Ontology-based workflow automation and execution

Abstract

Embodiments record execution of a workflow including skills, the record generating workflow data. Embodiments use the workflow data to select an ontology tree having a similarity to the workflow above a threshold amount. Embodiments construct a first skill tree corresponding to a workflow using an ontology tree and workflow data. Embodiments integrate the first skill tree into an existing skill tree of the application, the integration generating an integrated skill tree of the application. Embodiments execute skills using the integrated skill tree and the new data in response to an intent requesting to execute the skills using the new data.

Description

Technical Field

[0001] The present invention generally relates to workflow automation. More specifically, the present invention relates to a method, system and computer program for ontology-based workflow automation and execution. Background Art

[0002] Workflow automation refers to the process of automatically executing a sequence of tasks (i.e., a workflow) by a computer. For example, a workflow may include all of the tasks involved in composing an email (e.g., opening an email application, selecting "Compose," selecting one or more recipients, entering text in the "Subject" field, and entering text in the body of the email). Automating this workflow allows the entire sequence to be executed with one command and optional arguments (e.g., "email Laura to remind her of her meeting on Tuesday"). Automated workflows are useful in a variety of contexts, but are particularly useful when used in conjunction with a natural language-based virtual assistant that communicates with the user using spoken commands.

[0003] A virtual assistant is a software agent that can perform a range of tasks or services for a user based on user input such as commands or questions (including spoken commands or questions). A skill is a named workflow, i.e., one or more tasks that a software application knows how to perform. Some skills are pre-programmed, while other skills can be added to a virtual assistant or automation implementation after it is deployed for use.

[0004] An intent is an action to fulfill a user request, such as by invoking one or more skills. An intent can optionally have parameters with placeholders called slots. For example, an intent to invoke the Email skill might be "Send Laura an email to remind her of her meeting on Tuesday"), where "Laura" and "remind her of her meeting on Tuesday" are parameters that are filled into the slots when the Email skill is invoked.

[0005] An ontology is a representation, formal naming, and definition of categories, properties, and relationships among concepts, data, and entities that implement a subject domain. An ontology is a way of organizing the properties of a subject domain and how these properties are related by defining a collection of concepts and categories that represent the subject domain.

[0006] The illustrative embodiments recognize that organizations are investing in a variety of software tools to automate workflows, increasing the complexity of information technology infrastructure. Different applications have different interfaces and features, and existing automation tools often rely on proprietary scripting languages ​​or visual sequencing interfaces that limit usability. Therefore, there is a need for a workflow automation implementation that does not rely on scripting languages ​​and is simple for non-technical users to "teach" automation tools new skills.

[0007] One existing automation approach involves using a desktop recorder that collects information about peripheral (e.g., mouse or keyboard) input and visual changes on the screen to collect the user's skill execution. The recorded flow can be converted into a script that can be recreated on another user's desktop, thereby achieving automation. However, currently available robotic process automation (RPA) implementations cannot recognize steps in the recording that may vary from user to user. Existing RPA implementations typically require users to explicitly encode interactions in a specific logical sequence to achieve effective generalization, which is difficult for non-technical users. Typically, subject matter experts are required to automate specific workflows. In addition, recording-based tools that rely only on specific input sequences (e.g., mouse clicks or keyboard inputs) are fragile and will break if it is a user interface for a specific application. Similarly, recording-based tools are application-specific (e.g., if a new application replaces an existing application, it must be re-taught), and therefore the workflows they have been taught are not easy to generalize between applications of the same type. For example, the steps for writing an email in different email applications tend to be similar, even if the user interface of each application is slightly different. Therefore, it would be useful to automate the workflow once and generalize the workflow on similar applications with minimal additional application-specific efforts.

[0008] Thus, the illustrative embodiments recognize a need for a workflow automation implementation that is not dependent on scripting languages, is simple for non-technical users to "teach" automation tools new skills, and can be implemented through a single user demonstration of an example outlining the workflow to be automated. Summary of the invention

[0009] Illustrative embodiments provide workflow automation and execution based on ontology. Embodiments include recording the execution of a workflow including a skill, the recording generating workflow data. Embodiments include using the workflow data to select an ontology tree having a similarity with the workflow that is greater than a threshold amount. Embodiments include using the ontology tree and the workflow data to construct a first skill tree corresponding to the workflow. Embodiments include integrating the first skill tree into an existing skill tree of an application, the integration producing an integrated skill tree of the application. Embodiments include executing the skill using the integrated skill tree and the new data in response to a request for an intent to execute the skill using new data. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the embodiments. Thus, embodiments provide workflow automation and execution based on ontology.

[0010] Further embodiments include validating workflow data, the validation including confirming intent associated with the workflow. Thus, embodiments provide for validation of workflow data used in ontology-based workflow automation and execution.

[0011] Further embodiments include validating workflow data, the validation including confirming user-specificity of the workflow. Thus, embodiments provide for validation of workflow data used in ontology-based workflow automation and execution.

[0012] Further embodiments include validating workflow data, the validation including removing steps in the workflow. Thus, embodiments provide validation of workflow data for use in ontology-based workflow automation and execution.

[0013] In a further embodiment, constructing the first skill tree includes adding a first node in the ontology tree to the first skill tree, the first node in the ontology tree corresponding to an action identified in the workflow data. Thus, embodiments provide additional details for constructing a skill tree for use in ontology-based workflow automation and execution.

[0014] Further embodiments include validating the first skill tree, the validating including removing steps in the first skill tree.Thus, embodiments provide validation of skill trees used in ontology-based workflow automation and execution.

[0015] Embodiments include a computer usable program product. The computer usable program product includes a computer readable storage medium and program instructions stored on the storage medium.

[0016] An embodiment includes a computer system. The computer system includes a processor, a computer-readable memory, a computer-readable storage medium, and program instructions stored on the storage medium for execution by the processor via the memory. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The novel features which are believed to be characteristic of the invention are set forth in the appended claims. However, the invention itself, together with its preferred mode of use, further objects and advantages will be best understood by reference to the following detailed description of illustrative embodiments taken in conjunction with the accompanying drawings, in which:

[0018] Figure 1 depicts a block diagram of a computing environment according to an illustrative embodiment;

[0019] Figure 2 depicts a flow chart of an example process for loading process software in accordance with an illustrative embodiment;

[0020] Figure 3 depicts a block diagram of an example configuration for ontology-based workflow automation and execution in accordance with an illustrative embodiment;

[0021] Figure 4 depicts an example of ontology-based workflow automation and execution in accordance with an illustrative embodiment;

[0022] Figure 5 depicts another example of ontology-based workflow automation and execution in accordance with an illustrative embodiment;

[0023] Figure 6 depicts a continued example of ontology-based workflow automation and execution in accordance with an illustrative embodiment;

[0024] Figure 7 depicts a continued example of ontology-based workflow automation and execution in accordance with an illustrative embodiment;

[0025] Figure 8 depicts a continued example of ontology-based workflow automation and execution in accordance with an illustrative embodiment; and

[0026] Fig. 9 Depicted is a flowchart of an example process for ontology-based workflow automation and execution in accordance with an illustrative embodiment. DETAILED DESCRIPTION

[0027] The illustrative embodiments recognize the need for a workflow automation implementation that is not dependent on scripting languages, is simple for non-technical users to "teach" automation tools new skills, and can be implemented through a single user demonstration of an example of a workflow to be automated. The present disclosure addresses the above-mentioned deficiencies by providing the following process (as well as systems, methods, machine-readable media, etc.): recording the execution of a workflow including a skill, the recording generating workflow data; using the workflow data to select an ontology tree that has a similarity with the workflow above a threshold amount; using the ontology tree and the workflow data to construct a first skill tree corresponding to the workflow; integrating the first skill tree into an existing skill tree of an application, the integration generating an integrated skill tree of the application; and in response to a request for an intent to execute a skill using new data, executing the skill using the integrated skill tree and the new data. Thus, the illustrative embodiments provide ontology-based workflow automation and execution.

[0028] Illustrative embodiments record the execution of a workflow including a skill that the workflow is intended to automate. The record generates workflow data. Some non-limiting examples of workflow data are user interface actions recorded when a user demonstrates a workflow on a computing device, such as mouse clicks with timestamps, mouse scrolls, key presses, and active user interface windows in which key presses, mouse activities, and other user interface activities occur. Another non-limiting example of workflow data is audio data of a user's verbal description of the workflow obtained when the workflow is demonstrated or at different times. Another non-limiting example of workflow data is screen capture data of an active user interface window obtained when the user demonstrates the workflow. Another non-limiting example of workflow data is video data of a user when the user demonstrates the workflow. Another non-limiting example of workflow data is a uniform resource locator (URL) of an active user interface window obtained when the user demonstrates the workflow (if applicable). The embodiment uses one or more currently available technologies to record user interface actions and associate specific user interface actions with specific user interface windows. The embodiment uses currently available speech-to-text conversion technology to convert audio data into corresponding text data. Embodiments use currently available character recognition technology to identify text labels associated with particular user interface actions (eg, a label near a text box into which a user is typing or a label of a window into which a user clicks a mouse).

[0029] One embodiment prompts the user to specify an intent associated with the demonstrated skill, and receives and processes the user's response. In one embodiment, the user's response is in a structured form (e.g., by selecting a predefined intent or skill from a menu). In another embodiment, the user's response is an utterance (in an unstructured natural language form, either in text form or converted to text from another form), such as "Start recording a demonstration of how I record time in our time management application"), and the embodiment uses currently available natural language understanding technology to simplify the input utterance to a general intent representing the demonstrated skill. If the embodiment does not have a skill mapped to the intent of the utterance, the embodiment defines a new skill invoked by the input utterance. Another embodiment does not prompt the user to specify an intent associated with the demonstrated skill, but instead uses currently available natural language understanding technology to extract the intent from the user's demonstration of the workflow. For example, a user may specify an intent during a demonstration (e.g., "Now I will demonstrate how to record time in our time management application").

[0030] One embodiment verifies the workflow data to the user. Some non-limiting examples of verifying the workflow data include confirming the intent of the workflow data, allowing the user to specify a privacy level or restriction on the distribution of a portion of the workflow data (e.g., a user's login credentials that may be exposed during a demonstration), allowing the user to specify whether the workflow data is user-specific or common to a group of users, allowing the user to edit the recorded workflow data to adjust or remove steps (e.g., a user may have performed an unrelated action during a demonstration), allowing the user to confirm the export of embodiment-specific information (e.g., intuitive tags and the context of the tags), etc.

[0031] Using (optionally verified) workflow data and currently available natural language understanding technology, an embodiment sets the values ​​of two key-value pairs. One key-value pair has a key marked as application type and a value representing a specific application type associated with the workflow. For example, the value of application type can be "calendar" or "human resource management". The other key-value pair has a key marked as application and a value representing a specific application associated with the workflow. For example, the value of application can be a specific calendar application.

[0032] An embodiment may access one or more ontology trees. An ontology tree is a tree-based hierarchical representation of steps that are common to a particular application type. A node object or node of an ontology tree represents one or more steps. The node includes the natural language intent of the step, whether the step requires input from the user and whether the input is user-specific or universal, and whether the step is optional or mandatory for a particular path in the tree representing a common workflow of the application type. The hierarchies in the ontology tree represent the paths of various workflows in the application and their ordering. For example, an ontology tree may include a node representing a login step in the head node, and the tree may branch to multiple possible next steps. An ontology tree is typically (but not necessarily) developed by a human expert.

[0033] Embodiments may access one or more skill trees. Each skill tree is a hierarchical representation of application types and learning skills within specific applications of the application type. Each node in the skill tree represents an action, and the path from node to node in the skill tree represents the available paths that can be executed from a specific node.

[0034] One embodiment maintains a data structure comprising one or more nodes, where each node is dedicated to a particular application type. A node comprises a keyword referencing the application type, a pointer to a head node of an ontology tree for the application type, and one or more pointers, each of which points to a head node of an existing skill tree for an application of the application type (or a placeholder for a pointer if a skill tree for a particular application does not currently exist). For example, a node for a calendar application type may include a pointer to an ontology tree for the calendar application type, and one or more pointers, each of which points to a skill tree for a particular calendar application. As new application types are defined and new applications of existing types are released or updated, the node structure allows additional ontology trees and skill trees to be added in a modular manner.

[0035] An embodiment uses the workflow data to select an ontology tree that has a similarity with the workflow that is above a threshold amount. One embodiment selects an ontology tree by using currently available embedding techniques to generate word embeddings (numerical representations) for one or more words in the intent, and measuring the similarity between the generated word embeddings and the word embeddings of the keywords of the ontology tree. A non-limiting example of a similarity measurement technique for embeddings is cosine similarity. One embodiment uses 0.75 as a threshold amount of similarity. Other thresholds are also possible and are considered to be within the scope of the illustrative embodiments.

[0036] An embodiment uses an ontology tree and workflow data to construct a skill tree corresponding to a workflow. Specifically, in order to construct the skill tree, an embodiment traverses the selected ontology tree in depth-first fashion, and utilizes corresponding actions in the recorded workflow to identify one or more nodes in the ontology tree. An embodiment assembles matching ontology tree nodes into a skill tree. In addition, an embodiment adds recorded workflow actions that do not correspond to ontology tree nodes to the constructed skill tree. If there is a loop in the recorded workflow, for simplicity, an embodiment treats the loop as a series of sequential steps. For example, if the recorded workflow includes an action at website X, followed by an action at website Y, and then returns to website X, an embodiment includes three separate steps in the skill tree. An embodiment may use the constructed skill tree to re-execute the actions performed in the recorded workflow, but in a generalized manner.

[0037] One embodiment validates the constructed skill tree to the user. Some non-limiting examples of validating the constructed skill tree include allowing the user to specify whether the skill tree is user-specific or common to a group of users, allowing the user to edit the skill tree to adjust or remove steps (e.g., the user may have performed an irrelevant action during the demonstration), allowing the user to confirm the embodiment's derivation of specific data in the skill tree (e.g., intuitive labels and the context of the labels), etc.

[0038] An embodiment integrates the constructed skill tree into the existing skill tree of the application, thereby forming an integrated skill tree of the application. An embodiment traverses the existing skill tree of the application in a depth-first manner until a node matching the head node in the constructed skill tree is reached, and inserts the constructed skill tree into the existing skill tree at the matching node. An embodiment also verifies the insertion point of the constructed skill tree to the user.

[0039] An embodiment receives an intent requesting that a skill be performed using new data, and in response, performs the skill using the integrated skill tree and the new data. The received intent may be in a structured form (e.g., in a menu selection) or in an unstructured natural language form (e.g., "Enter my eight hours of vacation time into a time management application for me").

[0040] For the sake of clarity of description, and without implying any limitation thereto, some example configurations are used to describe the illustrative embodiments. Based on this disclosure, a person of ordinary skill in the art will be able to conceive of many changes, adaptations and modifications of the described constructions for achieving the described purposes, and these are all considered to be within the scope of the exemplary embodiments.

[0041] In addition, simplified diagrams of data processing environments are used in the drawings and illustrative embodiments. In an actual computing environment, additional structures or components not shown or described herein, or structures or components different from those shown but used for functions similar to those described herein, may be present without departing from the scope of the illustrative embodiments.

[0042] In addition, the illustrative embodiments are described with respect to specific actual or hypothetical components only as examples. Any particular representation of these and other similar products is not intended to limit the present invention. Any appropriate representation of these and other similar products can be selected within the scope of the exemplary embodiments.

[0043] The examples in this disclosure are only for clear description and are not intended to limit the illustrative embodiments. Any advantages listed herein are only examples and are not intended to limit the illustrative embodiments. Additional or different advantages can be achieved through specific illustrative embodiments. In addition, specific illustrative embodiments may have some, all, or none of the advantages listed above.

[0044] Furthermore, the illustrative embodiments may be implemented for any type of data, data source, or access to a data source over a data network. Any type of data storage device may provide data to embodiments of the present invention locally at a data processing system or over a data network within the scope of the present invention. Where embodiments are described using a mobile device, any type of data storage device suitable for use with the mobile device may provide data to the embodiments locally at the mobile device or over a data network within the scope of the illustrative embodiments.

[0045] The illustrative embodiments are described using specific codes, computer-readable storage media, high-level features, designs, architectures, protocols, layouts, schematics, and tools, which are examples only, not limitations of the illustrative embodiments. In addition, for clarity of description, specific software, tools, and data processing environments are used in some instances to describe the illustrative embodiments only as examples. The illustrative embodiments can be used in conjunction with other comparable or similar purpose structures, systems, applications, or architectures. For example, within the scope of the present invention, other comparable mobile devices, structures, systems, applications, or their architectures can be used in conjunction with such embodiments of the present invention. The illustrative embodiments can be implemented in hardware, software, or a combination thereof.

[0046] The examples in this disclosure are only for clear description and are not limited to the illustrative embodiments. Additional data, operations, actions, tasks, activities and manipulations can be imagined from this disclosure and can be envisioned within the scope of the illustrative embodiments.

[0047] Various aspects of the present disclosure are described by narrative text, flow charts, block diagrams of computer systems, and / or block diagrams of machine logic included in computer program product (CPP) embodiments. With respect to any flow chart, depending on the technology involved, the operations may be performed in an order different from the order shown in a given flow chart. For example, again depending on the technology involved, two operations shown in consecutive flow chart blocks may be performed in reverse order, as a single integrated step, simultaneously, or in a manner that at least partially overlaps in time.

[0048] The term computer program product embodiment ("CPP embodiment" or "CPP") as used in this disclosure is used to describe any collection of one or more storage media (also referred to as "media") collectively included in a collection of one or more storage devices that collectively include machine-readable code corresponding to instructions and / or data for performing the computer operations specified in a given CPP claim. A "storage device" is any tangible device that can hold and store instructions for use by a computer processor. Without limitation, a computer-readable storage medium may be an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, a mechanical storage medium, or any suitable combination of the foregoing. Some known types of storage devices that include these media include: a magnetic disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device (such as a punch card or pits / land formed in a major surface of a disk), or any suitable combination of the foregoing. The term computer-readable storage medium as used in this disclosure is not to be interpreted as storage in the form of a transitory signal per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides, light pulses through fiber optic cables, electrical signals transmitted through wires, and / or other transmission media. As will be appreciated by those skilled in the art, data is typically moved at certain occasional points in time during normal operation of the storage device, such as during access, de-fragmentation, or garbage collection, but this does not make the storage device transitory because the data is not transitory when it is stored.

[0049] refer to Figure 1, which depicts a block diagram of a computing environment 100. The computing environment 100 includes an example of an environment for executing at least some of the computer codes involved in performing the methods of the present invention, such as an application 200 that implements ontology-based workflow automation and execution. In addition to the block 200, the computing environment 100 includes, for example, a computer 101, a wide area network (WAN) 102, an end-user device (EUD) 103, a remote server 104, a public cloud 105, and a private cloud 106. In this embodiment, the computer 101 includes a processor group 110 (including a processing circuit 120 and a cache 121), a communication structure 111, a volatile memory 112, a persistent storage 113 (including an operating system 122 and a block 200, as described above), a peripheral device group 114 (including a user interface (UI) device group 123, a storage 124, and an Internet of Things (IoT) sensor group 125), and a network module 115. The remote server 104 includes a remote database 130. The public cloud 105 includes a gateway 140 , a cloud coordination module 141 , a host physical machine group 142 , a virtual machine group 143 , and a container group 144 .

[0050] Computer 101 may take the form of a desktop computer, laptop computer, tablet computer, smart phone, smart watch or other wearable computer, mainframe computer, quantum computer, or any other form of computer or mobile device now known or developed in the future that is capable of running programs, accessing a network, or querying a database such as remote database 130. As is well known in the art of computer technology, and depending on the technology, the performance of computer-implemented methods may be distributed among multiple computers and / or among multiple locations. On the other hand, in this presentation of computing environment 100, the detailed discussion focuses on a single computer (particularly computer 101) to keep the presentation as simple as possible. Computer 101 may be located in the cloud, even though Figure 1 On the other hand, unless to any extent that can be positively indicated, there is no requirement that computer 101 is in the cloud.

[0051] Processor group 110 includes one or more computer processors of any type now known or to be developed in the future. Processing circuit 120 may be distributed over multiple packages, such as multiple cooperating integrated circuit chips. Processing circuit 120 may implement multiple processor threads and / or multiple processor cores. Cache 121 is a memory located in the processor chip package and is typically used for data or code that should be quickly accessed by threads or cores running on processor group 110. Cache memory is typically organized into multiple levels based on relative proximity to the processing circuit. Alternatively, some or all of the caches of the processor group may be located "off chip". In some computing environments, processor group 110 may be designed to work with qubits and perform quantum computing.

[0052] Computer readable program instructions are typically loaded onto computer 101 to cause processor group 110 of computer 101 to perform a series of operating steps to implement a computer-implemented method, such that the instructions so executed will instantiate the method specified in the flow chart and / or the narrative description of the computer-implemented method included in this document (collectively referred to as "the present method"). These computer readable program instructions are stored in various types of computer readable storage media, such as cache 121 and other storage media discussed below. The program instructions and related data are accessed by processor group 110 to control and direct the execution of the present method. In computing environment 100, at least some of the instructions for performing the present method in block 150 may be stored in persistent storage 113.

[0053] Communications fabric 111 is the signaling pathways that allow the various components of computer 101 to communicate with each other. Typically, the fabric is comprised of switches and conductive pathways, such as those that constitute a bus, a bridge, physical input / output ports, etc. Other types of signal communication pathways may be used, such as fiber optic communication pathways and / or wireless communication pathways.

[0054] The volatile memory 112 is any type of volatile memory now known or developed in the future. Examples include dynamic random access memory (RAM) or static RAM. Typically, the volatile memory 112 is characterized by random access, but this is not required unless expressly stated. In the computer 101, the volatile memory 112 is located in a single package and is internal to the computer 101, but, alternatively or additionally, the volatile memory may be distributed among multiple packages and / or located externally relative to the computer 101.

[0055] Persistent storage 113 is any form of non-volatile memory for computers known now or developed in the future. The non-volatility of the memory means that the stored data is maintained regardless of whether power is supplied to the computer 101 and / or directly to the persistent storage 113. Persistent storage 113 can be a read-only memory (ROM), but typically at least a portion of the persistent storage allows the writing of data, the deletion of data, and the rewriting of data. Some common forms of persistent storage include disks and solid-state storage devices. Operating system 122 can take several forms, such as various known proprietary operating systems or operating systems of the open source portable operating system interface type using a kernel. The code included in block 200 typically includes at least some of the computer codes involved in executing the method of the present invention.

[0056] The peripheral device group 114 includes a group of peripheral devices of the computer 101. The data communication connection between the peripheral devices and other components of the computer 101 can be implemented in various ways, such as a Bluetooth connection, a near field communication (NFC) connection, a connection made by a cable (such as a universal serial bus (USB) type cable), a plug-in type connection (e.g., a secure digital (SD) card), a connection made through a local area communication network, and even a connection made through a wide area network such as the Internet. In various embodiments, the UI device group 123 may include components such as display screens, speakers, microphones, wearable devices (such as goggles and smart watches), keyboards, mice, printers, touchpads, game controllers, and tactile devices. Storage 124 is an external storage device, such as an external hard drive, or a pluggable storage device, such as an SD card. Storage 124 can be persistent and / or volatile. In some embodiments, storage 124 can take the form of a quantum computing storage device for storing data in the form of quantum bits. In embodiments where the computer 101 needs to have a large amount of storage (e.g., where the computer 101 locally stores and manages a large database), the storage may be provided by a peripheral storage device designed to store very large amounts of data, such as a storage area network (SAN) shared by multiple geographically distributed computers. The IoT sensor group 125 is composed of sensors that can be used in IoT applications. For example, one sensor may be a thermometer, while another sensor may be a motion detector.

[0057] The network module 115 is a collection of computer software, hardware, and firmware that allows the computer 101 to communicate with other computers via the WAN 102. The network module 115 may include hardware such as a modem or a Wi-Fi signal transceiver, software for packetizing and / or depacketizing data transmitted over a communication network, and / or a network browser software for transmitting data over the Internet. In some embodiments, the network control function and the network forwarding function of the network module 115 are executed on the same physical hardware device. In other embodiments (e.g., embodiments utilizing software defined networks (SDN)), the control function and the forwarding function of the network module 115 are executed on physically separated devices so that the control function manages several different network hardware devices. Computer-readable program instructions for executing the method of the present invention can generally be downloaded to the computer 101 from an external computer or an external storage device via a network adapter card or a network interface included in the network module 115.

[0058] WAN 102 is any wide area network (e.g., the Internet) capable of transmitting computer data over non-local distances by any technology now known or developed in the future for transmitting computer data. In some embodiments, WAN 102 may be replaced and / or supplemented by a local area network (LAN) designed to transmit data between devices located in a local area, such as a Wi-Fi network. WANs and / or LANs typically include computer hardware, such as copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers.

[0059] End-user device (EUD) 103 is any computer system used and controlled by an end-user (e.g., a business customer operating computer 101), and may take any of the forms discussed above in conjunction with computer 101. EUD 103 typically receives helpful and useful data from the operation of computer 101. For example, in the hypothetical case where computer 101 is designed to provide recommendations to an end-user, the recommendations would typically be transmitted from network module 115 of computer 101 to EUD 103 via WAN 102. In this manner, EUD 103 may display or otherwise present the recommendations to the end-user. In some embodiments, EUD 103 may be a client device, such as a thin client, a heavy client, a mainframe computer, a desktop computer, or the like.

[0060] Remote server 104 is any computer system that provides at least some data and / or functionality to computer 101. Remote server 104 may be controlled and used by the same entity that operates computer 101. Remote server 104 represents a machine that collects and stores helpful and useful data for use by other computers, such as computer 101. For example, in the hypothetical case where computer 101 is designed and programmed to provide recommendations based on historical data, then the historical data may be provided to computer 101 from remote database 130 of remote server 104.

[0061] The public cloud 105 is any computer system available for use by multiple entities that provides on-demand availability of computer system resources and / or other computer capabilities, particularly data storage (cloud storage) and computing capabilities, without direct active management by users. Cloud computing typically leverages the sharing of resources to achieve consistency and economy of scale. The direct and active management of the computing resources of the public cloud 105 is performed by computer hardware and / or software of the cloud coordination module 141. The computing resources provided by the public cloud 105 are typically implemented by virtual computing environments running on various computers that constitute the host physical machine group 142, which is the universe of physical computers in and / or available to the public cloud 105. Virtual computing environments (VCEs) typically take the form of virtual machines from the virtual machine group 143 and / or containers from the container group 144. It will be appreciated that these VCEs can be stored as images and can be transferred between various physical machine hosts as images or after instantiation of the VCEs. The cloud coordination module 141 manages the transmission and storage of images, deploys new instantiations of VCEs, and manages active instantiations of VCE deployments. Gateway 140 is a collection of computer software, hardware, and firmware that allows public cloud 105 to communicate over WAN 102 .

[0062] Some further explanation of virtualized computing environments (VCEs) will now be provided. A VCE can be stored as an "image". A new active instance of the VCE can be instantiated from the image. Two common types of VCEs are virtual machines and containers. Containers are VCEs that use operating system-level virtualization. This refers to an operating system feature in which the kernel allows the existence of multiple isolated user space instances, called containers. From the perspective of the programs running in them, these isolated user space instances typically behave like actual computers. Computer programs running on ordinary operating systems can utilize all of the resources of the computer, such as connected devices, files and folders, network shares, CPU capabilities, and quantifiable hardware capabilities. However, programs running within a container can only use the contents of the container and the devices assigned to the container, a feature known as containerization.

[0063] Private cloud 106 is similar to public cloud 105, except that the computing resources are only available to a single enterprise. Although private cloud 106 is depicted as communicating with WAN 102, in other embodiments, the private cloud can be completely disconnected from the Internet and only accessible through a local / private network. A hybrid cloud is a combination of multiple clouds of different types (e.g., private, community, or public cloud types), typically implemented by different vendors. Each of the multiple clouds remains a separate and discrete entity, but the larger hybrid cloud architecture is bound together by standardized or proprietary technologies that enable coordination, management, and / or data / application portability between the multiple constituent clouds. In this embodiment, both public cloud 105 and private cloud 106 are part of a larger hybrid cloud.

[0064] Metered Services: Cloud systems automatically control and optimize resource usage by leveraging metering capabilities at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, reported, and invoiced, providing transparency to both providers and consumers of the services used.

[0065] refer to Figure 2 , which depicts a flow chart of an example process for loading process software according to an illustrative embodiment. The flow chart may be provided by, for example, Figure 1 The process is performed by a device such as a computer 101 in the system, an end-user device 103, a remote server 104, or a device in a private cloud 106 or a public cloud 105.

[0066] Although it can be understood that the processing software for realizing workflow automation and execution based on ontology can be deployed by directly manually loading into the client, server and proxy computer via loading storage media such as CD, DVD, etc., the processing software can also be automatically or semi-automatically deployed in the computer system by sending the processing software to a central server or a group of central servers. Then, the processing software is downloaded to the client computer that will execute the processing software. Alternatively, the processing software is directly sent to the client system via email. Then, by executing a set of program instructions that separate the processing software into a directory, the processing software is separated into a directory or loaded into a directory. Another replacement is to send the processing software directly to the directory on the client computer hard drive. When there is a proxy server, the process will select the proxy server code, determine which computers the proxy server code is placed on, transmit the proxy server code, and then install the proxy server code on the proxy computer. The processing software will be sent to the proxy server, and then it will be stored on the proxy server.

[0067] Step 202 begins deploying the process software. The initial step is to determine if any programs will reside on one or more servers when the process software is executed (203). If this is the case, the servers that will include the executable programs are identified (229). The process software for one or more servers is transferred directly to the server's memory via FTP or some other protocol or by copying using a shared file system (230). The process software is then installed on the server (231).

[0068] Next, a determination is made whether to deploy the process software by having the user access the process software on one or more servers (204). If the user is to access the process software on a server, the server address where the process software will be stored is identified (205).

[0069] A determination is made as to whether to establish a proxy server (220) to store the process software. A proxy server is a server that sits between a client application such as a web browser and a real server. It intercepts all requests to the real server to see if it can satisfy the request itself. If not, it forwards the request to the real server. Two main benefits of a proxy server are improved performance and filtering requests. If a proxy server is needed, the proxy server is installed (221). The process software is sent to the server(s) via a protocol such as FTP, or copied directly from the source file to the server file via file sharing (222). Another embodiment involves sending a transaction to the server(s) containing the process software, and having the server process the transaction, then receiving the process software and copying it to the server's file system. Once the process software is stored on the server, the user accesses the process software on the server through their client computer and copies it to their client computer file system (223). Another embodiment is to have the server automatically copy the process software to each client, and then run an installer for the process software at each client computer. The user executes a program to install the process software on their client computer (232), and then exits the process (210).

[0070] At step 206, a determination is made whether to deploy the process software by sending the process software to the users via email. The set of users to whom the process software will be deployed is identified along with the addresses of the users' client computers (207). The process software is sent to each user's client computer via email (224). The users then receive the email (225) and then detach the process software from the email to a directory on their client computer (226). The users execute a program that installs the process software on their client computers (232) and then exit the process (210).

[0071] Finally, a determination is made as to whether the process software is to be sent directly to the user's directory on their client computer (208). If so, the user directory is identified (209). The process software is transferred directly to the user's client computer directory (227). This can be accomplished in several ways, such as, but not limited to, sharing a file system directory and then copying from the sender's file system to the recipient user's file system, or alternatively, using a transfer protocol such as the File Transfer Protocol (FTP). The user accesses a directory on their client file system in preparation for installing the process software (228). The user executes a program that installs the process software on their client computer (232), and then exits the process (210).

[0072] refer to Figure 3 , which depicts a block diagram of an example configuration for ontology-based workflow automation and execution according to an illustrative embodiment. Figure 1 The same as in application 200.

[0073] In the illustrated embodiment, the workflow collection module 310 records the execution of the workflow, which includes the skills that the workflow is intended to automate. The recording generates workflow data. Some non-limiting examples of workflow data are user interface actions recorded when a user demonstrates a workflow on a computing device, such as time-stamped mouse clicks, mouse scrolls, key presses, and active user interface windows in which key presses, mouse activities, and other user interface activities occur. Another non-limiting example of workflow data is audio data of a user's verbal description of the workflow obtained when the workflow is demonstrated or at different times. Another non-limiting example of workflow data is screen capture data of an active user interface window obtained when the user demonstrates the workflow. Another non-limiting example of workflow data is video data of a user when the user demonstrates the workflow. Another non-limiting example of workflow data is the uniform resource locator (URL) of an active user interface window obtained when the user demonstrates the workflow (if applicable). Module 310 uses one or more currently available technologies to record user interface actions and associates specific user interface actions with specific user interface windows. Module 310 uses currently available speech-to-text conversion technology to convert audio data into corresponding text data. Module 310 uses currently available character recognition technology to identify text labels associated with particular user interface actions (eg, labels near a text box into which a user types or labels of a window into which a user clicks a mouse).

[0074] One implementation of module 310 prompts the user to specify an intent associated with the demonstrated skill, and receives and processes the user's response. In one implementation of module 310, the user's response is in a structured form (e.g., by selecting a predefined intent or skill from a menu). In another implementation of module 310, the user's response is in an utterance (an unstructured, natural language form, or in text form or converted from another form to text), such as "Start recording a demonstration of how I record time in our time management application"), and the implementation uses currently available natural language understanding technology to simplify the input utterance into a general intent representing the demonstrated skill. If module 310 does not have a skill mapped to the intent of the utterance, module 310 defines a new skill invoked by the input utterance. Another implementation of module 310 does not prompt the user to specify an intent associated with the demonstrated skill, but instead uses currently available natural language understanding technology to extract the intent from the user's demonstration of the workflow. For example, a user may specify an intent during a demonstration (e.g., "Now I will demonstrate how to record time in our time management application").

[0075] One implementation of module 310 validates the workflow data to the user. Some non-limiting examples of validating the workflow data include confirming the intent of the workflow data, allowing the user to specify a privacy level or restriction on the distribution of a portion of the workflow data (e.g., a user's login credentials that may be exposed during a demonstration), allowing the user to specify whether the workflow data is user-specific or common to a group of users, allowing the user to edit the recorded workflow data to adjust or remove steps (e.g., a user may have performed an unrelated action during a demonstration), allowing the user to confirm the export of specific information (e.g., intuitive tags and the context of the tags), etc.

[0076] Using (optionally, validated) workflow data and currently available natural language understanding techniques, module 310 sets the values ​​of two key-value pairs. One key-value pair has a key labeled as application type and a value representing a specific application type associated with the workflow. For example, the value of application type may be "calendar" or "human resource management". The other key-value pair has a key labeled as application and a value representing a specific application associated with the workflow. For example, the value of application may be a specific calendar application.

[0077] The ontology identification (ID) module 320 can access one or more ontology trees. An ontology tree is a hierarchical representation of tree-based steps that are common to a specific application type. A node object or node of an ontology tree represents one or more steps. The node includes the natural language intent of the step, whether the step requires input from the user and whether the input is user-specific or universal, and whether the step is optional or mandatory for a specific path in the tree representing a common workflow of the application type. The hierarchy in the ontology tree represents the paths of various workflows in the application and their ordering. For example, an ontology tree may include a node representing a login step in the head node, and the tree may branch to multiple possible next steps. An ontology tree is typically (but not necessarily) developed by a human expert.

[0078] The skill construction module 330 can access one or more skill trees. Each skill tree is a hierarchical representation of application types and learned skills within specific applications of the application type. Each node in the skill tree represents an action, and the path from node to node in the skill tree represents the available paths that can be executed from a specific node.

[0079] One implementation of application 300 maintains a data structure comprising one or more nodes, where each node is dedicated to a particular application type. A node includes a keyword referencing the application type, a pointer to the head node of an ontology tree for the application type, and one or more pointers, each of which points to the head node of an existing skill tree for an application of the application type (or a placeholder for a pointer if a skill tree for a particular application does not currently exist). For example, a node for a calendar application type may include a pointer to an ontology tree for the calendar application type, and one or more pointers, each of which points to a skill tree for a particular calendar application. As new application types are defined and new applications of existing types are released or updated, the node structure allows additional ontology trees and skill trees to be added in a modular manner.

[0080] Module 320 uses the workflow data to select an ontology tree that has a similarity with the workflow that is higher than a threshold amount. One implementation of module 320 selects an ontology tree by using currently available embedding technology to generate word embeddings (numerical representations) of one or more words in the intent, and measuring the similarity between the generated word embeddings and the word embeddings of the keywords of the ontology tree. A non-limiting example of a similarity measurement technique for embeddings is cosine similarity. One implementation of module 320 uses 0.75 as a threshold amount of similarity. Other thresholds are also possible.

[0081] Module 330 uses the ontology tree and workflow data to construct a skill tree corresponding to the workflow. Specifically, in order to construct the skill tree, module 330 traverses the selected ontology tree in depth first, and uses the corresponding actions in the recorded workflow to identify one or more nodes in the ontology tree. Module 330 assembles the matching ontology tree nodes into a skill tree. In addition, module 330 adds the recorded workflow actions that do not correspond to the ontology tree nodes to the constructed skill tree. If there is a loop in the recorded workflow, for simplicity, module 330 treats the loop as a series of sequential steps. For example, if the recorded workflow includes an action at website X, then an action at website Y, and then returns to website X, module 330 includes three separate steps in the skill tree. Module 330 can use the constructed skill tree to re-execute the actions performed in the recorded workflow, but in a generalized manner.

[0082] Module 330 verifies the constructed skill tree to the user. Some non-limiting examples of verifying the constructed skill tree include allowing the user to specify whether the skill tree is user-specific or common to a group of users, allowing the user to edit the skill tree to adjust or remove steps (e.g., the user may have performed an irrelevant action during the demonstration), allowing the user to confirm the embodiment's derivation of specific data in the skill tree (e.g., intuitive labels and the context of the labels), etc.

[0083] The skill integration module 340 integrates the constructed skill tree into the existing skill tree of the application, thereby forming an integrated skill tree of the application. An implementation of the module 340 traverses the existing skill tree of the application in a depth-first manner until a node matching the head node in the constructed skill tree is reached, and inserts the constructed skill tree into the existing skill tree at the matching node. An implementation of the module 340 also verifies the insertion point of the constructed skill tree to the user.

[0084] The skill execution module 350 receives an intent requesting the execution of a skill using the new data, and in response, executes the skill using the integrated skill tree and the new data. The received intent may be in a structured form (e.g., in a menu selection) or in an unstructured natural language form (e.g., "Enter my eight hours of vacation time into a time management application for me").

[0085] refer to Figure 4 , which depicts an example of ontology-based workflow automation and execution according to an illustrative embodiment. This example can be used Figure 3 The application 300 in is executed.

[0086] As shown, the recorded workflow 400 includes steps 410, 420, and 430. Note that the depicted applications and URLs are merely simplified examples and are not intended to limit the present invention. Using (optionally validated) workflow data and currently available natural language understanding techniques, key-value pairs 440 (labeled as application type) and key-value pairs 450 (labeled as application) are also set.

[0087] refer to Figure 5 , which depicts another example of ontology-based workflow automation and execution according to an illustrative embodiment. This example can be used Figure 3 The application 300 in is executed.

[0088] Ontology data store 500 includes nodes 510, 520, and 530. Each node is dedicated to a specific application type. A node includes a keyword referencing the application type, a pointer to the head node of the ontology tree of the application type, and one or more pointers each pointing to the head node of an existing skill tree for an application of the application type (or a placeholder for the pointer if a skill tree for a specific application does not currently exist). For example, node 510 (for a calendar application type) includes a pointer to a calendar ontology 540, an ontology for the calendar application type, and one or more pointers each pointing to a skill tree for a specific calendar application.

[0089] refer to Figure 6 , which depicts a continued example of ontology-based workflow automation and execution according to an illustrative embodiment. The recorded workflow 400 and steps 420 and 430 are similar to Figure 4 The workflow 400 and steps 420 and 430 recorded in are the same. Node 520 is the same as Figure 5 The node 520 in is the same.

[0090] Node 520 includes a pointer to a human resources (HR) management ontology 610, which has a similarity above a threshold with the recorded workflow 400. Specifically, application 300 traverses ontology 610 depth-first and identifies one or more nodes in the ontology tree that have corresponding actions of step 420 (indicated by match 620, which matches step 420 with ontology step 615) and step 430 (indicated by match 630).

[0091] refer to Figure 7 , which depicts a continued example of ontology-based workflow automation and execution according to an illustrative embodiment. Step 420 is Figure 4 The same as step 420 in the main body step 615 Figure 6 The same as the main body step 615 in.

[0092] As depicted, using the body step 615 and step 420 (from Figure 4 ), the application 300 selects an existing skill tree 710 and inserts a new skill tree 720 into the existing skill tree 710.

[0093] refer to Figure 8 , which depicts a continued example of ontology-based workflow automation and execution according to an illustrative embodiment. The new skill tree 720 is Figure 7 Same as the new skill tree 720 in.

[0094] Here, application 300 receives intent 810, i.e., an intent requesting to execute a skill using new data. In response, application 300 executes the skill (depicted as skill execution 820) using new skill tree 720 (now part of the integrated skill tree) and intent 810.

[0095] refer to Fig. 9 , which depicts a flow chart of an example process for ontology-based workflow automation and execution according to an illustrative embodiment. Process 900 may be performed at Figure 3 The application 300 is implemented in the embodiment.

[0096] In the illustrated embodiment, at box 902, the process records the execution of a workflow that includes a skill, which generates workflow data. At box 904, the process uses the workflow data to select an ontology tree that has a similarity with the workflow that is greater than a threshold amount. At box 906, the process uses the ontology tree and the workflow data to construct a first skill tree corresponding to the workflow. At box 908, the process integrates the first skill tree into an existing skill tree for the application, which integration generates an integrated skill tree for the application. At box 910, the process performs the skill using the integrated skill tree and the new data in response to a request for an intent to perform the skill using the new data. The process then ends.

[0097] The following definitions and abbreviations are used to interpret the claims and specification. As used herein, the terms "comprises," "including," "having," "containing," or any other variation thereof, are intended to cover a non-exclusive inclusion. For example, a composition, mixture, process, method, article, or apparatus that includes a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent to such composition, mixture, process, method, article, or apparatus.

[0098] Additionally, the term "illustrative" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or design described herein as "illustrative" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. The terms "at least one" and "one or more" should be understood to include any integer greater than or equal to one, i.e., one, two, three, four, etc. The term "plurality" should be understood to include any integer greater than or equal to two, i.e., two, three, four, five, etc. The term "connected" may include both indirect "connected" and direct "connected."

[0099] References in the specification to "one embodiment," "example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but each embodiment may or may not include the particular feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments, whether or not explicitly described.

[0100] The terms "about," "substantially," "approximately," and variations thereof are intended to include the degree of error associated with the measurement of a particular quantity based on the equipment available at the time the application was filed. For example, "about" may include a range of ±8% or 5% or 2% of a given value.

[0101] The description of various embodiments of the present invention is given for the purpose of illustration, but it is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications or technical improvements existing in the market, or to enable other persons of ordinary skill in the art to understand the embodiments described herein.

[0102] The description of various embodiments of the present invention is given for the purpose of illustration, but it is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications or technical improvements existing in the market, or to enable other persons of ordinary skill in the art to understand the embodiments described herein.

[0103] Thus, in illustrative embodiments, a computer-implemented method, system or apparatus, and computer program product are provided for managing participation in an online community and other related features, functions, or operations. Where embodiments or portions thereof are described with respect to one type of device, the computer-implemented method, system or apparatus, computer program product, or portions thereof, is adapted or configured for use with appropriate and comparable representations of that type of device.

[0104] Where the embodiments are described as being implemented in an application, delivery of the application in a software as a service (SaaS) model may be envisioned within the scope of the illustrative embodiments. In the SaaS model, the ability to implement the application of the embodiments is provided to the user by executing the application in a cloud infrastructure. The user may access the application using a variety of client devices through a thin client interface such as a web browser (e.g., web-based email) or other lightweight client applications. The user does not manage or control the underlying cloud infrastructure, which includes the network, servers, operating system, or storage of the cloud infrastructure. In some cases, the user may not even manage or control the capabilities of the SaaS application. In some other cases, the SaaS implementation of the application may allow for possible exceptions to limited user-specific application configuration settings.

[0105] Embodiments of the present invention may also be delivered as part of a service engagement with a client company, non-profit organization, government entity, internal organizational structure, etc. Aspects of these embodiments may include configuring a computer system to perform, and deploying software, hardware, and web services that implement some or all of the methods described herein. Aspects of these embodiments may also include analyzing the operations of a client, creating recommendations in response to the analysis, building a system that implements parts of the recommendations, integrating the system into existing processes and infrastructure, metering the use of the system, allocating fees to users of the system, and billing for the use of the system. Although the above-mentioned embodiments of the present invention have been described by stating their respective advantages separately, the present invention is not limited to specific combinations thereof. On the contrary, according to the intended deployment of the present invention, these embodiments may also be combined in any manner and quantity without losing their beneficial effects.

Claims

1. A computer-implemented method comprising: recording the execution of a workflow including a skill, the recording generating workflow data; selecting, using the workflow data, an ontology tree having a similarity to the workflow above a threshold amount; constructing a first skill tree corresponding to the workflow using the ontology tree and the workflow data; Integrating the first skill tree into an existing skill tree of an application, wherein the integration generates an integrated skill tree of the application; as well as In response to an intent requesting to execute the skill using new data, the skill is executed using the integrated skill tree and the new data.

2. The computer-implemented method of claim 1 , further comprising: The workflow data is validated, the validation comprising confirming an intent associated with the workflow.

3. The computer-implemented method of claim 1 , further comprising: The workflow data is validated, the validation comprising confirming user specificity of the workflow.

4. The computer-implemented method of claim 1 , further comprising: The workflow data is validated, the validation comprising removing steps in the workflow.

5. The computer-implemented method of claim 1 , wherein: Constructing the first skill tree includes adding a first node in the ontology tree to the first skill tree, the first node in the ontology tree corresponding to an action identified in the workflow data.

6. The computer-implemented method of claim 1 , further comprising: The first skill tree is verified, the verification comprising removing steps in the first skill tree.

7. A computer program product, comprising one or more computer-readable storage media and program instructions stored together on the one or more computer-readable storage media, the program instructions being executable by a processor to cause the processor to perform operations, the operations comprising: recording the execution of a workflow including a skill, the recording generating workflow data; selecting, using the workflow data, an ontology tree having a similarity to the workflow above a threshold amount; constructing a first skill tree corresponding to the workflow using the ontology tree and the workflow data; Integrating the first skill tree into an existing skill tree of an application, wherein the integration generates an integrated skill tree of the application; as well as In response to an intent requesting to execute the skill using new data, the skill is executed using the integrated skill tree and the new data.

8. The computer program product according to claim 7, wherein: The stored program instructions are stored in a computer readable storage device in the data processing system and wherein the stored program instructions are transmitted over a network from a remote data processing system.

9. The computer program product according to claim 7, wherein: The stored program instructions are stored in a computer-readable storage device in a server data processing system, and wherein the stored program instructions are downloaded to a remote data processing system over a network in response to a request for use in a computer-readable storage device associated with the remote data processing system, the stored program instructions further comprising: program instructions to meter usage of the program instructions associated with the request; and Program instructions for generating invoices based on metered usage.

10. The computer program product of claim 7, further comprising: The workflow data is validated, the validation comprising confirming an intent associated with the workflow.

11. The computer program product of claim 7, further comprising: The workflow data is validated, the validation comprising confirming user specificity of the workflow.

12. The computer program product of claim 7, further comprising: The workflow data is validated, the validation comprising removing steps in the workflow.

13. The computer program product of claim 7, wherein: Constructing the first skill tree includes adding a first node in the ontology tree to the first skill tree, the first node in the ontology tree corresponding to an action identified in the workflow data.

14. The computer program product of claim 7, further comprising: The first skill tree is verified, the verification comprising removing steps in the first skill tree.

15. A computer system comprising a processor and one or more computer-readable storage media, and program instructions stored together on the one or more computer-readable storage media, the program instructions being executable by the processor to cause the processor to perform operations, the operations comprising: recording the execution of a workflow including a skill, the recording generating workflow data; selecting, using the workflow data, an ontology tree having a similarity to the workflow above a threshold amount; constructing a first skill tree corresponding to the workflow using the ontology tree and the workflow data; Integrating the first skill tree into an existing skill tree of an application, wherein the integration generates an integrated skill tree of the application; as well as In response to an intent requesting to execute the skill using new data, the skill is executed using the integrated skill tree and the new data.

16. The computer system of claim 15, further comprising: The workflow data is validated, the validation comprising confirming an intent associated with the workflow.

17. The computer system of claim 15, further comprising: The workflow data is validated, the validation comprising confirming user specificity of the workflow.

18. The computer system of claim 15, further comprising: The workflow data is validated, the validation comprising removing steps in the workflow.

19. The computer system of claim 15, wherein: Constructing the first skill tree includes adding a first node in the ontology tree to the first skill tree, the first node in the ontology tree corresponding to an action identified in the workflow data.

20. The computer system of claim 15, further comprising: The first skill tree is verified, the verification comprising removing steps in the first skill tree.

21. A system comprising modules respectively configured to perform the steps of the method according to any one of claims 1 to 6.

Images