Generating process flow models using unstructured conversational bots

The unstructured conversation robot records interaction and generates a personalized process flow model, which solves the problem of artificial limitations in the prior art process flow sequence, improves workers' efficiency and task accuracy, and optimizes workflows.

CN112307177BActive Publication Date: 2024-12-06INTERNATIONAL BUSINESS MACHINE CORPORATION
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010701615.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-08-01
Filing Date
2020-07-20
Publication Date
2024-12-06
Estimated Expiration
2040-07-20

AI Technical Summary

Technical Problem

The order of existing process flows is often artificially limited, resulting in workers being inefficient and impaired in accuracy when performing tasks, and being unable to effectively adapt to the preferences and habits of individual workers.

Method used

Through the unstructured conversation robot, a personalized process flow model is generated, and instructions are presented to users in real time through the conversation robot to adapt to workers' preferences and habits and optimize the efficiency of workflow.

Benefits of technology

It achieves improving workers' efficiency while maintaining task accuracy, and optimize work processes through continuous learning and optimization, adapting to workers' individual preferences and improving workers' inefficient habits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112307177B_ABST
    Figure CN112307177B_ABST
Patent Text Reader

Abstract

In the example computer implementation, unstructured interactions between an unstructured chatbot and multiple users are recorded. A process flow model is generated based on the recorded unstructured interactions. The chatbot then presents instructions based on the process flow model to the users in real time.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0001] The present technology relates to process flow. More specifically, the technology relates to optimizing the sequence of process flow. Summary of the invention

[0002] According to the embodiments described herein, the system may include a processor to record unstructured interactions between an unstructured conversational robot and multiple users. The processor may further generate a process flow model based on the recorded unstructured interactions. The processor may also display instructions to the user in real time based on the process flow model through the conversational robot.

[0003] According to another embodiment described herein, a computer-implemented method may include recording, by a processor, unstructured interactions between an unstructured conversational robot and a plurality of users. The computer-implemented method may further include generating, by the processor, a process flow model based on the recorded unstructured interactions. The computer-implemented method may further include: presenting instructions to the user in real time based on the process flow model via the conversational robot.

[0004] According to another embodiment described herein, a computer program product for generating a process flow model may include a computer-readable storage medium with program code embedded therein. The computer-readable storage medium itself is not a transient signal. The program code can be executed by a processor to cause the processor to record unstructured interactions between an unstructured conversational robot and multiple users. The program code can also cause the processor to generate a process flow model based on the recorded unstructured interactions. The program code can also cause the processor to present instructions to the user in real time by the conversational robot based on the conversation flow model. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Figure 1 is a block diagram of an example system for generating a process flow model based on recorded unstructured interactions;

[0006] Figure 2 is a process flow diagram of an example process that can generate a process flow model based on recorded unstructured interactions;

[0007] Figure 3 is a process flow diagram of an example method by which a process flow model can be generated based on recorded unstructured interactions;

[0008] Figure 4 is a block diagram of an example computing device that can generate a process flow model based on recorded unstructured interactions;

[0009] Figure 5 is a flow chart of an example cloud computing environment according to embodiments described herein;

[0010] Figure 6is a flow chart of an example abstract model layer according to embodiments described herein; and

[0011] Figure 7 An example tangible, non-transitory computer-readable medium that can generate a process flow model based on recorded unstructured interactions. DETAILED DESCRIPTION

[0012] Workers in different environments across different industries may be involved in many processes every day. These processes are often characterized as routine and repetitive sequences of micro-operations that are performed in a predetermined order using paper forms or electronic spreadsheets. An example of such a process is an inspection workflow, where users perform a series of tests and checks on system conditions, record status and sensor readings, and apply maintenance routines to system components.

[0013] However, the specific order or flow (referred to herein as process flow) for executing these processes may be subject to artificial constraints of the interface used to execute the process flow. For example, the checklists used to execute these processes are designed and constructed by subject matter experts in the relevant fields and may be constructed based on either a logical hierarchical order or an order that aggregates data in a way that allows supervisors to review more easily. These forms can then be directly converted into some form of screen-based interface. However, the logical order imposed by this process may be inconsistent with, or even contradictory to, the natural order of the business process. For example, the natural order may be an optimal order in which the worker can execute the natural order if the worker is not constrained to the order of the form. In some examples, the natural order may reflect the physical or practical arrangement of the subject, but may also be affected by the worker's proficiency in a particular task, the worker's habits and convenience, and other objective and subjective factors. Therefore, workers may have to comply with a non-natural order to complete the process. As a result, their performance may not be optimal due to the need to bridge the gap between the guide procedure and the actual procedure that may be most effective for them. For example, workers can use the form as is and compromise their efficiency, or perform the process in a natural order, but compromise the accuracy of the task.

[0014] According to an embodiment of the present disclosure, an unstructured conversational robot can be used to generate a process flow model based on recorded unstructured interactions. The example system includes a processor for recording unstructured interactions between an unstructured conversational robot and multiple users. For example, unstructured interactions may not have a specific order. Therefore, unstructured interactions may not follow a specified conversational pattern or structure, so the user may not follow the guided path led by the conversational robot. The processor can generate a process flow model based on the recorded unstructured interactions. The processor can also display instructions to the user in real time based on the process flow model through the conversational robot. In some examples, the processor can modify the process flow model based on the unstructured interaction with the user to adapt to the user's preferences. Therefore, an embodiment of the present disclosure enables the generation of a process flow model customized for the personal preferences of a specific worker or group of workers. In addition, by using unstructured conversational robot data, the generated process flow model can be customized to a specific process by the actual group of workers engaged in the task. Therefore, this technology can be used to generate a process flow model that maintains the accuracy of the process when it is executed while improving efficiency. In some examples, the system can even use new process flow models to continuously learn to optimize the efficiency of the work process. The system can thus enable the generation of recommendations to workers with a single preference order to change their habits and examine alternative commands that are popular with a broad base of workers and relatively superior to their own, thereby also serving as an educational tool. In this way, the technology can enable conversational robots to effectively identify and gradually change inefficient habits of a group of workers while maintaining accuracy in the process flow.

[0015] Reference now Figure 1 , which shows an example system for generating a process flow model based on recorded unstructured interactions. The example system 100 can be used to implement Figure 2 and Figure 3 The system 100 may also be used to Figure 4 The computing device 400 or Figure 7 The computer readable medium 700 is implemented.

[0016] Figure 1 The system 100 includes a plurality of users 102 shown interacting with an unstructured conversational robot 104. For example, the unstructured conversational robot may be implemented on a plurality of mobile devices. The mobile device may include a speech-based personal assistant that provides unstructured feedback. The system 100 includes an interaction recorder 106 to record interactions between the users 102 and the unstructured conversational robot 104. As an example, the interaction recorder 106 may be a subunit of the unstructured conversational robot 104. The system 100 includes a process flow model generator and updater 108. For example, the process flow model generator and updater 108 may be implemented on a service (e.g., a cloud server).

[0017] exist Figure 1 In the example of , many users 102 can participate in performing a particular process. For example, the process can include a series of tests and checks on the system condition, and record the status and sensor readings, and apply maintenance routines on system components. In various examples, the unstructured conversational robot 104 can include a voice-based interface. For example, a voice-based interface can allow a user to ignore any artificial barriers imposed by other traditional interfaces and perform the process in the most efficient manner for the user. The system 100 can therefore allow users to complete the process using natural language and natural sequence of voice interactions. The sequence of the process is unstructured and allows the user to complete the process in a non-directed manner.

[0018] Still reference Figure 1 , the system 100 can record the information entered by the user in the order in which the user performs each process. Recording user interactions can allow the system to learn from the data and develop a general model that describes the optimal order of related business processes. The system will further understand the personal preferred order of each worker and apply this personalization to the general model to create a separate model for each worker and each business process type. The interaction recorder 106 can be any logging device used to perform the process, which allows the project, time and location to be recorded when the process is performed. As an example, a worker can use a mobile handheld device with a microphone and speaker and an Internet connection. The mobile device may include a voice interface application that allows the worker to perform the process. Therefore, in various examples, the collection of data is based on an online voice-enabled tracking and recording device, such as a personal assistant running on a mobile or radio handheld device. In some examples, the logging device records the workflow process and transmits the log data online to a central database. In some examples, after the process ends, the logging device can transmit the log data offline to a central database.

[0019] The process flow generator and updater 108 may include a learning algorithm that processes the data in the database to classify the best path or the best order to execute the process, thereby generating an optimal recommended order. In various examples, the system can learn an optimized model as recorded events accumulate over time. For example, the recorded events can describe the performance of each process item and the timing and location data associated with each item. The timing and location data can be collected by an end-user input device. In various examples, the optimization model can include a statistical analysis of the correlation between the traversal path of the session (indicated by the sequence of the session nodes) and the successful or efficient completion of the process flow. This analysis can highlight the best paths and trace their common properties to generate the best recommended order.

[0020] In some examples, the best order of recommendations can be obtained using various machine learning models. For example, a system can be used that includes a random forest model that takes as input multiple attributes describing the steps in a session in the order in which they are performed. In various examples, the random forest model also receives performance metrics such as the quality, speed, and efficiency of completing the task. Over time, the random forest model can learn an ideal set of attributes and their order to achieve the best results.

[0021] After learning the best model for each business process type, the system 100 can generate a process flow model based on the learned model, which can be used for subsequent processes. Even with new process flow models, the system 100 can continue to learn to optimize the efficiency of the workflow. In various examples, the system 100 can recommend workers with personal preference sequences to change their habits and enable workers to check alternative sequences that are beneficial to the general group of workers and may be better than their own. Therefore, the system 100 can improve the efficiency of workers by feeding the learned sequence back into the various logging devices used for subsequent workflows.

[0022] In some examples, any individual deviations from the generated process flow model are recorded as individual preferences and analyzed to determine cluster behavior and quantify whether these new routes or sequences are better than the currently recommended process flow model's options. If the new route or sequence is improved, the system 100 can add the new improved route or sequence to the general model and update the process flow model accordingly. The resulting processes and sequences are organized based on the actual sequence of the processes and performance information of many workflow instances, and are most suitable for the types of tasks performed by the worker. In various examples, with respect to the original default order of the processes (which may be structured more hierarchically to suit the supervisor's view), the system 100 can still convert the new order of items back to the original logical default order to suit the user's perspective and preferences, depending on the specific application.

[0023] It should be understood that Figure 1 The block diagram is not intended to indicate that system 100 will include Figure 1 Instead, system 100 may include Figure 1 Fewer or additional components not shown (e.g., additional client devices or additional resource servers, etc.).

[0024] Figure 2 is a schematic diagram of an example process by which a process flow model may be generated based on recorded unstructured interactions. Process 200 may be implemented using any suitable computing device, such as Figure 4 The computing device 400, and referring to Figure 1For example, the method described below may be performed by Figure 4 and Figure 7 The processor 402 or the processor 702 may be implemented.

[0025] Figure 2 A set of different users 202 are included that interact with a process flow through an unstructured conversational robot using voice. The different users 202 include users 204 that follow the default structure of the process flow. For example, when the user 204 is presented to the staff 204, the user 204 may follow the process on the form verbatim, or follow verbal commands or prompts, or visual commands or prompts. The different users 202 include users 206 that partially follow the default structure of the process flow. The different users 202 also include free-flow users 208 that do not follow the default structure of the process flow. For example, such free-flow users 208 can completely deviate from the sequence of the default structure of the process flow.

[0026] At block 210, the interactions of the user 202 are recorded. For example, unstructured interactions may be recorded and sent to a central database.

[0027] At block 212, the model generator generates a process flow model based on the recorded interactions and analyzes the deviations of each user from the process flow model. For example, the model generator may determine whether any deviations of each user from the process flow model exceed the efficiency of the process flow model. For example, the efficiency may be measured using the time taken to execute the process flow. In some examples, a secondary indicator of efficiency may be the quality of completion as measured by an external observer. Additionally, in some examples, user frustration in the process may be measured by surveys, physical distance traversed in the process, and other frustration indicators, if applicable.

[0028] At block 214, the system provides the user with a process flow model having each user's personal preferences applied. For example, the generated process flow model can be used as a generic process flow model that a worker can interact with through an unstructured conversational bot. In some examples, the order or sequence of the generic process flow model can be modified according to the user's personal preferences and presented to the user in a single process flow model.

[0029] At block 216, the system iteratively updates the process flow model based on the additional recorded interactions with the process flow model. For example, the system can identify clustered behaviors in the additional recorded unstructured interactions and, in response to detecting that the clustered behaviors contain improved routes or sequences, update the process flow model based on the clustered behaviors. In this way, the process flow model can be continuously improved over time based on the process types and preferences of the workers performing the processes. Thus, efficiency can be improved while maintaining accuracy in process execution.

[0030] Figure 2The schematic diagram is not intended to indicate that the operations of process 200 are to be performed in any particular order, or that all operations of process 200 are included in every case. Furthermore, process 200 may include any suitable number of additional operations.

[0031] Figure 3 is a flowchart of an example process that can generate a process flow model based on recorded unstructured interactions. The method 300 can be implemented with any suitable computing device, such as Figure 4 The computing device 400 and referring to Figure 1 For example, the method described below can be used by Figure 4 and Figure 7 The processor 402 or the processor 702 is implemented.

[0032] In block 302, unstructured interactions between an unstructured conversational robot and a plurality of users are recorded. In some examples, the unstructured interactions are recorded and sent to a database. For example, Figure 1 As discussed in , recorded interactions can be sent to a central database either offline or online.

[0033] In block 304, a process flow model is generated based on the recorded unstructured interactions. For example, a generic process flow model may be generated for a particular type of process flow based on the interactions of users executing the particular type of process flow. In some examples, the generated process flow model may include comparing paths of execution of multiple users and selecting a path that is more efficient than other paths.

[0034] At box 306, instructions based on the process flow model are presented to the user in real time via a conversational robot. In various examples, views of the process flow model can be generated and presented from different angles. In some examples, a top-down model view or a ground view can be generated and presented. The top-down model view is a view that describes the arrangement of a specific logical hierarchy of data. The top-down model allows recursively drilling down from the top data element to its auxiliary data element. Optionally, the top-down model allows low-level data elements to be folded by grouping them into high-order data elements again and again. In various examples, the top-down model view can be presented to the supervisor. The top-down model view can be generated based on the default process flow model. In various examples, the bottom view can be generated based on the process flow model. The bottom view is a view that depicts the actual arrangement of data elements, which is reflected by the person performing the hands-on operation. The bottom view does not have to follow any logical hierarchy, but is consistent with the natural traversal order, because the individual and the environment are most likely or suitable for executing the process. For example, the bottom view can be presented to the user.

[0035] In box 308, deviations from the process flow model are recorded, and the process flow model is iteratively updated based on deviations that are more valid than other deviations of the recorded deviations. In some examples, individual deviations from the process flow model can be recorded for each of a plurality of users, and an individual model can be generated for each user based on the recorded individual deviations of each of the plurality of users. In various examples, in response to detecting that the cluster behavior includes an improved route or sequence, cluster behavior is identified in additional recorded unstructured interactions, and the process flow model is updated based on the cluster behavior. As used herein, cluster behavior refers to similar or identical patterns in an entire process flow or a portion of a process flow. In some examples, these patterns can be conversation steps of a series of process flow actions that occur in a certain order.

[0036] Figure 3 The process flow diagram of method 300 is not intended to indicate that the operations of method 300 will be performed in any particular order, or that all operations of method 300 will be included in every case. In addition, method 300 may include any suitable number of additional operations.

[0037] Figure 4 4 is a block diagram of an example computing device that can generate a process flow model based on recorded unstructured interactions. Computing device 400 can be, for example, a server, a desktop computer, a laptop computer, a tablet computer, or a mobile device such as a smart phone. In some examples, computing device 400 can be a cloud computing node. Computing device 400 can be described in the general context of computer system executable instructions (e.g., program modules) executed by a computer system. Typically, program modules can include routines, programs, objects, components, logic, data structures, etc. that perform specific tasks or implement specific abstract data types. Computing device 400 can be practiced in a distributed cloud computing environment, in which tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located in local and remote computer system storage media including memory storage devices.

[0038] The computing device 400 may include a processor 402 for executing stored instructions and a memory device 404 for providing temporary storage space for the operation of the instructions during operation. The processor may be a single-core processor, a multi-core processor, a computing cluster, or any number of other configurations. The memory 404 may include random access memory (RAM), read-only memory, flash memory, or any other suitable memory system.

[0039] Processor 402 may be connected via system interconnect 406 (e.g., and PCI The computing device 400 may be connected to an input / output (I / O) device interface 408 suitable for connecting the computing device 400 to one or more I / O devices 410. The input / output devices 410 may include, for example, a keyboard and a pointer device, wherein the pointer device may include a touch pad or a touch screen, etc. The I / O devices 410 may be built-in components of the computing device 400, or may be devices externally connected to the computing device 400.

[0040] Processor 402 may also be connected to a display interface 412 adapted to connect computing device 400 to display device 414 via system interconnect 406. Display device 414 may include a display screen as a built-in component of computing device 400. Display device 414 may also include a computer monitor, television, or projector, etc., externally connected to computing device 400. In addition, network interface controller (NIC) 416 may be adapted to connect computing device 400 to network 418 via system interconnect 406. In some embodiments, NIC 416 may use any suitable interface (e.g., Internet Small Computer System Interface, etc.) or protocol to send data. Network 418 may be a cellular network, a wireless network, a wide area network (WAN), a local area network (LAN), or the Internet, etc. External computing device 420 may be connected to computing device 400 via network 418. In some examples, external computing device 420 may be an external network server 420. In some examples, external computing device 420 may be a cloud computing node.

[0041] The processor 402 may also be connected to a memory device 422 via a system interconnect 406, which may include a hard drive, an optical drive, a USB flash drive, a drive array, or any combination thereof. In some examples, the memory device may include an interaction recorder module 424, a model generator module 426, a renderer module 428, and a model updater module 430. The interaction recorder module 424 may record unstructured interactions between an unstructured conversational robot and multiple users. For example, the interaction recorder module 424 may be a voice-based interface on a mobile device. In some examples, the data contained in the recorded unstructured interactions include location data and timestamps. The interaction recorder module 424 may also record a single deviation from a process flow model for each of the multiple users. The model generation module 426 may generate a process flow model based on the recorded unstructured interactions. In some examples, the model generator module 426 may generate a single model for each user based on the recorded single deviation. The renderer module 428 may present instructions to the user in real time based on the process flow model via the conversational robot. In various examples, the renderer module 428 may generate and present views of the process flow model from different angles. For example, the views may include a bottom-level view and a hierarchical top-down view.The model updater module 430 may iteratively update the process flow model based on deviations that are more valid than other ones of the recorded deviations.

[0042] The memory device 422 may also include a log database 432 to store recorded interactions with various users. For example, the log database 432 may store location data, time, and sequence of interactions with users. For example, the log database 432 may store location data, interaction time and duration, interaction content including user input and system output, system interpretation of the interaction, and resulting actions of the interaction. Sequence order and additional information may also be inferred from the recorded data and may also be stored in the log database 432.

[0043] It should be understood that Figure 4 The block diagram is not intended to indicate that computing device 400 will include Figure 4 Instead, computing device 400 may include Figure 4402). In some embodiments, the functions of the interaction recorder module 424, the model generator module 426, the renderer module 428, and the model updater module 430 may be implemented in part or in whole in hardware and / or in the processor 402. For example, the functions may be implemented using a dedicated integrated circuit, logic implemented in an embedded controller, or logic implemented in the processor 402, etc. In some embodiments, the functions of the interaction recorder module 424, the model generator module 426, the renderer module 428, and the model updater module 430 may be implemented using logic, wherein the logic referred to herein may include any appropriate hardware (e.g., a processor, etc.), software (e.g., an application), firmware, or any appropriate combination of hardware, software, and firmware.

[0044] In some cases, the techniques described herein can be implemented in a cloud computing environment. Figure 5-6 As discussed in more detail, a computing device configured to generate a process flow model based on recorded unstructured interactions can be implemented in a cloud computing environment. First, it should be understood that although the present disclosure may include a detailed description of cloud computing, the implementation of the technical solutions recorded therein is not limited to a cloud computing environment, but can be implemented in conjunction with any other type of computing environment now known or later developed.

[0045] Cloud computing is a service delivery model for convenient, on-demand network access to a shared pool of configurable computing resources. Configurable computing resources are resources that can be quickly deployed and released with minimal management cost or interaction with the service provider, such as networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services. This cloud model can include at least five characteristics, at least three service models, and at least four deployment models.

[0046] Features include:

[0047] On-demand self-service: Cloud consumers can unilaterally and automatically deploy computing capabilities such as server time and network storage on demand without human interaction with the service provider.

[0048] Broad network access: Computing power can be accessed over the network through standard mechanisms that facilitate the use of the cloud through different types of thin-client or thick-client platforms (e.g., mobile phones, laptops, personal digital assistants (PDAs)).

[0049] Resource pool: The computing resources of the provider are grouped into resource pools and serve multiple consumers through a multi-tenant model, where different physical and virtual resources are dynamically allocated and reallocated on demand. Generally, consumers cannot control or even know the exact location of the provided resources, but can specify the location (such as country, state or data center) at a higher level of abstraction, so it is location-independent.

[0050] Rapid elasticity: The ability to quickly and elastically (sometimes automatically) deploy computing power to scale up quickly, and quickly release it to scale down quickly. To consumers, the computing power available for deployment often appears to be unlimited, and any amount of computing power can be accessed at any time.

[0051] Measurable services: Cloud systems automatically control and optimize resource usage by leveraging metering capabilities at a level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported, providing transparency to both service providers and consumers.

[0052] The service model is as follows:

[0053] Software as a Service (SaaS): The capability provided to consumers is to use the provider's applications running on a cloud infrastructure. Applications can be accessed from a variety of client devices through a thin client interface such as a web browser (e.g., web-based email). Aside from limited user-specific application configuration settings, consumers neither manage nor control the underlying cloud infrastructure including networks, servers, operating systems, storage, or even individual application capabilities.

[0054] Platform as a Service (PaaS): The capability provided to consumers is to deploy applications created or acquired by consumers on the cloud infrastructure, which are created using programming languages ​​and tools supported by the provider. Consumers neither manage nor control the underlying cloud infrastructure including networks, servers, operating systems or storage, but have control over the applications they deploy and may also have control over the configuration of the application hosting environment.

[0055] Infrastructure as a Service (IaaS): The capabilities provided to consumers are processing, storage, network, and other basic computing resources on which consumers can deploy and run arbitrary software including operating systems and applications. Consumers neither manage nor control the underlying cloud infrastructure, but have control over the operating system, storage, and applications they deploy, and may have limited control over selected network components (such as host firewalls).

[0056] The deployment model is as follows:

[0057] Private Cloud: Cloud infrastructure is run solely for an organization. The cloud infrastructure can be managed by the organization or a third party and can exist inside or outside the organization.

[0058] Community Cloud: A cloud infrastructure is shared by several organizations and supports a specific community with common interests (e.g., mission, security requirements, policies, and compliance considerations). A community cloud can be managed by multiple organizations within the community or by a third party and can exist inside or outside the community.

[0059] Public cloud: Cloud infrastructure is provided to the public or to large industry groups and is owned by an organization that sells cloud services.

[0060] Hybrid cloud: A cloud infrastructure consisting of two or more clouds (private, community or public) in a deployment model that remain distinct entities but are bound together by standardized or proprietary technologies (such as cloud burst sharing for load balancing between clouds) that enable data and application portability.

[0061] The cloud computing environment is service-oriented, with characteristics centered on statelessness, low coupling, modularity, and semantic interoperability. The core of cloud computing is the infrastructure that includes a network of interconnected nodes.

[0062] Reference now Figure 5 , in which an exemplary cloud computing environment 500 is shown. As shown, the cloud computing environment 500 includes one or more cloud computing nodes 502 with which a local computing device used by a cloud computing consumer can communicate, and the local computing device can be, for example, a personal digital assistant (PDA) or a mobile phone 504A, a desktop computer 504B, a laptop computer 504C and / or an automobile computer system 504N. The cloud computing nodes 502 can communicate with each other. The cloud computing nodes can be physically or virtually grouped in one or more networks including but not limited to private clouds, community clouds, public clouds or hybrid clouds, or a combination thereof as described above (not shown in the figure). In this way, cloud consumers can request infrastructure as a service (IaaS), platform as a service (PaaS) and / or software as a service (SaaS) provided by the cloud computing environment 500 without having to maintain resources on local computing devices. It should be understood that Figure 5 The various types of computing devices 504A-N shown are merely illustrative, and cloud computing node 502 and cloud computing environment 500 can communicate with any type of computing device on any type of network and / or network addressable connection (eg, using a web browser).

[0063] Reference now Figure 6 , which shows a cloud computing environment 500 ( Figure 5 ) provides a set of functional abstraction layers. First of all, it should be understood that Figure 6The components, layers, and functions shown are only exemplary and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the following layers and corresponding functions are provided:

[0064] The hardware and software layer 600 includes hardware and software components. Examples of hardware components include mainframes, in one example, system. In an example In the system, a server based on RISC (Reduced Instruction Set Computer) architecture; System; IBM systems; storage devices; networks and network components. Examples of software components include network application server software, in one example IBM Application server software; and database software, in one example IBM Database software. (IBM, zSeries, pSeries, xSeries, BladeCenter, WebSphere and DB2 are trademarks of International Business Machines Corporation, registered in many jurisdictions worldwide).

[0065] The virtualization layer 602 provides an abstraction layer that can provide examples of the following virtual entities: virtual servers, virtual storage, virtual networks (including virtual private networks), virtual applications and operating systems, and virtual clients. In one example, the management layer 604 can provide the following functions: Resource provisioning function: providing dynamic acquisition of computing resources and other resources for performing tasks in a cloud computing environment; Metering and pricing function: tracking the cost of resource usage within the cloud computing environment and providing bills and invoices for this purpose. In one example, the resources can include application software licenses. Security function: providing identity authentication for cloud consumers and tasks, and providing protection for data and other resources. User portal function: providing access to the cloud computing environment for consumers and system administrators. Service level management function: providing allocation and management of cloud computing resources to meet the required service levels. Service level agreement (SLA) planning and fulfillment function: providing pre-arrangement and provision for future demand for cloud computing resources predicted according to the SLA.

[0066] The workload layer 606 provides examples of functions that may be implemented in a cloud computing environment. In this layer, examples of workloads or functions that may be provided include: mapping and navigation; software development and lifecycle management; virtual classroom teaching provision; data analysis processing; transaction processing; and process flow modeling.

[0067] At any possible level of technical detail combination, the present technology may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0068] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer 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 portable 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 a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0069] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0070] The computer program instructions for performing the operation of the present technology can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and traditional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can 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 can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions, thereby realizing various aspects of the present technology.

[0071] Various aspects of the present technology are described herein with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present technology. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0072] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0073] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0074] Reference now Figure 7 , which depicts a block diagram of an exemplary tangible, non-transitory computer-readable medium 700 that can generate a process flow model based on recorded unstructured interactions. A processor 702 can access the tangible, non-transitory computer-readable medium 700 via a computer interconnect 704. In addition, the tangible, non-transitory computer-readable medium 700 can include instructions to direct the processor 702 to perform Figure 3 The operation code of method 300 is as follows.

[0075] like Figure 7 As shown, various software components discussed herein may be stored on a tangible, non-transitory computer-readable medium 700. For example, the interaction recorder module 706 includes code for recording unstructured interactions between a conversational robot and a plurality of users. The interaction recorder module 706 also includes code for recording deviations from a process flow model. In some examples, the interaction recorder module 706 includes code for recording individual deviations from a process flow model for each of a plurality of users. The model generator module 708 includes code for generating a process flow model based on the recorded unstructured interactions. The model generator module 708 includes code for generating a process flow model for a particular type of process flow based on the interactions of users executing a particular type of process flow. For example, the model generator module 708 may include code for comparing the execution paths of a plurality of users and selecting a path that is more effective than other paths. The model generator module 708 also includes code for generating individual models for each user based on the recorded individual deviations. The renderer module 710 includes code for presenting instructions to a user in real time via a conversational robot based on the process flow model. The renderer module 710 also includes code for generating and presenting views of the process flow model from different perspectives. The model updater module 712 includes code for iteratively updating the process flow model based on deviations that are more valid than other deviations of the recorded deviations. It should be understood that the tangible, non-transitory computer readable medium 700 may include the following, depending on the particular application: Figure 7 Any number of additional software components not shown.

[0076] The flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present technology. In this regard, each box in the flowchart or block diagram may represent a module, a program segment or a portion of an instruction, and the module, a program segment or a portion of an instruction contains one or more executable instructions for implementing the specified logical functions. In some alternative implementations, the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified functions or actions, or can be implemented with a combination of dedicated hardware and computer instructions. It should be understood that, depending on the specific application, the tangible, non-temporary computer-readable medium 700 may include Figure 7 Any number of additional software components not shown.

[0077] Embodiments of the present technology have been described above, and the above description is exemplary, not exhaustive, and is not 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 choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A system comprising a processor to: recording unstructured interactions between an unstructured conversational robot on a mobile device and a plurality of users to generate recorded events, the recorded events including performance of each process item and a timestamp for each process item and physical location data of the mobile device associated with each process item; learning a recommended sequence of the processes via a machine learning model that receives as input the attributes of the recorded events, wherein the recommended sequence includes a set of selected attributes and an order of execution of the set of selected attributes; generating a process flow model of the process based on the machine learning model; as well as Instructions are presented to a user via the conversational robot in real time based on the process flow model.

2. The system of claim 1, wherein: The conversational bot includes a voice-based interface on the mobile device.

3. The system of claim 1, wherein: The processor will generate and present views of the process flow model from different perspectives.

4. The system of claim 3, wherein: The views include bottom-level views and hierarchical top-down views.

5. The system of claim 1, wherein: The data included in the recorded unstructured interactions includes location data and timestamps.

6. The system of claim 1, wherein: The processor records individual deviations from the process flow model for each of the plurality of users and generates an individual model for each of the users based on the recorded individual deviations.

7. The system of claim 1, wherein: The processor will record deviations from the process flow model and iteratively update the process flow model based on deviations that are more valid than other ones of the recorded deviations.

8. A computer-implemented method comprising: recording, by a processor, unstructured interactions between an unstructured conversational robot on a mobile device and a plurality of users to generate recorded events, the recorded events including performance of each process item and a timestamp for each process item and physical location data of the mobile device associated with each process item; learning a recommended sequence of the processes via a machine learning model that receives as input the attributes of the recorded events, wherein the recommended sequence includes a set of selected attributes and an order of execution of the set of selected attributes; generating, via a processor, a process flow model of the process based on the machine learning model; and Instructions are presented to a user via the conversational robot in real time based on the process flow model.

9. The computer-implemented method of claim 8, further comprising: Deviations from the process flow model are recorded, and the process flow model is iteratively updated based on deviations that are more valid than other ones of the recorded deviations.

10. The computer-implemented method of claim 8, comprising: An individual deviation from the process flow model is recorded for each of the plurality of users, and an individual model is generated for each user based on the recorded individual deviation for each of the plurality of users.

11. The computer-implemented method of claim 8, wherein generating the process flow model comprises generating a generic process flow model for a specific type of process flow based on interactions of users executing the specific type of process flow.

12. The computer-implemented method of claim 8, wherein generating the process flow model comprises comparing paths of execution of the plurality of users and selecting a path that is more efficient than other paths.

13. The computer-implemented method of claim 8, comprising: Views of the process flow model are generated and presented from different perspectives.

14. The computer-implemented method of claim 8, further comprising identifying cluster behaviors in the additionally recorded unstructured interactions in response to detecting that the cluster behaviors include a modified route or sequence, and updating the process flow model based on the cluster behaviors.

15. A computer program product for generating a process flow model, the computer program product comprising a computer-readable storage medium having a program code embedded therein, the program code being executable by a processor to cause the processor to perform the steps of the method of any one of claims 8 to 14.

16. A system comprising modules for performing the steps of the method of any one of claims 8-14.