KR102324201B1 - Apparatus and method for user experience based path computation - Google Patents

Abstract

In order for the route generating device to generate a route of a transmission network line, route information for a plurality of routes that have already been created is collected as learning data, and the learned route information is generated by learning route information for each section based on the collected learning data. do. When a route generation request signal for a certain section is received, a recommended route corresponding to the route generation request signal is designed based on the learned section route information, and the presence or absence of available resources for the designed recommended route is checked, and if there are available resources, the recommended route is provided as a candidate path.

Description

Apparatus and method for user experience based path computation}

The present invention relates to an apparatus and method for generating a transmission network circuit path based on user experience data using a deep learning algorithm.

Recently, a packet-based transmission device or an integrated device such as a Packet Transport Network (PTN) and a Packet-Optic Transport Network (POTN) device has been widely used. With the use of integrated devices, transmission networks having a complex configuration in which devices of multi-layer, multi-domain, and multi-vendor are mixed are increasing. Accordingly, network providers are introducing SDN (Software Defined Networking) controller technology for transmission networks that quickly design and automatically configure lines even between multi-vendor and multi-domain networks.

However, actually selecting a network path requires a lot of operator's know-how. And, in a complex transmission network, there are many paths from a start node to an end node according to the number of hops. Therefore, even a longer path is often selected as a path according to the user's preference, so there is a problem in that it is difficult to select a path by reflecting the user's preference with a simple path design algorithm.

In addition, in the prior art, since the path of the line is set using a rule-based path design algorithm, there is a disadvantage in that the user's satisfaction with the set path result is low.

Accordingly, the present invention provides an apparatus and method for generating a transmission network circuit path to which a deep learning technique is applied in order to apply user experience values to a path finding algorithm.

A method for generating a path of a transmission network line by a path generating device, which is a feature of the present invention for achieving the technical problem of the present invention,

Generating the learned section route information by collecting route information for a plurality of routes already created as learning data, learning route information for each section based on the collected learning data, and receiving a route creation request signal for a certain section then, designing a recommended route corresponding to the route generation request signal based on the learned section route information, checking whether there are available resources for the designed recommended route, and providing the recommended route as a candidate route if there are available resources including the steps of

The step of generating the learned section route information includes: extracting route attribute information from the learning data; identifying a plurality of routes for each section based on the extracted route property information; It may include extracting, and learning the section-by-section route information for each of the section-by-section routes to generate the learned section route information.

The learning data includes a plurality of pieces of information among a start node, an end node, a plurality of pieces of equipment information on a path, service information, and user preference information, and the learned section path information includes learning data and a section path corresponding to the learning data. may include

The step of designing the recommended route includes extracting parameters for route design for the predetermined section from the route generation request signal, and checking whether there are available resources for the learned section route information based on the extracted parameters. , and when there are available resources, determining the section route of the learned section route route as the recommended route for the predetermined section.

The step of providing the recommended route as a candidate route may include: checking a plurality of section routes forming the designed recommended route, and checking whether resources are available for each of the plurality of section routes; the plurality of section routes If there are no available resources in any of the section routes, checking whether there is other section route information learned in response to the arbitrary section route without available resources; If the resource exists, replacing the other section route with the arbitrary section route may include the step of including the route as a recommended route.

After determining the recommended route, the method may further include designing an alternative route for the parameter based on a preset route design rule, and providing the designed alternative route together with the recommended route as a candidate route. can

Another feature of the present invention for achieving the technical problem of the present invention is an apparatus for generating a circuit path,

A topology/resource management unit that calculates the resources each device uses to create a path and stores the available resource information of the device based on the device event received from a plurality of interworking devices, and a path for a plurality of already created paths Information is collected as learning data and learned to generate learned section route information, and when a route creation request signal for a certain section is received, a route is created based on the generated section route information and the available resource information stored by the topology/resource management unit and a path design unit for designing and providing a candidate path.

The path design unit extracts path attribute information from the learning data, identifies a plurality of partial paths constituting the already created path based on the extracted path attribute information, extracts path combinations, and learns and learns the extracted path combinations section route information can be created.

The route design unit is configured to determine the learned section route as a recommended route for the route generation request signal when available resources exist in the learned section route information and the learned section route in response to the parameter extracted from the route generation request signal. can

The path design unit, if there are no available resources in any section path among the learned section paths, another section in which available resources exist among other section paths learned in response to the arbitrary section path in which the available resources do not exist A route may be provided by being included in the candidate route.

The path design unit may design an alternative path to the parameter based on a preset path design rule, and the parameter may include a node's starting and ending points, bandwidth, and user request information for a path to be designed.

When the device receives a selection path selected based on the candidate path provided by the path design unit from the manager terminal, a control unit for generating a job list for at least one or more devices located in the selection path, and the job list generated by the path design unit The processor may further include a processing unit for generating a work command signal corresponding to , and transmitting the generated work command signal to at least one or more devices located in the selection path.

According to the present invention, rather than designing a line according to a uniform line design rule, it is possible to design a route with the operator's line design know-how for each user, each region, and each device.

In addition, since the route design results can be reflected in the next route design, the user's operational satisfaction can be increased.

1 is an exemplary diagram of an environment to which an apparatus for generating a path according to an embodiment of the present invention is applied.
2 is a structural diagram of an apparatus for generating a path according to an embodiment of the present invention.
3 is a flowchart of a method for generating a path according to an embodiment of the present invention.
4 is a flowchart of a method for learning a path generating apparatus according to an embodiment of the present invention.
5 is a flowchart of a method for designing a route based on user experience according to an embodiment of the present invention.
6 is an exemplary diagram of all extractable path combinations according to an embodiment of the present invention.
7 is an exemplary diagram of a screen providing a generated line path according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

Hereinafter, an apparatus and method for generating a circuit path of a transmission network based on learning path information generated based on user experience according to an embodiment of the present invention will be described with reference to the drawings. In the embodiment of the present invention, the transport network software-defined networking, that is, the Transport SDN server, is referred to as the path generating device 100, but is not necessarily limited thereto. Further, in the embodiment of the present invention, only the generation of a line path among various line control requests is described, but the present invention is not limited thereto. In addition, in the embodiment of the present invention, a route is also referred to as a “section” for convenience of description.

1 is an exemplary diagram of an environment to which an apparatus for generating a path according to an embodiment of the present invention is applied.

As shown in FIG. 1 , a transmission network according to an embodiment of the present invention is a multi-domain case, and will be described with an example of three domains. In the embodiment of the present invention, each domain is illustrated as an example of a Packet Transport Network (PTN), a Multi Service Provisioning Platform (MSPP), and an Optical Cross Connect (OXC), but the present invention is not necessarily limited thereto. It can be applied to all transport networks composed of In addition, a plurality of network devices are installed in each domain.

The path generating apparatus 100 that is a transport network software defined networking (Transport SDN) server interworks with the database 400 , the transport network equipment information collection server 200 , and the plurality of manager terminals 300 . The path generating apparatus 100 generates path information in which user experience is reflected according to a path generation request signal for requesting generation of a section between a start node and an end node transmitted from the manager terminal 300 .

To this end, when the path generating apparatus 100 receives learning information from the outside, it performs deep learning learning using the received learning information. Here, the learning information is route information for a plurality of network routes that have already been designed by reflecting user experience. etc.

When the path generating apparatus 100 creates a section between a node and a node, it also uses available resource information on at least one or more devices constituting the transmission network. This will be described in detail later.

In addition, when receiving various line control request signals transmitted from the manager terminal 300 , the path generating apparatus 100 processes a line control event corresponding to the line control request signal. Then, a work command signal corresponding to the processed line control event is generated. Here, the manager terminal 300 is a terminal possessed by a manager or an operator.

The transmission network device information collection server 200 interworks with a plurality of devices included in various domains and the path generating device 100 . The transmission network equipment information collection server 200 receives equipment events from equipment. The device event includes at least one or more of status information, device information, and failure information for each device.

Equipment events are periodically transmitted from a plurality of equipments, or received by requesting equipments to provide equipment events. The equipment event is not limited to any one, and the method for receiving the equipment event is also not limited to any one method.

When the transmission network equipment information collection server 200 receives the work command signal from the path generating device 100 , it transmits the work command signal to the devices so that a plurality of devices can be operated according to the received work command signal. In addition, when the transmission network equipment information collection server 200 receives a notification signal notifying that the work on the work command signal has been completed from a plurality of devices, it transmits the notification signal to the path generating device 100 to the database 400 to be stored in

The database 400 stores and manages line information for each user designed by the path generating device 100 , and equipment events for a plurality of devices collected by the transmission network equipment information collection server 200 . The line information for each user includes user identification information, line identification information, line path information, and the like.

In the above environment, the structure of the path generating apparatus 100 for generating a circuit path according to a predefined rule or based on learning path information reflecting user experience will be described with reference to FIG. 2 .

2 is a structural diagram of an apparatus for generating a path according to an embodiment of the present invention.

As shown in FIG. 2 , the path generating apparatus 100 includes a path design unit 110 , a control unit 120 , a processing unit 130 , and a topology/resource management unit 140 .

The path design unit 110 receives a path design request signal from the manager terminal 300 . The path design request signal includes as parameters the start and end points, bandwidth, and user request information of a node that an administrator or user wants to design for service provision. Here, the user request information includes options requested when designing a route, information on when a route should be constructed, information on sections to be excluded or added when designing a route, Shared Risk Link Group (SRLG), etc. The type of information is not necessarily limited in this way.

The path design unit 110 extracts parameters for path generation based on the path design request signal. And using the node start point, node end point, and user request information among the extracted parameters, it is checked whether the learned section path information exists. Here, between the node start point and the node end point, one or more intermediate nodes of equipment may be included. In addition, a plurality of partial paths may be included in one full path according to equipment selected to generate a path for each section among intermediate nodes.

If the section route information exists, the route design unit 110 checks whether there are available resources for the section route. That is, it is checked whether available resources necessary for designing a new route remain in the intermediate nodes that will generate the section route. If there are available resources for the entire section route, the section route is set as a recommended route (also referred to as a 'first route').

However, when it is impossible to design a path because some of the plurality of devices located on the entire section path do not have available resources, that is, when it is confirmed that there are no available resources in any device that will create a partial section, the part with no available resources Check if there is another section route information learned for the route. If there is another section route information for a partial route without available resources, after checking whether the route has available resources, it is set as a recommended route along with other section routes with available resources.

If there is no section path path learned in response to the parameter, the path design unit 110 designs an alternative path (or also referred to as a 'second path') based on the extracted parameters and path design rules. Also, the route design unit 110 designs an alternative route for a partial route without another learned section route information among partial routes without available resources.

The route design unit 110 provides the designed recommended route and the alternative route or alternative route as a candidate route to the manager terminal 300 . In order for the route design unit 110 to provide a recommended route to the manager terminal 300 , the route design unit 110 learns route information for each section based on learning data received from the outside.

Here, the learning data corresponds to path information for a plurality of already generated paths. The training data includes a start node and an end node of a path, a plurality of pieces of equipment information on the path, service information, and user preference information. Service information includes service speed, service provider, service area, service layer, service type, service domain, or service level (Class of Service, Priority) provided through the line, and user preference information is information on the section that must be passed or node port information, and the like, but is not necessarily limited thereto.

That is, when the path design unit 110 receives the learning data from the manager terminal 300 , it learns the received learning data using a deep learning algorithm, and learns a path having a high user preference for a plurality of paths for each section. And, when there is a route design request, a recommended route is designed based on the learned section route information.

To this end, the path design unit 110 extracts parameters from the learning data transmitted from the manager terminal 300 . And based on the extracted parameters, the routes are classified by section.

The route design unit 110 learns route information on the classified route for each section. The learning method of the deep learning algorithm used by the path design unit 110 to learn the path information, or the type of the deep learning algorithm, is not limited to any one method.

Here, in order to increase the accuracy of the learning path, the path design unit 110 needs to learn a large amount of data. Accordingly, it is also possible to learn a large amount of learning data during a specific time period when the path generating apparatus 100 is not used, or to learn a path so that when a new path is created, the data can be reflected in real time.

The route design unit 110 generates and stores the learned section route information by learning the learning data. Herein, the learned section route information is described as an example of being stored in the form of (learning data, section route), but is not necessarily limited thereto.

Also, the route design unit 110 may compare the recommended route and the alternative route based on the learned section route information to extract and provide a more specialized route to the user. The method for this may be performed in several ways, and the description is not limited to any one method in the embodiment of the present invention.

The control unit 120 receives information on a selected path selected by the manager from among the candidate paths provided by the path design unit 110 . When the control unit 120 receives the information on the selected path, based on the received information on the selected path, the control unit 120 creates a task list and temporarily stores the event.

In addition, the controller 120 receives various line control events transmitted from the manager terminal 300 , and creates and stores a task list according to the received line control event. In the embodiment of the present invention, a line control event is divided into a cancellation event, a change event, a recovery event, and the like, and a method for processing each event can be performed in various ways, so a detailed description will be omitted in the embodiment of the present invention. .

When the transmission network equipment information collection server 200 receives an equipment event including failure information or shape information transmitted from at least one equipment located in a plurality of domains, the processing unit 130 stores the received equipment events in the database 400 ) and store it. In addition, when a signal notifying that the equipment event has been received from the transmission network equipment information collection server 200 is transmitted, the processing unit 130 checks whether a work list for the equipment that has transmitted the equipment event is stored in the controller 120 .

If the work list is stored, a work command signal corresponding to the work list is generated. Then, the processing unit 130 transmits a work command signal to the transmission network equipment information collection server 200 to be processed by each equipment.

The topology/resource management unit 140 stores and manages topology information including logical line and physical line information of the transmission network for circuit design for the transmission network, and resource information of devices constituting each line. That is, the topology/resource management unit 140 manages topology information according to an event in which a plurality of devices interlocked with the path generating device 100 and links between the devices are created/changed/deleted.

In addition, the topology/resource management unit 140 receives an equipment event for each equipment from the transmission network equipment information collection server 200 , and calculates in real time available resource information of a path configured by the equipment based on the received equipment event. That is, it calculates and manages information on resources used by each device.

And the topology/resource management unit 140 manages the ratio of resources available in each device. This is because the resources used by the equipment in real time continuously change according to the configuration/change/cancellation of the line, the topology/resource management unit 140 calculates and manages the amount of resources based on the event information transmitted from each device. do.

Here, topology information and resource information are already known, and detailed descriptions thereof will be omitted in the embodiment of the present invention. Based on the topology information and resource information managed by the topology/resource management unit 140 , the path design unit 110 designs a path.

A method of generating a path through the path generating apparatus 100 described above will be described with reference to FIG. 3 .

3 is a flowchart of a method for generating a path according to an embodiment of the present invention.

As shown in FIG. 3 , the path generating apparatus 100 generates learned section path information by learning the learning data transmitted from the manager terminal 300 using a deep learning algorithm ( S100 ). The learned section path information is generated by pairing the input learning data and the section path confirmed by learning the learning data.

That is, the learned section path information in the form of (learning data, section path) is generated. Here, the training data includes a start node, an end node of a path, a plurality of pieces of equipment information on the path, service information, and user preference information. Service information includes service speed, service provider, service area, service layer, service type, service domain, or service level (Class of Service, Priority) provided through the line, and user preference information is information on the section that must be passed or node port information, and the like, but is not necessarily limited thereto.

And, when the manager terminal 300 receives the route creation request signal, the route generating apparatus 100 that has already learned the route based on various learning data creates a new route and provides it to the manager terminal 300 ( S200 ). When a new route is created, a recommended route generated based on the learned section route information is provided, and when there is no learned section route information, an alternative route generated through the existing route generation method is provided.

Here, a method for the path generating apparatus 100 to learn learning data using a deep learning algorithm according to step S100 will be described with reference to FIG. 4 .

4 is a flowchart of a method for learning a path generating apparatus according to an embodiment of the present invention.

As shown in FIG. 4 , the path generating apparatus 100 receives a plurality of path information including a pre-generated path or a newly created path from the manager terminal 300 as learning data ( S101 ). And in order to learn the received learning data using a deep learning algorithm, the path design unit 110 extracts path attribute information from the learning data (S102).

The path attribute information extracted by the path design unit 110 from the learning data includes path information according to a plurality of attributes. Here, the plurality of attributes may be classified by user, region, device, bandwidth, path, service, and the like, and the embodiment of the present invention is not limited to any one attribute information. In the embodiment of the present invention, it is described as an example that the learning data is transmitted from the manager terminal 300, but is not necessarily limited thereto.

The path design unit 110 checks whether partial paths exist between the start node and the end node based on the extracted path attribute information (S103). This will first be described with reference to FIG. 6 .

6 is an exemplary diagram of all extractable path combinations according to an embodiment of the present invention.

As shown in FIG. 6 , the start node of the path extracted by the path design unit 110 is “Garak” and the end node is “Geoje”, and the path from the Garak node to the Geoje node is “Garak-Guro-Busan-Geoje” It will be described with an example created by .

Then, the path of all combinations that the path design unit 110 can derive from the path is from the "Garak-Geoje" path, which is the longest path generated at once from the start node to the end node, to "Garak-Guro-Busan/Guro- Various routes are derived up to a two-hop route of "Busan-Geoje" or a one-hop route of "Garak-Guro/Guro-Busan/Busan-Geoje".

In this way, by deriving and learning a plurality of paths from a single path from a melodic node to a Geoje node, a lot of information can be learned at once, and accordingly, the accuracy of circuit design can be improved. In the embodiment of the present invention, the path generated from the start node to the end node is described with the same number of hops, for example, 1 hop if 1 hop or 2 hop if 2 hops as an example. The number of hops may be set differently.

Meanwhile, referring to FIG. 4, if the path design unit 110 extracts path attribute information in step S103 and confirms that a partial path exists, all combinations of paths that can be derived from the path are extracted (S104) . Then, deep learning for each of all the extracted combinations generates the learned section path information (S105). The path generating apparatus 100 may identify a user's preferred path between an arbitrary start node and an end node based on the learned section path information, and reflects the user's preferred path when creating a new path later. You may.

Next, a method for generating a new path by the path generating apparatus 100 according to step S200 of FIG. 3 will be described with reference to FIG. 5 .

5 is a flowchart of a method for designing a route based on user experience according to an embodiment of the present invention.

As shown in FIG. 5 , when the manager terminal 300 transmits a path design request signal to the path generating device 100 ( S201 ), the path generating device 100 receives the path design request signal from the path design request signal for path design. The parameters are extracted (S202).

The route generating apparatus 100 checks whether there is pre-learned section route information for the entire route based on the extracted parameters (S203). If there is no pre-learned section route information, the route generating apparatus 100 designs an alternative route, which is an alternative route, based on the extracted parameters and route design rules ( S206 ). Then, information on the designed alternative path is provided to the manager terminal 300 as a candidate path (S207).

On the other hand, as a result of checking in step S203, if there is section route information learned through the learning data in advance, it is checked whether there are available resources for the entire section route (S204). That is, based on the equipment event received by the topology/resource management unit 140 , the path design unit 110 has available resources that can provide a service through a new path to all equipment located from the start node to the end node of the path. make sure you do

If there are available resources in the entire learned section route checked in step S203, the route generating apparatus 100 determines the route as a recommended route (S205). At the same time, the path generating apparatus 100 designs an alternative path based on the parameters extracted in step S202 and the path design rule ( S206 ). In addition, the path generating apparatus 100 provides the recommended path determined in step S205 and the alternative path designed in step S206 to the manager terminal 300 as a candidate path (S207).

On the other hand, in step S204, if the path generating apparatus 100 determines that the learned section route information exists but that there are no available resources in some sections, the path generating device 100 checks a partial path in which there are no available resources (S208) . Then, it is checked whether other section route information learned for the checked partial route exists ( S203 ). If there is other section route information, a procedure of determining whether there are available resources for the corresponding route is performed, and steps after step S203 are repeatedly performed.

When the manager selects any one of the candidate paths generated and provided to the manager terminal 300 in this way, the path generating apparatus 100 generates a work command signal based on the selected path information, and devices located on the designed path Requests a line to be created by sending a work command signal to

An example of designing a circuit through the procedure of FIG. 5 will be described by taking the one-hop path of 'Garak-Guro-Busan-Geoje' described in FIG. 6 as an example. First, the path design unit 110 extracts the start node 'Garak' and the end node 'Geoje' included in the parameter.

It is assumed that a path consisting of one hop between the Garak node and the Geoje node is already created with section path information learned by deep learning learning. The path design unit 110 confirms that the topology/resource management unit 140 checks an equipment event for a plurality of devices located on the path of Garak-Guro-Busan-Geoje, and confirms whether an available resource exists in each device. And, if available resources exist in devices on the Garak-Guro-Busan-Geoje path, the path is set as a recommended path.

When the recommended route is set in this way, the route design unit 110 also designs an alternative route using the route design rule. In addition, a candidate path including the recommended path and the alternative path is provided to the manager terminal 300 .

On the other hand, if it is confirmed that the resources of any one partial section of the route of Garak-Guro-Busan-Geoje have already been used up and it is not possible to create a new route any more, other learned Check again whether there is section route information. For example, if the route forming 'Garak-Guro' has ample resources, but the 'Guro-Busan-Geoje' section has no resources, the route design unit 110 corresponds to the 'Guro-Busan-Geoje' section. It finds another route by checking if there is other learned section route information. If there is no route in the corresponding part, since the learned section route information cannot be found, the route design unit 110 generates a route for only the corresponding section using the route design rule, and as a candidate route for the entire section along with the recommended route. create

An example of a screen on which the manager terminal 300 displays a line path generated according to the method of designing a line path described above will be described with reference to FIG. 7 .

7 is an exemplary diagram of a screen providing a generated line path according to an embodiment of the present invention.

7A shows a path from a melodic node to a Geoje node, and a path from a melodic node to a planetary node.

There are two lines going from the Garak node to the Geoje node: a line passing through the P1 port and a line passing through the P2 port. At this time, it is assumed that the circuit design manager of the Garak node designed the path so that all lines connecting to the Busan area, such as Geoje, pass through the P1 port, and all lines connecting to the Daejeon area pass through the P2 port.

This may be a design rule designed by an administrator in consideration of operational convenience such as quick response to line failure. However, it may not be possible to give the circuit design result reflecting the requirements of the operator with the circuit design method according to the existing rules.

In this case, the path generating apparatus 100 may provide a circuit design result that meets the requirements of the node operator. That is, the circuit path from the melodic node to the geoje node must pass through the P1 port of the melodic node, and the result can be displayed.

The circuit path designed in this way is provided to the manager through the screen of the manager terminal 300 as shown in FIG. 7B. For example, when the manager selects the upper station, that is, the start node as the melodic node and the end node as the Busan node using the manager terminal 300 , and presses the “find path” button, the screen shown in (b) is displayed. As shown, a route automatically designed based on the learned section route information generated according to the learning result of the deep learning algorithm is provided as a recommended route.

The user has already requested that the melodic node must pass through the P1 port, and the user's preference has been identified through learning. Therefore, the path generating apparatus 100 designs a path by using the S2P1 port of the melodic node without going through the P2 port of the melodic node.

At the same time, the result of the circuit path generated using the existing rule-based circuit design algorithm is displayed as an alternative path. It can be seen that this information is designed using the S2 P2 port in accordance with the existing rules.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improved forms of the present invention are also provided by those skilled in the art using the basic concept of the present invention as defined in the following claims. is within the scope of the right.

Claims (13)

A method for generating a path for a transmission network line by a path generating device, the method comprising:
Collecting path information for a plurality of paths that have already been created as learning data, and extracting path attribute information of a previously generated path according to a plurality of attributes from the collected learning data;
extracting a plurality of route combinations for a plurality of sections between a start node and an end node of each of the plurality of routes;
learning a path design unit to output a path according to the attribute between the start node and the end node using the plurality of path combinations, and
providing a candidate route corresponding to the new route creation request signal in the learned route design unit when a new route generation request signal for a predetermined section is received
How to create a path that includes . According to claim 1,
The step of extracting the plurality of path combinations,
Checking whether a partial path exists for the plurality of sections between the start node and the end node based on the extracted path attribute information, and
If the partial path exists, extracting the partial path as a path combination for each section between the start node and the end node.
How to create a path that includes . 3. The method of claim 2,
The learning data includes a plurality of pieces of information among the start node, the end node, a plurality of pieces of equipment information on a path connecting the start node to the end node, service information, and user preference information. According to claim 1,
The step of providing the candidate path comprises:
extracting parameters for route design for the predetermined section from the new route creation request signal;
Checking whether there are available resources for the section path of the predetermined section generated based on the extracted parameters, and
If there are available resources, determining the candidate route as a recommended route for the predetermined section
How to create a path that includes . 5. The method of claim 4,
The parameter is
A path creation method, which is attribute information including start and end points, bandwidth, and user request information of a path to be designed. 6. The method of claim 5,
The step of providing the recommended route is,
If there is no available resource to be used in the candidate route, checking whether there is information on other section routes learned for the predetermined section, and
providing the other section route as a recommended route for an arbitrary section when there is information on the learned other section route and resources available in the other section route
How to create a path that includes . 6. The method of claim 5,
After the step of providing the recommended route,
designing an alternative route for the parameter based on a preset route design rule; and
providing the designed alternative route as a candidate route together with the recommended route
How to create a path that further includes. A device for generating a circuit path, comprising:
A topology/resource management unit that calculates resources used by each device to create a path based on device events received from a plurality of interworking devices, and stores available resource information of each device, and
Path information for a plurality of paths that have already been created is collected as learning data, and based on the learning data, a path is learned to be output between the start node and the end node of each path, and a new path creation request signal for a certain section is provided. Upon reception, the route design unit provides a candidate route by designing a route based on the section route output for the predetermined section and the available resource information for the section route stored by the topology/resource management unit
A path generating device comprising a. 9. The method of claim 8,
The path design unit,
Extracting path attribute information from the learning data, identifying a plurality of partial paths constituting the already created path based on the extracted path attribute information to extract a path combination, and learning the extracted path combination to generate a learned section path path generating device. 10. The method of claim 9,
The path design unit,
If there are available resources in the learned section path information and the learned section route in response to the parameter extracted from the new route creation request signal, the path generating apparatus determines the learned section as a recommended route for the new route creation request signal. 11. The method of claim 10,
The path design unit,
If there are no available resources in any section path among the learned section paths, another section path in which available resources exist among other section paths learned in response to a section path in which no available resources exist is selected as the candidate path Included in the provided route generating device. 12. The method of claim 11,
The path design unit,
design an alternative route for the parameters based on a preset route design rule,
The parameter is a path generating device including starting and ending points, bandwidth, and user request information of a node for a path to be designed. 9. The method of claim 8,
When receiving a selection path selected based on the candidate path provided by the path design unit from the manager terminal, a control unit for generating a work list for at least one or more equipment located in the selection path, and
A processing unit that generates a work command signal corresponding to the work list generated by the path design unit and transmits it to at least one or more devices located in the selected path
A path generating device further comprising a.

Images