A method, device and equipment for evaluating a vehicle parking site, and a storage medium

Abstract

This disclosure provides a method, apparatus, device, and storage medium for evaluating vehicle stop locations, relating to the field of artificial intelligence, particularly to autonomous driving and intelligent transportation. The specific implementation involves: acquiring raw data for at least one dimension of each vehicle stop location, where the at least one dimension includes at least one of network latency, walking navigation distance, stop data, and number of rides; using the raw data for at least one dimension of each vehicle stop location, determining the evaluation result for each vehicle stop location in each dimension; and using the evaluation results for each vehicle stop location in each dimension to perform a value assessment of each vehicle stop location. This disclosure enables multi-dimensional value assessment of multiple vehicle stop locations.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, particularly to autonomous driving and intelligent transportation. Background Technology

[0002] With the development of autonomous driving technology, autonomous taxis are gradually becoming a mode of transportation for people. However, in real life, due to the complexity of urban road scenarios and the changing nature of social vehicles, pedestrians, and the environment, autonomous taxis cannot yet park flexibly in any location like human-driven taxis.

[0003] Therefore, considering pedestrian safety, road traffic, and laws and regulations, it is more beneficial for the operation of autonomous taxis at this stage to build a certain number of stops in designated locations within the area. Summary of the Invention

[0004] This disclosure provides a method, apparatus, device, and storage medium for evaluating vehicle parking stations.

[0005] According to one aspect of this disclosure, a method for evaluating vehicle stop locations is provided, comprising:

[0006] For multiple vehicle stops, obtain raw data for at least one dimension of each vehicle stop, where the at least one dimension includes at least one of network latency, walking navigation distance, stop data, and number of rides;

[0007] Using raw data from at least one dimension of each vehicle stop, determine the evaluation result for each vehicle stop in each dimension; and,

[0008] The value of each vehicle stop is assessed using the evaluation results of each dimension.

[0009] According to another aspect of this disclosure, an evaluation device for vehicle parking stations is provided, comprising:

[0010] The acquisition module is used to acquire raw data for at least one dimension of each vehicle stop for multiple vehicle stops, wherein the at least one dimension includes at least one of network latency, walking navigation distance, stop data and number of rides;

[0011] The first determining module is used to determine the evaluation result of each vehicle stop in each dimension using raw data of at least one dimension of each vehicle stop; and,

[0012] The evaluation module is used to evaluate the value of each vehicle stop based on the evaluation results of each dimension.

[0013] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0014] At least one processor; and

[0015] The memory is communicatively connected to the at least one processor; wherein,

[0016] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods of any embodiment of the present disclosure.

[0017] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform a method according to any embodiment of this disclosure.

[0018] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements a method according to any embodiment of this disclosure.

[0019] The vehicle stop evaluation method proposed in this disclosure assesses the value of each vehicle stop by utilizing raw data from at least one dimension of multiple vehicle stops. The evaluation process comprehensively considers factors from various dimensions of the vehicle stop, thereby improving the reliability of the vehicle stop value assessment.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0021] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0022] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this disclosure;

[0023] Figure 2 This is a flowchart illustrating the implementation of the vehicle stop evaluation method 200 according to an embodiment of the present disclosure;

[0024] Figure 3A This is a schematic diagram illustrating the probability distribution of raw data in the manually taken-over data dimension according to an embodiment of this disclosure;

[0025] Figure 3B This is a schematic diagram illustrating the distribution probability of the original data scores for the manually taken-over data dimension according to an embodiment of this disclosure;

[0026] Figure 4This is a schematic diagram of an automated offline vehicle stop evaluation method according to an embodiment of the present disclosure;

[0027] Figure 5 This is a schematic diagram of the overall process of the vehicle stop evaluation method according to an embodiment of the present disclosure;

[0028] Figure 6 This is a schematic diagram of the structure of a vehicle stop evaluation device 600 according to an embodiment of the present disclosure;

[0029] Figure 7 This is a schematic diagram of the structure of a vehicle stop evaluation device 700 according to an embodiment of the present disclosure;

[0030] Figure 8 A schematic block diagram of an example electronic device 1300 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0031] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0032] In this document, the term "and / or" merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The term "at least one" in this document indicates any combination of at least two of a plurality of elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C. The terms "first" and "second" in this document refer to and distinguish between multiple similar technical terms, not to restrict the order or to limit there to only two. For example, "first feature" and "second feature" refer to two categories / two features; the first feature can be one or more, and the second feature can also be one or more.

[0033] With the development of autonomous driving technology, autonomous taxis are gradually becoming a mode of transportation. However, in real life, due to the complexity of urban road scenarios and the changing nature of social vehicles, pedestrians, and the environment, autonomous taxis cannot yet park flexibly in any location like human-driven taxis. Therefore, considering pedestrian safety, road traffic, and legal regulations, constructing a certain number of vehicle parking stations in designated locations within an area is more conducive to the current operation of autonomous taxis.

[0034] Currently, vehicle stop locations are typically determined based on experience, but these locations are often not optimal and fail to meet people's travel needs. Therefore, how to conduct a more scientific, multi-dimensional evaluation of vehicle stop locations based on existing locations and the operational capabilities of autonomous taxis is becoming an increasingly important issue.

[0035] The present invention discloses a method for evaluating vehicle stop sites, which enables a scientific, multi-dimensional evaluation of vehicle stop sites. Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this disclosure. The vehicles involved in this disclosure may include autonomous vehicles. In some embodiments, the vehicle parking station evaluation system 100 can perform value assessments on existing vehicle parking stations. For example... Figure 1 As shown, the vehicle stop evaluation system 100 may include a data acquisition device 110, a storage device 120, and a processing device 130. The data acquisition device 110 can be used to collect vehicle driving data and / or vehicle stop operation data; the storage device 120 can be used to store the vehicle driving data and / or the vehicle stop operation data; and the processing device 130 is used to evaluate the value of the vehicle stop based on the data in the storage device 120. In some embodiments, the vehicle stop evaluation system 100 may further include a network for facilitating the exchange of vehicle driving data and / or vehicle stop operation data. In some embodiments, one or more components of the vehicle stop evaluation system 100 (e.g., the data acquisition device 110, the processing device 120, or the storage device 130) can transmit vehicle driving data and / or vehicle stop operation data to other components of the vehicle stop evaluation system 100 via the network. It should be noted that the network can be any type of wired or wireless network.

[0036] This disclosure provides an evaluation method for vehicle stop sites. Figure 2 This is a flowchart illustrating the implementation of a vehicle stop evaluation method 200 according to an embodiment of the present disclosure, including:

[0037] S210: For multiple vehicle stops, obtain raw data for at least one dimension of each vehicle stop, where the at least one dimension includes at least one of network latency, walking navigation distance, stop data, and number of rides;

[0038] S220: Using the raw data of at least one dimension of each vehicle stop, determine the evaluation result of each vehicle stop in each dimension; and,

[0039] S230: Use the evaluation results of each vehicle stop in each dimension to conduct a value assessment of each vehicle stop.

[0040] The vehicle stop evaluation method proposed in this disclosure can be performed periodically; or a trigger condition can be preset and executed when the trigger condition is met. For example, the execution period can be preset to T, a timer can be set in the device used to perform the vehicle stop evaluation method, and the initial value of the timer can be set to 0; the timer can be started, and when the timer reaches T, the evaluation of each vehicle stop can be performed, and the timer can be reset to 0; the timer can be started again, and so on. As another example, the range of the sum of the number of rides at all vehicle stops within 24 hours can be set to [n1, n2]. When the sum of the number of rides at all vehicle stops within 24 hours is less than n1, the evaluation of each vehicle stop can be performed; or, when the sum of the number of rides at all vehicle stops within 24 hours is greater than n2, the evaluation of each vehicle stop can be performed.

[0041] The vehicle stop evaluation method proposed in this disclosure can determine the value of each vehicle stop based on the evaluation results of raw data from various dimensions, thus performing a scientific multi-dimensional evaluation of vehicle stops. The value of a vehicle stop can refer to its quality, such as its suitability as a stop for autonomous vehicles to pick up and drop off passengers. Since this disclosure evaluates the value of vehicle stops based on data from dimensions such as network latency, walking navigation distance, stop data, and number of rides, the value of a vehicle stop can be related to these dimensions. For example, network latency reflects the autonomous driving capability of an autonomous vehicle at the stop; therefore, the lower the network latency, the higher the value of the stop. Similarly, a shorter walking navigation distance indicates greater convenience for users to reach the stop, thus increasing its value. Furthermore, a higher number of rides indicates more users choosing to get on and off at the stop, thus increasing its value.

[0042] In one example, in step S210, the raw data for at least one dimension of each vehicle stop can be obtained by parsing and / or processing the log data, the processing including at least one of cleaning, filtering and extraction.

[0043] The log data includes at least one of the following: the operation logs of autonomous vehicles, the operation logs of cloud servers, and third-party data.

[0044] In some implementations, the log data can refer to multi-dimensional data from various stages of the autonomous vehicle's operation. It should be noted that the autonomous vehicle's operational log can refer to time-dimensional log data periodically generated by each module of the autonomous vehicle. These modules can include at least one of a human-machine interface (HMI) terminal module, a network module, and a global positioning system (GPS) module. The cloud server's operational log can refer to operational data from various stages, such as vehicle scheduling data or order status, stored and recorded on the cloud server. Third-party data can refer to external data that affects the autonomous vehicle's operation, such as traffic accident data, road infrastructure data, road traffic flow data, or weather data.

[0045] In some implementations, the log data can be written to a data warehouse via hard disk and / or network communication.

[0046] Because abnormal data, such as duplicate data, missing data, redundant data, or erroneous data, inevitably appears during the generation of the aforementioned log data, embodiments of this disclosure can further process the log data to obtain raw data with higher accuracy for each vehicle stop.

[0047] In some implementations, at least one of cleaning, filtering, and extraction processes can be used when processing the log data.

[0048] Specifically, cleaning can filter out duplicate or redundant data in the log data and remove the filtered data; simultaneously, cleaning can also modify and / or delete incorrect data in the log data and supplement missing parts of the log data to obtain data that can be further processed. Filtering can filter out data in the log data that meets preset conditions and / or contains key parts to obtain optimal data. Extraction can extract some or all of the data that meets preset conditions from the log data. It should be noted that the above three methods for processing log data are only examples, and this disclosure does not limit the specific methods for processing log data.

[0049] The embodiments disclosed herein use multi-dimensional log data to evaluate the value of vehicle stop sites, enabling a comprehensive evaluation of various dimensions of vehicle stop sites and improving the reliability of vehicle stop site value evaluation.

[0050] It is important to emphasize that the aforementioned log data may include raw data from at least one dimension of each vehicle stop. This dimension may include at least one of network latency, walking navigation distance, stop data, and number of rides. Of course, the dimensions of the raw data presented in this disclosure are merely examples, and this disclosure does not limit the dimensions of the raw data; in addition to the aforementioned dimensions, this disclosure may also utilize raw data from other dimensions for site evaluation. It should be noted that the specific dimensions of the raw data generally depend on the business needs and planning of the vehicle stop. For example, the dimensions of the raw data may also include user waiting time, vehicle waiting time, or user waiting comfort, etc.

[0051] In some implementations, the aforementioned network latency may include the network transmission latency between the vehicle and the server at each vehicle stop. It should be noted that network latency can reflect the autonomous driving capability of the autonomous vehicle at that vehicle stop. For example, the autonomous driving capability of the autonomous vehicle can be driver-controlled, passenger-controlled, or fully driverless. Generally, the lower the network latency at a vehicle stop, the higher the autonomous driving capability of the autonomous vehicle at that stop.

[0052] The walking navigation distance can include the distance between the vehicle stop and the user's desired pick-up point. It's important to note that this walking navigation distance reflects the convenience of getting on the bus. For example, the shorter the walking navigation distance, the closer the vehicle stop is to the user's desired pick-up point, the higher the convenience of getting on the bus. Generally, the higher the convenience of getting on the bus, the higher the user's willingness to go to that vehicle stop to board the bus.

[0053] Ride count refers to the number of times a user rides an autonomous vehicle at a designated stop. It's important to note that this ride count reflects the utilization rate of that stop. For example, the more times a user rides at a stop, the higher the utilization rate of that stop. Generally, the higher the utilization rate of a stop, the more likely a user is to ride there.

[0054] Parking data refers to the parking complexity of vehicle stops. It's important to note that this parking data reflects the complexity of the parking stop. In some implementations, this parking data may include at least one of emergency braking data, manual intervention data, and parking duration data. This is to allow for a multi-dimensional evaluation of the autonomous vehicle's parking data. For example, a higher parking data value indicates a more difficult parking location, thus posing a greater challenge to the autonomous vehicle's autonomous driving capabilities. Of course, a more difficult parking location also increases the user's travel time, reducing the overall user experience. Therefore, generally, a lower parking data value at a vehicle stop indicates a better user experience at that stop. Emergency braking data can refer to the number of times the autonomous vehicle brakes at the vehicle stop, or the ratio of the number of emergency brakings to the number of stops. Human intervention data can refer to the number of times the autonomous vehicle is manually intervened at the vehicle stop, or the ratio of the number of times the autonomous vehicle is manually intervened to the number of stops, where the number of human interventions indicates the number of times the autonomous vehicle is manually intervened during the stop. Stop duration data can refer to the time required for the autonomous vehicle to stop at the vehicle stop, or the ratio of the time required for the autonomous vehicle to stop at the vehicle stop to the number of stops at the vehicle stop.

[0055] The above briefly introduces the raw data of vehicle stop stations in various dimensions in the embodiments of this disclosure, as well as the method for obtaining raw data of at least one dimension of each vehicle stop station. However, when evaluating the value of vehicle stop stations, it is necessary not only to determine the raw data of each vehicle stop station, but also to determine the evaluation results of the raw data of at least one dimension of each vehicle stop station.

[0056] Specifically, the method for determining the evaluation results of each vehicle stop in each dimension according to the embodiments of this disclosure includes the following steps:

[0057] For each dimension, the following methods are used to determine the evaluation result of each vehicle stop in that dimension:

[0058] Determine the raw data for each vehicle stop in this dimension;

[0059] The determined raw data is sorted in a predetermined order to obtain the raw data sequence;

[0060] Based on the original data sequence, the evaluation results of each vehicle stop in this dimension are determined.

[0061] The predetermined order can be from largest to smallest or from smallest to largest; that is, the original data can be sorted in either order to obtain the original data sequence. Of course, this disclosure does not restrict the predetermined order.

[0062] The above briefly describes how the embodiments of this disclosure utilize raw data of at least one dimension of each vehicle stop to determine the evaluation result of each vehicle stop in each dimension. This method can efficiently and accurately determine the evaluation result of each vehicle stop in each dimension.

[0063] To more accurately determine the evaluation result of each vehicle stop in this dimension based on the original data sequence, this disclosure proposes two implementation methods, the specific implementation methods of which differ. It should be emphasized that the two methods proposed in this disclosure are merely examples, and this disclosure does not limit the way the evaluation result of each vehicle stop in each dimension is determined.

[0064] Method 1: Quantile Assessment

[0065] When determining the evaluation results of vehicle stop stations in a certain dimension, this method includes at least the following:

[0066] For each vehicle stop, determine the quantile of the original data for that dimension in the original data sequence; and, based on the type of the vehicle stop, determine the corresponding first evaluation threshold, which is used to determine the evaluation result based on the quantile.

[0067] Using the quantile and the first evaluation threshold, the evaluation result of the vehicle stop in this dimension is determined.

[0068] In this embodiment of the disclosure, the quantile is a numerical value that represents the position of the original data of the vehicle stop in the original data sequence of that dimension. For example, when the quantile of the original data of the vehicle stop in the original data sequence of that dimension is the 70th quantile, it means that the original data of the vehicle stop is greater than 70% of the original data in the original data sequence of that dimension.

[0069] For example, the evaluation results of vehicle stops in this dimension can be categorized as high, medium, and low. The aforementioned first evaluation threshold includes 70% and 35%, used to determine the evaluation result based on the quantiles of the original data in the original data sequence; specifically, 70% is used to distinguish between "high" and "medium" evaluation results, and 35% is used to distinguish between "medium" and "low" evaluation results. When determining the evaluation result of a vehicle stop using the quantile evaluation method, if the quantile of the original data for that vehicle stop in this dimension is greater than 70% in the original data sequence, the evaluation result for that vehicle stop in this dimension is determined to be "high"; if the quantile of the original data for that vehicle stop in this dimension is less than 70% but greater than 35% in the original data sequence, the evaluation result for that vehicle stop in this dimension is determined to be "medium"; and if the quantile of the original data for that vehicle stop in this dimension is less than 35% in the original data sequence, the evaluation result for that vehicle stop in this dimension is determined to be "low".

[0070] It should be noted that the evaluation results of the above-mentioned vehicle stop stations in various dimensions can be determined using distributed Spark SQL computing tasks or offline Python scripts.

[0071] In some implementations, since the value of vehicle stop locations can be affected by external factors such as time, weather, or crowds, the type of vehicle stop also needs to be considered when assessing its value. The type of vehicle stop can be determined by its location. Generally, determining the type of vehicle stop based on its location is more accurate and representative than other methods. The location of a vehicle stop can include at least one of schools, shopping malls, subways, residential areas, and bus stops. Of course, this disclosure does not limit the location of vehicle stops; generally, any location that meets the standards for setting up vehicle stops can be used.

[0072] When assessing the value of bus stops, it's crucial to consider the type of stop, as it significantly impacts the reasonable threshold range of the original data. For instance, bus stops near subway stations typically experience much higher passenger flow than those in residential areas. Therefore, to ensure the reasonableness of bus stop value, it's necessary to determine the initial assessment threshold for each dimension based on the stop's type. For example, in terms of ride frequency, the initial assessment threshold for bus stops near subway stations should be higher than that for those in residential areas.

[0073] The method for determining the evaluation result of a vehicle stop in this dimension, as proposed in the embodiments of this disclosure, can determine a first evaluation threshold for this dimension based on the type of the vehicle stop, and then determine the evaluation result of the vehicle stop in this dimension based on the first evaluation threshold and the quantile of the vehicle stop in this dimension.

[0074] The embodiments disclosed herein comprehensively consider the impact of complex urban road scenarios on the value of vehicle stop sites, enabling scientific and multi-dimensional value assessment of vehicle stop sites.

[0075] Method 2: Score Assessment Method

[0076] When determining the evaluation results of vehicle stop stations in a certain dimension, this method includes at least the following:

[0077] Determine the scoring range corresponding to the raw data for this dimension;

[0078] The scoring range is divided into multiple scoring mapping intervals;

[0079] Based on the original data sequence, determine the multiple original data corresponding to each scoring mapping interval, and put the corresponding original data into the scoring mapping interval to establish the mapping relationship between the original data and the score;

[0080] By using the mapping relationship between the raw data and the rating, the rating corresponding to the raw data of each vehicle stop in this dimension can be determined.

[0081] This score is used to determine the evaluation result of each vehicle stop in this dimension.

[0082] In some implementations, Method Two first determines the scoring range corresponding to the raw data for that dimension. For example, the scoring range corresponding to the raw data for that dimension can be determined as 0-5 points, where 0 points represents the worst raw data and 5 points represents the best raw data.

[0083] Next, to facilitate management, maintenance, and visualization, this embodiment proposes determining multiple mapping relationships between scores and original values, i.e., score mapping intervals, based on the distribution and scoring range of the original data. This method requires first identifying the mean of the original data sequence, then determining the score for that mean, and finally establishing a mapping relationship between scores and original data based on the mean-score mapping relationship.

[0084] For example, Figure 3A This is a schematic diagram illustrating the probability distribution of raw data in the manually managed data dimension according to an embodiment of this disclosure. The horizontal axis represents the raw data, the vertical axis represents the probability distribution of the raw data, and the normal distribution curve represents the probability distribution of the raw data. Figure 3AAs shown, the mean of the original data is approximately 0.08, and the standard deviation σ of the normal distribution curve is approximately 0.08. Taking a score range of 0-5 points as an example, the score corresponding to the mean of the original data of 0.08 can be pre-set as the median value of the score range, i.e., 2.5 points. Since the larger the original data of the manual intervention dimension, the higher the parking complexity of the vehicle stop, that is, if the original data of the manual intervention dimension is larger, the score of the vehicle stop in the manual intervention dimension will be lower. Based on the scoring principles of the manual intervention dimension, the mapping relationship between the mean of the original data and the score, and the standard deviation σ of the normal distribution curve, the mapping relationship between the score and the original data can be determined. Specifically, if the score corresponding to one interval of the normal distribution curve is 0.5, then the correspondence between the score and the original data is as follows: the score corresponding to the original data 0-0.08 is 3-2.5; the score corresponding to the original data 0.08-0.16 is 2.5-2; the score corresponding to the original data 0.16-0.24 is 2-1.5; the score corresponding to the original data 0.24-0.32 is 1.5-1; the score corresponding to the original data 0.32-0.40 is 1-0.5; and the score corresponding to the original data 0.40-0.48 is 0.5-0. It should be noted that the scoring rule of 0.5 corresponding to one interval of the normal distribution curve is only an example.

[0085] It should be noted that there may be a one-to-one correspondence between the original data and the scoring range. For example, taking the manual takeover data dimension mentioned above as an example, the scoring range is 0-5 points, while the original data for this manual takeover dimension only scores in the 0-3 point range. This phenomenon causes the mapping relationship between the original data and the scoring to be too concentrated in the 0-3 point range, failing to fully utilize the 0-5 point scoring range, and also hindering the determination of the scoring for each vehicle stop in this dimension. Therefore, the embodiments of this disclosure can also adjust the unreasonable mapping relationship between the original data and the scoring, such as... Figure 3B As shown, the mapping relationship between the manually taken-over data and the score can be expanded from 0-3 points to 0-5 points. Figure 3B This is a schematic diagram of the distribution probability of the original data scores in the manually taken-over data dimension according to an embodiment of the present disclosure. The horizontal axis represents the scores of the original data, the vertical axis represents the distribution probability of the original data scores, and the normal distribution curve represents the distribution probability of the original data scores.

[0086] For example, when determining the value of a vehicle stop using a score-based evaluation method, if the vehicle stop scores greater than 4 in a certain dimension, then the vehicle stop has a high value in that dimension; if the vehicle stop scores less than 4 but greater than 2 in that dimension, then the vehicle stop has a medium value in that dimension; and if the vehicle stop scores less than 2 in that dimension, then the vehicle stop has a low value in that dimension.

[0087] It should be noted that the evaluation results of the above-mentioned vehicle stop stations in various dimensions can be determined using distributed Spark SQL computing tasks or offline Python scripts.

[0088] It should be noted that the embodiments disclosed herein do not limit the method for determining the scoring mapping interval. For example, the scoring mapping interval of the original data can also be determined based on the probability density area of ​​the original data.

[0089] In some implementations, Method Two is similar to Method One. To ensure the reasonableness of the value of vehicle stop locations, the type of vehicle stop also needs to be considered when evaluating the value of vehicle stop locations in this dimension. The specific methods are as follows:

[0090] Based on the type of vehicle stop, a corresponding second evaluation threshold is determined, which is used to determine the evaluation result based on the score;

[0091] Using this score and the second evaluation threshold, the evaluation result of the vehicle stop in this dimension is determined.

[0092] The method proposed in this disclosure can classify the raw data of at least one dimension of each vehicle stop under a unified standard for value assessment. This method facilitates management, maintenance, and visualization.

[0093] The above content briefly introduces how to evaluate the raw data of at least one dimension of the vehicle stop.

[0094] Next, this embodiment of the disclosure can use the evaluation results of each vehicle stop in each dimension to evaluate the value of each vehicle stop. As shown in Table 1, the number of rides at a vehicle stop can be used as the evaluation criterion, combined with at least one of the following: stop data, network latency, and walking distance, to determine the range of station value.

[0095]

[0096] Table 1

[0097] The scores for the docking data / network latency / walking distance metrics in Table 1 can be determined based on the average, maximum, minimum, or weighted average of the docking data, network latency, and walking distance values. This disclosure does not limit the method used to determine the docking data / network latency / walking distance metrics.

[0098] To reduce the number of inappropriate vehicle stop locations, maximize the user's riding experience, and shorten the user's walking distance, this disclosure also proposes methods for adjusting and / or setting vehicle stop locations, including:

[0099] Identify a plurality of first locations that are at a distance greater than or equal to a preset threshold from the vehicle stop, the first location including the location that calls the first vehicle, the first vehicle being the vehicle that responds to the call and stops at the vehicle stop;

[0100] Clustering these multiple first positions yields cluster centers;

[0101] Based on the location of the cluster center, determine the adjusted location of the vehicle's stop;

[0102] Based on this adjustment, the vehicle stop location will be adjusted and / or a new vehicle stop location will be set up.

[0103] It should be noted that when adjusting the vehicle stop and / or setting up a new vehicle stop based on the adjusted location, social factors also need to be considered, such as determining whether the adjusted location allows for the establishment of a vehicle stop.

[0104] Since the value of vehicle parking stations is easily affected by external environmental factors such as social environment, natural environment and human factors, this disclosure proposes an automated offline vehicle parking station evaluation method in order to accurately determine the current value of vehicle parking stations. This method can be a routine periodic task; or it can be executed when the trigger conditions are set in advance.

[0105] In some implementations, this disclosure embodiment acquires raw data for at least one dimension of each vehicle stop for multiple vehicle stops, including:

[0106] According to a pre-set cycle, the first data obtained by parsing and / or processing log data is periodically retrieved from the database;

[0107] A pre-created distributed computing task is used to statistically analyze the first data to obtain at least one of the following for each vehicle stop: network latency, stop data, and number of rides. A pre-created offline task is used to calculate the vehicle's location to obtain the walking navigation distance for each vehicle stop.

[0108] by Figure 4For example, this automated offline task can obtain raw data for at least one dimension of each vehicle stop based on data in the data warehouse. Network latency, stop data, and number of rides can be determined using distributed computing tasks (such as Spark Structured Query Language (SQL) tasks), and walking navigation distance can be determined based on vehicle location (such as GPS location). Then, based on offline Python scripts and the methods described above for determining the evaluation results of each vehicle stop in each dimension, this automated offline task can determine the score of the raw data for at least one dimension of each vehicle stop, as well as the score of each vehicle stop. It should be noted that the automated offline task proposed in this embodiment can also store the vehicle stop scores in a database.

[0109] The data in the aforementioned data warehouse can be obtained by cleaning and processing vehicle logs, cloud logs, and third-party data. Vehicle logs refer to time-dimensional log data generated periodically by various modules of the autonomous vehicle; these modules can include at least one of the terminal module, network module, and GPS module. Cloud logs refer to operational data at various stages, such as vehicle scheduling data and order status, stored on a cloud server. Third-party data refers to external data that affects the operation of autonomous vehicles, such as traffic accident data, road infrastructure data, pedestrian traffic data, and weather data.

[0110] In some embodiments, this disclosure also provides an overall flowchart of the vehicle stop evaluation method, which illustrates the specific implementation of the aforementioned vehicle stop evaluation method. For example... Figure 5 As shown, this embodiment of the disclosure can extract raw data for at least one dimension of each vehicle stop based on data in the database, and determine the evaluation results of each vehicle stop in each dimension through the above-described method two. The scoring range for the raw data in each dimension is 0-5 points, for example. Then, the value of each vehicle stop is determined based on the evaluation results in each dimension, and inferior and superior vehicle stops are identified based on their values. Inferior vehicle stops are adjusted and / or new vehicle stops are established. It should be noted that the vehicle stop evaluation method proposed in this embodiment can also evaluate the value of adjusted and newly established vehicle stops.

[0111] The evaluation method for the aforementioned vehicle parking stations can be a routine, periodic task; or it can be executed when the trigger conditions are set in advance.

[0112] This disclosure also proposes an evaluation device for vehicle parking stations. Figure 6 This is a schematic diagram of the structure of a vehicle stop evaluation device 600 according to an embodiment of the present disclosure, including:

[0113] The acquisition module 610 is used to acquire raw data of at least one dimension of each vehicle stop for multiple vehicle stops, wherein the at least one dimension includes at least one of network latency, walking navigation distance, stop data and number of rides;

[0114] The first determining module 620 is used to determine the evaluation result of each vehicle stop in each dimension using the raw data of at least one dimension of each vehicle stop; and,

[0115] Evaluation module 630 is used to evaluate the value of each vehicle stop by using the evaluation results of each vehicle stop in each dimension.

[0116] In some implementations, the docking data includes at least one of emergency braking data, manual takeover data, and docking duration data.

[0117] In some implementations, the raw data for at least one dimension of each vehicle stop is obtained by parsing and / or processing log data, the processing including at least one of cleaning, filtering and extraction;

[0118] The log data includes at least one of the following: the operation logs of autonomous vehicles, the operation logs of cloud servers, and third-party data.

[0119] In some implementations, the first determining module 620 is configured to:

[0120] For each dimension, the following methods are used to determine the evaluation result of each vehicle stop in that dimension:

[0121] Determine the raw data for each vehicle stop in this dimension;

[0122] The determined raw data is sorted in a predetermined order to obtain the raw data sequence;

[0123] Based on the original data sequence, the evaluation results of each vehicle stop in this dimension are determined.

[0124] In some implementations, the first determining module 620 is configured to:

[0125] For each vehicle stop, determine the quantile of the original data for that dimension in the original data sequence; and, based on the type of the vehicle stop, determine the corresponding first evaluation threshold, which is used to determine the evaluation result based on the quantile.

[0126] Using the quantile and the first evaluation threshold, the evaluation result of the vehicle stop in this dimension is determined.

[0127] In some implementations, the first determining module 620 includes:

[0128] The first determining submodule 621 is used to determine the scoring range corresponding to the original data of this dimension;

[0129] Submodule 622 is used to divide the scoring range into multiple scoring mapping intervals;

[0130] A submodule 623 is established to determine multiple original data corresponding to each scoring mapping interval based on the original data sequence, and to put the corresponding original data into the scoring mapping interval in order to establish a mapping relationship between the original data and the scores.

[0131] The second determining submodule 624 is used to determine the score corresponding to the original data of each vehicle stop in this dimension by utilizing the mapping relationship between the original data and the score.

[0132] The third determining submodule 625 is used to determine the evaluation result of each vehicle stop in this dimension using the score.

[0133] In some implementations, the third determining submodule 625 is used for:

[0134] Based on the type of vehicle stop, a corresponding second evaluation threshold is determined, which is used to determine the evaluation result based on the score;

[0135] Using this score and the second evaluation threshold, the evaluation result of the vehicle stop in this dimension is determined.

[0136] In some implementations, the type of vehicle stop is determined based on the location of the vehicle stop.

[0137] In some implementations, the acquisition module 610 is used for:

[0138] According to a pre-set cycle, the first data obtained by parsing and / or processing log data is periodically retrieved from the database;

[0139] The first data is statistically analyzed using a pre-created distributed computing task to obtain at least one of the following for each vehicle stop: network latency, stop data, and number of rides. The vehicle's location is calculated using a pre-created offline task to obtain the walking navigation distance for each vehicle stop.

[0140] Figure 7 This is a schematic diagram of the structure of a vehicle stop evaluation device 700 according to an embodiment of the present disclosure, as shown below. Figure 7 As shown, in some embodiments, it also includes:

[0141] The second determining module 740 is used to determine a plurality of first locations whose distance from the vehicle stop is greater than or equal to a preset threshold, the first location including the location of calling the first vehicle, the first vehicle being the vehicle that responds to the call and stops at the vehicle stop;

[0142] Clustering module 750 is used to cluster multiple first positions to obtain cluster centers;

[0143] The adjustment module 760 is used to determine the adjustment position of the vehicle stop based on the location of the cluster center.

[0144] The site management module 770 is used to adjust the vehicle stop site and / or set a new vehicle stop site based on the adjusted location.

[0145] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0146] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0147] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0148] like Figure 8As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0149] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0150] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the vehicle stop evaluation method. For example, in some embodiments, the vehicle stop evaluation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the vehicle stop evaluation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform an evaluation method for vehicle docking stations by any other suitable means (e.g., by means of firmware).

[0151] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0152] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0153] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0154] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0155] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0156] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0157] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0158] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An evaluation method for parking stations of autonomous driving operating vehicles, comprising: For multiple vehicle stop locations, raw data for at least one dimension of each stop is acquired. This at least one dimension includes stop data, network latency, walking navigation distance, and number of rides. The vehicle stop locations include those where autonomous vehicles transport passengers. The network latency includes the network transmission latency between the vehicle and the server at each stop. The stop data represents the parking complexity of the stop. The walking navigation distance represents the convenience of user access to the vehicle. The number of rides represents the utilization rate of the stop. For each of the aforementioned dimensions, the original data for each vehicle stop in that dimension is determined; the determined original data is sorted in a predetermined order to obtain an original data sequence; based on the original data sequence, the evaluation result for each vehicle stop in that dimension is determined; and, The value of each vehicle stop is assessed using the evaluation results of each of the vehicle stops in each of the dimensions. A plurality of first locations are determined that are at a distance greater than or equal to a preset threshold from the vehicle stop. The first location includes the location where a first vehicle is called, and the first vehicle is a vehicle that responds to the call and stops at the vehicle stop. Clustering is performed on the plurality of first locations to obtain cluster centers; Based on the location of the cluster center, determine the adjustment location of the vehicle stop; Based on the adjusted location, the vehicle stopping points may be adjusted and / or new vehicle stopping points may be set up.

2. The method according to claim 1, wherein, The docking data includes at least one of emergency braking data, manual takeover data, and docking duration data.

3. The method according to claim 1, wherein, The raw data for at least one dimension of each vehicle stop is obtained by parsing and / or processing the log data, wherein the processing includes at least one of cleaning, filtering and extraction. The log data includes at least one of the following: the operation logs of autonomous vehicles, the operation logs of cloud servers, and third-party data.

4. The method according to claim 1, wherein, The step of determining the evaluation result of each vehicle stop in the dimension based on the original data sequence includes: For each vehicle stop, determine the quantile of the original data of the dimension of the vehicle stop in the original data sequence; and, according to the type of the vehicle stop, determine the corresponding first evaluation threshold, which is used to determine the evaluation result based on the quantile. Using the quantiles and the first evaluation threshold, the evaluation result of the vehicle stop station in that dimension is determined.

5. The method according to claim 1, wherein, The step of determining the evaluation result of each vehicle stop in the dimension based on the original data sequence includes: Determine the scoring range corresponding to the original data of the stated dimension; The scoring range is divided into multiple scoring mapping intervals; Based on the original data sequence, determine multiple original data corresponding to each of the scoring mapping intervals, and put the corresponding original data into the scoring mapping interval to establish a mapping relationship between the original data and the scores; By utilizing the mapping relationship between the raw data and the scores, the score corresponding to the raw data of each vehicle stop in the dimension is determined; Using the scoring, the evaluation result of each of the vehicle stops in that dimension is determined.

6. The method according to claim 5, wherein, The process of using the scoring to determine the evaluation result of each vehicle stop in the dimension includes: Based on the type of vehicle stop, a corresponding second evaluation threshold is determined, which is used to determine the evaluation result based on the score. Using the score and the second evaluation threshold, the evaluation result of the vehicle stop station in that dimension is determined.

7. The method according to claim 4 or 6, wherein, The type of vehicle stop is determined based on the location of the vehicle stop.

8. The method according to claim 1, wherein, The process of acquiring raw data for at least one dimension of each vehicle stop for multiple vehicle stops includes: According to a pre-set cycle, the first data obtained by parsing and / or processing log data is periodically retrieved from the database; The first data is statistically analyzed using a pre-created distributed computing task to obtain at least one of the following for each vehicle stop: network latency, stop data, and number of rides; and the vehicle's location is calculated using a pre-created offline task to obtain the walking navigation distance for each vehicle stop.

9. An evaluation device for parking stations of autonomous driving operating vehicles, comprising: The acquisition module is used to acquire raw data for at least one dimension of each vehicle stop for multiple vehicle stops. The at least one dimension includes stop data, and also includes network latency, walking navigation distance, and number of rides. The vehicle stops include stops where autonomous driving vehicles pick up and drop off passengers. The network latency includes the network transmission latency between the vehicle and the server at each vehicle stop. The stop data characterizes the parking complexity of the vehicle stops. The first determining module is used to determine the original data of each vehicle stop in each dimension; sort the determined original data in a predetermined order to obtain an original data sequence; and determine the evaluation result of each vehicle stop in the dimension based on the original data sequence. as well as, An evaluation module is used to evaluate the value of each vehicle stop using the evaluation results of each of the vehicle stops in each of the dimensions. The second determining module is used to determine a plurality of first locations whose distance from the vehicle stop is greater than or equal to a preset threshold, the first location including the location of calling the first vehicle, the first vehicle being the vehicle that responds to the call and stops at the vehicle stop; The clustering module is used to cluster the plurality of first locations to obtain cluster centers; An adjustment module is used to determine the adjustment position of the vehicle stopping station based on the location of the cluster center; The station management module is used to adjust the vehicle stopping stations and / or set new vehicle stopping stations according to the adjusted locations.

10. The apparatus according to claim 9, wherein, The docking data includes at least one of emergency braking data, manual takeover data, and docking duration data.

11. The apparatus according to claim 9, wherein, The raw data for at least one dimension of each vehicle stop is obtained by parsing and / or processing the log data, wherein the processing includes at least one of cleaning, filtering and extraction. The log data includes at least one of the following: the operation logs of autonomous vehicles, the operation logs of cloud servers, and third-party data.

12. The apparatus according to claim 9, wherein, The first determining module is used for: For each vehicle stop, determine the quantile of the original data for that dimension in the original data sequence. Furthermore, based on the type of the vehicle stop, a corresponding first evaluation threshold is determined, which is used to determine the evaluation result based on the quantile. Using the quantiles and the first evaluation threshold, the evaluation result of the vehicle stop station in that dimension is determined.

13. The apparatus according to claim 9, wherein, The first determining module includes: The first determining submodule is used to determine the scoring range corresponding to the original data of the dimension; A segmentation submodule is used to divide the scoring range into multiple scoring mapping intervals; A submodule is established to determine multiple original data corresponding to each of the scoring mapping intervals based on the original data sequence, and to put the corresponding original data into the scoring mapping intervals to establish a mapping relationship between the original data and the scores. The second determining submodule is used to determine the score corresponding to the original data of each vehicle stop in the dimension by utilizing the mapping relationship between the original data and the score. The third determining submodule is used to determine the evaluation result of each of the vehicle stopping stations in the dimension using the scoring.

14. The apparatus according to claim 13, wherein, The third determining submodule is used for: Based on the type of vehicle stop, a corresponding second evaluation threshold is determined, which is used to determine the evaluation result based on the score. Using the score and the second evaluation threshold, the evaluation result of the vehicle stop station in that dimension is determined.

15. The apparatus according to claim 12 or 14, wherein, The type of vehicle stop is determined based on the location of the vehicle stop.

16. The apparatus according to claim 9, wherein, The acquisition module is used for: According to a pre-set cycle, the first data obtained by parsing and / or processing log data is periodically retrieved from the database; The first data is statistically analyzed using a pre-created distributed computing task to obtain at least one of the following for each vehicle stop: network latency, stop data, and number of rides; and the vehicle's location is calculated using a pre-created offline task to obtain the walking navigation distance for each vehicle stop.

17. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

19. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-8.

Images