CN111445689B

CN111445689B - Vehicle information processing method and device and electronic equipment

Info

Publication number: CN111445689B
Application number: CN201910044412.8A
Authority: CN
Inventors: 裴成
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-01-17
Filing date: 2019-01-17
Publication date: 2022-06-07
Anticipated expiration: 2039-01-17
Also published as: CN111445689A

Abstract

The invention discloses a vehicle information processing method, a vehicle information processing device and electronic equipment, wherein the method comprises the following steps: matching the train number tasks in the train number set with the vehicles in the vehicle set to obtain candidate matching results; obtaining the predicted mileage of each vehicle executing the distributed vehicle number task in each candidate matching result; obtaining an allocation score of each candidate allocation result according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle; and selecting a final matching result from the candidate matching results according to the matching score and outputting the final matching result.

Description

Vehicle information processing method and device and electronic equipment

Technical Field

The present invention relates to the field of information processing technologies, and in particular, to a method for processing vehicle information, an apparatus for processing vehicle information, an electronic device, and a computer-readable storage medium.

Background

With the rapid development of urban transportation, public transportation such as rail transit plays an increasingly important role in passenger flow transportation, which will also put higher demands on its application. Taking a subway as an example, when the vehicle returns to a station track after finishing the operation plan on the same day, the vehicle returning to the garage needs to be compiled so as to meet the operation plan on the next day.

Generally, after the train number list of the second day is selected, a vehicle with good state is selected to serve as a corresponding train number task in the list, and the process is called vehicle operation daily plan compiling. In the prior art, a manual configuration mode is still adopted for planning, namely, maintenance scheduling is matched according to the vehicle state, parking position and other subjectives, and as the mileage corresponding to different vehicle number tasks is often different, the traveling mileage in the vehicle operation process has great difference, the reliability of the vehicle with overlarge traveling mileage is lower than a threshold value when the scheduled maintenance date is reached, so that the driving unsafe coefficient is increased, and for the vehicle with smaller traveling mileage, maintenance resource waste can be caused by frequent scheduled maintenance. Therefore, it is necessary to provide a new method for operating and compiling the vehicle number tasks of the operating day so that the driving mileage of all vehicles is performed in the direction of the scheduled maintenance date.

Disclosure of Invention

An object of the embodiments of the present invention is to provide a new vehicle information processing scheme for performing operation and configuration on the vehicle number task on the operation day.

According to a first aspect of the present invention, there is provided a vehicle information processing method including:

matching the train number tasks in the train number set with the vehicles in the vehicle set to obtain candidate matching results;

obtaining the predicted mileage of each vehicle executing the distributed vehicle number task in each candidate matching result;

obtaining an allocation score of each candidate allocation result according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle;

and selecting a final matching result from the candidate matching results according to the matching score and outputting the final matching result.

Optionally, the step of matching the train number tasks in the train number set with the vehicles in the vehicle set to obtain the candidate matching result includes:

for each train number task in the train number set, screening vehicles meeting the condition of executing the train number task from the vehicle set, and obtaining a vehicle subset corresponding to the train number task;

and obtaining the candidate matching result according to the corresponding relation between the train number task and the vehicle subset.

Optionally, the step of screening the set of vehicles for vehicles meeting the condition for performing the vehicle number task includes:

screening vehicles meeting the conditions for executing the vehicle-number task according to the state information of the vehicles in the vehicle set and set constraint conditions;

the state information comprises at least one of parking position information and established tasks except the vehicle number task on the operation day to be compiled.

Optionally, the method further comprises:

detecting a set event for processing vehicle information;

and under the condition that the event is detected to occur, acquiring the vehicle set and the train number set so as to execute the step of matching the train number tasks in the train number set with the vehicles in the vehicle set.

Optionally, the event comprises at least one of:

reaching the preset processing time;

and receiving a processing instruction of the vehicle information.

Optionally, the method further includes a step of obtaining a target mileage of each vehicle in each candidate orchestration result, including:

acquiring the planned mileage of the vehicle and the current actual mileage of the vehicle;

acquiring the number of running days of the current date from the overhaul date of the vehicle;

and obtaining the target mileage of the vehicle according to the overhaul plan mileage, the current actual mileage and the operation days.

Optionally, the step of obtaining an allocation score of each candidate allocation result according to a deviation between the predicted mileage and a target mileage of the corresponding vehicle includes:

obtaining the total deviation generated by each candidate matching result according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle;

and obtaining the allocation score of each candidate allocation result according to the overall deviation, wherein the lower the overall deviation is, the higher the corresponding allocation score is.

Optionally, the step of selecting a final assembly result from the candidate assembly results and outputting the final assembly result includes:

generating an allocation schedule according to the final allocation result, wherein the allocation schedule reflects the corresponding relation between the train number tasks and the allocated vehicles;

and outputting the compiling schedule.

Optionally, the step of obtaining the predicted mileage of each vehicle executing the assigned vehicle number task in each candidate matching result includes:

obtaining a selected feature vector, wherein the feature vector comprises a plurality of features influencing mileage of a vehicle to execute a vehicle number task, and the plurality of features comprise vehicle features and vehicle number features;

acquiring a mapping function between the feature vector and the driving mileage;

and obtaining the predicted mileage of each vehicle executing the assigned vehicle number task in each candidate matching result according to the mapping function and the vector value of the feature vector of each matching pair in each candidate matching result, wherein each matching pair comprises the matched vehicle number task and the matched vehicle.

Optionally, the vehicle characteristic comprises at least one of a vehicle number and a vehicle type; and/or the train number characteristics include at least one of a departure time, an arrival time, a departure location, and an arrival location.

Optionally, the plurality of features further comprises a cross-over feature, wherein the cross-over feature is a feature that cross-correlates the vehicle with the performed vehicle number assignment, the cross-over feature comprising a service assignment.

Optionally, the method further comprises the step of training the mapping function, including:

obtaining training samples according to historical operating data, wherein each training sample comprises matched vehicles and actually executed vehicle number tasks;

and training to obtain the mapping function according to the vector value of the feature vector of the training sample and the actual mileage corresponding to the training sample.

Optionally, the step of training to obtain the mapping function includes:

determining a mileage prediction expression of each training sample by taking undetermined coefficients of the mapping function as variables and respectively according to vector values of the feature vectors of each training sample;

constructing a loss function according to the mileage prediction expression of each training sample and the actual mileage of each training sample;

and determining the undetermined coefficient according to the loss function, and finishing the training of the mapping function.

Optionally, the step of constructing a loss function includes:

for each training sample, determining a corresponding loss expression according to the mileage prediction expression and the actual mileage;

and summing the loss expressions of each training sample to obtain the loss function.

Optionally, the method further comprises:

after operation is finished according to the final configuration result, acquiring the matched vehicles and the actually executed vehicle number tasks in the final configuration result as new training samples;

and correcting the mapping function according to the vector value of the feature vector of the new training sample and the actual mileage of the new training sample on the corresponding operation day.

According to a second aspect of the present invention, there is also provided a vehicle information processing apparatus comprising:

the candidate matching module is used for matching the train number tasks in the train number set with the vehicles in the vehicle set to obtain candidate matching results;

the mileage prediction module is used for acquiring the predicted mileage of each vehicle executing the distributed vehicle number task in each candidate matching result;

the matching scoring module is used for obtaining the matching scoring of each candidate matching result according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle; and the number of the first and second groups,

and the decision module is used for selecting a final assembly result from the candidate assembly results according to the assembly score and outputting the final assembly result.

According to a third aspect of the present invention, there is also provided an electronic apparatus including the vehicle information processing device according to the second aspect of the present invention; or, a memory for storing executable instructions and a processor; the processor is configured to execute the processing method according to any one of the first aspect of the present invention according to the control of the instruction.

According to a fourth aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the processing method according to any one of the first aspects of the present invention.

One advantageous effect of the present invention is that, according to the method, the apparatus, and the electronic device of the embodiments of the present invention, after obtaining the vehicle number task and the candidate configuration result of the corresponding vehicle, the predicted mileage of each vehicle executing the assigned specific vehicle number task in the candidate configuration result is obtained, that is, the mileage is predicted for the matching pair of the specific vehicle matching the specific vehicle number task, so that the prediction of the mileage can have higher accuracy, further, the configuration score of each candidate configuration result is obtained according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle, so as to select the final configuration result from the candidate configuration results to output, so as to schedule the vehicle to execute the vehicle number task on the operation day according to the final configuration result, and further, the driving mileage of all vehicles can be executed according to the planned maintenance direction, the mileage of the vehicle is controllable.

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 is a schematic diagram of a hardware configuration of an electronic apparatus according to a first embodiment of the present invention;

fig. 2 is a schematic diagram of a hardware configuration of an electronic apparatus according to a second embodiment of the present invention;

fig. 3 is a flowchart illustrating a processing method of vehicle information according to an embodiment of the present invention;

fig. 4 is a flowchart illustrating a processing method of vehicle information according to another embodiment of the present invention;

fig. 5 is a flowchart illustrating a processing method of vehicle information according to a third embodiment of the invention;

fig. 6 is a flowchart illustrating a processing method of vehicle information according to a fourth embodiment of the invention;

FIG. 7 is a flowchart illustrating a method of processing vehicle information according to an example of the present invention;

fig. 8 is a flowchart illustrating a processing method of vehicle information according to another example of the present invention;

fig. 9 is a functional block diagram of a vehicle information processing device according to an embodiment of the invention;

fig. 10 is a functional block diagram of an electronic device according to a third embodiment of the present invention;

fig. 11 is a schematic diagram of a hardware structure of an electronic device according to a fourth embodiment of the present 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.

< hardware configuration >

Fig. 1 and 2 are block diagrams of the hardware configuration of an electronic device 1000 that can be used to implement the processing method of vehicle information of any embodiment of the present invention.

In one embodiment, as shown in FIG. 1, the electronic device 1000 may be a server 1100.

The server 1100 provides a service point for processes, databases, and communications facilities. The server 1100 can be a unitary server or distributed servers 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.

The server 1100 may be a local server or a server deployed in the cloud.

In this embodiment, the server 1100 may include a processor 1110, a memory 1120, an interface device 1130, a communication device 1140, a display device 1150, and an input device 1160, as shown in fig. 1.

In this embodiment, the server 1100 may also include a speaker, a microphone, and the like, which are not limited herein.

The processor 1110 may be a dedicated server processor, or may be a desktop processor, a mobile version processor, or the like that meets performance requirements, and is not limited herein. The memory 1120 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 1130 includes various bus interfaces such as a serial bus interface (including a USB interface), a parallel bus interface, and the like. The communication device 1140 is capable of wired or wireless communication, for example. The display device 1150 is, for example, a liquid crystal display panel, an LED display panel touch display panel, or the like. Input devices 1160 may include, for example, a touch screen, a keyboard, and the like.

In this embodiment, the memory 1120 of the server 1100 is configured to store instructions for controlling the processor 1110 to operate to perform at least a processing method of vehicle information according to any of the embodiments of the present invention. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

Although shown as multiple devices in fig. 1, the present invention may relate to only some of the devices, e.g., server 1100 may relate to only memory 1120 and processor 1110.

In one embodiment, the electronic device 1000 may be a terminal device 1200 such as a PC, a notebook computer, or the like used by an operator, which is not limited herein.

In this embodiment, referring to fig. 2, the terminal apparatus 1200 may include a processor 1210, a memory 1220, an interface device 1230, a communication device 1240, a display device 1250, an input device 1260, a speaker 1270, a microphone 1280, and the like.

The processor 1210 may be a mobile version processor. The memory 1220 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 1230 includes, for example, a USB interface, a headphone interface, and the like. The communication device 1240 may be capable of wired or wireless communication, for example, the communication device 1240 may include a short-range communication device, such as any device that performs short-range wireless communication based on short-range wireless communication protocols, such as the Hilink protocol, WiFi (IEEE 802.11 protocol), Mesh, bluetooth, ZigBee, Thread, Z-Wave, NFC, UWB, LiFi, and the like, and the communication device 1240 may also include a long-range communication device, such as any device that performs WLAN, GPRS, 2G/3G/4G/5G long-range communication. The display device 1250 is, for example, a liquid crystal display, a touch display, or the like. The input device 1260 may include, for example, a touch screen, a keyboard, and the like. A user can input/output voice information through the speaker 1270 and the microphone 1280.

In this embodiment, the memory 1220 of the terminal device 1200 is used to store instructions for controlling the processor 1210 to operate to perform at least a processing method of vehicle information according to any of the embodiments of the present invention. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

Although a plurality of devices of the terminal apparatus 1200 are shown in fig. 2, the present invention may relate only to some of the devices, for example, the terminal apparatus 1200 relates only to the memory 1220 and the processor 1210 and the display device 1250.

In a further embodiment, referring to fig. 10, the electronic device 1000 may comprise a vehicle information processing device 9000 according to any embodiment of the present invention, wherein the vehicle information processing device 9000 is configured to execute a vehicle information processing method according to any embodiment of the present invention.

< method examples >

Fig. 3 is a flowchart illustrating a method for processing vehicle information according to an embodiment of the present invention, which may be implemented by the vehicle information processing apparatus 9000 or any of the above electronic devices 1000.

As shown in fig. 3, the vehicle information processing method of the present embodiment may include steps S2100 to S2400 of:

in step S2100, the processing device 9000 matches the train number tasks in the train number set with the vehicles in the vehicle set, and obtains a candidate matching result.

The vehicle in the embodiment may be a bus, a subway, a light rail, a train, or the like that travels along a predetermined route.

The vehicle set comprises all vehicles which return to the parking position after the vehicles execute the tasks in the night before the operation day to be compiled, and the parking position is the station track taking the subway as an example. For example, the day of operation to be orchestrated is 2018.12.14, and the set of vehicles may include all vehicles that performed tasks back to a parking location 2018.12.13 evening.

The train number set comprises all train number tasks in a train number list arranged for the operation days to be compiled, and here, the train number list of the operation days to be compiled can be obtained, so that all train number tasks of the operation days to be compiled are obtained from the train number list to form the train number set.

In step S2100, the processing device 9000 may obtain a vehicle number set and a vehicle set from a terminal device at an operation site. Here, the operator may enter the train number list and the yard route list into the terminal device, and the processing device 9000 may obtain the train number set according to the train number list and the train number set according to the yard route list.

In this embodiment, the processing device 9000 may be integrated in a terminal device in an operation site, or may be physically independent from the terminal device, for example, be disposed in a server or a local server located in a cloud.

In this embodiment, the vehicle number tasks in the vehicle number set are matched with the vehicles in the vehicle number set, so that a plurality of different candidate matching results can be obtained, and each candidate matching result includes vehicles matched with the vehicle number tasks in the vehicle number set one by one.

In this embodiment, the step S2100 of matching the train number tasks in the train number set with the vehicles in the vehicle set to obtain the candidate matching result may further include the following steps S2110 to S2120:

in step S2110, the operation device 9000 filters, for each of the number of vehicles in the number of vehicles set, vehicles that satisfy the condition for executing the number of vehicles in the number of vehicles set, and obtains a vehicle subset corresponding to the number of vehicles in the number of vehicles set.

In this embodiment, for each train number task in the train number set, vehicles meeting the condition for executing the corresponding train number task are screened from the vehicle set, so that vehicle subsets corresponding to each train number task one to one can be obtained, and a candidate matching result is obtained according to the train number task and the vehicle subsets corresponding to the train number task.

In this embodiment, the step S2110 of screening the vehicle set for vehicles meeting the condition for performing the vehicle-number task may further include: the processing device 9000 screens vehicles satisfying the condition for executing the vehicle-number task based on the state information of the vehicles in the vehicle group and the set constraint conditions.

The above status information may include at least one of parking position information and a given task other than a vehicle number task on the operation day to be orchestrated.

Taking subway, train and other rail vehicles as examples, the parking position information may include a parked track position, a parked track type and the like.

The parked station is used to indicate the parking position of the vehicle within the yard. For example, in the case of a subway, each track has a track number, and the track number may be a number or a letter, as long as different tracks can be distinguished, and is not limited herein. At most two vehicles can be parked on each track, which can be the north and south directions on the same track respectively identified by the letters "S" and "N", for example, the track number of the parked vehicle is 23, and at this time, the position of the parked track can be 23N, which indicates that the vehicle is parked in the north direction of the track with the track number of 23.

The established tasks of the operation days to be compiled comprise other tasks executed by the vehicle except the operation day and vehicle time tasks to be compiled. For example, the vehicle may perform a minor repair task on the operating day to be compiled, the vehicle may perform a washing task on the operating day to be compiled, or the vehicle may perform a wheel grinding task on the operating day to be compiled. Any task that can affect the vehicle to perform the train number task of the operation day to be compiled can be used as the given task, and is not limited herein.

The constraint conditions set above may include setting conditions that affect the configuration result.

For example, the set constraints may include that each vehicle-number task is, and can only be, served by one vehicle, and that one vehicle can serve at most any vehicle-number task.

For example, the set constraint condition may include a limit condition that the task completion rate P of the morning rush hour and the specified bus number task must be satisfied when the operation plan is compiled, and thus the task completion rate P of the morning rush hour and the specified bus number task_mThere are the following constraints:

wherein, MP_fMP for the early peak and number of assigned vehicle number tasks_totalThe total number of the tasks of the specified train number and the early peak are obtained.

For example, the set constraint conditions may further include that the switch switching needs to be performed when the switch requirement of the current train number is inconsistent with the switch state, and at this time, the constraint of the minimum time interval of the switch switching train number needs to be considered:

Time_l>60，l∈[2,3,...,n] (2)；

wherein, Time_lThe unit of the time interval between the current train number task and the last train number task is second(s), and l is the train number of the turnout required to be switched.

For another example, the set constraint condition may further include a requirement for satisfying the convenience of ex-warehouse; or, the problem of insufficient power supply is avoided by considering the issue quantity of the same power supply area; or, the problem that the vehicle fails to meet the emergency is avoided by considering the selection problem of the standby vehicle; or, the problem that two vehicles leave a regular bus continuously on the same track is considered, and the problem that the departure interval time is short is avoided.

According to the method, the vehicles corresponding to the vehicle-level tasks are screened according to the state information of the vehicles and the set constraint conditions, so that the vehicles which are basically impossible to become vehicles matched with the vehicle-level tasks in the vehicle set can be filtered, and the efficiency and the accuracy of obtaining candidate matching results are improved.

In step S2120, the processing device 9000 combines the vehicle-number tasks and the vehicle subset to obtain candidate matching results.

In this embodiment, after the vehicle subset corresponding to each vehicle task in the vehicle subset is obtained in step S2110, a plurality of different candidate configuration results can be obtained by combining the vehicle tasks and the vehicle subsets in step S2120.

According to the steps S2110 to S2120, the example screens out vehicles meeting the condition of executing the vehicle-level task, obtains the vehicle subset corresponding to the vehicle-level task, obtains the candidate matching result according to the vehicle-level task and the vehicle subset, and further improves efficiency and accuracy of obtaining the candidate matching result.

In step S2200, the processing device 9000 obtains the predicted mileage for each vehicle to execute the assigned vehicle number task in each candidate orchestration result.

The predicted mileage of the vehicle for executing the assigned vehicle number task may be determined according to a mapping function that reflects a correspondence between the feature vector and the traveled mileage, where the feature vector may include a plurality of features that affect the mileage of the vehicle for executing the vehicle number task, and since the mapping function is obtained by training a large number of training samples, a mapping relationship f (x) between the corresponding feature vector and the predicted mileage may be obtained according to the actual mileage corresponding to the plurality of training samples and the vector value of the corresponding feature vector.

In this embodiment, after the predicted mileage of each vehicle executing the assigned vehicle number task in each candidate matching result is obtained, the predicted mileage and the target mileage of the corresponding vehicle may be compared to obtain a deviation between the predicted mileage and the target mileage of the corresponding vehicle, so as to obtain a matching score of each candidate matching result.

In step S2300, the processing device 9000 obtains an allocation score for each candidate allocation result from a deviation between the predicted mileage and the target mileage of the corresponding vehicle.

The target mileage of the vehicle may be the daily average mileage traveled by the vehicle plan, and when the vehicle travels in accordance with the target mileage, the travel of the vehicle can be performed in the planned inspection direction, i.e., when the specified inspection date is reached, the vehicle has substantially traveled the planned inspection mileage.

The planned mileage for inspection of the vehicle is the mileage specified for travel of the vehicle when the inspection date of the vehicle is reached. For example, the specified inspection date is 2018.12.30, the planned mileage of the vehicle is 10000 km, and when the vehicle travels, if the vehicle travels in accordance with the target mileage, the vehicle can be made to travel almost 10000 km by the time the vehicle arrives at the specified inspection date 2018.12.30.

In this embodiment, the step S2300 in which the processing device 9000 obtains the matching score of each candidate matching result according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle may further include the following steps S2310 to S2320:

in step S2310, the processing device 9000 obtains a total deviation for each candidate matching result from the deviation between the predicted mileage and the target mileage of the corresponding vehicle.

In this embodiment, the vehicle number task in the candidate matching result and the matched vehicle may be used as a matching pair, and the deviation σ between the predicted mileage and the target mileage of each matching pair in the candidate matching result is calculated, so as to determine the total deviation α generated by the corresponding candidate matching result according to the deviation σ between the predicted mileage and the target mileage of each matching pair.

In the present embodiment, the total deviation α may be expressed in any form.

In one example, the total deviation α generated by each candidate matching result may be the sum of the absolute values of the deviations of the matching pairs in the corresponding matching, and the calculation formula of the total deviation α generated by each candidate matching result may be as follows:

wherein i is a natural number from 1 to N, and N is the total number of matching pairs in the candidate matching result.

In an example, the overall deviation α generated by each candidate matching result may be an average deviation of each matching pair in the corresponding matching, such as, but not limited to, an arithmetic average, a geometric average, a squared average, and the like, and is not limited herein.

For example, the total deviation α generated by each candidate matching result may be an arithmetic average of matching pairs in the corresponding matching, and the calculation formula of the total deviation α generated by each candidate matching result may be as follows:

for another example, the total deviation α generated by each candidate matching result may be a geometric mean of matching pairs in the corresponding matching, and the calculation formula of the total deviation α generated by each candidate matching result may be as follows:

for example, the total deviation α generated by each candidate matching result may be a square average of matching pairs in the corresponding matching, and the calculation formula of the total deviation α generated by each candidate matching result may be as follows:

in step S2320, the processing device 9000 obtains an allocation score of each candidate allocation result according to the overall deviation.

In this embodiment, the lower the overall deviation, the higher the corresponding allocation score. In one example, the processing device 9000 may obtain a total deviation range to which the total deviation of the candidate matching results belongs, and use the matching score corresponding to the total deviation range as the matching score corresponding to the candidate matching results.

In an example, the processing device 9000 may also compare the magnitude relationship between the total deviation of the candidate matching result and a specific total deviation to obtain a comparison result, and determine a matching score of the total deviation of the candidate matching result according to the comparison result, where the specific total deviation may be set according to the actual application and the specific scenario, and is not limited herein.

In one example, the processing device 9000 stores mapping data reflecting the correspondence between the overall deviation value and the matching score to obtain a matching score corresponding to the candidate matching result according to the mapping data and the overall deviation of the candidate matching result. For example, the processing device 9000 may directly map the corresponding orchestration score with the inverse of the overall deviation.

According to the steps S2310 to S2320, the example first obtains the total deviation of the candidate matching results, and then obtains the matching score of the candidate matching results based on the total deviation, so that the matching score can reflect the quality of the whole matching of the corresponding candidate matching results, and the accuracy of the obtained matching score is further improved.

In step S2400, the processing device 9000 selects a final matching result from the candidate matching results and outputs the selected final matching result based on the matching score obtained in step S2300.

In one example, the candidate orchestration result that results in the highest orchestration score may be selected to be output as the final orchestration result.

In one example, the candidate matching result with the matching score within the set range may be selected and output as the final matching result for the operator to select.

In one example, the processing device 9000 in this step S2400 may further include the following steps S2410 to S2420 of selecting a final orchestration result output among the candidate orchestration results according to the orchestration scores:

in step S2410, the processing device 9000 generates an assembly schedule from the final assembly result.

The compilation schedule reflects the corresponding relationship between the vehicle number tasks and the distributed vehicles.

In step S2420, the operation device 9000 outputs the compilation schedule.

In one example, the processing device 9000 in step S2400 may further select a final orchestration result output from the candidate orchestration results according to the orchestration score, including: and responding to the request for acquiring the processing result, and executing the step of selecting and outputting the final assembly result from the candidate assembly results according to the assembly scores.

The request may be triggered by the operator via the terminal device in the operating field and the final configuration result may be provided via the terminal device, for example, by displaying the final configuration result via a display device of the terminal device. Therefore, the operator can schedule the vehicles on the operation day according to the matching relation between the vehicles and the train number tasks reflected by the final configuration result, so that the specific vehicles can execute the specific train number tasks on the operation day.

For example, the operation means 9000 is integrated in the terminal device, and the operation means 9000 obtains a final orchestration result in response to the request and provides the final orchestration result through a display means of the terminal device.

For another example, the operation device 9000 is integrated in a server, the terminal device is in communication connection with the server, the terminal device receives the request and transmits the request to the operation device 9000, and the operation device 9000 obtains a final assembly result in response to the request and transmits the final assembly result to the terminal device to provide the final assembly result through a display device of the terminal device.

In one example, the processing device 9000 in step S2400 may further select a final orchestration result output among the candidate orchestration results according to the orchestration scores, including: and sending the train number task to the corresponding vehicle according to the final configuration result, so that the vehicle loads an operation control program for executing the assigned train number task.

In this example, the vehicle and the processing device 9000 each have a communication device, and the processing device 9000 and the vehicle can establish wireless communication connection via the respective communication devices, so that the processing device 9000 can transmit the vehicle number job to the corresponding vehicle according to the final configuration result, so that the control device of the vehicle can execute the vehicle number job in accordance with the loaded operation control program.

In this example, the vehicle may load an operation control program for executing the assigned vehicle-number task from a memory of the vehicle itself; the server may also be connected to download the operation control program from the server, and the loading of the operation control program is completed after the downloading.

In this example, the vehicle may first search for whether the own memory has an operation control program for executing the assigned vehicle-number task, and if so, load the operation control program from the own memory to execute the assigned vehicle-number task; if not, connecting the server to download the operation control program from the server, and completing the loading of the operation control program after the downloading.

In one example, the processing device 9000 in step S2400 may further select a final orchestration result output among the candidate orchestration results according to the orchestration scores, including: and sending the train number task and the corresponding operation control program to the corresponding vehicle according to the final configuration result, so that the vehicle executes the distributed train number task according to the received operation control program.

According to the steps S2410 to S2420, the example generates a more intuitive assembly schedule from the final assembly result, and further outputs the assembly schedule, so that an assembly worker can conveniently assemble a proper vehicle to perform the vehicle number task of the operation day according to the assembly schedule, and further the driving mileage of all vehicles can be performed according to the planned maintenance direction.

According to the method of the embodiment, after the vehicle-number task and the candidate matching result of the corresponding vehicle are obtained, the predicted mileage of each vehicle executing the allocated vehicle-number task in the candidate matching result is obtained, the matching score of each candidate matching result is obtained according to the deviation between the predicted mileage and the target mileage of the corresponding vehicle, so that the candidate matching result with the highest matching score is obtained, the specific vehicle-number task on the operation day of the specific vehicle is arranged according to the candidate matching result with the highest matching score, the driving mileage of all vehicles can be executed according to the planned overhaul direction, and the mileage of the vehicle is controllable.

In one embodiment, the method for processing vehicle information of the present invention may further include steps S3100 to S3200 as follows:

in step S3100, the processing device 9000 detects a set event for processing vehicle information.

The event includes at least one of reaching a preset processing time and receiving a processing instruction of the vehicle information.

In the example that the event includes reaching the preset processing time, the preset processing time may be set according to an application scenario or a specific requirement. For example, the preset treatment time may be 5 am per day. Then, the processing method of the present invention may be performed at 5 am per day.

In embodiments where the event includes receipt of a processing instruction for the vehicle information, the processing instruction may include an internal instruction, for example, an internal instruction triggered by the expiration of a preset processing time, an internal instruction triggered by receipt of an input vehicle number task and a vehicle set, and the like. The processing instruction may also include an external instruction, for example, an external instruction triggered by an operator through a terminal device in an operation field, which may be to install an operation management application on the terminal device and set a control for triggering the external instruction on an interface of the application.

In step S3200, the processing device 9000, upon detecting the occurrence of the event, acquires a set of vehicles and a set of train numbers to perform a step of matching the train number tasks in the set of train numbers with the vehicles in the set of vehicles.

In one example, the processing device 9000 may first obtain a train number list of the operation day to extract train number tasks in the train number list to obtain a train number set.

According to the embodiment of the invention, the processing method according to any embodiment of the invention can be implemented through the detection of the set event, so that the efficient configuration according to the requirement is realized.

In one embodiment, as shown in fig. 4, the method for processing vehicle information according to the present invention may further include obtaining a target mileage of each vehicle in each candidate configuration result, and may further include the following steps S4100 to S4300:

in step S4100, the processing device 9000 acquires the planned mileage of inspection of the vehicle and the current actual mileage of the vehicle.

The scheduled mileage for inspection of the vehicle is the mileage specified for the vehicle when the inspection date of the vehicle is reached, and the vehicles in the vehicle set may have the same inspection date or different inspection dates. For example, the specified inspection date is 2018.12.30, and the planned mileage of the vehicle is 10000 km, that is, when the specified inspection date 2018.12.30 is reached, it is necessary to ensure that the corresponding vehicle has traveled substantially 10000 km.

The current actual mileage of the vehicle is the total traveled mileage of the vehicle before the operating day to be compiled. Taking the operation day to be compiled as 2018.12.14 as an example, the current actual mileage of the vehicle obtained according to the step S4100 may be 2000 km, that is, the total distance traveled by the vehicle before 2018.12.14 (excluding 2018.12.14) is 2000 km.

In one example, the current actual mileage of the vehicle may be actively transmitted to the processing device 9000 by the terminal device on site after the vehicle has performed the task back to the parking position.

In one example, the processing device 9000 may request the terminal device on the spot to acquire the current actual mileage of the vehicle in response to a processing instruction of the vehicle information.

In step S4200, the processing device 9000 acquires the number of running days from the current date to the inspection date of the vehicle.

Still taking the specified inspection date of 2018.12.30 and the operation date to be compiled of 2018.12.14 as an example, the inspection scheduled mileage of the vehicle obtained according to step S4100 is 10000 km, and the current actual mileage of the vehicle is 2000 km, and the number of days of operation from the current date to the inspection date of the vehicle obtained according to step S4200 is 16 days.

In step S4300, the processing device 9000 obtains a target mileage of the vehicle from the maintenance plan mileage, the current actual mileage, and the number of days of operation.

In this embodiment, the calculation formula of the target mileage of the vehicle is as follows:

wherein M is_iRepresents the target mileage of the ith vehicle, b₂Representing the scheduled mileage of the vehicle, b₁The current actual mileage of the vehicle is represented, day represents the number of running days between the current date and the overhaul date of the vehicle, the value of i is each natural number from 1 to M, and M is the total number of vehicles in the vehicle set.

Still with prescribed examinationThe repair date is 2018.12.30, the operation day to be compiled is 2018.12.14 as an example, the planned mileage of the vehicle is 10000 km according to the step S4100, the current actual mileage of the vehicle is 2000 km, the number of operation days from the current date to the repair date of the vehicle is 16 days according to the step S4200, and the target mileage of the vehicle is obtained according to the step S4300

That is, the target mileage of the vehicle is 500 km, it can also be understood that the planned travel mileage of the vehicle at 2018.12.14 is 500 km, after the vehicle has executed the vehicle number task at 2018.12.14 according to the final configuration result, when the vehicle is configured at 2018.12.15, the mileage of the vehicle actually running at 2018.12.14 for executing the vehicle number task is added, and the target mileage of the vehicle at 2018.12.15 days is recalculated, so as to improve the accuracy of the obtained target mileage of the specific vehicle at each operating day, so that the current actual mileage gradually converges to the maintenance planned mileage when the vehicle reaches the set maintenance date.

According to the embodiment of the invention, the overhaul plan mileage of the vehicle and the current actual mileage of the vehicle can be obtained, the running days of the current date far away from the overhaul date of the vehicle are obtained, the target mileage of the vehicle on the running day to be compiled is obtained according to the overhaul plan mileage, the current actual mileage of the vehicle and the running days, and the target mileage is compared with the predicted mileage to obtain the compiling score of the candidate compiling result.

In one embodiment, referring to fig. 5, the obtaining of the predicted mileage of each vehicle performing the assigned task of the train number in each candidate configuration result in step S2200 may further include steps S5100 to S5400:

in step S5100, the processing device 9000 acquires the selected feature vector.

The feature vector X includes a plurality of features X that affect the mileage of the vehicle performing the vehicle number task_jJ takes a natural number from 1 to n, and n represents the total number of features of the feature vector X.

The plurality of features x_jVehicle features and vehicle number features may be included.

The vehicle characteristic may be at least one of a vehicle number and a vehicle type.

The train number characteristic may include at least one of a departure time, an arrival time, a departure location, and an arrival location.

In this example, x_jThe feature may be a vehicle feature, a vehicle number feature, a vehicle type feature, or the like that can affect the mileage of the vehicle performing the vehicle-number task, for example, the vehicle feature may be a vehicle number and a vehicle type, and the vehicle-number feature may be a departure time, an arrival time, a departure point, and an arrival point, where the feature vector X may have 6 features, that is, n is 6, and in this case, the feature vector X may be represented as X (X is 6)₁,x₂,x₃,x₄,x₅,x₆). Of course, other features relevant to vehicle configuration may also be included in the feature vector X.

The above other feature may be a cross-over feature, which is a feature that cross-correlates the vehicle with the performed vehicle-number task, and the cross-over feature includes a predetermined task other than the vehicle-number task, such as an overhaul task, which may be a minor repair operation performed on the vehicle on the operation day to be compiled, a water washing operation performed on the vehicle on the operation day to be compiled, a wheel grinding operation performed on the vehicle on the operation day to be compiled, and the like, and is not limited herein.

In step S5200, the processing device 9000 acquires a mapping function between the feature vector and the mileage.

The independent variable of the mapping function F (X) is the feature vector X, and the dependent variable F (X) is the predicted mileage determined by the feature vector X.

In one embodiment, the method of the present invention may further comprise the steps S5210 to S5220 of training the mapping function:

in step S5210, the processing device 9000 acquires training samples from the historical operating data.

Each training sample includes the paired vehicle and the number of vehicle tasks actually performed.

In step S5220, the processing device 9000 performs training to obtain a mapping function according to the vector value of the feature vector of the training sample and the actual mileage corresponding to the training sample.

In this embodiment, the mapping function f (x) may be obtained by various fitting means based on the vector value of the feature vector of the training sample and the actual mileage corresponding to the training sample, for example, the mapping function f (x) may be obtained by using an arbitrary multiple linear regression model, which is not limited herein.

In one example, the multiple linear regression model may be a simple polynomial function reflecting the mapping function f (x), wherein each order coefficient of the polynomial function is unknown, and each order coefficient of the polynomial function may be determined by substituting the vector value of the feature vector of the training sample and the actual mileage corresponding to the training sample into the polynomial function, thereby obtaining the mapping function f (x).

In another example, various regression models, such as an additive model, may be used to perform multiple rounds of training with the vector values of the feature vectors of the training samples and the actual mileage corresponding to the training samples as accurate samples, each round learns the residual after the last round of fitting, and the residual is controlled to a very low value by iterating T rounds, so that the finally obtained mapping function f (x) has very high accuracy. The addition model is, for example, LightGBM, GBDT, XGBoost, etc., and is not limited herein.

In step S5300, the processing device 9000 obtains the predicted mileage of each vehicle executing the assigned vehicle-number task in each candidate matching result according to the mapping function and the vector value of the feature vector of each matching pair in each candidate matching result.

Each matched pair includes a matched pair of a vehicle number task and a vehicle. For example, after the feature vectors are obtained in step S5100, vector values of the feature vectors of the matching pairs in the candidate matching result may be obtained. Taking the train number characteristic as an example, the corresponding characteristic values of the departure time, the arrival time, the departure place and the arrival place of the train number can be 5:53:44, 6:48:00, Beijing Western and Western style, respectively.

In this embodiment, after obtaining the vector value of the eigenvalue of each matching pair in each candidate matching result, the vector value may be substituted into the mapping function f (x) to obtain the predicted mileage of each vehicle executing the assigned vehicle number task in each candidate matching result.

According to the embodiment of the invention, the predicted mileage of each vehicle executing the assigned vehicle number task in the candidate configuration result can be obtained according to the feature vector and the mapping function, and the mapping function is obtained by training according to a large number of training samples, so that the accuracy of the obtained predicted mileage can be improved when the mapping function is used for determining the predicted mileage.

In one embodiment, as shown in fig. 6, the training of the mapping function in step S5220 may further include the following steps S5221 to S5223:

in step S5221, the processing device 9000 determines the mileage-predicting expression of each training sample according to the vector value of the feature vector of each training sample, with the undetermined coefficient of the mapping function as a variable.

Assume that the feature vector X in the mapping function includes n features X₁,x₂,......,x_nDetermining the value of the k training sample for n features

Then, the undetermined coefficient set comprises a constant weight b and n characteristic weights a₁,a₂,......,a_nAs a variable, the k training sample mileage predicting expression may be obtained as Y_k:

In step S5222, the processing device 9000 constructs a loss function according to the mileage-predicting expression of each training sample and the actual mileage of each training sample.

In this embodiment, the constructing of the loss function in step S5222 may further include the following steps S5222-1 to S5222-2:

in step S5222-1, the processing device 9000 determines, for each training sample, a corresponding loss expression according to the mileage prediction expression and the actual mileage.

Assuming that the number of the collected training samples is m, the obtained actual mileage is y for the k training sample_kThe mileage prediction expression is Y_kThe corresponding loss expression is (y)_k-Y_k)²(k ═ 1.., m); wherein,

in step S5222-2, the processing device 9000 sums the loss expressions of each training sample to obtain a loss function.

In this embodiment, the loss function is:

wherein,

in step S5223, the processing device 9000 determines an undetermined coefficient according to the loss function, and completes the present training of the mapping function.

In this embodiment, in step S5223, the undetermined coefficient is determined according to the loss function, and the completion of the training of the mapping function may further include steps S5223-1 to S5223-3:

and step S5223-1, setting constant weights in the undetermined coefficient set and the initial value of each characteristic weight as random numbers in a preset numerical range.

Suppose a set of pending coefficients b, a₁,a₂,......,a_nComprises a constant weight b and n characteristic weights a₁,a₂,......,a_nThe initial value may be set to a random number of a preset numerical range. The preset value range can be set according to application scenes or application requirements, for exampleFor example, the predetermined value range is set to 0-1, such that the constant weight b and the n feature weights a₁,a₂,......,a_nAre random numbers between 0 and 1.

Step S5223-2, the constant weight and each feature weight after the initial value is set are substituted into the loss function, and iterative processing is performed.

In this embodiment, the step S5223-2 of substituting the constant weight after setting the initial value and each feature weight into the loss function may further include the following steps S5223-21 to S5223-22:

and S5223-21, respectively, for the constant weight and each feature weight, obtaining the corresponding value of the constant weight or the feature weight after the iteration according to the constant weight or the value of the feature weight before the iteration, the convergence parameter and the loss function substituted into the undetermined coefficient set before the iteration.

The convergence parameter is a relevant parameter for controlling the convergence speed of the iterative process, and may be set according to an application scenario or an application requirement, for example, to 0.01.

And S5223-22, obtaining the undetermined coefficient set after the iteration according to the constant weight and the value after the iteration of each characteristic weight.

Assuming that the iteration is the (k + 1) th iteration (the initial value of k is 0, and 1 is added along with each iteration), the undetermined coefficient set after the iteration is the { b, a₁,a₂,...,a_n}^(k+1)。

And S5223-3, when the undetermined coefficient set obtained by the iterative processing meets the convergence condition, terminating the iterative processing, and determining the constant weight of the undetermined coefficient set and the value of each characteristic weight, otherwise, continuing the iterative processing.

The convergence condition may be set according to a specific application scenario or application requirements.

For example, the convergence condition is that the number of iterative processes is greater than a preset number threshold. The preset time threshold may be set according to engineering experience or experimental simulation results, and may be set to 300, for example. Correspondingly, assuming that the number of iterative processes is k +1, the number threshold is itemnams, and the corresponding convergence condition is: k is not less than itemNums.

For another example, the convergence condition is that an iteration result value of the undetermined coefficient set obtained by the iteration processing is smaller than a preset result threshold. The iteration result value is determined according to the result of partial derivation of the loss function substituted by the undetermined coefficient set obtained by iteration processing and the corresponding constant weight or each characteristic weight.

In an example, the convergence condition is that any one of the convergence conditions in the two examples is satisfied, and the specific convergence condition has been described in the two examples and is not described herein again.

Suppose that the undetermined coefficient set { b, a obtained by the (k + 1) th iteration processing₁,a₂,...,a_n}^(k+1)When the convergence condition is met, stopping the iterative processing to obtain all the corresponding a_i ^(k+1)(i ═ 1.., n) and b^(k+1)And taking values, otherwise, continuing the iterative processing until the undetermined coefficient set meets the convergence condition.

According to the embodiment of the invention, the mapping function can be obtained according to a large number of training samples, so that when the mapping function is used for determining the predicted mileage, the accuracy of the obtained predicted mileage can be improved.

In one embodiment, the vehicle information processing method of the present invention may further include the steps of:

in step S6100, after completing the operation according to the final configuration result, the processing device 9000 acquires the vehicle paired in the final configuration result and the actually executed vehicle number task as a new training sample.

In step S6200, the processing device 9000 corrects the mapping function according to the vector value of the feature vector of the new training sample and the actual mileage of the new training sample on the corresponding operation day.

According to the embodiment of the invention, after the operation is finished according to the final configuration result, the actual mileage of the vehicle for executing the assigned train number task can be obtained, the vehicle matched in the final configuration result and the actually executed train number task are used as new training samples, the mapping function is corrected, namely, the new training samples are added, and the mapping function is retrained, so that the mileage prediction is more and more accurate.

< example >

Fig. 7 is an exemplary method for operational orchestration of vehicles (particularly subways), which may include the steps of:

in step S7100, the processing device 9000 acquires a list of the number of cars on the operation day and a set of vehicles in response to the processing instruction of the vehicle information.

In step S7200, the processing device 9000 extracts the train number tasks in the train number list to obtain a train number set.

In step S7310, the processing device 9000 filters, for each of the number of vehicles in the number of vehicles set, vehicles satisfying the conditions for executing the number of vehicles in the number of vehicles set according to the status information of the vehicles in the number of vehicles set and the set constraint conditions, and obtains a subset of vehicles corresponding to the number of vehicles in the number of vehicles set.

In step S7320, the processing device 9000 combines the number-of-vehicles tasks with the subset of vehicles to obtain candidate matching results.

In step S7400, the processing device 9000 obtains the predicted mileage for each vehicle to execute the assigned vehicle number task in each candidate matching result.

In this example, as shown in fig. 8, the obtaining of the predicted mileage of each vehicle performing the assigned vehicle number task in each candidate configuration result in step S7400 may further include:

in step S7410, the processing device 9000 acquires the selected feature vector.

In step S7420, the processing device 9000 obtains training samples from historical operating data.

In step S7430, the processing device 9000 determines a mileage prediction expression of each training sample according to the vector value of the feature vector of each training sample, using the undetermined coefficient of the mapping function as a variable.

In step S7440, the processing device 9000 determines, for each training sample, a corresponding loss expression according to the mileage prediction expression and the actual mileage.

In step S7450, the processing device 9000 sums the loss expressions of each training sample to obtain a loss function.

In step S7460, the processing device 9000 determines the undetermined coefficient according to the loss function, and completes the training of the mapping function.

In step S7470, the processing device 9000 obtains vector values of feature vectors of each matching pair in each candidate matching result.

In step S7480, the processing device 9000 obtains the predicted mileage for each vehicle to execute the assigned vehicle number task in each candidate matching result according to the mapping function and the vector value.

In step S7510, the processing device 9000 acquires the planned mileage of the vehicle and the current actual mileage of the vehicle.

In step S7520, the processing device 9000 acquires the number of running days from the current date to the inspection date of the vehicle.

In step S7530, the processing device 9000 obtains a target mileage of the vehicle from the planned mileage, the current actual mileage, and the number of days of operation.

In step S7610, the processing device 9000 obtains an overall deviation of each candidate matching result from the deviation between the predicted mileage and the target mileage of the corresponding vehicle.

In step S7620, the processing device 9000 obtains an orchestration score for each candidate orchestration result according to the overall deviation.

In step S7710, the processing device 9000 generates an orchestration schedule from the final orchestration result.

In step S7720, the processing device 9000 outputs the compilation schedule via the terminal device.

< apparatus embodiment >

Fig. 9 is a functional block diagram of a vehicle information processing device 9000 according to an embodiment of the present invention.

As shown in fig. 9, the vehicle information processing apparatus 9000 of the present embodiment may include a candidate orchestration module 9100, a mileage predicting module 9200, an orchestration scoring module 9300, and a decision module 9400.

The candidate matching module 9100 is configured to match the vehicle-number tasks in the vehicle-number set with the vehicles in the vehicle set, so as to obtain a candidate matching result.

The mileage predicting module 9200 is configured to obtain a predicted mileage for each vehicle executing the assigned vehicle number task in each candidate compilation result.

The matching score module 9300 is configured to obtain a matching score for each candidate matching result according to a deviation between the predicted mileage and a target mileage of the corresponding vehicle.

The decision module 9400 is configured to select a final assembly result from the candidate assembly results according to the assembly score and output the final assembly result.

In one embodiment, the candidate orchestration module 9100 is further configured to, for each of the number of vehicles in the number of vehicles set, screen vehicles in the number of vehicles set that meet the condition for executing the number of vehicles, and obtain a subset of vehicles corresponding to the number of vehicles; and combining to obtain candidate matching results according to the corresponding relation between the vehicle number task and the vehicle subset.

In one embodiment, the candidate orchestration module 9100 is further configured to filter vehicles satisfying conditions for performing the vehicle-level task according to the status information of the vehicles in the vehicle set and the set constraint conditions.

In this embodiment, the status information includes at least one of parking position information and a predetermined task other than a vehicle number task on the operation day to be compiled.

In one embodiment, the candidate orchestration module 9100 is further configured to detect a set event for processing vehicle information, and upon detecting that the event occurs, obtain the vehicle set and the vehicle set to perform an operation of matching the vehicle tasks in the vehicle set with the vehicles in the vehicle set.

In one embodiment, the processing device 9000 may further comprise a target mileage acquiring module (not shown in the figure).

The target mileage acquisition module is used for acquiring the maintenance planned mileage of the vehicle and the current actual mileage of the vehicle; acquiring the number of running days between the current date and the overhaul date of the vehicle; and obtaining the target mileage of the vehicle according to the mileage of the maintenance plan, the current actual mileage and the operation days.

In one embodiment, the compilation scoring module 9300 is further configured to obtain a total deviation generated by each candidate compilation result according to a deviation between the predicted mileage and a target mileage of the corresponding vehicle; and obtaining the matching score of each candidate matching result according to the overall deviation.

In this embodiment, the lower the overall deviation, the higher the corresponding orchestration score.

In one embodiment, the decision module 9400 is further configured to generate a compilation schedule based on the final compilation results; and outputting the compilation schedule.

In this embodiment, the compilation schedule reflects the correspondence between the vehicle-number tasks and the assigned vehicles.

In one embodiment, the mileage predicting module 9200 is further configured to obtain selected feature vectors; acquiring a mapping function between the feature vector and the driving mileage; and obtaining the predicted mileage of each vehicle executing the assigned vehicle number task in each candidate matching result according to the mapping function and the vector value of the feature vector of each matching pair in each candidate matching result.

In this embodiment, the feature vector includes a plurality of features that affect the miles of the vehicle performing the vehicle number task, the plurality of features including vehicle features and vehicle number features.

In this embodiment, each matched pair includes a paired vehicle number assignment and vehicle.

In one embodiment, the vehicle characteristic includes at least one of a vehicle number and a vehicle type; and/or, the train number characteristic includes at least one of a departure time, an arrival time, a departure location, and an arrival location.

In one embodiment, the plurality of features further includes a cross feature. The cross-over feature is a feature that cross-correlates the vehicle with the performed turn number tasks, the cross-over feature including established tasks other than the turn number tasks, such as service tasks.

In one embodiment, the mileage predicting module 9200 is further configured to obtain training samples based on historical operating data; and training to obtain a mapping function according to the vector value of the feature vector of the training sample and the actual mileage corresponding to the training sample.

In this embodiment, each training sample includes the paired vehicle and the number of vehicle tasks actually performed.

In one embodiment, the mileage predicting module 9200 is further configured to determine a mileage predicting expression of each training sample according to a vector value of a feature vector of each training sample, respectively, with a pending coefficient of a mapping function as a variable; constructing a loss function according to the mileage prediction expression of each training sample and the actual mileage of each training sample; and determining the undetermined coefficient according to the loss function, and finishing the training of the mapping function.

In one embodiment, the mileage predicting module 9200 is further configured to determine, for each training sample, a corresponding loss expression according to a mileage prediction expression and an actual mileage; and summing the loss expressions of each training sample to obtain a loss function.

In one embodiment, the processing device 9000 may further comprise a correction module (not shown in the figure).

The correction module is used for acquiring matched vehicles and actually executed vehicle number tasks in the final configuration result as new training samples after operation is finished according to the final configuration result; and correcting the mapping function according to the vector value of the feature vector of the new training sample and the actual mileage of the new training sample in the corresponding operation day.

< electronic device embodiment >

In this embodiment, an electronic device 1000 is also provided, where the electronic device 1000 may be the server 1100 shown in fig. 1, or may be the terminal device 1200 shown in fig. 2.

As shown in fig. 10, the electronic device 1000 may include a processing device 9000 of the vehicle information according to any embodiment of the present invention for implementing a processing method of the vehicle information according to any embodiment of the present invention.

In another embodiment, as shown in fig. 11, the electronic device 1000 may further comprise a processor 1300 and a memory 1400, the memory 1400 for storing executable instructions; the processor 1300 is configured to operate the electronic device 1000 to perform a processing method of vehicle information according to any embodiment of the present invention according to the control of the instruction.

The electronic device 1000 may be the server 1100 shown in fig. 1, or may be the terminal device 1200 shown in fig. 2, which is not limited herein.

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 encoding device, such as punch cards or in-groove raised 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 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 processing vehicle information, comprising:

obtaining a predicted mileage and a target mileage of each vehicle executing the distributed vehicle number task in each candidate configuration result, wherein the predicted mileage is obtained according to the selected feature vector, and the target mileage represents a daily average walking mileage of the vehicle plan;

obtaining the total deviation of each candidate matching result according to the deviation of the predicted mileage and the target mileage of the corresponding vehicle, and determining a matching score according to the total deviation;

2. The method of claim 1, wherein the step of matching the vehicle number tasks in the vehicle number set with the vehicles in the vehicle number set to obtain the candidate orchestration result comprises:

for each train number task in the train number set, screening vehicles meeting conditions for executing the train number task from the vehicle set, and obtaining a vehicle subset corresponding to the train number task;

3. The method of claim 2, wherein the step of screening the set of vehicles for vehicles meeting the conditions for performing the vehicle number task comprises:

screening vehicles meeting the condition of executing the vehicle number task according to the state information of the vehicles in the vehicle set and set constraint conditions;

the state information comprises at least one of parking position information and established tasks except the train number task on the operation day to be compiled.

4. The method of claim 1, wherein the method further comprises:

detecting a set event for processing vehicle information;

5. The method of claim 4, wherein the event comprises at least one of:

reaching the preset processing time;

and receiving a processing instruction of the vehicle information.

6. The method of claim 1, wherein obtaining a target mileage for each vehicle in each candidate orchestration result comprises:

7. The method of claim 1, wherein the step of obtaining a matching score for each candidate matching result based on a deviation of the predicted mileage from a target mileage of the corresponding vehicle comprises:

8. The method of claim 1, wherein the step of selecting a final compilation result from the candidate compilation results for output comprises:

and outputting the compilation schedule.

9. The method of any one of claims 1 to 8, wherein the step of obtaining a predicted mileage for each vehicle performing the assigned vehicle number task in each of the candidate orchestration results comprises:

10. The method of claim 9, wherein the vehicle characteristic comprises at least one of a vehicle number and a vehicle type; and/or the train number characteristics include at least one of a departure time, an arrival time, a departure location, and an arrival location.

11. The method of claim 9, wherein the plurality of features further comprises a cross-over feature, wherein the cross-over feature is a feature that cross-correlates vehicles with performed turn number tasks, the cross-over feature comprising a service task.

12. The method of claim 9, wherein the method further comprises the step of training the mapping function, comprising:

13. The method of claim 12, wherein the step of training the mapping function comprises:

14. The method of claim 13, wherein the step of constructing a loss function comprises:

15. The method of claim 12, wherein the method further comprises:

16. A processing apparatus of vehicle information, comprising:

the mileage prediction module is used for obtaining a predicted mileage and a target mileage of each vehicle executing the distributed vehicle number task in each candidate configuration result, wherein the predicted mileage is obtained according to the selected feature vector, and the target mileage represents the daily average walking mileage of the vehicle plan;

the matching scoring module is used for obtaining the total deviation of each candidate matching result according to the deviation of the predicted mileage and the target mileage of the corresponding vehicle, and determining the matching scoring according to the total deviation; and the number of the first and second groups,

17. An electronic device comprising the processing apparatus of vehicle information of claim 16; or, a memory for storing executable instructions and a processor; the processor is configured to execute the processing method according to any one of claims 1 to 15 according to the control of the instruction.

18. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a processing method according to any one of claims 1 to 15.