# US 11,121,986 B2 · Generating process flow models using unstructure conversation bots > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,121,986 B2 - Document ID: US11121986B2 - Status: Granted - Kind: B2 - Application number: 16/528,681 - Filed: 2019-08-01 - Published: 2021-02-04 - Granted: 2021-09-14 - Earliest claimed: 2019-08-01 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Roy Abitbol; Eliezer Wasserkrug; Harold Jeffrey Ship; Jonathan Bnayahu - Web page: https://patentgrep.com/patent/US11121986B2 ## CPC - H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages - G06F 16/335: Filtering based on additional data, e.g. user or group profiles (filtering in web context G06F16/9535, G06F16/9536) - G06F 18/23: Clustering techniques - G10L 13/02: Methods for producing synthetic speech; Speech synthesisers - G10L 13/08: Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination - H04L 51/222: using geographical location information, e.g. messages transmitted or received in proximity of a certain spot or area - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract In an example computer-implemented method, unstructured interactions between an unstructured conversation bot and a plurality of users are logged. A process flow model is generated based on the logged unstructured interactions. Instructions based on the process flow model are presented to a user in real time via the conversation bot. ## Claims ### Claim 1 A system, comprising a processor to: log unstructured interactions between an unstructured conversation bot on a mobile device and a plurality of users to generate logged events comprising a performance of each process item along with a timestamp of each process item and physical location data of the mobile device associated with each process item; learn, via a machine learning model that receives the logged events as input attributes, a recommended order for a process, wherein the recommended order comprises a set of selected attributes and an order of execution for the set of selected attributes; generate a process flow model for the process based on the machine learning model; and present, via the conversation bot, instructions to a user in real time based on the process flow model. ### Claim 2 (depends on 1) The system of claim 1, wherein the conversation bot comprises a voice based interface on the mobile device. ### Claim 3 (depends on 1) The system of claim 1, wherein the processor is to generate and present views of the process flow model from different perspectives. ### Claim 4 (depends on 3) The system of claim 3, wherein the views comprise a ground level view and a hierarchical top down view. ### Claim 5 (depends on 1) The system of claim 1, wherein data included in the logged unstructured interactions comprises location data and time stamps. ### Claim 6 (depends on 1) The system of claim 1, wherein the processor is to log individual deviations from the process flow model for each of the plurality of users and generate an individual model for each of the users based on the logged individual deviations. ### Claim 7 (depends on 1) The system of claim 1, wherein the processor is to log deviations from the process flow model and iteratively update the process flow model based on a deviation that is more efficient than other deviations of the logged deviations. ### Claim 8 A computer-implemented method, comprising: logging, via a processor, unstructured interactions between an unstructured conversation bot on a mobile device and a plurality of users to generate logged events comprising a performance of each process item along with a timestamp of each process item and physical location data of the mobile device associated with each process item; learning, via a machine learning model that receives the logged events as input attributes, a recommended order for a process, wherein the recommended order comprises a set of selected attributes and an order of execution for the set of selected attributes; generating, via the processor, a process flow model for the process based on the machine learning model; and presenting, via the conversation bot, instructions to a user in real time based on the process flow model. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, further comprising logging deviations from the process flow model and iteratively updating the process flow model based on a deviation that is more efficient than other deviations of the logged deviations. ### Claim 10 (depends on 8) The computer-implemented method of claim 8, comprising logging individual deviations from the process flow model for each of the plurality of users and generating an individual model for each of the users based on the logged individual deviations for each of the plurality of users. ### Claim 11 (depends on 8) The computer-implemented method of claim 8, wherein generating the process flow model comprises generating a generic process flow model for a particular type of process flow based on interactions of users performing the particular type of process flow. ### Claim 12 (depends on 8) 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. ### Claim 13 (depends on 8) The computer-implemented method of claim 8, comprising generating and presenting views of the process flow model from different perspectives. ### Claim 14 (depends on 8) The computer-implemented method of claim 8, further comprising identifying clustered behavior in additional logged unstructured interactions and updating the process flow model based on the clustered behavior in response to detecting that the clustered behavior comprises an improved route or order. ### Claim 15 A computer program product for generating process flow models, the computer program product comprising a computer-readable storage medium having program code embodied therewith, wherein the computer-readable storage medium is not a transitory signal per se, the program code executable by a processor to cause the processor to: log unstructured interactions between an unstructured conversation bot on a mobile device and a plurality of users to generate logged events comprising a performance of each process item along with a timestamp of each process item and physical location data of the mobile device associated with each process item; learn, via a machine learning model that receives the logged events as input attributes, a recommended order for a process, wherein the recommended order comprises a set of selected attributes and an order of execution for the set of selected attributes; generate a process flow model for the process based on the machine learning model; and present, via the conversation bot, instructions to a user in real time based on the process flow model. ### Claim 16 (depends on 15) The computer program product of claim 15, further comprising program code executable by the processor to log deviations from the process flow model and iteratively update the process flow model based on a deviation that is more efficient than other deviations of the logged deviations. ### Claim 17 (depends on 15) The computer program product of claim 15, further comprising program code executable by the processor to log individual deviations from the process flow model for each of the plurality of users and generate an individual model for each of the users based on the logged individual deviations. ### Claim 18 (depends on 15) The computer program product of claim 15, further comprising program code executable by the processor to generate a generic process flow model for a particular type of process flow based on interactions of users performing the particular type of process flow. ### Claim 19 (depends on 15) The computer program product of claim 15, further comprising program code executable by the processor to compare paths of execution of the plurality of users and selecting a path that is more efficient than other paths. ### Claim 20 (depends on 15) The computer program product of claim 15, further comprising program code executable by the processor to generate and present views of the process flow model from different perspectives.