CN114932929A - Train control method, apparatus, device, storage medium, and program product - Google Patents

Abstract

The application discloses a train control method, a train control device, train control equipment, a train control storage medium and a train control program product. The method comprises the following steps: acquiring N scene types, wherein N is a positive integer; extracting a knowledge graph sub graph from a knowledge graph based on the N scene types, wherein the knowledge graph sub graph comprises the N scene types and N treatment processes which are in one-to-one correspondence with the N scene types; determining a control flow of the train according to the N disposal flows; and controlling the train based on the control flow. According to the embodiment of the application, the autonomous control of the train can be realized, and the problem of low efficiency of the existing train control mode is solved.

Description

Train control method, apparatus, device, storage medium, and program product

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a train control method, apparatus, device, storage medium, and program product.

Background

With the continuous increase of the running speed and the automation degree of the urban rail transit train, the application range of a Full Automatic Operation (FAO) system is continuously expanded, and the usability of the FAO system, particularly the handling efficiency and the safety in the case of a fault and an emergency, are particularly important in the Operation process. At present, in the FAO operation process, if a fault condition occurs, the general treatment process is 'field sensing, information pushing, center confirmation, manual decision-making and field execution'.

For example, when a fire occurs in a vehicle, a dispatcher of a control center receives a vehicle fire alarm, calls a monitoring screen of a designated car, confirms the fire situation, and arranges car crews and station crews at a front platform to evacuate people, perform emergency treatment of the fire, and the like. In the whole process, the staff needs to collect and confirm information of all aspects to make a final decision. When a plurality of abnormal scenes are compounded, more time is needed for manually collecting information and making a decision, and the handling efficiency of abnormal handling is seriously influenced.

Disclosure of Invention

The embodiment of the application provides a train control method, a train control device, train control equipment, a train control storage medium and a train control program product, and can solve the problem of low efficiency of the existing train control mode.

In a first aspect, an embodiment of the present application provides a train control method, where the method includes:

acquiring N scene types according to the current running state of the train, wherein N is a positive integer;

extracting a knowledge graph sub-graph from a knowledge graph based on the N scene types, wherein the knowledge graph sub-graph comprises the N scene types and N treatment processes in one-to-one correspondence with the N scene types;

determining a control flow of the train according to the N handling flows;

and controlling the train based on the control flow.

In some embodiments, the determining a control flow for the train from the N handling flows comprises:

determining the handling flow as a control flow of the train if the N is 1.

In some embodiments, the determining a control flow for the train from the N handling flows comprises:

determining an execution order of the N handling flows according to priorities of the N scene types if the N is a positive integer greater than 1;

and determining the N handling processes arranged according to the execution sequence as the control process of the train.

In some embodiments, before said determining a control flow of said train according to said N handling flows, said method further comprises:

obtaining loss degrees corresponding to various scene types;

setting the priority of each scene type according to each loss degree.

In some embodiments, the determining a control flow for the train from the N handling flows comprises:

if the N handling flows only comprise handling steps, determining a control flow of the train according to the order relationship between the handling steps;

detecting whether the current running state of the train meets a precondition or not under the condition that the N handling processes comprise a handling step and the precondition;

and determining the control flow of the train according to a first precondition met by the current operation state, the handling step and the sequence relation between the first precondition and the handling step.

In an embodiment, each of said treatment flows comprises at least one treatment step; before the obtaining N scene types, the method further includes:

constructing a schema layer of a knowledge graph, wherein the schema layer comprises entity nodes and relations among the entity nodes;

receiving input information, wherein the input information comprises operation states of the trains in the warehouse and in the normal operation, handling principles for handling the operation states, and occurrence relations between the operation states and the handling principles;

and filling a mode layer of the knowledge graph according to the input information to generate the knowledge graph.

In one embodiment, populating a schema layer of the knowledge-graph based on the input information, generating the knowledge-graph, includes:

detecting the operating state, the disposal principle and the occurrence relation in the input information;

mapping the running state to the entity node of the mode layer to generate P scene types;

mapping the treatment principle to an entity node of the mode layer, and generating P treatment flows corresponding to the P scene types one by one, and treatment steps and preconditions included in the P treatment flows;

mapping the occurrence relation to a relation between the entity nodes in the mode layer, generating a first relation among the P scene types, the P treatment processes, the processing steps and the preconditions, and generating the knowledge graph.

In an embodiment, after said determining a control flow of the train according to the N handling flows, the method further comprises:

and displaying the control flow through a visual interface.

In a second aspect, an embodiment of the present application provides a control device for a train, the device including:

the acquisition module is used for acquiring N scene types according to the current running state of the train, wherein N is a positive integer;

an extraction module, configured to extract a knowledge-graph subgraph from a knowledge-graph based on the N scene types, where the knowledge-graph subgraph includes the N scene types and N treatment procedures in one-to-one correspondence with the N scene types;

a determining module for determining a control flow of the train according to the N handling flows;

and the control module is used for controlling the train based on the control flow.

In a third aspect, an embodiment of the present application provides a control device for a train, where the device includes: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements the train control method as described above.

In a fourth aspect, an embodiment of the present application provides a computer storage medium, where computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by a processor, the method for controlling a train as above is implemented.

In a fifth aspect, the present application provides a computer program product, where the computer program product includes computer program instructions, and the computer program instructions, when executed by a processor, implement the above train control method.

In the method, by acquiring N scene types, wherein N is a positive integer, a knowledge graph subgraph is extracted from a knowledge graph based on the N scene types, wherein the knowledge graph subgraph comprises the N scene types and N treatment processes corresponding to the N scene types one by one; determining a control flow of the train according to the N handling flows; and controlling the train based on the control flow. Therefore, compared with the prior art, when an abnormal scene occurs, the decision-making comparison needs to be carried out manually according to the acquired information, and the autonomous decision-making of the train can be carried out based on the knowledge graph, so that the control efficiency of the train is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a train control method according to an embodiment of the present application;

fig. 2 is a schematic view of a control device of a train according to an embodiment of the present application;

fig. 3 is a schematic flow chart of a train control method according to another embodiment of the present application;

fig. 4 is a schematic flow chart of a train control method according to a further embodiment of the present application;

fig. 5 is a schematic flowchart of a train control method according to yet another embodiment of the present application;

fig. 6 is a schematic view of a control device of a train according to still another embodiment of the present application;

fig. 7 is a schematic view of a control device of a train according to an embodiment of the present application;

fig. 8 is a schematic view of a control device of a train according to an embodiment of the present application;

fig. 9 is a schematic flow chart of a control device of a train according to another embodiment of the present application;

fig. 10 is a schematic view of a control device of a train according to another embodiment of the present application;

fig. 11 is a schematic structural diagram of a control device of a train according to a further embodiment of the present application;

fig. 12 is a schematic structural diagram of a train control device according to still another embodiment of the present application.

Detailed Description

Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The embodiments will be described in detail below with reference to the accompanying drawings.

With the continuous improvement of the running speed and the automation degree of the urban rail transit train, the application range of a Full Automatic Operation (FAO) system is continuously expanded, and the usability of the FAO system, particularly the handling efficiency and the safety under faults and emergency conditions are particularly important in the Operation process. At present, in the FAO operation process, if a fault condition occurs, the general processing process is 'field sensing, information pushing, center confirmation, manual decision-making and field execution'.

For example, when a fire occurs in a vehicle, a dispatcher in a control center receives a vehicle fire alarm, calls a monitoring screen of a designated car, confirms the fire situation, and arranges car crew members and station staff members at a front platform for evacuation of people, emergency treatment of the fire, and the like. In the whole process, the staff need to collect information on all aspects of confirmation to make a final decision. When a plurality of abnormal scenes are compounded, more time is needed for manually collecting information and then making a decision, the handling efficiency of abnormal handling is seriously influenced, even the influence range of faults can be enlarged under certain conditions, and the problems of operation delay and the like are directly caused.

Therefore, in order to solve the above technical problems in the prior art, the present application provides a train autonomous decision and control method for coping with multiple composite scenes based on a knowledge graph: firstly, combing the composite multi-scene conditions which may occur when an urban rail transit FAO system operates, and then establishing the disposal principle and criterion relation when the composite multi-scene occurs; furthermore, a knowledge graph related to the composite multi-scene is constructed according to the composite multi-scene and the criterion relation of the composite multi-scene, and after the construction of the knowledge graph is completed, the decision can be independently made under the condition that the train faces various composite multi-scenes on the basis of the knowledge graph, and the train is controlled on the basis of the decision, so that the train does not need to be controlled manually, and the control efficiency of the train is improved.

Specifically, in order to solve the prior art problems, embodiments of the present application provide a method, an apparatus, a device, a storage medium, and a program product for controlling a train. First, a train control method provided in an embodiment of the present application will be described below.

Fig. 1 shows a flow chart of a train control method according to an embodiment of the present application. The method comprises the following steps:

s110, acquiring N scene types according to the current running state of the train, wherein N is a positive integer.

In this embodiment, the N scene types are the scene types of the currently running operation scene determined by the train based on the collected data, and the scene types may include a normal scene and an abnormal scene; the normal scene means that the train normally runs, and the abnormal scene means that a fault event occurs currently and needs to be analyzed and handled correspondingly. The normal scenes may include power-on, wake-up, warehouse-out, entering main line service, and the like in the morning, and the abnormal scenes may include vehicle fire, platform fire, obstacle derailment detection, rain and snow modes, and the like.

It should be noted that N is a positive integer, that is, the current scene type may be not only a single abnormal scene, but also a composite scene formed by a plurality of abnormal scenes, or a composite scene of at least one normal scene and at least one abnormal scene.

S120, extracting a knowledge graph subgraph from a knowledge graph based on the N scene types, wherein the knowledge graph subgraph comprises the N scene types and N treatment processes corresponding to the N scene types one by one.

In this embodiment, the train control can be performed using the knowledge map. The knowledge graph can be obtained in advance, and the obtaining mode can be construction obtaining or receiving obtaining. The entities in the knowledge graph comprise all scene types possibly encountered by train operation, and handling flows, handling steps, preconditions and handling evaluations corresponding to the scene types. The relationships in the knowledge-graph are the relationships between the entities.

After the current N scene types are acquired, entities and relationships related to the N scene types may be extracted from the knowledge graph, that is, N treatment flows corresponding to the N scene types and the N scene types one to one are extracted, where all preconditions and treatment steps included in the N treatment flows, treatment evaluations corresponding to the N treatment flows, and relationships among the entities form a knowledge graph subgraph together;

in an embodiment, fig. 2 is a knowledge graph sub-graph, where the scene type in the knowledge graph sub-graph is 2, and the scene type in the knowledge graph sub-graph is a rain and snow scene and a station fire scene, respectively, and therefore the knowledge graph sub-graph includes the rain and snow scene and the station fire scene, two handling processes corresponding to the two scenes one to one, and preconditions and handling steps associated with the two handling processes.

S130, determining a control flow of the train according to the N handling flows.

In this embodiment, because each of the current N scene types corresponds to one handling procedure, the train may sort the N handling procedures according to a predetermined handling rule, so as to obtain a control procedure of the train.

And S140, controlling the train based on the control flow.

In this embodiment, the train may perform autonomous control on the train according to the determined control flow. Therefore, compared with the prior art that the decision is made manually according to the acquired information when an abnormal scene occurs, the method and the device can be used for making the autonomous decision of the train based on the knowledge graph, so that the control efficiency of the train is improved.

As an alternative embodiment, referring to fig. 3, in order to make a decision for train control in a single scenario, the step S130 may include:

and S210, determining the disposal flow as the control flow of the train when the N is 1.

In this embodiment, when N is 1, if the current scene only includes a single scene type, the handling procedure corresponding to the scene type may be determined as a control procedure of the train, and the train is controlled according to the control procedure.

As an alternative embodiment, referring to fig. 4, in order to make a decision of train control in a composite scenario, the step S130 may further include:

s310, determining the execution sequence of the N handling flows according to the priority of the N scene types under the condition that the N is a positive integer larger than 1;

and S320, determining the N handling processes arranged according to the execution sequence as the control process of the train.

In this embodiment, when N is a positive integer greater than 1, it is necessary to determine an execution order of N handling procedures corresponding to the N scene types according to priorities of the N scene types, and then determine the N handling procedures arranged according to the execution order as a control procedure of the train.

Normally, the priority of an abnormal scene is higher than that of a normal scene. For example, N is 2, and the current 2 scene types are a jump stop scene and a rain and snow mode scene. The jump-stop scene is a scene type of a normal mode, and the rain-snow mode scene is a scene type of an abnormal mode. The control flow of the train is to execute the handling flow corresponding to the rain and snow mode scene first and then execute the handling flow corresponding to the jump-stop scene.

Specifically, in the process of train entering, the instructions of the rain and snow mode scene and the jump-stop scene sent by the dispatching center are received at the same time. At this time, the priority of the rain and snow mode scene is higher than that of the jump-stop scene, so that the train preferentially responds to the instruction of the rain and snow mode scene to execute the handling process corresponding to the rain and snow mode scene, and after the execution of the handling process corresponding to the rain and snow mode scene is finished, the handling process corresponding to the jump-stop scene is executed. Namely, the train is stopped according to the preset service brake and then enters a rain and snow mode, and the maximum traction and the maximum brake output are limited. Particularly, if the out-of-station parking condition is met, the train preferentially stops outside the station until the conversion of the rain and snow mode is completed, and then a disposal process corresponding to a jump-stop scene, namely a jump-stop command, is executed.

In addition, if the 2 currently compounded scenes are all abnormal scenes, the priority relationships of the 2 abnormal scenes need to be compared, and then the control flow of the train is determined.

For example, when the train is operated in the second section, the train simultaneously receives the instructions of the rain and snow mode scene and the station fire scene sent by the dispatching center, if the priority of the rain and snow mode scene is higher than that of the station fire scene, the handling process corresponding to the rain and snow mode scene is executed first, and then the processing process of the station fire scene is executed. The train is preferably stopped according to a preset service brake to enter a rain and snow mode, the maximum traction and the maximum brake output are limited, and the disposal process of the rain and snow mode scene is finished.

Then, a disposal process of the fire scene is executed, namely: and if the front outbound signal machine is opened and meets the jump stop condition and the platform fire emergency instruction is not cancelled, directly implementing jump stop after the movement authorization is extended. Otherwise, the ATO control train stops at a proper position outside the station or is executed according to the operation instruction of the train dispatcher (for example, returns to the previous station). Meanwhile, the train autonomously sends a broadcast to inform and pacify passengers.

As an alternative embodiment, referring to fig. 5, in order to determine the priority relationship of each scene type, before S130, the method may further include:

s410, obtaining loss degrees corresponding to various scene types;

and S420, setting the priority of each scene type according to each loss degree.

In this embodiment, the corresponding loss degree of the subsequent result is different for different scene types. In order to establish a criterion relationship of multi-scene handling, it is necessary to determine a loss degree corresponding to each scene type, and set a scene type with a higher loss degree as a higher priority.

In one embodiment, the determination of the extent of loss is based first on the safety of the passengers, the line equipment and the train, and then on the line demand and the associated emergency strategy. For example, normally, the loss of a normal scene type is zero or the loss degree is small, so the priority of the normal scene type is low, and the loss degree of an abnormal scene type is large, so the priority of the abnormal scene type is high.

As an alternative embodiment, the step S130 includes:

s510, when the N disposal flows only comprise disposal steps, determining a control flow of the train according to the disposal steps and the order relation between the disposal steps;

s520, under the condition that the N disposal processes comprise disposal steps and preconditions, detecting whether the current running state of the train meets the preconditions;

s530, determining a control flow of the train according to a first precondition satisfied by the current operation state, the disposing step and a sequence relation between the first precondition and the disposing step.

As an optional embodiment, before S110, the method may further include:

s610, constructing a mode layer of the knowledge graph, wherein the mode layer comprises entity nodes and relations among the entity nodes;

s620, receiving input information, wherein the input information comprises the running state of the train in the warehouse and in the normal running process, the handling principle for handling the running state, and the occurrence relationship between each running state and each handling principle;

s630, filling the mode layer of the knowledge graph according to the input information to generate the knowledge graph.

In this embodiment, in the process of constructing the knowledge graph for assisting the train autonomous decision, a bottom-up construction mode may be adopted, a top-down construction mode may be adopted, or a mixed construction mode of the two may be adopted.

In an embodiment, as shown in fig. 6, the knowledge graph is constructed in a top-down manner, and a mode layer of the knowledge graph is firstly constructed, so as to perform rule definition on an organization form of knowledge data, and then information extraction is completed to construct the knowledge graph based on input data. Namely, the top concept is defined, and is gradually refined downwards, and the extracted entity is corresponding to the predefined concept. Specifically, in the construction process of the mode layer, firstly, a composite multi-scene concept system is constructed, then, a composite multi-scene body is constructed, and finally, composite multi-scene attributes are constructed; in the construction process of the data layer, data acquisition is firstly carried out, then entities and relations (attributes) are determined, and finally, instances are added based on the entities and the relations.

As an alternative embodiment, the step S630 includes:

s710, detecting the operation state, the treatment principle and the occurrence relation in the input information;

s720, mapping the running state to the entity node of the mode layer to generate P scene types;

s730, mapping the treatment principle to an entity node of the mode layer, and generating P treatment flows corresponding to the P scene types one to one, and treatment steps and preconditions included in the P treatment flows;

s740, mapping the occurrence relationship to the relationship between the entity nodes in the mode layer, generating the first relationship among the P scene types, the P treatment flows, the processing steps, and the preconditions, and generating the knowledge graph.

Specifically, a schema layer of the knowledge graph is first constructed, and according to the requirements of the schema layer in the present embodiment, as shown in fig. 7, the nodes in the present embodiment include two types, namely an entity type and an attribute type. Entity types may include scenarios, treatment flows, preconditions, treatment steps, treatment evaluations, and the like; the attribute types can include scene description, scene category, flow description and the like; the black directed edge with the arrow is a relationship type between nodes, and may include following relationship, membership relationship, order relationship, and the like.

The concurrency relationship in the knowledge graph means that two scenes may occur simultaneously in a certain period of time, and two treatment steps of a treatment process may be executed simultaneously; the following relationship means that when a certain scene occurs, the corresponding treatment process is activated immediately; the membership relationship means that the precondition and the disposal step corresponding to the same scene are all affiliated to the disposal process corresponding to the scene; the order relationship means an execution order between the treatment steps included in the same treatment flow; mutual exclusion means that the processing steps of different processing flows may be mutually exclusive.

After the model layer of the completed knowledge graph is constructed, a data layer of the knowledge graph needs to be further constructed, namely the data layer is filled according to the input information which is manually carded. In an embodiment, the input information may be a plurality of scene types which may be compounded during operation of the FAO system obtained by combing the FAO system of the urban rail transit, and these scene types are not only bases for function settings of each equipment and each post in the full-automatic operation system and logic links linked between the systems, but also reflect the concept and requirements of operation with the scene and the operation rule as main lines.

As shown in fig. 8, in an embodiment, the FAO running fully automatically, there may be a composite scene divided into 41, which includes 18 normal scene types and 23 abnormal scene types, covering all the states of train operation in the warehouse and on the train line. The main operation scenes are as follows: the method comprises the following steps of power-on in the morning, awakening, delivery from a warehouse, entering main line service, operation of a paddling truck, automatic shunting, car washing, obstacle detection, fire, rain and snow modes, shielding door failure and the like.

In addition, each of the scene types includes a set of corresponding handling procedures for ensuring normal operation of the urban rail system. In turn, at least one treatment step, preconditions and treatment evaluations may be included in a treatment procedure.

In this embodiment, the input information includes the above-mentioned scene types, and the treatment flow, treatment step, precondition, and treatment evaluation corresponding to the scene types, and the first relationship therebetween. The scene type, the treatment flow, the treatment step, the preconditions and the treatment evaluations may be populated on the nodes of the respective knowledge-graph according to the input information, and further the relationships between these nodes may be populated according to the input information.

The filling process firstly aims at the entities in the input information, then under the guidance of the mode-level knowledge graph, the input information is subjected to entity identification to obtain corresponding entities, and the corresponding entities are linked to corresponding concept nodes, so that the related abstract concepts are instantiated. After entity extraction is completed, under the guidance of the mode-level knowledge graph, relationship and attribute detection is performed on input information, and the input information is mapped to a predefined relationship type, so that a first relationship between nodes is obtained.

In addition, after the relation and the nodes of the knowledge graph are filled, the knowledge graph can be further manually checked, so that the quality of the knowledge graph is improved, and the decision efficiency is improved.

As an alternative embodiment, referring to fig. 9, in order to facilitate the staff to make an auxiliary decision on the control flow of the train, after S130, the method may further include:

and S810, displaying the control flow through a visual interface.

In this embodiment, the train control flow obtained based on the knowledge graph is often expressed by machine language, may be in the form of formatted character strings, and is only used for controlling the machine to execute, but is not beneficial for the staff of the train to review. Therefore, in order to facilitate the real-time review and evaluation of the control flow of the train by the staff and the review or auxiliary decision of the control flow, the control flow needs to be converted into visual forms such as characters or pictures, audio and video and the like.

Furthermore, the display of the control flow can be displayed on a visual interface before the control flow is executed, so that the control flow can be conveniently adjusted by a worker in real time, and a decision of a train is assisted; and the control flow can be displayed on a visual interface after being executed, so that the staff can conveniently adjust the knowledge graph.

In an embodiment, as shown in fig. 10, firstly, the sorted knowledge is processed and collected to complete the construction of the knowledge graph, after the construction of the knowledge graph is completed, the current scene can be input into an execution module which is in bidirectional interaction with the knowledge graph, the execution module can perform treatment process retrieval by means of the knowledge graph, that is, the knowledge stored in the knowledge graph is used for retrieving and extracting the relevant treatment processes of the composite multi-scene to obtain a knowledge graph subgraph, the retrieval result is processed to obtain the control process of the train, and the result can be displayed and visualized for the control process of the autonomous decision of the train.

Based on the control method of the train provided by the embodiment, correspondingly, the application further provides a specific implementation mode of the control device of the train. Please see the examples below.

Referring first to fig. 11, a control device 700 of a train according to an embodiment of the present application includes the following modules:

an obtaining module 701, configured to obtain N scene types according to a current operation state of a train, where N is a positive integer;

an extracting module 702, configured to extract a knowledge-graph sub-graph from a knowledge-graph based on the N scene types, where the knowledge-graph sub-graph includes the N scene types and N treatment procedures corresponding to the N scene types one to one;

a determining module 703, configured to determine a control procedure of the train according to the N handling procedures;

and a control module 704, configured to control the train based on the control flow.

The device may extract a knowledge graph subgraph from a knowledge graph based on N scene types by obtaining N scene types, where N is a positive integer, where the knowledge graph subgraph includes the N scene types and N treatment processes corresponding to the N scene types one to one; determining a control flow of the train according to the N handling flows; and controlling the train based on the control flow. Therefore, compared with the prior art that when an abnormal scene occurs, the decision is needed to be made manually according to the acquired information, the method and the device can be used for making the autonomous decision of the train based on the knowledge graph, and therefore the control efficiency of the train is improved.

As an implementation manner of the present application, in order to make a decision for train control in a single scenario, the determining module 703 may further include:

a first determination unit configured to determine the handling flow as a control flow of the train if the N is 1.

As an implementation manner of the present application, in order to make a decision for train control in a composite scene, the determining module 703 may further include:

an order determination unit, configured to determine an execution order of the N treatment procedures according to priorities of the N scene types if N is a positive integer greater than 1;

a second determination unit configured to determine the N treatment flows arranged in the execution order as a control flow of the train.

As an implementation manner of the present application, in order to construct a knowledge graph for assisting autonomous decision-making of a train, the obtaining module 701 may further include:

a node determining unit, configured to determine, according to input information, P scene types, P treatment flows corresponding to the P scene types one to one, and processing steps included in the P treatment flows, where the P scene types include the N scene types, and P is an integer greater than or equal to N;

a relationship determination unit configured to generate, according to the input information, first relationships among the P scene types, the P treatment procedures, and processing steps included in the P treatment procedures;

a construction unit for constructing the knowledge-graph based on the P scene types, the P treatment procedures, the processing steps comprised by the P processing procedures and the first relation.

As an implementation manner of the present application, in order to determine a priority relationship between scene types, the determining module 703 may further include:

the acquisition unit is used for acquiring loss degrees corresponding to various scene types;

a setting unit configured to set a priority of each of the scene types according to each of the loss degrees.

As an implementation manner of the present application, in order to facilitate an assistant decision-making of a control flow of a train by a worker, the determining module 703 may further include:

and the display unit is used for displaying the control flow through a visual interface.

The train control device provided by the embodiment of the invention can realize the steps in the method embodiments of fig. 1 to 6, and is not described again to avoid repetition.

Fig. 12 shows a hardware structure schematic diagram of a control device of a train according to an embodiment of the present application.

The control equipment at the train may include a processor 1001 and a memory 1002 storing computer program instructions.

Specifically, the processor 1001 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.

Memory 1002 may include mass storage for data or instructions. By way of example, and not limitation, memory 1002 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, magnetic tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 1002 may include removable or non-removable (or fixed) media, where appropriate. The memory 1002 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 1002 is non-volatile solid-state memory.

The memory may include Read Only Memory (ROM), Random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the methods according to an aspect of the present disclosure.

The processor 1001 realizes the control method of any one of the trains in the above-described embodiments by reading and executing computer program instructions stored in the memory 1002.

In one example, the control devices of the train may also include a communication interface 1003 and a bus 1010. As shown in fig. 10, the processor 1001, the memory 1002, and the communication interface 1003 are connected to each other via a bus 1010 to complete communication therebetween.

The communication interface 1003 is mainly used for implementing communication between modules, apparatuses, units and/or devices in this embodiment.

The bus 1010 includes hardware, software, or both that couple the components of the control devices of the train to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 1010 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

The control device of the train can be based on the above embodiments, so as to implement the control method and apparatus of the train described in conjunction with fig. 1 to 9.

In addition, in combination with the train control method in the foregoing embodiment, the embodiment of the present application may be implemented by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; when executed by the processor, the computer program instructions implement any one of the above-described train control methods, and achieve the same technical effects, which are not described herein again to avoid repetition. The computer-readable storage medium may include a non-transitory computer-readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and is not limited herein.

In addition, the present application also provides a computer program product, which includes computer program instructions, and when the computer program instructions are executed by a processor, the steps and the corresponding contents of the foregoing method embodiments can be implemented.

It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.

The functional blocks shown in the above structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.

Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus and computer program products according to embodiments of the disclosure. 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 program instructions. These computer 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, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood 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 for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.

As will be apparent to those skilled in the art, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.

Claims (12)

1. A method of controlling a train, the method comprising:

acquiring N scene types according to the current running state of the train, wherein N is a positive integer;

extracting a knowledge-graph sub-graph from a knowledge-graph based on the N scene types, wherein the knowledge-graph sub-graph comprises the N scene types and N treatment processes in one-to-one correspondence with the N scene types;

determining a control flow of the train according to the N handling flows;

and controlling the train based on the control flow.

2. The method for controlling a train according to claim 1, wherein the determining the control flow of the train according to the N handling flows includes:

determining the handling flow as a control flow of the train if the N is 1.

3. The method of controlling a train according to claim 1, wherein the determining a control flow of the train according to the N handling flows includes:

determining an execution order of the N treatment flows according to priorities of the N scene types if the N is a positive integer greater than 1;

and determining the N handling processes arranged according to the execution sequence as the control process of the train.

4. The method of controlling a train according to claim 3, wherein prior to said determining a control flow of the train according to the N handling flows, the method further comprises:

obtaining loss degrees corresponding to various scene types;

setting the priority of each scene type according to each loss degree.

5. The method of controlling a train according to claim 1, wherein the determining a control flow of the train according to the N handling flows includes:

if the N handling flows only comprise handling steps, determining a control flow of the train according to the order relationship between the handling steps;

detecting whether the current running state of the train meets a precondition or not under the condition that the N handling processes comprise a handling step and the precondition;

and determining the control flow of the train according to a first precondition met by the current operation state, the handling step and the sequence relation between the first precondition and the handling step.

6. The method of controlling a train according to claim 1, wherein each of the disposal procedures includes at least one disposal step; before the obtaining N scene types, the method further includes:

constructing a schema layer of a knowledge graph, wherein the schema layer comprises entity nodes and relations among the entity nodes;

receiving input information, wherein the input information comprises operation states of the trains in the warehouse and in the normal operation, handling principles for handling the operation states, and occurrence relations between the operation states and the handling principles;

and filling a mode layer of the knowledge graph according to the input information to generate the knowledge graph.

7. The train control method according to claim 6, wherein the step of filling a mode layer of the knowledge graph according to the input information to generate the knowledge graph comprises:

detecting the operating state, the disposal principle and the occurrence relation in the input information;

mapping the running state to the entity node of the mode layer to generate P scene types;

mapping the treatment principle to an entity node of the mode layer, and generating P treatment flows corresponding to the P scene types one by one, and treatment steps and preconditions included in the P treatment flows;

mapping the occurrence relation to a relation between the entity nodes in the mode layer, generating a first relation among the P scene types, the P treatment processes, the processing steps and the preconditions, and generating the knowledge graph.

8. The method of controlling a train according to claim 1, wherein after determining the control flow of the train according to the N handling flows, the method further comprises:

and displaying the control flow through a visual interface.

9. A control device for a train, the device comprising:

the acquisition module is used for acquiring N scene types according to the current running state of the train, wherein N is a positive integer;

an extraction module, configured to extract a knowledge graph sub-graph from a knowledge graph based on the N scene types, where the knowledge graph sub-graph includes the N scene types and N treatment procedures in one-to-one correspondence with the N scene types;

a determining module for determining a control flow of the train according to the N handling flows;

and the control module is used for controlling the train based on the control flow.

10. A control apparatus of a train, characterized by comprising: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements a method of controlling a train as claimed in any one of claims 1 to 8.

11. A computer storage medium having computer program instructions stored thereon which, when executed by a processor, implement a method of controlling a train as claimed in any one of claims 1 to 8.

12. A computer program product, characterized in that it comprises computer program instructions which, when executed by a processor, implement the method of controlling a train according to any one of claims 1 to 8.

Images