CN115936522A

CN115936522A - Vehicle stop station evaluation method, device, equipment and storage medium

Info

Publication number: CN115936522A
Application number: CN202211659841.4A
Authority: CN
Inventors: 李冉超; 邹静; 张博
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-12-23
Filing date: 2022-12-23
Publication date: 2023-04-07

Abstract

The disclosure provides a vehicle stop station evaluation method, device, equipment and storage medium, and relates to the field of artificial intelligence, in particular to the fields of automatic driving, intelligent traffic and the like. The specific implementation scheme is as follows: for a plurality of vehicle stop stations, acquiring original data of at least one dimension of each vehicle stop station, wherein the at least one dimension comprises at least one of network delay, walking navigation distance, stop data and riding times; determining an evaluation result of each vehicle stop station in each dimension by using the original data of at least one dimension of each vehicle stop station; and evaluating the value of each vehicle stop station by adopting the evaluation result of each dimension of each vehicle stop station. The present disclosure enables multi-dimensional value assessment for multiple vehicle docking stations.

Description

Vehicle stop station evaluation method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and in particular to the fields of automatic driving, intelligent traffic, etc.

Background

With the development of the automatic driving technology, the automatic driving of the taxi gradually becomes a travel mode of people. However, in actual life, due to the fact that urban road scenes are complex, social vehicles, pedestrians and environments are changeable, automatic driving taxis cannot be the same as those of people driving taxis, and flexible parking at any position can be achieved.

Therefore, in consideration of the aspects of pedestrian safety, road traffic, laws and regulations and the like, a certain number of parking stations are built at specified positions in the area, and the operation of automatically driving taxis at the present stage is facilitated.

Disclosure of Invention

The disclosure provides a vehicle docking station evaluation method, device, equipment and storage medium.

According to an aspect of the present disclosure, there is provided an evaluation method of a vehicle docking station, including:

for a plurality of vehicle stop stations, obtaining original data of at least one dimension of each vehicle stop station, wherein the at least one dimension comprises at least one of network delay, walking navigation distance, stop data and riding times;

determining an evaluation result of each vehicle stop station in each dimension by using the original data of at least one dimension of each vehicle stop station; and (c) a second step of,

and evaluating the value of each vehicle stop station by adopting the evaluation result of each dimension of each vehicle stop station.

According to another aspect of the present disclosure, there is provided an evaluation apparatus of a vehicle stop, including:

the system comprises an acquisition module, a display module and a control module, wherein the acquisition module is used for acquiring at least one dimension of original data of each vehicle stop station aiming at a plurality of vehicle stop stations, and the at least one dimension comprises at least one of network delay, walking navigation distance, stop data and riding times;

the first determination module is used for determining the evaluation result of each vehicle stop station in each dimension by using the original data of at least one dimension of each vehicle stop station; and the number of the first and second groups,

and the evaluation module is used for evaluating the value of each vehicle stop station by adopting the evaluation result of each vehicle stop station in each dimension.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to cause the at least one processor to perform a method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of the embodiments of the present disclosure.

According to the vehicle stop station evaluation method, value evaluation is performed on each vehicle stop station by using the original data of at least one dimension of the plurality of vehicle stop stations. In the process of evaluating the vehicle stop stations, factors of all dimensions of the vehicle stop stations are comprehensively considered, and the reliability of the value evaluation of the vehicle stop stations is improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of an implementation of a method 200 of evaluating a vehicle docking station according to an embodiment of the present disclosure;

FIG. 3A is a schematic diagram of a distribution probability of raw data for a manual takeover of data dimensions, according to an embodiment of the present disclosure;

FIG. 3B is a schematic diagram of a distribution probability of raw data scores for manually taking over a data dimension, according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of an automated offline vehicle stop assessment method according to an embodiment of the present disclosure;

FIG. 5 is an overall flow diagram schematic of a vehicle stop assessment method according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an evaluation device 600 of a vehicle stop station according to an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an evaluation device 700 of a vehicle docking station according to an embodiment of the present disclosure;

fig. 8 illustrates a schematic block diagram of an example electronic device 1300 that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The term "and/or" herein is merely an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The term "at least one" herein means any combination of any one or more of a plurality, for example, including at least one of a, B, C, and may mean including any one or more elements selected from the group consisting of a, B, and C. The terms "first" and "second" used herein refer to and distinguish one from another in the similar art, without necessarily implying a sequence or order, or implying only two, such as first and second, to indicate that there are two types/two, first and second, and first and second may also be one or more.

With the development of the automatic driving technology, the automatic driving taxi gradually becomes a travel mode of people. However, in actual life, due to the fact that urban road scenes are complex, social vehicles, pedestrians and environments are changeable, automatic driving taxis cannot be the same as those of people driving taxis, and flexible parking at any position can be achieved. Therefore, in consideration of pedestrian safety, road traffic, laws and regulations and the like, a certain number of vehicle parking stations are built at specified positions in the area, and the operation of automatically driving taxies at the present stage is facilitated.

At present, a vehicle parking station is usually set up by depending on experience, but the determined vehicle parking station is not reasonable enough and cannot meet the travel requirements of people. Therefore, how to realize more scientific multidimensional assessment of vehicle stop stations according to the existing vehicle stop stations and the operation capacity of automatically driving taxis becomes an increasingly important problem.

The assessment method for the vehicle stop station provided by the embodiment of the disclosure can realize scientific multidimensional assessment of the vehicle stop station. Fig. 1 is a schematic view of an application scenario according to an embodiment of the present disclosure, and a vehicle related to the present disclosure may include an autonomous vehicle. In some embodiments, the vehicle docking station evaluation system 100 can evaluate the value of an existing vehicle docking station. As shown in fig. 1, the evaluation system 100 of the vehicle docking station may include a collection device 110, a storage device 120, and a processing device 130. The collection device 110 may be configured to collect driving data of a vehicle and/or operation data of a vehicle stop; the storage device 120 may be used to store travel data for the vehicle and/or operational data for the vehicle docking station; the processing device 130 is used to evaluate the value of the vehicle docking station based on the data in the storage device 120. In some embodiments, the vehicle docking station evaluation system 100 may further include a network for facilitating the exchange of travel data of the vehicle and/or operational data of the vehicle docking station. In some embodiments, one or more components (e.g., the acquisition device 110, the processing device 120, or the storage device 130) in the vehicle docking station evaluation system 100 may send the vehicle's travel data and/or the vehicle docking station's operational data to other components in the vehicle docking station evaluation system 100 over a network. It should be noted that the network may be any type of wired or wireless network.

The embodiment of the present disclosure provides an evaluation method for a vehicle stop, and fig. 2 is an implementation flowchart of an evaluation method 200 for a vehicle stop according to an embodiment of the present disclosure, including:

s210: for a plurality of vehicle stop stations, obtaining original data of at least one dimension of each vehicle stop station, wherein the at least one dimension comprises at least one of network delay, walking navigation distance, stop data and riding times;

s220: determining an evaluation result of each vehicle stop station in each dimension by using the original data of at least one dimension of each vehicle stop station; and the number of the first and second groups,

s230: and evaluating the value of each vehicle stop station by adopting the evaluation result of each dimension of each vehicle stop station.

The evaluation method for the vehicle stop station provided by the embodiment of the disclosure can be periodically performed; or the trigger condition is preset and executed when the trigger condition is met. For example, an execution cycle is set in advance to T, a timer is set in an apparatus for executing the vehicle stop point evaluation method, and an initial value of the timer is set to 0; starting a timer, when the timer reaches T, executing the evaluation of each vehicle stop station, and resetting the timer to be 0; the timer is started again and the process loops. For another example, setting the range of the sum of the number of times of riding of all vehicle stop stations within 24 hours as [ n1, n2], and when the sum of the number of times of riding of all vehicle stop stations within 24 hours is less than n1, performing evaluation on each vehicle stop station; alternatively, when the sum of the number of times of riding of all the vehicle stop stations in 24 hours is larger than n2, the evaluation of each vehicle stop station is performed.

The evaluation method for the vehicle stop stations, which is provided by the embodiment of the disclosure, can determine the value of each vehicle stop station according to the evaluation result of the original data of each dimension, namely, scientific multi-dimensional evaluation is performed on the vehicle stop stations. The value of a vehicle stop may refer to the degree of quality of the vehicle stop, such as whether it is suitable as a stop for a passenger to be picked up by an autonomous operating vehicle. Since the disclosed embodiments are based on data of the vehicle stop station in dimensions such as network delay, walking navigation distance, stop data, and riding times, the value of the vehicle stop station can be related to the aforementioned several dimensions. For example, the network delay can reflect the autonomous driving capability of an autonomous vehicle at the vehicle stop, so the smaller the network delay, the higher the value of the vehicle stop. For another example, a smaller walking navigation distance indicates that it is more convenient for the user to reach the vehicle stop, and thus a smaller walking navigation distance is more valuable for the vehicle stop. For example, the larger the number of times of riding, the more the user chooses to get on or off the vehicle at the vehicle stop, and therefore the larger the number of times of riding, the higher the value of the vehicle stop.

In one example, in step S210, the raw data of at least one dimension of each vehicle docking station can be obtained by parsing and/or processing the log data, wherein the processing includes at least one of washing, filtering and extracting;

wherein the log data includes at least one of an operation log of the autonomous vehicle, an operation log of the cloud server, and third party data.

In some embodiments, the log data may refer to multi-dimensional data for various stages of the autonomous vehicle during travel. It should be noted that the operation log of the autonomous driving vehicle may refer to time dimension log data generated by periodically dotting each module of the autonomous driving vehicle, where each module may include at least one of a human machine interface (hmi) terminal module, a network module, and a Global Positioning System (gps) module; the operation log of the cloud server can refer to vehicle scheduling data or operation data of each stage such as order states and the like which are checked and stored by the cloud server; the third party data may refer to external data that affects the travel of the autonomous vehicle, such as traffic accident data, asset data, road traffic data, or weather data.

In some embodiments, the log data may be destaged to the data repository by means of a hard disk and/or network communication.

Abnormal data, such as duplicate data, data with missing contents, redundant data or error data, inevitably occurs in the log data during the generation process. Therefore, the embodiment of the present disclosure may further process the log data to obtain original data with higher accuracy at each vehicle stop station.

In some embodiments, at least one of a cleaning process, a filtering process, and an extraction process may be employed in processing the log data.

Specifically, the cleaning process may screen out duplicate or redundant data in the log data, and perform a clearing process on the screened data; meanwhile, the cleaning treatment can also modify and/or delete incorrect data in the log data and supplement missing parts in the log data to obtain data which can be further processed. The filtering process may screen out data that satisfies a preset condition and/or includes a critical portion from the log data to obtain optimal data. The extraction processing may extract a part or all of the data satisfying a preset condition from the log data. It should be noted that the three processing methods of the log data are only examples, and the disclosure does not limit the specific processing method of the log data.

The method and the device for evaluating the value of the vehicle stop station adopt the multi-dimensional log data to evaluate the value of the vehicle stop station, can comprehensively evaluate all dimensions of the vehicle stop station, and improve the credibility of the value evaluation of the vehicle stop station.

It is emphasized that the log data described above may include raw data for at least one dimension of each vehicle docking station. Wherein the dimension may include at least one of network latency, walking navigation distance, parking data, and number of rides. Of course, the dimensions of the original data provided by the embodiments of the present disclosure are merely examples, and the present disclosure does not limit the dimensions of the original data; in addition to the foregoing dimensions, embodiments of the present disclosure may utilize raw data of other dimensions for site evaluation. It should be noted that the specific dimension of the raw data generally depends on the service requirement and the plan of the vehicle parking station, for example, the dimension of the raw data may further include a waiting time of a user, a waiting time of a vehicle, or a vehicle comfort level of the user.

In some embodiments, the network delay may include a network transmission delay between the vehicle and the server at each vehicle stopping point. It should be noted that the network delay can reflect the autonomous driving capability of the autonomous vehicle at the vehicle stop location. For example, the autopilot capability of an autonomous vehicle may be a primary rider capability, a secondary rider capability, or a full unmanned capability. Generally, the lower the network delay of a vehicle stop, the higher the autopilot capability of the autonomous vehicle at the vehicle stop.

The walking navigation distance may include a distance between a location at which the vehicle is parked and a point at which the user desires to get on the vehicle. It should be noted that the walking navigation distance can reflect the degree of convenience of the user in riding the car. For example, the closer the walking navigation distance, i.e., the distance between the position of the vehicle stop point and the point where the user desires to get on, the higher the convenience of the user taking a car. Generally, the higher the convenience degree of the user for taking a car, the higher the willingness degree of the user to take the car at the car stop station.

The number of rides may refer to the number of times a user rides an autonomous vehicle at the vehicle stop. It should be noted that the number of rides can reflect the usage rate of the vehicle stop. For example, the more the number of times of riding a user to the vehicle stop station is, the higher the usage rate of the vehicle stop station is. In general, the higher the usage rate of the vehicle stop, the higher the possibility that the user gets on the bus at the vehicle stop.

The parking data may refer to the parking complexity of the vehicle parking station. It should be noted that the parking data can reflect the complexity of the vehicle parking station. In some embodiments, the parking data may include at least one of emergency braking data, manual take-over data, and parking duration data, in order to enable multi-dimensional evaluation of the parking data of the autonomous vehicle. For example, the larger the value of the stop data, the harder the vehicle stop is to stop, and the greater the vehicle stop is challenged to the autopilot capability of the autonomous vehicle. Of course, if the vehicle stops at a station more difficultly, the riding time of the user is increased, and the overall experience of the user is reduced. Therefore, in general, the lower the value of the stop data at the vehicle stop, the higher the riding experience of the user at the vehicle stop. The emergency braking data can refer to the emergency braking times of the automatic driving vehicle at the vehicle stop station or the ratio of the emergency braking times of the automatic driving vehicle at the vehicle stop station to the stop times; the manual takeover data can refer to the manual takeover times of the automatically-driven vehicle at the vehicle stop station or the ratio of the manual takeover times of the automatically-driven vehicle at the vehicle stop station to the stop times, wherein the manual takeover times represent the times of manually intervening the automatically-driven vehicle in the stop process; the stop duration data may 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 of the autonomous vehicle at the vehicle stop.

The method for obtaining the raw data of at least one dimension of each vehicle stop station in the embodiment of the present disclosure is briefly described above. However, when the value of the vehicle stop is evaluated, it is necessary to determine not only the raw data of each vehicle stop but also an evaluation result of raw data of at least one dimension of each vehicle stop.

Specifically, the method for determining the evaluation result of each vehicle stop station in each dimension provided by the embodiment of the disclosure comprises the following steps:

for each dimension, determining the evaluation result of each vehicle stop station in the dimension by adopting the following modes respectively:

determining the original data of each vehicle stop station in the dimension;

sequencing the determined original data according to a preset sequence to obtain an original data sequence;

and determining the evaluation result of each vehicle stop station in the dimension according to the original data sequence.

The predetermined order may be from large to small, or from small to large, that is, the original data may be sorted in the order from large to small, or from small to large, so as to obtain the original data sequence. Of course, the present disclosure is not limited to the predetermined order.

The method for determining the evaluation result of each vehicle stop station in each dimension by using the raw data of at least one dimension of each vehicle stop station is capable of efficiently and accurately determining the evaluation result of each vehicle stop station in each dimension.

In order to determine the evaluation result of each vehicle stop station in the dimension more accurately according to the original data sequence, the embodiment of the present disclosure provides the following two implementation manners, and specific implementation methods of the two manners are different. It should be emphasized that the two ways presented by the embodiments of the present disclosure are merely examples, and the present disclosure is not limited to the way of determining the evaluation result of each vehicle stop station in each dimension.

The method I comprises the following steps: quantile evaluation method

In determining the evaluation result of the vehicle docking station in a certain dimension, the method at least comprises the following steps:

for each vehicle stop station, determining the quantile of the original data of the dimension of the vehicle stop station in the original data sequence; determining a corresponding first evaluation threshold according to the type of the vehicle stop station, wherein the first evaluation threshold is used for determining an evaluation result according to the quantile;

and determining the evaluation result of the vehicle stopping station in the dimension by using the quantile and the first evaluation threshold value.

The quantile in the disclosed embodiment is a numerical value that may represent the position of the vehicle docking station's raw data in the dimensional raw data sequence. For example, when the quantile of the original data of the vehicle stop station in the original data sequence of the dimension is 70 quantiles, it means that the original data of the vehicle stop station is greater than 70% of the original data in the original data sequence of the dimension.

For example, the evaluation result of the vehicle stop station in the dimension can be divided into: high, medium and low. The first evaluation threshold comprises 70% and 35% and is used for determining an evaluation result according to the quantile of the original data in the original data sequence; of these, 70% are used to divide the "high" evaluation result and the "medium" evaluation result, and 35% are used to divide the "medium" evaluation result and the "low" evaluation result. When the assessment result of the vehicle stop station is determined by a quantile assessment method, if the quantile of the original data of the vehicle stop station in the dimension in the original data sequence is more than 70%, determining that the assessment result of the vehicle stop station in the dimension is 'high'; if the quantile of the original data of the vehicle stop station in the dimension in the original data sequence is less than 70% and more than 35%, determining that the evaluation result of the vehicle stop station in the dimension is 'medium'; and if the quantile of the original data of the vehicle stop station in the dimension in the original data sequence is less than 35%, determining that the evaluation result of the vehicle stop station in the dimension is low.

It should be noted that the evaluation result of the vehicle stop station in each dimension can be determined by using a distributed spark sql calculation task or an offline python script.

In some embodiments, since the value of the vehicle stop station may also be affected by external factors such as time, weather, or people, the type of vehicle stop station may also need to be considered when evaluating the value of the vehicle stop station. The type of the vehicle stop may be determined by the location of the vehicle stop. Generally, the manner in which the type of the vehicle stop is determined based on the position of the vehicle stop is more accurate and representative than other manners in which the type of the vehicle stop is determined. Wherein the location of the vehicle docking station may include at least one of a school, a mall, a subway, a residential area, and a bus station. Of course, the embodiments of the present disclosure do not limit the position of the vehicle stop, and in general, the vehicle stop may be set in any position that meets the vehicle stop setting standard.

The reason for the type of vehicle docking station needs to be taken into account when evaluating the value of the vehicle docking station, mainly because the type of vehicle docking station has an impact on a reasonable threshold range of the raw data of the vehicle docking station, for example, the traffic of a vehicle docking station located at a subway is significantly greater than that of a vehicle docking station located at a residential district. Therefore, in order to ensure the rationality of the value of the vehicle stop, it is necessary to determine the first evaluation threshold of the vehicle stop in each dimension according to the type of the vehicle stop, for example, in the number of times of ride dimension, the first evaluation threshold of the vehicle stop located at the subway needs to be larger than the first evaluation threshold of the vehicle stop located at the residential area.

The method for determining the evaluation result of the vehicle stop station in the dimension, which is required to be provided by the embodiment of the disclosure, may determine the first evaluation threshold value of the dimension according to the type of the vehicle stop station, and then determine the evaluation result of the vehicle stop station in the dimension based on the first evaluation threshold value and the quantile of the vehicle stop station in the dimension.

The method and the device comprehensively consider the influence of the complex road scene of the city on the value of the vehicle stop station, and can scientifically and multidimensional evaluate the value of the vehicle stop station.

The second method comprises the following steps: score evaluation method

determining a grading range corresponding to the original data of the dimension;

dividing the grading range into a plurality of grading mapping intervals;

determining a plurality of original data corresponding to each rating mapping interval according to the original data sequence, and putting the corresponding original data into the rating mapping interval to establish a mapping relation between the original data and the rating;

determining scores corresponding to the original data of the vehicle parking stations in the dimension by utilizing the mapping relation between the original data and the scores;

and determining the evaluation result of each vehicle stop station in the dimension by using the score.

In some embodiments, the second method first determines the score range corresponding to the raw data of the dimension. For example, the score range corresponding to the raw data of the dimension may be determined as 0 to 5 points, where 0 point represents the worst raw data, and 5 points represents the best raw data.

Next, to facilitate management of maintenance and visualization operations, the embodiments of the present disclosure propose to determine a plurality of score-original value mapping relationships, i.e., score mapping intervals, based on the distribution and score range of the original data. The method comprises the steps of firstly confirming the mean value of an original data sequence, then determining the score of the mean value, and then establishing the mapping relation of the score and the original data on the basis of the mapping relation of the mean value and the score.

For example, fig. 3A is a schematic diagram of a distribution probability of raw data for manually taking over a data dimension according to an embodiment of the present disclosure. The abscissa represents the raw data, the ordinate represents the distribution probability of the raw data, and the normal distribution curve represents the distribution probability of the raw data. As shown in fig. 3A, the mean of the raw data is about 0.08, and the standard deviation σ of the normal distribution curve is about 0.08. Taking a score range of 0-5 as an example, a score corresponding to a mean value of 0.08 of the original data may be preset as a middle value of the score range, that is, 2.5 scores. The parking complexity of the vehicle parking station is higher as the raw data of the manual takeover dimension is larger, that is, the score of the vehicle parking station in the manual takeover data dimension is lower if the raw data of the manual takeover data dimension is larger. And determining the mapping relation between the scores and the original data according to a manual taking over data dimension scoring principle, the mapping relation between the original data mean value and the scores and the standard deviation sigma of a normal distribution curve. Specifically, if the score corresponding to one interval of the normal distribution curve is 0.5, the score-raw data correspondence relationship is as follows: the corresponding score of 0-0.08 of the original data is 3-2.5; the corresponding score of 0.08-0.16 of the original data is 2.5-2; the corresponding score of 0.16-0.24 of the original data is 2-1.5; the corresponding score of the original data of 0.24-0.32 is 1.5-1; the corresponding score of 0.32-0.40 of the original data is 1-0.5; raw data 0.40-0.48 corresponds to scores of 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.

It should be noted that there may be a problem that the raw data and the score range may not be in one-to-one correspondence. For example, taking the above-mentioned manual takeover data dimension as an example, the score range is 0-5 points, while the score of the original data of the manual takeover dimension is only between 0-3 points. This phenomenon results in an overconcentration of the mapping relationships between raw data and scores at 0-3, and the score range of 0-5 cannot be fully utilized, and it is also not easy to determine the score of each vehicle stop in that dimension. Therefore, the embodiment of the present disclosure may also adjust the relationship between unreasonable original data and score mapping, as shown in fig. 3B, the mapping relationship between the manually taken over data and score may be scaled from 0 to 3 to 0 to 5. Fig. 3B is a schematic diagram of a distribution probability of raw data scores for manually taking over data dimensions according to an embodiment of the present disclosure, where an abscissa represents the scores of the raw data, an ordinate represents the distribution probability of the raw data scores, and a normal distribution curve represents the distribution probability of the raw data scores.

For example, when the value of the vehicle stop is determined by a score evaluation method, if the score of the vehicle stop in the dimension is greater than 4, the value of the vehicle stop in the dimension is high; if the score of the vehicle stop station in the dimension is less than 4 and greater than 2, the value of the vehicle stop station in the dimension is middle; if the vehicle stop score in that dimension is less than 2, then the value of that vehicle stop in that dimension is low.

It should be noted that the method for determining the score mapping interval is not limited in the embodiments of the present disclosure, and for example, the score mapping interval of the raw data may also be determined according to the probability density area of the raw data.

In some embodiments, in a manner similar to the first manner, in order to ensure the rationality of the value of the vehicle docking station, the type of vehicle docking station also needs to be considered when evaluating the value of the vehicle docking station in this dimension, as follows:

determining a corresponding second evaluation threshold according to the type of the vehicle stop station, wherein the second evaluation threshold is used for determining an evaluation result according to the grade;

and determining an evaluation result of the vehicle stopping station in the dimension by using the score and the second evaluation threshold.

The method provided by the embodiment of the disclosure can be used for performing value evaluation on the original data of at least one dimension of each vehicle parking station under the unified standard. The method is convenient for management maintenance and visualization operation.

The foregoing briefly describes how raw data for at least one dimension of the vehicle docking station may be evaluated.

Then, the embodiment of the present disclosure may perform value evaluation on each vehicle stop station by using the evaluation result of each vehicle stop station in each dimension. As shown in table 1, the division range of the station value may be determined by using the number of times of taking a bus at a vehicle stop station as a criterion in combination with at least one of stop data, network delay, and walking distance.

TABLE 1

The score for the docking data/network delay/walking distance index in table 1 may be determined from the average, maximum, minimum, weighted average, etc. of the docking data, network delay, and walking distance values. Embodiments of the present disclosure are not limited to methods of determining a landing data/network delay/walking distance index.

In order to reduce the setting of unreasonable vehicle stop stations, improve the riding experience of users to the maximum extent, and shorten the walking distance of users, the embodiment of the disclosure further provides a method for adjusting and/or setting the vehicle stop stations, which includes:

determining a plurality of first locations having a distance from the vehicle stop greater than or equal to a preset threshold, the first locations including a location to call a first vehicle, the first vehicle being a vehicle that responds to the call and stops at the vehicle stop;

clustering the plurality of first positions to obtain a clustering center;

determining the adjusting position of the vehicle stop station according to the position of the clustering center;

and adjusting the vehicle stop station and/or setting a new vehicle stop station according to the adjusting position.

It should be noted that, depending on the adjusted position, social factors are also taken into consideration when adjusting the vehicle stop and/or setting up a new vehicle stop, for example, determining whether the adjusted position allows the vehicle stop to be established.

Because the value of a vehicle stop station is easily influenced by external environments such as social environments, natural environments, human factors and the like, in order to accurately determine the value of the current vehicle stop station, the embodiment of the disclosure provides an automatic off-line vehicle stop station evaluation method, which can be a routine periodic task; or the trigger condition is preset and executed when the trigger condition is met.

In some embodiments, the obtaining raw data for at least one dimension of each vehicle docking station for a plurality of vehicle docking stations in embodiments of the present disclosure includes:

according to a preset period, periodically acquiring first data obtained by analyzing and/or processing log data from a database;

counting the first data by adopting a pre-established distributed computing task to obtain at least one of network delay, stop data and riding times of each vehicle stop station; and calculating the positions of the vehicles by adopting a pre-established off-line task to obtain the walking navigation distance of each vehicle stop station.

Taking fig. 4 as an example, the automatic offline task may obtain raw data of at least one dimension of each vehicle stop station according to data in the data warehouse, where the network delay, the stop data, and the number of times of taking a bus may be determined according to a distributed computing task (e.g., a Spark Structured Query Language (SQL) computing task), and the walking navigation distance may be determined according to a vehicle location (e.g., a Global Positioning System (GPS) location). The automated offline task may then determine a score for the raw data for at least one dimension of each vehicle docking station, and a score for each vehicle docking station, based on the offline python script and the above-described method of determining the results of the evaluation of each vehicle docking station in each dimension. It should be noted that, the automated offline task proposed by the embodiment of the present disclosure may also store the score of the vehicle stop station in the database.

The data in the data warehouse can be obtained after cleaning processing is carried out according to the vehicle end log, the cloud end log and the third party data. The vehicle-end log can refer to time dimension log data generated by periodically dotting each module of the automatic driving vehicle, and each module can comprise at least one of a terminal module, a network module and a GPS module; the cloud log can refer to running data of each stage such as vehicle scheduling data, order states and the like which are checked and stored by a cloud server; the third party data may refer to external data that affects the travel of the autonomous vehicle, such as traffic accident data, asset data, road pedestrian flow data, weather data, and the like.

In some embodiments, the embodiments of the present disclosure further provide an overall flowchart of the vehicle stop point evaluation method, where the overall flowchart can represent a specific implementation manner of the vehicle stop point evaluation method. As shown in fig. 5, in the embodiment of the present disclosure, based on data in the database, raw data of at least one dimension of each vehicle docking station may be extracted, and an evaluation result of each vehicle docking station in each dimension may be determined in the above-mentioned manner two, where a score range corresponding to the raw data of each dimension is divided into 0 to 5. And then, determining the value of the vehicle stop stations according to the evaluation result of each vehicle stop station in each dimension, determining the inferior vehicle stop stations and the superior vehicle stop stations according to the value of each vehicle stop station, and adjusting the inferior vehicle stop stations and/or setting new vehicle stop stations. It should be noted that the method for evaluating a vehicle stop provided in the embodiment of the present disclosure can also evaluate the value of the adjusted vehicle stop and the newly set vehicle stop.

The above-described evaluation method of the vehicle stop station may be a routine periodic task; or the trigger condition is preset and executed when the trigger condition is met.

An embodiment of the present disclosure further provides an apparatus for evaluating a vehicle stop, and fig. 6 is a schematic structural diagram of an apparatus 600 for evaluating a vehicle stop according to an embodiment of the present disclosure, including:

an obtaining module 610, configured to obtain, for a plurality of vehicle stop stations, raw data of at least one dimension of each vehicle stop station, where the at least one dimension includes at least one of network delay, walking navigation distance, stop data, and number of rides;

a first determining module 620, configured to determine an evaluation result of each vehicle stop station in each dimension by using the raw data of at least one dimension of each vehicle stop station; and the number of the first and second groups,

the evaluation module 630 is configured to perform value evaluation on each vehicle stop station by using the evaluation result of each vehicle stop station in each dimension.

In some embodiments, the parking data includes at least one of emergency braking data, manual takeover data, and parking duration data.

In some embodiments, the raw data for at least one dimension of each vehicle docking station is obtained by parsing and/or processing the log data, the processing including at least one of washing, filtering, and extracting;

In some embodiments, the first determining module 620 is configured to:

for each dimension, determining the evaluation result of each vehicle parking station in the dimension by adopting the following modes respectively:

determining the original data of each vehicle stop station in the dimension;

In some embodiments, the first determining module 620 is configured to:

In some embodiments, the first determining module 620 includes:

the first determining submodule 621 is configured to determine a scoring range corresponding to the original data of the dimension;

a dividing sub-module 622, configured to divide the score range into a plurality of score mapping intervals;

the establishing sub-module 623 is configured to determine, according to the raw data sequence, a plurality of raw data corresponding to each score mapping interval, and place the corresponding raw data into the score mapping interval to establish a mapping relationship between the raw data and the score;

the second determining submodule 624 is configured to determine, by using a mapping relationship between the raw data and the score, a score corresponding to the raw data of each vehicle parking station in the dimension;

a third determination submodule 625, configured to determine an evaluation result of each vehicle stop station in the dimension using the score.

In some embodiments, the third determining submodule 625 is configured to:

and determining an evaluation result of the vehicle stop station in the dimension by using the score and the second evaluation threshold value.

In some embodiments, the type of the vehicle stop is determined according to a location of the vehicle stop.

In some embodiments, the obtaining module 610 is configured to:

according to a preset period, first data obtained by analyzing and/or processing the log data are periodically obtained from a database;

counting the first data by adopting a pre-established distributed computing task to obtain at least one of network delay, stop data and riding times of each vehicle stop station; and calculating the positions of the vehicles by adopting the off-line tasks established in advance to obtain the walking navigation distance of each vehicle stop station.

Fig. 7 is a schematic structural diagram of an evaluation apparatus 700 for a vehicle docking station according to an embodiment of the present disclosure, as shown in fig. 7, in some embodiments, the evaluation apparatus further includes:

a second determining module 740 for determining a plurality of first locations having a distance from the vehicle stop greater than or equal to a preset threshold, the first locations including a location of a call to a first vehicle, the first vehicle being a vehicle that responds to the call and stops at the vehicle stop;

a clustering module 750, configured to cluster the plurality of first locations to obtain a clustering center;

the adjusting module 760 is configured to determine an adjusted position of the vehicle stop according to the position of the cluster center;

a station management module 770 for adjusting the vehicle stop station and/or setting a new vehicle stop station according to the adjusted position.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 8 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 8, the apparatus 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM803, various programs and data necessary for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.

A number of components in the device 800 are connected to the I/O interface 805, including: an input unit 806, such as a keyboard, a mouse, or the like; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, or the like; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

Computing unit 801 may be a variety of general 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 dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 801 executes the respective methods and processes described above, such as the evaluation method of the vehicle stop station. For example, in some embodiments, the method of evaluating a vehicle docking station may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and/or installed onto device 800 via ROM 802 and/or communications unit 809. When the computer program is loaded into the RAM803 and executed by the computing unit 801, one or more steps of the vehicle stop station evaluation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the vehicle docking station evaluation method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

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

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a 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 acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of evaluating a vehicle docking station, comprising:

determining an evaluation result of each vehicle stop station in each dimension by using the raw data of at least one dimension of each vehicle stop station; and the number of the first and second groups,

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

3. The method of claim 1 or 2,

the original data of at least one dimension of each vehicle parking station is obtained by analyzing and/or processing the log data, wherein the processing comprises at least one of cleaning, filtering and extracting;

4. The method of any of claims 1-3, wherein said determining an assessment of each of the vehicle docking stations in each of the dimensions using raw data for at least one of the dimensions of the respective vehicle docking station comprises:

determining raw data of each vehicle stop station in the dimension;

5. The method of claim 4, wherein said determining an assessment of each of the vehicle docking stations in the dimension from the raw data sequence comprises:

for each vehicle stop station, determining a quantile of the original data of the dimension of the vehicle stop station in the original data sequence; determining a corresponding first evaluation threshold according to the type of the vehicle stop station, wherein the first evaluation threshold is used for determining an evaluation result according to the quantile;

and determining an evaluation result of the vehicle parking station in the dimension by using the quantile and the first evaluation threshold value.

6. The method of claim 4, wherein said determining an assessment of each of the vehicle docking stations in the dimension from the raw data sequence comprises:

determining a grading range corresponding to the original data of the dimensionality;

dividing the grading range into a plurality of grading mapping intervals;

determining a plurality of original data corresponding to each score mapping interval according to the original data sequence, and putting the corresponding original data into the score mapping intervals to establish a mapping relation between the original data and the scores;

determining scores corresponding to the original data of the vehicle parking stations in the dimension by using the mapping relation between the original data and the scores;

7. The method of claim 6, wherein said determining, using said score, an assessment of each of said vehicle docking stations in said dimension comprises:

and determining an evaluation result of the vehicle stopping station in the dimension by using the score and the second evaluation threshold value.

8. The method of claim 5 or 7, wherein the type of the vehicle docking station is determined according to a location of the vehicle docking station.

9. The method of any of claims 1-8, wherein the obtaining raw data for at least one dimension for each vehicle docking station for a plurality of vehicle docking stations comprises:

10. The method according to any one of claims 1-9, further comprising:

determining a plurality of first locations having a distance from the vehicle docking station greater than or equal to a preset threshold, the first locations including a location to call a first vehicle, the first vehicle being a vehicle that responds to the call and is docked at the vehicle docking station;

clustering the first positions to obtain a clustering center;

determining an adjusting position of the vehicle parking station according to the position of the clustering center;

11. An evaluation device of a vehicle stop, comprising:

the first determining module is used for determining the evaluation result of each vehicle stop station in each dimension by utilizing the original data of at least one dimension of each vehicle stop station; and the number of the first and second groups,

12. The apparatus of claim 11, wherein the parking data comprises at least one of emergency braking data, manual takeover data, and parking duration data.

13. The apparatus of claim 11 or 12,

wherein the log data includes at least one of an operation log of the autonomous vehicle, an operation log of a cloud server, and third party data.

14. The apparatus of any one of claims 11-13, wherein the first determining means is to:

determining raw data of each vehicle stop station in the dimension;

15. The apparatus of claim 14, wherein the first determining means is configured to:

for each vehicle stop, determining a quantile of the original data of the dimension of the vehicle stop in the original data sequence; determining a corresponding first evaluation threshold according to the type of the vehicle stop station, wherein the first evaluation threshold is used for determining an evaluation result according to the quantile;

16. The apparatus of claim 14, wherein the first determining means comprises:

the first determining submodule is used for determining a grading range corresponding to the original data of the dimension;

the dividing submodule is used for dividing the scoring range into a plurality of scoring mapping intervals;

the establishing submodule is used for determining a plurality of original data corresponding to each rating mapping interval according to the original data sequence and putting the corresponding original data into the rating mapping interval so as to establish a mapping relation between the original data and the rating;

the second determining submodule is used for determining scores corresponding to the original data of the vehicle parking stations in the dimensionality by utilizing the mapping relation between the original data and the scores;

and the third determining submodule is used for determining the evaluation result of each vehicle stop station in the dimension by using the scores.

17. The apparatus of claim 16, wherein the third determination submodule is to:

18. The apparatus of claim 15 or 17, wherein the type of the vehicle docking station is determined according to a location of the vehicle docking station.

19. The apparatus of any of claims 11-18, wherein the means for obtaining is configured to:

20. The apparatus of any of claims 11-19, further comprising:

a second determination module, configured to determine a plurality of first locations having a distance to the vehicle stop greater than or equal to a preset threshold, where the first locations include a 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;

the clustering module is used for clustering the first positions to obtain a clustering center;

the adjusting module is used for determining the adjusting position of the vehicle stop station according to the position of the clustering center;

and the station management module is used for adjusting the vehicle stop station and/or setting a new vehicle stop station according to the adjusted position.

21. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-10.

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