mean and standard deviation of the high-speed section to obtain the empirical speed limit.

[0054] In this embodiment, since the high-speed section is the speed at which most drivers travel at relatively high speeds when there are speed limits on traffic signs, by taking the interval to the right of the average of the high-speed section, we can ensure that the experienced speed limit does not exceed the speed limit on the speed limit sign, and make the process of extracting the experienced speed limit more convenient, accurate and intuitive.

[0055] Figure 2 This paper illustrates a specific example of a method for obtaining experience speed and experience speed limit according to this application.

[0056] exist Figure 2In the specific example shown, three Gaussian coefficients are used to fit the velocity distribution map. The gray curve on the left represents the low-speed range, the middle gray curve represents the normal range, and the gray curve on the right represents the high-speed range. These ranges are distinguished by probability, and since there are no precise boundary points, they more closely resemble reality. The empirical speed limit (E_limit) is taken as the first sigma(σ3) to the right of the mean (μ3) of the high-speed range as the new empirical speed limit value.

[0057] E limit =μ3+σ3

[0058] The empirical speed (E_norm) is equal to the weighted average of the mean (μ2) of the normal range and the mean (μ3) of the high-speed range, over the area covered by these ranges. It represents the normal speed when there is no traffic congestion.

[0059] E norm =αμ2+βμ3

[0060] Where μ2 and μ3 are the mean values ​​of the normal and high-speed intervals, σ3 is the standard deviation of the high-speed interval, and α and β are weighted values, calculated as follows:

[0061]

[0062]

[0063]

[0064] Note: This empirical speed and speed limit value can be used if and only if the model's log-likelihood is within a reasonable range (LL represents the log-likelihood of the entire model, and LL_n represents the log-likelihood of the nth curve from left to right).

[0065] This application first calculates the speed value for each trajectory point based on the timestamp and the location of the trajectory point. It then matches the trajectory with the base map, recording the road ID corresponding to each trajectory point. During the matching and binding process, the road IDs of the preceding and following trajectory points are also recorded. Similarly, the associated trajectory point ID is recorded for the road center point corresponding to each trajectory point. Based on the association between the road center point and the trajectory point, multiple speed values ​​associated with each road center point are statistically calculated. Based on these multiple speed values ​​associated with each center point, Gaussian curve fitting is performed. Since it is necessary to divide the speed range into low-speed, high-speed, and normal speed ranges, three Gaussian-fitted speed distribution curves are clustered based on each road center point. This effectively filters out the low-speed range, making the filtering of the low-speed range more intuitive. Furthermore, the application uses the normal and high-speed ranges to calculate empirical speeds and empirical speed limits, making the calculation results of empirical speeds and empirical speed limits more accurate.

[0066] Figure 3 This application illustrates a specific embodiment of an experience speed and experience speed limit acquisition device.

[0067] exist Figure 3 In the specific embodiment shown, an experience speed and experience speed limit acquisition device mainly includes:

[0068] The trajectory point speed acquisition module 301 is used to acquire multiple speed values ​​of multiple trajectories passing through the center point of a road segment;

[0069] The speed clustering module 302 is used to cluster and fit Gaussian distributions to multiple speed values ​​to obtain a preset number of Gaussian-fitted speed distribution curves. Based on the Gaussian-fitted speed distribution curves, the speed at the center point of the road is divided into low-speed interval, normal interval, and high-speed interval. The preset number of Gaussian-fitted speed distribution curves correspond one-to-one with the low-speed interval, normal interval, and high-speed interval.

[0070] The experience speed acquisition module 303 is used to acquire the experience speed at the center point of the road using the speed values ​​of the normal range and the high-speed range.

[0071] The experience speed limit acquisition module 304 is used to obtain the experience speed limit at the center point of the road using the speed value of the high-speed section.

[0072] In this embodiment, based on a large number of trajectory points on the acquired trajectory, the speed value of each trajectory point is calculated. Then, the trajectory points are matched with the road center point, and the number of samples of speed values ​​corresponding to each road center point is counted. Then, Gaussian distribution fitting is performed based on each road center point to cluster three Gaussian fitted speed distribution curves, which are divided into low-speed interval, normal interval, and high-speed interval in sequence. The low-speed interval can be filtered out intuitively, reducing the impact of the low-speed interval on the calculation of empirical speed and empirical speed limit.

[0073] In one specific embodiment of this application, multiple speed values ​​are clustered and fitted with a Gaussian distribution to obtain a preset number of Gaussian-fitted speed distribution curves. This includes: using the speed values ​​of multiple trajectory points associated with the road center point, counting the number of multiple trajectory points in different speed ranges, and calculating the probability in different speed ranges; and calculating the mean and standard deviation based on the number and probability in different speed ranges, thereby obtaining a preset number of Gaussian-fitted speed distribution curves respectively.

[0074] In this embodiment, the number of samples within each range of fluctuation of each integer value of speed is counted, that is, the number of speed values ​​of the trajectory points. After the speed value samples corresponding to each road center point are counted, curve fitting and clustering are performed to calculate the probability of each speed value and fit three Gaussian curves. This method is highly intuitive, facilitates the filtering out of low-speed intervals, and has a better effect of reducing the influence of low-speed intervals.

[0075] In one specific embodiment of this application, the speed at the center point of the road is divided into a low-speed interval, a normal interval, and a high-speed interval based on the Gaussian-fitted speed distribution curve. This includes: sorting the mean values ​​of the Gaussian-fitted speed distribution curves in ascending order to obtain a first mean, a second mean, and a third mean; using the probability density distribution of the corresponding Gaussian-fitted speed distribution curve based on the first mean as the low-speed interval; using the probability density distribution of the corresponding Gaussian-fitted speed distribution curve based on the second mean as the normal interval; and using the probability density distribution of the corresponding Gaussian-fitted speed distribution curve based on the third mean as the high-speed interval, wherein the low-speed interval, the normal interval, and the high-speed interval include overlapping intervals.

[0076] In this embodiment, the first mean, the second mean, and the third mean are used as the axes of symmetry of the curve, respectively. Based on the calculated probability density distribution, the low-speed interval, the normal interval, and the high-speed interval are obtained respectively. The intervals distinguished by probability do not have accurate dividing points, which is more in line with the real situation.

[0077] In one specific embodiment of this application, the empirical speed at the center point of the road is calculated using the speed values ​​of the normal interval and the high-speed interval, including: calculating the weighted value corresponding to the normal interval and the high-speed interval respectively using the mean and standard deviation of the normal interval and the high-speed interval respectively; and adding the corresponding weighted values ​​extracted from the mean of the normal interval and the mean of the high-speed interval to obtain the empirical speed.

[0078] In this embodiment, the area of ​​the normal interval and the high-speed interval are calculated separately, and the proportion of the area of ​​the two intervals is used as the weighted value of each interval. The mean of the normal interval and the mean of the high-speed interval are weighted, and the sum of the two is used as the empirical speed, so that the result is more accurate.

[0079] In one specific embodiment of this application, the empirical speed limit at the center point of the road is calculated using the speed values ​​of the high-speed section, including: adding the mean and standard deviation of the high-speed section to obtain the empirical speed limit.

[0080] In this embodiment, since the high-speed section is the speed at which most drivers travel at relatively high speeds when there are speed limits on traffic signs, by taking the interval to the right of the average of the high-speed section, we can ensure that the experienced speed limit does not exceed the speed limit on the speed limit sign, and make the process of extracting the experienced speed limit more convenient, accurate and intuitive.

[0081] The present application provides an experience speed and experience speed limit acquisition device, which can be used to execute the experience speed and experience speed limit acquisition method described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0082] In one specific embodiment of this application, the functional modules in the experience speed and experience speed limit acquisition device of this application can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0083] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0084] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0085] In another specific embodiment of this application, a vehicle is provided, wherein the vehicle includes the experienced speed and experienced speed limit acquisition device of any embodiment. Optionally, the vehicle includes a processor and a memory, the processor and memory being coupled, the vehicle being used to implement the appendix to this application specification. Figure 1 The method for obtaining the experience speed and experience speed limit in any of the embodiments shown.

[0086] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores computer instructions that, when executed, cause a computer to perform the experience speed and experience speed limit acquisition method of any embodiment.

[0087] In another specific embodiment of this application, a computer device includes a processor and a memory, the memory storing computer instructions, which, when executed by the processor, implement the experience speed and experience speed limit acquisition method of any embodiment.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for obtaining experience speed and experience speed limit, characterized in that, include: Obtain multiple velocity values ​​at the center point of multiple trajectories along a road segment; Clustering and Gaussian distribution fitting are performed on the multiple speed values ​​to obtain a preset number of Gaussian fitted speed distribution curves. Based on the Gaussian fitted speed distribution curves, the speed at the center point of the road is divided into a low-speed interval, a normal interval, and a high-speed interval. The preset number of Gaussian fitted speed distribution curves correspond one-to-one with the low-speed interval, the normal interval, and the high-speed interval. Using the speed values ​​from the normal section and the high-speed section, the empirical speed at the road center point is obtained, wherein, Using the mean and standard deviation of the normal interval and the high-speed interval respectively, the weighted values ​​corresponding to the normal interval and the high-speed interval are calculated respectively. The calculation method is as follows: Where μ2 and μ3 are the means of the normal interval and the high-speed interval, respectively, σ3 is the standard deviation of the high-speed interval, α and β are the weighted values ​​corresponding to the normal interval and the high-speed interval, respectively, and E limit Speed ​​limit based on experience, E norm For experience speed; The empirical speed is obtained by extracting the corresponding weighted values ​​of the mean of the normal interval and the mean of the high-speed interval, and then adding them together. Using the speed values ​​of the high-speed section, the empirical speed limit at the center point of the road is obtained.

2. The method for obtaining empirical speed and empirical speed limit as described in claim 1, characterized in that, The calculation of the empirical speed limit at the center point of the road using the speed value of the high-speed section includes: The empirical speed limit is obtained by adding the mean and standard deviation of the high-speed range.

3. The method for obtaining experience speed and experience speed limit as described in claim 1, characterized in that, The process of obtaining the speed values ​​of multiple trajectories passing through the center point of a road segment includes: Obtain a first number of trajectories in a road segment, and obtain a second number of trajectory points in each trajectory and the velocity value of each trajectory point; Each trajectory point is associated with the nearest road center point, wherein each road center point is associated with multiple trajectory points; The velocity values ​​of the associated plurality of trajectory points are used as the velocity value at the center point of the road.

4. The method for obtaining experience speed and experience speed limit as described in claim 1, characterized in that, The process of dividing the speed at the center point of the road into low-speed, normal, and high-speed ranges based on the Gaussian-fitted speed distribution curve includes: The mean values ​​of the Gaussian fitted velocity distribution curves are sorted in ascending order to obtain the first mean, the second mean, and the third mean. Based on the first mean, the probability density distribution of the corresponding Gaussian fitted velocity distribution curve is taken as the low-speed interval; Based on the second mean, the probability density distribution of the corresponding Gaussian fitted velocity distribution curve is taken as the normal interval; Based on the third mean, the probability density distribution of the corresponding Gaussian fitted velocity distribution curve is taken as the high-speed interval, wherein the low-speed interval, the normal interval, and the high-speed interval contain overlapping intervals.

5. The method for obtaining experience speed and experience speed limit as described in claim 1, characterized in that, The process of clustering and fitting multiple velocity values ​​to a Gaussian distribution to obtain a preset number of Gaussian-fitted velocity distribution curves includes: Using the speed values ​​of multiple trajectory points associated with the center point of the road, the number of these trajectory points in different speed ranges is counted, and the probability in different speed ranges is calculated. Based on the quantity and probability under different speed ranges, the mean and standard deviation are calculated to obtain the preset number of Gaussian fitted speed distribution curves.

6. A device for acquiring empirical speed and empirical speed limit, characterized in that, include: The trajectory point speed acquisition module is used to acquire multiple speed values ​​of multiple trajectories passing through the center point of a road segment; The speed clustering module is used to cluster and fit Gaussian distributions to the multiple speed values ​​to obtain a preset number of Gaussian-fitted speed distribution curves. Based on the Gaussian-fitted speed distribution curves, the speed at the center point of the road is divided into a low-speed interval, a normal interval, and a high-speed interval. The preset number of Gaussian-fitted speed distribution curves correspond one-to-one with the low-speed interval, the normal interval, and the high-speed interval. The empirical speed acquisition module is used to obtain the empirical speed at the center point of the road using the speed values ​​of the normal interval and the high-speed interval. Specifically, it calculates a weighted value for the normal interval and the high-speed interval using the mean and standard deviation of each interval. The calculation method is as follows: Where μ2 and μ3 are the means of the normal interval and the high-speed interval, respectively, σ3 is the standard deviation of the high-speed interval, α and β are the weighted values ​​corresponding to the normal interval and the high-speed interval, respectively, and E limit Speed ​​limit based on experience, E norm For experience speed; The empirical speed is obtained by extracting the corresponding weighted values ​​of the mean of the normal interval and the mean of the high-speed interval, and then adding them together. The experience-based speed limit acquisition module is used to obtain the experience-based speed limit at the center point of the road using the speed value of the high-speed section.

7. A vehicle, characterized in that, The vehicle includes the experience speed and experience speed limit acquisition device as described in claim 6.

8. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed, the computer performs the experience speed and experience speed limit acquisition method as described in any one of claims 1-5.

9. A computer device comprising a processor and a memory, the memory storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the experience speed and experience speed limit acquisition method as described in any one of claims 1-5.

Images