CN110852499A

CN110852499A - Method and device for recovering fault vehicle

Info

Publication number: CN110852499A
Application number: CN201911052925.XA
Authority: CN
Inventors: 林剑峰
Original assignee: Beijing Mobike Technology Co Ltd
Current assignee: Hanhai Information Technology Shanghai Co Ltd
Priority date: 2019-10-31
Filing date: 2019-10-31
Publication date: 2020-02-28

Abstract

The invention discloses a method for recovering a failed vehicle and a device for recovering the failed vehicle. The method comprises the following steps: acquiring the recovery value and the geographical position of the unassigned fault vehicle in the area; clustering the unassigned fault vehicles in the area based on the geographic position to obtain a cluster of the fault vehicles; under the constraint of the maximum bearing capacity of a transport tool used by a recovery person, according to the geographical position of the fault vehicle in the cluster and map network data, performing recovery path planning on the fault vehicle in the cluster to determine the optimal recovery path of the cluster; and allocating the optimal recovery path for recovery personnel.

Description

Method and device for recovering fault vehicle

Technical Field

The present invention relates to the field of vehicle recovery technology, and more particularly, to a method of recovering a malfunctioning vehicle and an apparatus for recovering a malfunctioning vehicle.

Background

The shared economy becomes the trend of the times, various shared vehicles, such as public bicycles paid by governments, shared bicycles operated by enterprises, tricycles, electric vehicles, automobiles and the like appear in life, and the convenience of resident trip is greatly improved. A user uses a shared vehicle through a terminal (for example, a mobile phone) loaded with an APP (application).

However, due to the large daily usage and lack of efficient maintenance, the number of shared vehicles in good condition is greatly decreasing and many large cities have a pile of broken vehicles. These faulty vehicles may obstruct urban public transportation and also make it difficult for users to obtain a healthy vehicle, thereby causing socio-economic and environmental problems, which are more evident for the shared vehicle without piles. Therefore, it is necessary to establish a more efficient recovery method of a faulty vehicle.

Disclosure of Invention

It is an object of the present invention to provide a new solution for recovering a faulty vehicle.

According to a first aspect of the present invention, there is provided a method of recovering a faulty vehicle, comprising:

acquiring the recovery value and the geographical position of the unassigned fault vehicle in the area;

clustering the unassigned fault vehicles in the area based on the geographic position to obtain a cluster of the fault vehicles;

under the constraint of the maximum bearing capacity of a transport tool used by a recovery person, according to the geographical position of the fault vehicle in the cluster and map network data, performing recovery path planning on the fault vehicle in the cluster to determine the optimal recovery path of the cluster; the best recovery path of the cluster is the recovery path with the highest efficiency in the recovery paths of the cluster, and the efficiency of the recovery path is the ratio of the sum of the recovery values of the fault vehicles contained in the recovery path to the estimated recovery time cost of the recovery path;

and allocating the optimal recovery path for recovery personnel.

Optionally or preferably, the allocating the optimal recycling path for recycling personnel comprises:

adding the optimal recycling path to the path set of the area;

selecting an optimal recovery path from the path set of the area to distribute to recovery personnel; and the number of the first and second groups,

after allocation, the optimal recovery path containing the failed vehicle that has been allocated is removed from the set of paths for the zone.

Optionally or preferably, the selecting an optimal recycling path from the path set of the area to allocate to a recycling person includes:

and selecting the best recovery path with the highest efficiency to be allocated to the recovery personnel under the constraint of the actual remaining working time of the recovery personnel.

Optionally or preferably, the selecting the best recovery path with the highest efficiency to allocate to the recovery staff under the constraint of the actual remaining working time of the recovery staff comprises:

selecting the best recycling path with the highest efficiency from the first type of best recycling paths in the path set of the area to distribute to recycling personnel; the first type of optimal recovery path is an optimal recovery path with the estimated recovery time cost less than or equal to the actual remaining working time of recovery personnel;

and if the first type of optimal recycling path does not exist in the path set of the area, allocating the optimal recycling path with the highest efficiency to recycling personnel or abandoning the allocation.

Optionally or preferably, the faulty vehicle is a vehicle with a fault probability greater than a preset threshold, and the recovery value of the faulty vehicle is determined according to the fault probability.

Optionally or preferably, the determining of the recovery value of the faulty vehicle according to the fault probability and the value adjustment coefficient thereof includes:

calculating a first parameter according to the fault probability of the fault vehicle, wherein the first parameter is the ratio of the fault probability of the fault vehicle to the minimum value of the fault probability of the fault vehicle in the region;

the recovery value of the fault vehicle is an exponential function value, the exponential function takes the value adjustment coefficient as a base number, and the first parameter is taken as an independent variable.

Optionally or preferably, the method further comprises:

and providing a value adjustment coefficient setting window for setting the value adjustment coefficient.

Optionally or preferably, the probability of failure of the vehicle is determined by:

determining the fault probability of the vehicle according to the state information, the geographical position information and the use record of the vehicle;

the state information of the vehicle comprises vehicle state information reported by the vehicle and/or vehicle state information reported by a user;

the geographic position information of the vehicle comprises the geographic position of the vehicle and/or a geographic grid to which the vehicle belongs;

the usage record of the vehicle comprises a code scanning record of the vehicle and/or the usage time of the vehicle.

Optionally or preferably, the determining the failure probability of the vehicle according to the state information, the geographical position information and the usage record of the vehicle includes:

extracting characteristic data of the vehicle from the state information, the geographical position information and the use record of the vehicle;

and inputting the characteristic data of the vehicle into a fault probability identification model to obtain the fault probability of the vehicle.

According to a second aspect of the present invention, there is provided an apparatus for recovering a faulty vehicle, comprising a memory and a processor, the memory having stored therein computer instructions which, when executed by the processor, implement the method of any of the preceding claims.

According to the scheme for recovering the fault vehicle, the recovery value of the fault vehicle is introduced into the path planning of the fault vehicle, and the efficiency of recovering the fault vehicle can be improved.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 illustrates a block diagram of a vehicle recovery system that may be used to implement an embodiment of the present invention;

FIG. 2 shows a schematic representation of the steps of a method of recovering a faulty vehicle according to an embodiment of the present invention;

FIG. 3 illustrates a schematic step diagram of a method of assigning optimal reclamation paths in accordance with an embodiment of the present invention;

FIG. 4 shows a block diagram of a server of an embodiment of the invention.

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

< vehicle recovery System >

As shown in fig. 1, the vehicle recovery system 100 includes a server 1000, a terminal 2000 of a recovery person, a vehicle 3000, and a network 4000.

The server 1000 is a service point that provides processing power, databases, and communications facilities. The server 1000 may be a unitary server or a distributed server across multiple computers or computer data centers. The server may be of various types, such as, but not limited to, a web server, a news server, a mail server, a message server, an advertisement server, a file server, an application server, an interaction server, a database server, or a proxy server. In some embodiments, each server may include hardware, software, or embedded logic components or a combination of two or more such components for performing the appropriate functions supported or implemented by the server. For example, a server, such as a blade server, a cloud server, etc., or may be a server group consisting of a plurality of servers, which may include one or more of the above types of servers, etc.

In one example, the server 1000 may be as shown in fig. 1, including a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600. Although the server may also include speakers, microphones, etc., these components are not relevant to the present invention and are omitted here. The processor 1100 may be, for example, a central processing unit CPU, a microprocessor MCU, or the like. The memory 1200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1300 includes, for example, a USB interface, a serial interface, an infrared interface, and the like. Communication device 1400 is capable of wired or wireless communication, for example. The display device 1500 is, for example, a liquid crystal display, an LED display touch panel, or the like. The input device 1600 may include, for example, a touch screen, a keyboard, and the like.

In the present embodiment, the terminal 2000 of the recovery person is an electronic device having a communication function and a service processing function. The terminal 2000 may be a mobile terminal held by a recycling person, such as a mobile phone, a portable computer, a tablet computer, a palmtop computer, and the like, on which a corresponding APP is loaded, and the recycling person may search for and register a faulty vehicle through the APP.

As shown in fig. 1, the terminal 2000 of the recycling person may include a processor 2100, a memory 2200, an interface device 2300, a communication device 2400, a display device 2500, an input device 2600, an output device 2700, a camera device 2800, and the like. The processor 2100 may be a central processing unit CPU, a microprocessor MCU, or the like. The memory 2200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 2300 includes, for example, a USB interface, a headphone interface, and the like. The communication device 2400 is capable of wired or wireless communication, for example, and includes a Wifi communication module, a bluetooth communication module, a 2G/3G/4G communication module, and the like. The display device 2500 is, for example, a liquid crystal display panel, a touch panel, or the like. The input device 2600 may include, for example, a touch screen, a keyboard, or a microphone. The output device 2700 is used for outputting information, and may be a speaker, for example, for outputting voice information to the recycling person. The camera 2800 is used to capture a faulty vehicle, for example, scan the faulty vehicle to register the faulty vehicle, for example, capture a picture of a fault of the faulty vehicle and upload the picture to a server or the like, and the camera 2800 is a camera or the like, for example. The terminal 2000 may include a positioning device (not shown), for example, a GNSS positioning module such as a GPS positioning module, a beidou positioning module, etc.

The vehicle 3000 is any vehicle that can give the right to share the use by different users in time or separately, for example, a shared bicycle, a shared moped, a shared electric vehicle, a shared vehicle, and the like. The vehicle 3000 may be a bicycle, a tricycle, an electric scooter, a motorcycle, a four-wheeled passenger vehicle, or the like.

As shown in fig. 1, vehicle 3000 may include a processor 3100, a memory 3200, an interface device 3300, a communication device 3400, an output device 3500, an input device 3600, a positioning device 3700, sensors 3800, and so forth. The processor 3100 may be a central processing unit CPU, a microprocessor MCU, or the like. The memory 3200 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface 3300 includes, for example, a USB interface, a headphone interface, and the like. The communication device 3400 is capable of wired or wireless communication, for example, and includes a Wifi communication module, a bluetooth communication module, a 2G/3G/4G communication module, and the like, for example. The output device 3500 may be, for example, a device that outputs a signal, may be a display device such as a liquid crystal display panel or a touch panel, or may be a speaker or the like that outputs voice information or the like. The input device 3600 may include, for example, a touch panel, a keyboard, or the like, and may input voice information through a microphone. The positioning device 3700 is used to provide positioning function, and may include a GNSS positioning module such as a GPS positioning module and a beidou positioning module. The sensor 3800 is used for acquiring vehicle attitude information, and may be, for example, an accelerometer, a gyroscope, or a three-axis, six-axis, nine-axis micro-electro-mechanical system (MEMS), or the like.

The network 4000 may be a wireless communication network or a wired communication network, and may be a local area network or a wide area network. In the vehicle system shown in fig. 1, a vehicle 3000 and a server 1000, and a terminal 2000 and the server 1000 can communicate with each other through a network 4000. The vehicle 3000 may be the same as the server 1000, and the network 4000 through which the terminal 2000 communicates with the server 1000 may be different from each other.

It should be understood that although fig. 1 shows only one server 1000, terminal 2000, vehicle 3000, it is not meant to limit the corresponding number, and multiple servers 1000, multiple terminals 2000, multiple vehicles 3000 may be included in the recycling system 100.

Taking the vehicle 3000 as an example of a shared bicycle, the recycling system 100 is a recycling system of the shared bicycle. The server 1000 is used to provide the functionality needed to support recovery of a malfunctioning shared bicycle. The terminal 2000 may be a mobile phone on which an application related to shared bicycles is installed, and the shared bicycle application may help recovery personnel to recover failed shared bicycles.

The vehicle recovery system 100 shown in FIG. 1 is illustrative only and is not intended to limit the invention, its application, or uses in any way. Although a plurality of devices are shown in fig. 1 for the server 1000, the terminal 2000, and the vehicle 3000, the present invention may relate to only some of the devices.

In an embodiment of the present invention, the memory 1200 of the server 1000 is used for storing instructions for controlling the processor 1100 to operate so as to execute the part of the recovery method for a faulty vehicle according to the embodiment of the present invention, which is executed by the server. In an embodiment of the present invention, the memory 2200 of the terminal 2000 of the recovery person is configured to store instructions for controlling the processor 2100 to operate to execute the portion of the method for recovering a faulty vehicle provided by the embodiment of the present invention, where the portion is executed by the terminal. The memory 3200 of the vehicle 3000 is used to store instructions for controlling the processor 3100 to operate to perform the portions of the method for recovery of a malfunctioning vehicle provided by embodiments of the present invention that are performed by the vehicle.

Those skilled in the art can design instructions in accordance with the teachings of the present invention. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

< probability of failure of vehicle >

Before describing the embodiment of the recovery method for a faulty vehicle, how to determine whether the vehicle is faulty or non-faulty will be described.

Before the vehicle is checked in the field, it cannot be really determined whether the vehicle has a fault at all, so in this embodiment, the probability of the fault of the vehicle is used to indicate the possibility of the fault of the vehicle, and the probability of the fault of the vehicle can be obtained through estimation.

In one embodiment, the failure probability of a vehicle may be estimated based on big data analysis. For example, the failure probability of the vehicle is determined by using a failure probability recognition model trained in advance.

First, the process of establishing the fault identification model is described, including steps S102-S110.

S102, selecting a sample vehicle and constructing sample data.

In one embodiment, the characteristic data of the sample vehicle can be extracted from the state information, the geographical position information and the use record of the sample vehicle as sample data.

Specifically, the status information, the geographic position information, and the usage records of the sample vehicle may be subjected to data preprocessing, such as data cleansing, discretization, normalization, and the like. Then, feature data of the sample vehicle, that is, sample data is extracted from the data after the preprocessing. The feature data of the sample vehicle may be a multi-dimensional vector X.

And S104, marking a first label or a second label on the sample data according to the real fault condition of the sample vehicle. And when the sample vehicle is a real fault vehicle, marking a first label on the sample vehicle. And when the sample vehicle is a real non-fault vehicle, marking a second label on the sample vehicle. The sample data with the first label is a positive sample, and the sample data with the second label is a negative sample. The actual fault condition of the sample vehicle can be obtained by the operator through actual survey of the sample vehicle.

And S106, dividing the sample data into a training set and a testing set.

And S108, carrying out supervised training on the basic model by using the sample data of the training set to obtain a fault probability recognition model.

And S110, testing the trained fault probability recognition model by using sample data of the test set to verify the performance of the model, and if the performance of the model meets the requirements, indicating that the model can be successfully trained and applied. And if the performance of the model does not meet the requirement, retraining the model.

In one embodiment, the base model may employ a neural network model. In another embodiment, the base model may employ a logistic regression model. A Logistic Regression (LR) model is a generalized linear Regression model, and is a classification model widely used in supervised learning; the logistic regression model does not need to assume data distribution in advance, can avoid the problems caused by inaccurate assumed distribution, and can predict the classification and the probability of the category to which the vector belongs. The function of the logistic regression model is a convex function with any order of derivation, the optimization and solving process is simple and easy to realize, and very good engineering performance can be achieved. In other embodiments, other classification models may be selected.

The following describes a process for determining the failure probability of a vehicle using a trained failure probability model, including steps S202-S204:

s202, obtaining characteristic data of the vehicle in the same way as the training process.

In one embodiment, the characteristic data of the vehicle is extracted from the state information, the geographical position information and the usage record of the vehicle as sample data in the same way as in the training process. Similarly, the vehicle status information, geographic location information, usage records may be pre-processed, such as data cleansing, discretization, normalization, and so on. Then, the feature data of the vehicle is extracted from the data after the preprocessing. The feature data of the vehicle may be a multi-dimensional vector X.

And S204, inputting the characteristic data of the vehicle into the fault probability identification model to obtain the fault probability of the vehicle.

The state information, the geographical position information and the use record of the vehicle are possibly related to the fault condition of the vehicle, so the characteristic data are extracted by utilizing the data in the embodiment of the invention.

The vehicle state information may include vehicle state information reported by the vehicle and/or vehicle state information reported by the user. The state information of the vehicle includes information that can embody a performance state of a component of the vehicle. The state information of the vehicle may reflect the possibility of a failure of the vehicle. For example, the state information of the vehicle may include information on the battery level, such as whether the battery level is too low. The state information of the vehicle may include information obtained by self-checking of the electronic device of the vehicle, such as information about a failure of a lock sensor. The state information of the vehicle may include fault information reported by the user, for example, information that a chain falls off, a lock cannot be closed, and the like reported by the user.

The geographic location information of the vehicle may include the geographic location of the vehicle and/or the geographic grid to which the vehicle belongs. The geographical position of the vehicle can be obtained through the positioning function of the vehicle, the vehicle reports the positioning data to the server side, and the server side can determine the geographical grid to which the vehicle belongs according to the geographical position of the vehicle. The geographic grid is obtained by dividing the region into a plurality of grid regions, each of which serves as one geographic grid. The geographic position information of the vehicle may further include attribute information of a geographic position where the vehicle is located and/or attribute information of a geographic grid to which the vehicle belongs, which may be obtained through big data analysis and stored in the server side in advance, and the attribute information may be, for example, "vehicle usage is high", "vehicle usage is low", "subway entrance", "pedestrian flow dense area".

The usage record of the vehicle may include a barcode record of the vehicle and/or a time of use of the vehicle. The usage record of the vehicle may reflect the fault condition of the vehicle, for example, when a certain vehicle has a plurality of scanned codes but is not unlocked and ridden by the user, the vehicle may have a fault, for example, when a certain vehicle has a plurality of continuous short riding records, the vehicle may have a fault.

By means of the integration of the data, the possibility of the vehicle fault can be reflected, and the accurate identification of the vehicle fault probability is facilitated. For example, a vehicle is in a "high vehicle usage area", but there is no usage record for a long time, which indicates that there is a high possibility that the vehicle has a failure.

The higher the failure probability of a vehicle, the greater the likelihood of failure of that vehicle. In one embodiment, the vehicle with the failure probability greater than the preset threshold is regarded as a failed vehicle, that is, a vehicle that needs to be recovered. And regarding the vehicles with the fault probability less than or equal to the preset threshold as non-faulty vehicles, namely vehicles which do not need to be recovered. In one embodiment, the failure probability of the vehicle is set between 0 and 1; if the preset threshold value is 1, all vehicles are considered to be fault vehicles, and all vehicles need to be recovered.

The embodiment of the invention provides a method for determining the fault probability of a vehicle, which estimates the fault probability of the vehicle by utilizing big data and is more accurate and reliable.

< method of recovering faulty vehicle >

Referring to fig. 2, the method for recovering a failed vehicle according to the embodiment of the present invention may be implemented by a server, including steps S302 to S308.

S302, acquiring the recovery value and the geographical position of the unassigned fault vehicle in the area.

In one embodiment, the vehicle itself has a positioning function, and the server can determine the geographical position of the faulty vehicle through the positioning data reported by the faulty vehicle. In other embodiments, the geographic location of the faulty vehicle may also be determined in other manners, which is not limited in this embodiment.

A defective vehicle that is not assigned within an area refers to a defective vehicle that is within the area and has not been assigned to a recovery person. In one embodiment, the initial state of the faulty vehicle is "unassigned", and when the faulty vehicle is assigned to a recovery person, the server marks the faulty vehicle as "assigned", thereby distinguishing the faulty vehicle that has been assigned from the faulty vehicle that has not been assigned. In one embodiment, a set of unassigned faulty vehicles is created for the area and dynamically maintained. After each dispense, the failed vehicle that was dispensed is marked as "dispensed" and removed from the set of unassigned failed vehicles. If the assigned failed vehicle is not later successfully recovered by the recovery personnel, the failed vehicle may be marked as "unassigned" again and rejoined into the unassigned failed vehicle pool.

The recovery value of the failed vehicle is due to the value that the recovery management party defines to have to recover the failed vehicle. For example, if the recovery value of faulty vehicle H1 is 2, the recovery value of faulty vehicle H2 is 1, and the recovery value of faulty vehicle H3 is 0.5, the value resulting from recovering two vehicles, i.e., faulty vehicle H2 and H3, is 1.5, and the value resulting from recovering one vehicle, i.e., faulty vehicle H1, is greater than the value resulting from recovering two vehicles, i.e., faulty vehicle H2 and H3.

According to the embodiment, the recovery value is set for the fault vehicle, and the recovery strategy is designed by utilizing the recovery value in the follow-up process, for example, a scheme for planning the recovery path is designed, so that the recovery personnel can output the recovery value as high as possible in unit time, and the efficiency of recovery work is improved. In addition, the recycling value can be used for measuring the performance of a recycling person and stimulating the work of the recycling person.

Four ways of determining the value of recovery of a faulty vehicle are presented below.

The first mode is as follows: the recovery value of a failed vehicle is determined by the probability of failure of the failed vehicle.

For example, the salvage value of a failed vehicle is equal to the failure probability of the failed vehicle. The recovery value of the fault vehicle is equal to the fault probability of the fault vehicle, and recovery personnel can be encouraged to recover vehicles with higher fault probability.

The second mode is as follows: the recovery value of the faulty vehicle is determined by the fault probability of the faulty vehicle and the value adjustment coefficient.

In the embodiment of the invention, the following factors need to be weighed when selecting the fault vehicle for recovery: if only vehicles with a high probability of failure are sought, it may take a lot of time but only a small number of vehicles are collected. Conversely, if the demand for failure probability is low, a large number of vehicles may be recovered in a short period of time, but there may be more vehicles that are misjudged as failed vehicles (actually good vehicles or actually slightly damaged vehicles), and the embodiments of the present invention capture this tradeoff by setting the recovery value associated with the failure probability.

The following is a specific example of how to determine the recycling value of a faulty vehicle based on the fault probability and the value adjustment coefficient of the faulty vehicle:

the recovery value of the malfunctioning vehicle is determined by a recovery value function. The recovery cost function may be an exponential function, based on the cost adjustment factor, and with the first parameter as an argument. Specifically, Scorei ═ a^bA is a value adjustment coefficient, a ≧ 1, b is a first parameter corresponding to the faulty vehicle, and Scorei is the recycling value of the faulty vehicle. And calculating a first parameter according to the fault probability of the fault vehicle, wherein the first parameter is the ratio of the fault probability of the fault vehicle to the minimum value of the fault probability of the fault vehicle in the region. Specifically, b is Pi/Pmin, where Pi is the failure probability of the faulty vehicle, Pmin is the minimum value of the failure probability of the faulty vehicle in the area, and b is the first parameter corresponding to the faulty vehicle.

The reason why the recycle value is determined using the above recycle value function is: when a is greater than 1, the recovery value of the vehicle with higher failure probability is amplified. When the value adjustment coefficient a is far from 1, it is more likely to collect faulty vehicles with a high probability of failure. When the value adjustment coefficient a is close to 1, the failed vehicles are more likely to be collected more widely. In particular, when the value adjustment coefficient a is 1, the probability of failure of a faulty vehicle is not considered, and each faulty vehicle has the same recycling value.

The value adjustment coefficient a is an adjustable parameter, a more flexible choice is provided for formulating a recovery strategy of the vehicle, and the value adjustment coefficient a can be used for balancing the number of collected vehicles and the vehicles with high failure probability. From the viewpoint of the recovery management side, the recovery expectation may be different in different situations, and for example, when a faulty vehicle is collected in a difficult area, the value adjustment coefficient a may be set to be close to 1 with the aim of collecting the faulty vehicle as much as possible. In densely populated areas, such as downtown areas, it is preferred to collect each vehicle with a high failure rate accurately (since slightly failing vehicles can also ride and move), and the value adjustment coefficient a can be set to a larger value.

The value adjustment coefficients may be dynamically adjusted to accommodate different recycling scenarios and recycling expectations. In one specific example, a value adjustment factor setting window is provided for the recycling manager to set the value adjustment factor.

The third mode is as follows: the salvage value of a malfunctioning vehicle can be related to the level of malfunction of the malfunctioning vehicle. And classifying the fault degrees of all possible fault types, and setting corresponding recovery values for each level. Take sharing a bicycle as an example: the vehicle lock fault and the positioning fault belong to the highest-level fault, namely the most serious fault, and the recovery value corresponding to the highest-level fault is 5; the failure of the bell belongs to a middle-level failure, and the corresponding recovery value of the middle-level failure is 3; the fault of the vehicle lamp belongs to the fault of the lowest level, namely the lightest fault, and the recovery value corresponding to the fault of the lowest level is 1. If a faulty vehicle has a plurality of faults of different grades, the grade of the faulty vehicle is set according to the fault of which the grade is the highest.

The fourth mode is that: the salvage value of a failed vehicle may be related to the type of failure of the failed vehicle. And respectively setting corresponding recycling values for all possible fault types. Take sharing a bicycle as an example: the recovery value corresponding to the switch failure of the lock is 4, the recovery value corresponding to the positioning failure of the lock is 3, the recovery value corresponding to the failure of the bell is 2, and the recovery value corresponding to the failure of the lamp is 1. If the fault vehicle has a plurality of faults, the recovery value is the sum of the recovery values corresponding to the plurality of faults.

S304, clustering the unallocated fault vehicles in the area based on the geographic position to obtain a cluster of the fault vehicles.

At this stage, spatial clustering algorithms such as kMeans are used for clustering vehicles which are inferred to be faulty, so that k clusters, namely a plurality of faulty vehicle clusters, are obtained. The faulty vehicles within the cluster are geographically close to each other. k is an integer.

And S306, under the constraint of the maximum bearing capacity M of the transport means used by the recovery personnel, according to the geographical position of the fault vehicle in the cluster and the map network data, planning the recovery path of the fault vehicle in the cluster to determine the optimal recovery path of the cluster.

The maximum load capacity M of the vehicle used by the recovery personnel is the number of faulty vehicles that the vehicle can transport at most at one time. Under the constraint of the maximum carrying capacity M of the transportation means used by the recovery personnel, the number of the fault vehicles included in each recovery path at the planning place cannot exceed M.

The best reclamation path of the cluster is the most efficient reclamation path among the reclamation paths of the cluster, and the efficiency of the reclamation path is the ratio of the sum of the reclamation values of the faulty vehicles included in the reclamation path to the estimated reclamation time cost of the reclamation path.

The recovery path can be planned by using an existing path planning algorithm, such as a greedy algorithm, a backtracking method, a branch boundary method, a dynamic planning algorithm, a routing algorithm based on scatter search, and the like. The same faulty vehicle can only appear once in the same planned path.

And if the number of the fault vehicles in the cluster is less than or equal to the maximum bearing capacity M, traversing all the fault vehicles in the cluster by the recovery path. If the number of failed vehicles within the cluster is greater than the maximum capacity M, the recovery path may contain M failed vehicles.

In the following, a specific example is described how to perform route planning and determine the optimal recovery route if the number of faulty vehicles in the cluster is greater than the maximum carrying capacity M, including steps S402-S414.

S402, selecting M fault vehicles with the highest recovery value in the cluster as M target vehicles.

S404, planning a recovery path for the M target vehicles, wherein the recovery path needs to traverse each of the M target vehicles to obtain the recovery path with the minimum expected recovery time cost and add the recovery path into a candidate path library of the cluster.

S406, replacing one target vehicle randomly by using other fault vehicles in the cluster, namely fault vehicles which are not used as target vehicles in the cluster.

And S410, planning the recovery paths for the replaced M target vehicles again, wherein the recovery paths need to traverse each of the M target vehicles to obtain the recovery path with the minimum expected recovery time cost and add the recovery path into the candidate path library of the cluster.

S412, comparing the performance of the recovery paths in the candidate path library of the cluster, only keeping the recovery path with the highest performance, and removing other recovery paths.

And executing steps S406-S412 in a plurality of loops until the replacement times reach a preset replacement time threshold value. Alternatively, steps S406-S412 are performed in a plurality of loops until convergence of the performance of the recycling path with the lowest estimated recycling time cost determined in step S410 begins to occur. The skilled person can design the cut-off conditions for the cycle according to requirements and practical experience, which are not described herein too much.

And S414, after the circulation is finished, taking the recovery path reserved in the candidate path library as the optimal recovery path of the cluster.

The predicted recycling time cost of the recycling path is described below as a specific example:

the starting point and the ending point of each recycling path are the same point, which is called as an aggregation point, and the aggregation point is the position of the warehouse. For any one recovery path R_jAssuming that it includes n faulty vehicles, the recovery path R_jS → br1 → · · → bri → · · · · · · · · · · · → brn → s, s denotes a collection point, i denotes an i-th faulty vehicle passing through the recovery path, br1 denotes a geographical location where the 1-th faulty vehicle passing through the recovery path is located, and bri denotes a place where the i-th faulty vehicle passing through the recovery path is locatedThe geographic location brn represents the geographic location of the nth failed vehicle (i.e., the last failed vehicle passed by the recovery route) passed by the recovery route.

For the recovery path R_jPredicted recovery time cost T_jCan be obtained by calculation in the following way:

in the above formula, Ttravel (R)_j) For the total travel time of the vehicles in the recovery path, dist (s, br)₁) For recovery personnel to use the transport means from the gathering point s to the geographical location of the 1 st defective vehicle, dist (br)_nS) distance traveled by recovery personnel using the vehicle from the geographical location of the nth faulty vehicle back to the rendezvous point s, dist (br)_i,br_i+1) For the recovery personnel to use the transport means from the geographical location of the i-th faulty vehicle to the geographical location of the i + 1-th faulty vehicle, v_dRepresenting the travel speed of the vehicle.

Tvisit(br_i) The walking time required for recovering the i-th faulty vehicle for the recovering person in the recovery route, Shiftr_iIn order for a recovery worker to walk from a transportation tool to the traveling route of the ith faulty vehicle after reaching the vicinity of the ith faulty vehicle by using the transportation tool, rt is the time required for the recovery worker to perform a recovery processing operation (for example, an operation of scanning a code to upload information of the faulty vehicle) on one faulty vehicle, and Vw is the walking speed. The rt value can be obtained by calculating the average value of the historical data or by actual measurement, and will not be described herein.

And S308, distributing the optimal recovery path for the recovery personnel.

In a specific example, referring to FIG. 3, an optimal recycling path is assigned to the recycling personnel, including steps S502-S506.

S502, adding the optimal recovery path of each cluster into the path set of the area.

The faulty vehicle clusters in the area can be obtained through step S304, an optimal recovery path can be planned for each faulty vehicle cluster through step S306, and all the optimal recovery paths are added to the path set of the area.

S504, at least one optimal recovery path is selected from the path set of the area and distributed to recovery personnel.

Selecting the best recycling path from the path set to distribute to recycling personnel can include: and selecting the best recovery path with the highest efficiency to be allocated to the recovery personnel under the constraint of the actual remaining working time of the recovery personnel.

In one specific example, the best recycling path with the highest efficiency is selected to be allocated to the recycling staff under the constraint of the actual remaining working time of the recycling staff, and the method comprises the following steps: selecting the best recycling path with the highest efficiency from the first type of best recycling paths in the path set to distribute to recycling personnel; the first type of optimal recycling path is the optimal recycling path with the estimated recycling time cost less than or equal to the actual remaining working time of the recycling personnel. And if the first type of optimal recovery path does not exist in the path set, allocating the optimal recovery path with the highest efficiency to a recovery person or abandoning the allocation.

In a specific example, selecting the best recycling path from the path set to distribute to recycling personnel comprises: and queuing the optimal recovery paths in the path set according to the efficiency, selecting one or more optimal recovery paths from high to low to distribute to recovery personnel, wherein the sum of the estimated recovery time cost of the selected optimal recovery paths is less than or equal to the actual residual working time of the recovery personnel.

S506, after the distribution, the optimal collection route including the distributed faulty vehicle is removed from the route set in the area.

That is, the route allocated to the recovery worker is removed, and if any vehicle included in the allocated route is included in the other unallocated routes, the unallocated route is also deleted.

As a hypothetical example, the set of paths for the region would originally include the best recycle path A, the best recycle path B, and the best recycle path C. In step S604, the optimal collection route a and the optimal collection route B are assigned to the collection staff. The optimal recovery path A comprises the vehicles with faults H1, H2 and H3, and the optimal recovery path B comprises the vehicles with faults H6 and H7. After the allocation, to remove the optimal recovery path a and the optimal recovery path B from the path set of the area, if any one of the faulty vehicles H1, H2, H3, H6, and H7 is included in the optimal recovery path C, the optimal recovery path C needs to be removed together, and if the faulty vehicles H1, H2, H3, H6, and H7 are not included in the optimal recovery path C, the optimal recovery path C is left in the path set of the area.

Through steps S302-308, the present round of dispensing operation is ended.

If the next round of distribution work needs to be carried out, the step S302-308 is executed again, namely, the remaining unallocated fault vehicles in the area are clustered again to update the fault vehicle cluster, and path planning is carried out again to obtain the updated optimal recovery path of the fault vehicle cluster; step S502 is executed, and the optimal re-planned recycling path is added into the path set of the area; at this time, the path set of the area includes the optimal recycling path obtained by the re-planning, and also includes the previously reserved optimal recycling path. Then, step S504 is executed to select an optimal collection route from all the optimal collection routes in the route set of the area and assign the optimal collection route to a collection worker, and step S506 is executed again after the optimal collection route is assigned. At this point, the next round of dispensing is completed. That is to say, the route set includes the unallocated routes which are planned all the time and do not include the allocated vehicles, and not only includes the routes newly planned in the current round, but also selects and allocates from all the routes in the route set when allocating the routes to the recycling personnel, which is more beneficial to obtaining the routes with the highest efficiency, improving the efficiency of the recycling work and reducing the recycling cost.

When the first round of distribution work is carried out on the fault vehicles in the area and the fault vehicles in the area are clustered for the first time, the number k of the clusters is set to be equal to round (N/M), N is the total number of the fault vehicles in the area, M is the maximum bearing capacity of a transport vehicle used by a recycling person, and the round () function represents that the value of N/M is rounded to obtain an integer. And the k value of the cluster of the next round of distribution work is equal to the k of the previous round of distribution work-the number of the optimal recovery paths distributed by the previous round of distribution work. The person skilled in the art can also set the number of clusters of a cluster according to the number of unassigned faulty vehicles in the area and the maximum capacity of the transport means used by the recovery personnel, based on practical experience.

The actual remaining working time of the recycling staff is the total working time of the recycling staff in one day-the total time spent actually performing the recycling work. For example, the total working time of a recycling staff per day is 5 hours, the recycling task of completing the first round of distribution actually takes 2 hours, and the actual remaining working time of the recycling staff in the second round of distribution is 4 hours; the recovery task of the second round of allocation actually takes 3 hours, and the actual remaining working time of the recovery staff at the time of the third round of allocation is 1 hour. In the third round of distribution, if the estimated recovery time cost of the optimal recovery path allocated to the recovery personnel is 2 hours, which is larger than the actual remaining working time (1 hour) of the recovery personnel, the recovery personnel can work according to 1 hour, and after the recovery personnel finish working according to 1 hour, the failed vehicles which are not successfully recovered are marked as 'unassigned' again and are added into the unassigned failed vehicle set for subsequent redistribution.

According to the method for recovering the fault vehicle, provided by the embodiment of the invention, the recovery value and the recovery time cost of the vehicle are comprehensively considered when the recovery path is planned, so that the recovery efficiency is favorably improved.

The method for recovering the fault vehicles provided by the embodiment of the invention provides a more flexible choice for formulating the recovery strategy of the vehicles, and can balance the quantity of the collected vehicles and the vehicles with high fault probability. The method for recovering the fault vehicle provided by the embodiment of the invention can be suitable for different recovery scenes and recovery expectations.

The method for recovering the fault vehicle provided by the embodiment of the invention also takes the working time of the recovery personnel into consideration, so that the task can be better distributed to the recovery personnel and the work of the recovery personnel can be managed.

< apparatus for recovering faulty vehicle >

The embodiment of the invention provides a device for recovering a failed vehicle, which comprises a memory and a processor, wherein the memory stores computer instructions, and the computer instructions are executed by the processor to realize the method for recovering the failed vehicle in any one of the preceding embodiments.

< Server >

Referring to fig. 4, an embodiment of the present invention provides a server 200, where the server 200 includes a memory 210 and a processor 220.

The memory 210 has stored therein computer instructions that, when executed by the processor 220, implement the method of recovering a malfunctioning vehicle as described in any of the preceding embodiments.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device embodiment and the server embodiment, since they are substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.

The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: 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), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.

Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A method of recovering a malfunctioning vehicle, comprising:

and allocating the optimal recovery path for recovery personnel.

2. The method of claim 1, the assigning the optimal recycling path for recycling personnel comprising:

adding the optimal recycling path to the path set of the area;

3. The method of claim 2, the selecting an optimal recycling path from the set of paths for the area to assign to recycling personnel, comprising:

4. The method of claim 3, wherein selecting the best recovery path with the highest efficiency to assign to the recovery personnel under the constraint of the actual remaining working time of the recovery personnel comprises:

5. The method according to claim 1, wherein the faulty vehicle is a vehicle with a fault probability greater than a preset threshold, and the recovery value of the faulty vehicle is determined according to the fault probability.

6. The method of claim 5, the recovered value of the failed vehicle being determined from its failure probability and a value adjustment factor, comprising:

7. The method of claim 6, further comprising:

8. The method of claim 5, the probability of failure of the vehicle being determined by:

9. The method of claim 8, the determining a probability of failure of the vehicle from the status information, the geographic location information, the usage record of the vehicle, comprising:

10. An apparatus for recovering a malfunctioning vehicle, comprising a memory and a processor, the memory having stored therein computer instructions which, when executed by the processor, implement the method of any of claims 1-9.