WO2019164503A1

WO2019164503A1 - Ranking of engineering templates via machine learning

Info

Publication number: WO2019164503A1
Application number: PCT/US2018/019389
Authority: WO
Inventors: Yufeng Li; Rizwan MAJEED; Gustavo Quiros Araya; Richard Gary Mcdaniel; Kaan BARDAK; Oswin Noetzelmann
Original assignee: Siemens Aktiengesellschaft
Priority date: 2018-02-23
Filing date: 2018-02-23
Publication date: 2019-08-29

Abstract

A system for ranking templates used to engineer control application programs of a project assisted by machine learning includes a data extraction tool configured to extract a plurality of textual descriptions corresponding to a plurality of projects and associated engineering templates. A pre-processing data tool maps the plurality of textual descriptions to high-dimensional vectors. A machine learning engine clusters the vectors into clusters, with each cluster being associated with a respective engineering template. A query is mapped to a high-dimensional query vector using a same mapping process as for the plurality of textual descriptions, with the query including a textual description for a current project. A ranking tool produces a ranking of the engineering templates based on analogy of the query vector to clustering information from the machine learning engine.

Description

RANKING OF ENGINEERING TEMPLATES VIA MACHINE LEARNING

TECHNICAL FIELD

[0001] This application relates to automation and control. More particularly, this application relates to machine learning assisted engineering of control application programs.

BACKGROUND

[0002] Automation systems can be applied to production processes having a multitude of devices requiring automated control. Controllers can be programmed during an engineering phase with the assistance of graphical computer-based tools. For example, an engineer can open a new project in a software application, such as a Siemens Totally Integrated Automation (TIA) Portal, to develop the control program for one or more programmable logic controllers (PLC) in an automation system. This engineering system offers capabilities to design and build control systems elements, along with the control programs, in several programming languages such as Ladder (LAD), Statement List (STL), Structured Control Language (SCL), Function Block Diagram (FBD), S7-GRAPH, including control variable definition. When embarking on a new project, the engineer can benefit from having a template library to reuse past experience and knowledge and apply to new problems and projects. The engineer can search for templates or libraries by name, for instance via string matching in a database or searching for filenames in a directory structure. However, as the number of templates in the library grows, navigation and obtaining the best fit solution becomes difficult and cumbersome, particularly when many templates offer similar solutions.

BRIEF DESCRIPTION OF THE DRAWINGS

[0003] The foregoing and other aspects of the present invention are best understood from the following detailed description when read in connection with the accompanying drawings. For the purpose of illustrating the invention, there is shown in the drawings embodiments that are presently preferred, it being understood, however, that the invention is not limited to the specific instrumentalities disclosed. Included in the drawings are the following Figures:

FIG. 1 shows an example of a system of computer based tools according to embodiments of this disclosure;

FIG. 2 illustrates a conversion of high level textual descriptions associated with an engineering template into high dimensional vectors;

FIG. 3A shows a diagram of clustered vectors of training examples in accordance with embodiments of the disclosure;

FIG. 3B illustrates an example of the distance-based template ranking in accordance with embodiments of the disclosure;

FIG. 4 shows a data flow diagram for the process of ranking templates used for an engineering project with machine based intelligence assistance in accordance with embodiments of the disclosure; and

FIG. 5 illustrates an example of a computing environment within which embodiments of the present disclosure may be implemented.

DETAILED DESCRIPTION

[0004] A method and system is disclosed in which a specialized computer applies machine learning algorithms to improve an automation of tasks related to generating a control application program. During engineering mode of an automation control system, a computer based engineering system may assist a user with the task of setting control parameters while building the code for the control application program. The disclosed method and system presents an improvement to the functionality of the computer used to perform such a computer based task.

[0005] FIG. 1 shows an example of a system of computer based tools according to embodiments of this disclosure. In an embodiment, a user seeks a best fit template for engineering a control application program used by a controller in an automation system within the context of a design project. There may be hundreds of templates from which to choose without any direct approach for quickly or easily focusing the search. In order to reduce manual efforts and costs during engineering mode for such an automation system, system 100 may provide the user with a ranking of suitable engineering templates based on a descriptive language query. System 100 includes a data extraction tool 1 10, a data pre-processing tool 120, a machine learning engine 130, and a ranking tool 140. Before the system 100 is capable of ranking templates, a period of initial training is activated for the machine learning engine 130. During the initial training mode, the data extraction tool 1 10 may extract descriptive information from project data 104 stored in project files. For example, data files accumulated from previous projects may be stored in libraries, including project files, template files, and template usage files. As an example, the data extraction tool 1 10 may extract metadata found within the project data 104 associated with templates used for respective projects.

[0006] From the project data 104, the data extraction tool 1 10 may extract and compile descriptive information that may include one or more of the following information types: problem, input, output, requirements, cost and other parameters. In an embodiment to design a control application program for implementation by a programmable logic controller (PLC), the knowledge about the control system manipulated during the design and engineering phase maintained in a project, and hence description information for extraction, may include one or more of the following: connectivity between devices; sensors and actuators, inputs and outputs for devices and device connectivity; functions, function blocks, organization blocks, programs, processes, and logical relationships amongst them; control variable names and address assignment of variables to specific programs and processes on one side and devices on the other side; data types and variable types (e.g., global, direct, I/O, external, temporary, time etc.); and explanation and justification of control logic, control loops, control structure in the control program in form of comments and notes; and auxiliary code used for testing, observing, tracing, and debugging a by a portal.

[0007] The descriptive information may be labeling in the form of natural language, such as plain English, with a high level textual description. In an embodiment, the data extraction tool 1 10 may extract information relating to the template used for a particular project and may compile all such template association information. In an embodiment, project templates may be stored as individual data files in the project data 104 from which the data extraction tool 1 10 may extract description information. The data extraction tool 1 10 may generate high level descriptions from the extracted information, which may be in a format as follows:

{

"project":

{

"title": "Assembly Line for customer xyz",

"domain": "Factory Automation",

"station count": "2",

"Stations": [

{

"name": "tier 1 assembly",

"description" : "assembling end-products; montage of main parts;",

"requirements" : "adjustable feed; safety",

"devices" : [

{

"name" : "conveyor feed motor",

"type" : "AC induction"

},

{

"name" : "conveyor safety switch",

"type" : "inductive"

}

Extracted data may be persisted in natural language form, such as plain English, high level descriptions, so that template matching can leverage the natural language processing techniques. The high level descriptions may be accumulated for the corresponding projects and stored in a database 1 15 in a form notation that supports queries and provides data consistency.

[0008] In an embodiment, the data extraction tool 110 may receive input from a user using a graphical user interface (GUI) 102, whereby the input may be high level descriptions of templates and projects, enhancements of previously extracted high level descriptions, assistance with associating descriptions to templates and/or projects, or a combination thereof.

[0009] The data pre-processing tool 120 may convert the high level descriptions and template association information into a high-dimensional mapping usable by the machine learning engine 130. The high-dimensional mapping may be derived using an algorithm that converts text in the description to a vector in the space of an entire vocabulary of a particular language used by the textual descriptions, such as the English vocabulary for example, in which case the dimension of the vector is proportional to the number of words in the English language. Alternatively, the high- dimensional mapping may employ a mapping algorithm that may use other high- dimensional mapping metrics, such as the size of the code in the engineering template, the kinds of networks defined in the code, the number and type of input/output (I/O) connections, kinds of object blocks such as main block or error handling, or other such metrics.

[0010] FIG. 2 illustrates a conversion of high level textual descriptions associated with an engineering template into high dimensional vectors. For each engineering template 212, there may be one or more high-level descriptions 213A/213B/213C extracted due to each template being used more than once for multiple previous projects. Each high level description 213A/213B/213C may relate to different contexts, different algorithms, different sources, multiple past searches, and/or different markets for previous projects. A description 213A/213B/213C may be any kind of identifying data that could be used to associate the template to a project. Potential examples include textual descriptions from documentation, comments or codes from the engineering template itself, and prior searches where the user selected this template as the best match. The descriptions 213A/213B/213C for each template may be converted to respective vectors 223A/223B/223C in a high-dimensional space 225 and serve as examples for the training data. High dimensional space 225 is shown in FIG. 2 as a two- dimensional space for illustrative purpose only.

[0011] Returning to FIG. 1 , during the initial training phase, the machine learning engine 130 may obtain the high level description vectors and may perform a supervised, semi-supervised or reinforced learning process to associate the high level descriptions to corresponding templates as used in previous projects. In an embodiment, the machine learning engine 130 may implement a clustering algorithm for generating a clustering of the high level descriptions and associated templates. Examples of clustering algorithms that may be applied include a learning to rank algorithm or a k- means clustering algorithm, or any such algorithms capable of performing subspace clustering or correlation clustering of high-dimensional data, such as CLIQUE or SUBCLU. The machine learning engine 130 may maintain a clustering of the descriptions, distance between clusters, distance between description points, as well as mapping information from description point to cluster, and description to templates. In an alternative embodiment, the machine learning engine may be configured to execute a Gaussian-based neural network in which clusters of vectors are formed based on gauging probabilities of correctness that each vector belongs to a cluster associated with a particular template.

[0012] FIG. 3A shows a diagram of clustered vectors of training examples in accordance with embodiments of the disclosure. The machine learning engine 130 may maintain a clustering of the vectorized description information. As shown, by way of example, a cluster T1 corresponding to a first template may include vectors 31 1 , 312, 313, a cluster T2 corresponding to a second template may include vectors 321 , 322, 323, and a cluster T3 corresponding to a third template may include vector 331. Each cluster may be formed in a common high-dimensional space 310 having vectors of high level descriptions that have similar meaning. The distance between two description vectors may be used to define their similarity. As an example, a distance function D may be defined for each pair of description vectors, and prioritized as follows:

D(car-truck) < D(car-bike) < D(car-screw driver)

where car, truck, bike and screw driver represent description vectors, and D() represents the distance between vectors. The terms belonging to the same cluster T1/T2/T3 may have distances D between one another that do not exceed a predetermined threshold.

[0013] Returning to FIG. 1 , during the engineering mode of the control program, a user may use a GUI 152 to enter a query for a template to begin a new project. The query may be a string of words or it may also contain constraints or snippets of code that convey the gist of the kind of template the user wants. The query may be formed in response to a questionnaire to suggest search terms that best correspond to the high level description information stored in description database 1 15. The ranking tool 140 may interpret the query information and perform a ranking of templates based on an analogy between the query information to each respective template cluster as defined by the clustering performed by the machine learning engine 130. For example, the ranking tool 140 may translate the query information using the same high-dimensional mapping used by the pre-processing data tool 120 as previously described. The ranking tool 140 may retrieve the clustering information from the trained machine learning engine 130. Then the ranking tool 140 may determine a distance analogy between the mapped vector for the query and the template clusters to generate a ranking of templates with priority according to shortest distance to each cluster.

[0014] FIG. 3B illustrates an example of the distance-based template ranking in accordance with embodiments of the disclosure. To determine ranking of templates for a new query, the machine learning engine 130 may treat the query words as high level description for training input and convert the description to a high-dimensional vector 340 in the same high-dimensional space 310 as clusters T1/T2/T3 using the same method as used in the initial training described above. The ranking tool 140 may receive the mapping information from the machine learning tool 130 and calculate the distances d1/d2/d3 from the vector 340 to each of the respective template clusters T1/T2/T3. By sorting the distances d1/d2/d3, the ranking tool 140 may determine which templates will satisfy the user’s query based on the template cluster having the shortest distance. Various methods are available to determine distances d1/d2/d3 including, but not limited to, center-to-center distance, shortest edge-to-edge distance, and mean distance.

[0015] In an embodiment, the ranking tool 140 may base the ranking using another form of analogy to the clustering. For an example in which the clustering may be based on probabilities of correctness according to a probabilistic neural network, the ranking may be based on the probabilities. It follows then that according to other variations of embodiments, the ranking tool 140 may apply a metric-based ranking process compatible with a metric used for the clustering by the machine learning engine 130.

[0016] In response to the query for a template, the ranking tool 140 may present a user at GUI 152 with a set of ranked templates as best fits for the present project. For example, user may view on a display screen of an engineering station a list of templates sorted according to the ranking, from which user may select. Alternatively, a top ranked template may be presented as a first page, and user may scroll a series of templates by paging down the display. When the template is selected for the current project, the selection may be stored as a project-template association or a template usage in the project data 154. The machine learning engine 130 may receive from the project data 154 the association for this template usage in the present project as feedback data to retrain the clustering by the machine learning engine 130. For example, the machine learning engine may receive information related to at least one of the association, the query or the template selection, and may treat the information as an additional training sample for updating the clustering for the template that was selected. Any subsequent projects with template selections allow the machine learning engine 130 to refine the clustering for the given template with additional retraining via the feedback. While project data 154 is shown as separate from project data 104 in FIG. 1 , there may be a common storage of project data.

[0017] FIG. 4 shows a data flow diagram for the process of ranking templates used for an engineering project with machine based intelligence assistance in accordance with embodiments of the disclosure. During initial training, the machine learning engine 130 may receive training information 226 based on the high level descriptions 213. Training information 228 from the templates 212 may become available from extraction of textual labels and comments found in the template data files. The high level descriptions 213 may be extracted from the project data 21 1 and/or may be user generated. Past usage 224 of templates 212 for particular projects 21 1 may also provide training information 228 for the machine learning engine 130.

[0018] In addition to the high-level description 213 of projects, an association 222 of the templates 212 used by the corresponding project may be used to train 226/228 the machine learning component 230. Some associations 222 may be determined from data pre-processing to align high level descriptions extracted from a respective project 21 1 with the template actually used for that project 21 1. Some associations 222 may also be determined during the clustering operation of the machine learning engine 130. During an engineering mode of operation, the ranking tool 140 may produce 253 a ranking of templates 245 based on user query 243 when an engineer seeks a template 242 for a new engineering project 241. [0019] The selected engineering template usage data 254 for the new engineering project 241 may be provided to the machine learning engine 130 as a secondary training input 258. This secondary training includes an association 252 of the user high level description of user query 243 as training input 256 with the engineering template selection 242 as training input 258. Thus, the system is dynamically updated by a machine learning process that continues after the initial training of the machine learning engine 130. The ranking of templates 245 suggested by the ranking tool 140 become increasingly accurate as the machine learning component 130 gains more experience through ongoing feedback with respect to associations 252 of the selected engineering template 242 and the high level description of user query 243 to form updated clustering.

[0020] FIG. 5 illustrates an example of a computing environment within which embodiments of the present disclosure may be implemented. A computing environment 500 includes a computer system 510 that may include a communication mechanism such as a system bus 521 or other communication mechanism for communicating information within the computer system 510. The computer system 510 further includes one or more processors 520 coupled with the system bus 521 for processing the information.

[0021] The processors 520 may include one or more central processing units (CPUs), graphical processing units (GPUs), or any other processor known in the art. More generally, a processor as described herein is a device for executing machine- readable instructions stored on a computer readable medium, for performing tasks and may comprise any one or combination of, hardware and firmware. A processor may also comprise memory storing machine-readable instructions executable for performing tasks. A processor acts upon information by manipulating, analyzing, modifying, converting or transmitting information for use by an executable procedure or an information device, and/or by routing the information to an output device. A processor may use or comprise the capabilities of a computer, controller or microprocessor, for example, and be conditioned using executable instructions to perform special purpose functions not performed by a general purpose computer. A processor may include any type of suitable processing unit including, but not limited to, a central processing unit, a microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, a Complex Instruction Set Computer (CISC) microprocessor, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a System-on-a-Chip (SoC), a digital signal processor (DSP), and so forth. Further, the processor(s) 520 may have any suitable microarchitecture design that includes any number of constituent components such as, for example, registers, multiplexers, arithmetic logic units, cache controllers for controlling read/write operations to cache memory, branch predictors, or the like. The microarchitecture design of the processor may be capable of supporting any of a variety of instruction sets. A processor may be coupled (electrically and/or as comprising executable components) with any other processor enabling interaction and/or communication there-between. A user interface processor or generator is a known element comprising electronic circuitry or software or a combination of both for generating display images or portions thereof. A user interface comprises one or more display images enabling user interaction with a processor or other device.

[0022] The system bus 521 may include at least one of a system bus, a memory bus, an address bus, or a message bus, and may permit exchange of information (e.g., data (including computer-executable code), signaling, etc.) between various components of the computer system 510. The system bus 521 may include, without limitation, a memory bus or a memory controller, a peripheral bus, an accelerated graphics port, and so forth. The system bus 521 may be associated with any suitable bus architecture including, without limitation, an Industry Standard Architecture (ISA), a Micro Channel Architecture (MCA), an Enhanced ISA (EISA), a Video Electronics Standards Association (VESA) architecture, an Accelerated Graphics Port (AGP) architecture, a Peripheral Component Interconnects (PCI) architecture, a PCI-Express architecture, a Personal Computer Memory Card International Association (PCMCIA) architecture, a Universal Serial Bus (USB) architecture, and so forth.

[0023] Continuing with reference to FIG. 5, the computer system 510 may also include a system memory 530 coupled to the system bus 521 for storing information and instructions to be executed by processors 520. The system memory 530 may include computer readable storage media in the form of volatile and/or nonvolatile memory, such as read only memory (ROM) 531 and/or random access memory (RAM) 532. The RAM 532 may include other dynamic storage device(s) (e.g., dynamic RAM, static RAM, and synchronous DRAM). The ROM 531 may include other static storage device(s) (e.g., programmable ROM, erasable PROM, and electrically erasable PROM). In addition, the system memory 530 may be used for storing temporary variables or other intermediate information during the execution of instructions by the processors 520. A basic input/output system 533 (BIOS) containing the basic routines that help to transfer information between elements within computer system 510, such as during start-up, may be stored in the ROM 531. RAM 532 may contain data and/or program modules that are immediately accessible to and/or presently being operated on by the processors 520. System memory 530 may additionally include, for example, operating system 534, application programs 535, and other program modules 536. For example, the application programs 535 may include data extraction tool 1 10, pre-processing data tool 120, machine learning engine 130, and ranking tool 140 as shown in FIG. 1 and described herein.

[0024] The operating system 534 may be loaded into the memory 530 and may provide an interface between other application software executing on the computer system 510 and hardware resources of the computer system 510. More specifically, the operating system 534 may include a set of computer-executable instructions for managing hardware resources of the computer system 510 and for providing common services to other application programs (e.g., managing memory allocation among various application programs). In certain example embodiments, the operating system 534 may control execution of one or more of the program modules depicted as being stored in the data storage 540. The operating system 534 may include any operating system now known or which may be developed in the future including, but not limited to, any server operating system, any mainframe operating system, or any other proprietary or non-proprietary operating system.

[0025] The computer system 510 may also include a disk/media controller 543 coupled to the system bus 521 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 541 and/or a removable media drive 542 (e.g., floppy disk drive, compact disc drive, tape drive, flash drive, and/or solid state drive). Storage devices 540 may be added to the computer system 510 using an appropriate device interface (e.g., a small computer system interface (SCSI), integrated device electronics (IDE), Universal Serial Bus (USB), or FireWire). Storage devices 541 , 542 may be external to the computer system 510.

[0026] The computer system 510 may also include a field device interface 565 coupled to the system bus 521 to control a field device 566, such as a device used in a production line. The computer system 510 may include a user input interface or HMI 561 , which may comprise one or more input devices, such as a keyboard, touchscreen, tablet and/or a pointing device, for interacting with a computer user and providing information to the processors 520.

[0027] The computer system 510 may perform a portion or all of the processing steps of embodiments of the invention in response to the processors 520 executing one or more sequences of one or more instructions contained in a memory, such as the system memory 530. Such instructions may be read into the system memory 530 from another computer readable medium, such as the magnetic hard disk 541 or the removable media drive 542. The magnetic hard disk 541 may contain one or more data stores and data files used by embodiments of the present invention. The data store may include, but are not limited to, databases (e.g., relational, object-oriented, etc.), file systems, flat files, distributed data stores in which data is stored on more than one node of a computer network, peer-to-peer network data stores, or the like. The data stores may store various types of data such as, for example, project data 104, 154, extracted descriptions, high level descriptions, mapping information, cluster information, template associations or any other data generated during initial training and engineering mode in accordance with the embodiments of the disclosure. Data store contents and data files may be encrypted to improve security. The processors 520 may also be employed in a multi-processing arrangement to execute the one or more sequences of instructions contained in system memory 530. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions. Thus, embodiments are not limited to any specific combination of hardware circuitry and software.

[0028] As stated above, the computer system 510 may include at least one computer readable medium or memory for holding instructions programmed according to embodiments of the invention and for containing data structures, tables, records, or other data described herein. The term“computer readable medium” as used herein refers to any medium that participates in providing instructions to the processors 520 for execution. A computer readable medium may take many forms including, but not limited to, non-transitory, non-volatile media, volatile media, and transmission media. Non-limiting examples of non-volatile media include optical disks, solid state drives, magnetic disks, and magneto-optical disks, such as magnetic hard disk 541 or removable media drive 542. Non-limiting examples of volatile media include dynamic memory, such as system memory 530. Non-limiting examples of transmission media include coaxial cables, copper wire, and fiber optics, including the wires that make up the system bus 521. Transmission media may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0029] Computer readable medium instructions for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure. [0030] Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the 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, may be implemented by computer readable medium instructions.

[0031] The computing environment 500 may further include the computer system 510 operating in a networked environment using logical connections to one or more remote computers, such as remote computing device 580. The network interface 570 may enable communication, for example, with other remote devices 580 or systems and/or the storage devices 541 , 542 via the network 571. Remote computing device 580 may be a personal computer (laptop or desktop), a mobile device, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to computer system 510. When used in a networking environment, computer system 510 may include modem 572 for establishing communications over a network 571 , such as the Internet. Modem 572 may be connected to system bus 521 via user network interface 570, or via another appropriate mechanism.

[0032] Network 571 may be any network or system generally known in the art, including the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between computer system 510 and other computers (e.g., remote computing device 580). The network 571 may be wired, wireless or a combination thereof. Wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-6, or any other wired connection generally known in the art. Wireless connections may be implemented using Wi-Fi, WiMAX, and Bluetooth, infrared, cellular networks, satellite or any other wireless connection methodology generally known in the art. Additionally, several networks may work alone or in communication with each other to facilitate communication in the network 571. [0033] It should be appreciated that the program modules, applications, computer- executable instructions, code, or the like depicted in FIG. 5 as being stored in the system memory 530 are merely illustrative and not exhaustive and that processing described as being supported by any particular module may alternatively be distributed across multiple modules or performed by a different module. In addition, various program module(s), script(s), plug-in(s), Application Programming Interface(s) (API(s)), or any other suitable computer-executable code hosted locally on the computer system 510, the remote device 580, and/or hosted on other computing device(s) accessible via one or more of the network(s) 571 , may be provided to support functionality provided by the program modules, applications, or computer-executable code depicted in FIG. 5 and/or additional or alternate functionality. Further, functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted in FIG. 5 may be performed by a fewer or greater number of modules, or functionality described as being supported by any particular module may be supported, at least in part, by another module. In addition, program modules that support the functionality described herein may form part of one or more applications executable across any number of systems or devices in accordance with any suitable computing model such as, for example, a client-server model, a peer- to-peer model, and so forth. In addition, any of the functionality described as being supported by any of the program modules depicted in FIG. 5 may be implemented, at least partially, in hardware and/or firmware across any number of devices.

[0034] It should further be appreciated that the computer system 510 may include alternate and/or additional hardware, software, or firmware components beyond those described or depicted without departing from the scope of the disclosure. More particularly, it should be appreciated that software, firmware, or hardware components depicted as forming part of the computer system 510 are merely illustrative and that some components may not be present or additional components may be provided in various embodiments. While various illustrative program modules have been depicted and described as software modules stored in system memory 530, it should be appreciated that functionality described as being supported by the program modules may be enabled by any combination of hardware, software, and/or firmware. It should further be appreciated that each of the above-mentioned modules may, in various embodiments, represent a logical partitioning of supported functionality. This logical partitioning is depicted for ease of explanation of the functionality and may not be representative of the structure of software, hardware, and/or firmware for implementing the functionality. Accordingly, it should be appreciated that functionality described as being provided by a particular module may, in various embodiments, be provided at least in part by one or more other modules. Further, one or more depicted modules may not be present in certain embodiments, while in other embodiments, additional modules not depicted may be present and may support at least a portion of the described functionality and/or additional functionality. Moreover, while certain modules may be depicted and described as sub-modules of another module, in certain embodiments, such modules may be provided as independent modules or as sub-modules of other modules.

[0035] Although specific embodiments of the disclosure have been described, one of ordinary skill in the art will recognize that numerous other modifications and alternative embodiments are within the scope of the disclosure. For example, any of the functionality and/or processing capabilities described with respect to a particular device or component may be performed by any other device or component. Further, while various illustrative implementations and architectures have been described in accordance with embodiments of the disclosure, one of ordinary skill in the art will appreciate that numerous other modifications to the illustrative implementations and architectures described herein are also within the scope of this disclosure. In addition, it should be appreciated that any operation, element, component, data, or the like described herein as being based on another operation, element, component, data, or the like can be additionally based on one or more other operations, elements, components, data, or the like. Accordingly, the phrase“based on,” or variants thereof, should be interpreted as“based at least in part on.”

[0036] Although embodiments have been described in language specific to structural features and/or methodological acts, it is to be understood that the disclosure is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as illustrative forms of implementing the embodiments. Conditional language, such as, among others,“can,”“could,”“might,” or“may,” unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments could include, while other embodiments do not include, certain features, elements, and/or steps. Thus, such conditional language is not generally intended to imply that features, elements, and/or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements, and/or steps are included or are to be performed in any particular embodiment.

[0037] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

CLAIMS What is claimed is:

1. A computer-based method of ranking templates for control application programs of a project assisted by machine learning, comprising:

training a machine learning engine, comprising:

extracting, by a data extraction tool, a plurality of textual descriptions

corresponding to a plurality of projects and associated engineering templates; mapping, by a pre-processing data tool, the plurality of textual descriptions to high-dimensional vectors; and

clustering, by a machine learning engine, the vectors into clusters, wherein each cluster is associated with a respective engineering template; and

generating a ranking of templates for a current project, comprising:

receiving, by a ranking tool, a query for a template ranking, wherein the query includes a textual description for the current project;

mapping, by the ranking tool, the query to a high-dimensional query vector using a same mapping process as performed during the training; and

ranking, by the ranking tool, the engineering templates based on analogy of the query vector to clustering information from the trained machine learning engine.

2. The method of claim 1 , wherein the textual descriptions are mapped according to a dimensional metric that includes one of: number of words in the vocabulary of the textual descriptions, size of engineering template code, or number and type of input/output connections.

3. The method of claim 1 , wherein the clustering is determined by a distance-based clustering algorithm, wherein clustering is confined to include vector pairs having a distance between one another that does not exceed a threshold.

4. The method of claim 1 , wherein the clustering is based on probabilities of correctness from a Gaussian-based neural network and the ranking is according to the probabilities.

5. The method of claim 1 , wherein the extracted textual descriptions include types of information including at least one of: problem, input, output, requirements, or cost; and the textual descriptions are extracted from stored project data.

6. The method of claim 1 , further comprising:

displaying the ranking of templates to a user.

7. The method of claim 1 , further comprising:

receiving a template selection for the current project from among the ranking of engineering templates;

receiving, by the machine learning engine, an association of the query and the template selection; and

using at least one of the association, the query, or the template selection as an additional training sample for updating the clustering.

8. A system for ranking templates used to engineer control application programs of a project assisted by machine learning, comprising:

a data extraction tool configured to extract a plurality of textual descriptions corresponding to a plurality of projects and associated engineering templates; a pre-processing data tool configured to map the plurality of textual descriptions to high-dimensional vectors;

a machine learning engine configured to cluster the vectors into clusters, wherein each cluster is associated with a respective engineering template; and a ranking tool configured to map a query to a high-dimensional query vector using a same mapping process as for the plurality of textual descriptions, wherein the query includes a textual description for a current project; and to rank the engineering templates based on analogy of the query vector to clustering information from the machine learning engine.

9. The system of claim 8, wherein the pre-processing tool is configured to map the textual descriptions according to a dimensional metric that includes one of: number of words in the vocabulary of the textual descriptions, size of engineering template code, or number and type of input/output connections.

10. The system of claim 8, wherein the machine learning engine is configured to perform clustering by executing a distance-based clustering algorithm, wherein clustering is confined to include vector pairs having a distance between one another that does not exceed a threshold.

1 1. The system of claim 8, wherein the machine learning engine is configured to perform clustering based on probabilities of correctness from a Gaussian-based neural network and the ranking is according to the probabilities.

12. The system of claim 8, wherein the data extraction tool is configured to extract textual descriptions to include types of information including at least one of: problem, input, output, requirements, or cost; and the textual descriptions are extracted from stored project data.

13. The system of claim 8, further comprising a display configured to display the ranking of engineering templates to a user.

14. The system of claim 8, wherein

the ranking tool is configured to receive a template selection for the current project from among the ranking of engineering templates; and

the machine learning engine is configured to receive an association of the query and the template selection; and to update clustering for the selected template using at least one of the association, the query, or the template selection.