# US 2021/0241142 A1 · Virtual operation assistant > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241142 A1 - Document ID: US20210241142A1 - Status: Published application - Kind: A1 - Application number: 17/148,707 - Filed: 2021-01-14 - Published: 2021-08-05 - Earliest claimed: 2020-01-30 - Applicants: ExxonMobil Research and Engineering Company - Inventors: Apostolos T. Georgiou; Kiran R. Sheth; Onur Onel - Web page: https://patentgrep.com/patent/US20210241142A1 ## CPC - G06N 5/04: Inference or reasoning models - G06F 16/24522: {Translation of natural language queries to structured queries} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/0475: Generative networks - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06N 3/092: Reinforcement learning - G06N 3/094: Adversarial learning - G06N 20/00: Machine learning - G16C 20/70: Machine learning, data mining or chemometrics - G06N 5/041: {Abduction} - G16C 20/10: Analysis or design of chemical reactions, syntheses or processes - G16C 20/90: Programming languages; Computing architectures; Database systems; Data warehousing - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE ## Abstract A virtual operation assistant for use in a processing/manufacturing facility (e.g., processing/manufacturing facility) may be an autonomous system that interfaces with a user. The virtual operation assistant may collect real-time and/or historical data about processes and/or hardware in a processing/manufacturing facility, analyze the data, provide reporting and/or recommendations based on the data, execute commands relating to the operational parameters of the processes and/or hardware, and any combination thereof. ## Claims ### Claim 1 A method comprising: communicating a question relating to a processing/manufacturing facility to a virtual operation assistant; parsing the question into keywords and phrases (KWP) using a KWP model; identifying one or more queries and/or adaptive analytical models (queries/models) based on the KWP, wherein the queries/models are configured to answer the question or portions of the question; executing the queries/models to yield data; formulating the data into an answer using the virtual operation assistant; and reporting the answer. ### Claim 2 (depends on 1) The method of claim 1, wherein one or more of the adaptive analytical model of the queries/models are configured to collect additional data relating to the answer, the question, and/or the portions of the question but not required for formulating the answer, and wherein the method further comprises reporting the additional data with answer. ### Claim 3 (depends on 1) The method of claim 1, wherein one or more of the adaptive analytical model of the queries/models are configured to identify a prompt for additional data relating to the question and/or the answer, and wherein the method further comprises reporting the prompt for additional data with answer. ### Claim 4 (depends on 1) The method of claim 1, wherein one or more of the adaptive analytical model of the queries/models are configured to identify one or more recommendations for changes to operational parameters of the processing/manufacturing facility in relation to the question and/or answer, and wherein the method further comprises reporting the recommendations with answer. ### Claim 5 (depends on 1) The method of claim 1, wherein the adaptive analytical models are based on neural networks, decision trees/random forest methods, kernal methods, reinforcement learning methods, and any ensemble thereof. ### Claim 6 (depends on 1) The method of claim 1, wherein the question relates to a status of a portion of the processing/manufacturing facility. ### Claim 7 (depends on 1) The method of claim 1, wherein the question is a complex question. ### Claim 8 A method comprising: communicating a command relating to a processing/manufacturing facility to a virtual operation assistant; parsing the command into keywords and phrases (KWP) using a KWP model; identifying one or more queries and/or adaptive analytical models (queries/models) based on the KWP, wherein the queries/models are configured to identify instructions or portions of instructions for executing the command; executing the queries/models to yield the instructions or portions of instructions; formulating the instructions or portions of instructions into digital commands using the virtual operation assistant; and communicating the digital commands to the processing/manufacturing facility, thereby changing an operational parameter of the processing/manufacturing facility. ### Claim 9 (depends on 8) The method of claim 8, wherein the adaptive analytical models are based on neural networks, decision trees/random forest methods, kernal methods, reinforcement learning methods, and any ensemble thereof. ### Claim 10 (depends on 9) The method of claim 9, wherein the command is a complex command. ### Claim 11 A method comprising: monitoring processes and/or hardware in a processing/manufacturing facility with a virtual operation assistant; detecting an upset and/or condition that requires attention by the virtual operation assistant; communicating a recommendation from the virtual operation assistant to a user and/or taking an action by the virtual operation assistant to mitigate and/or remedy the upset and/or condition. ### Claim 12 (depends on 11) The method of claim 11, wherein the recommendation is based on one or more queries and/or adaptive analytical models (queries/models) instructed to be executed by the virtual operation assistant. ### Claim 13 (depends on 11) The method of claim 11, wherein the action is based on one or more queries/models instructed to be executed by the virtual operation assistant. ### Claim 14 (depends on 12) The method of claim 12, wherein the adaptive analytical models are based on neural networks, decision trees/random forest methods, kernal methods, reinforcement learning methods, and any ensemble thereof.