# US 12,222,691 B2 · Automated system control with data analytics using doubly stochastic model > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,222,691 B2 - Document ID: US12222691B2 - Status: Granted - Kind: B2 - Application number: 17/645,599 - Filed: 2021-12-22 - Published: 2022-06-30 - Granted: 2025-02-11 - Earliest claimed: 2020-12-29 - Assignees: Smart Software, Inc. - Applicants: Smart Software, Inc. - Inventors: Brock Estel Osborn; Thomas Reed Willemain; Nelson Seth Hartunian - Web page: https://patentgrep.com/patent/US12222691B2 ## CPC - G05B 17/02: electric - G06Q 10/08726: {for replenishment processing, procedures, or recommendations using forecasting or optimisation} - G06Q 10/0877: {by inventory control or reporting using inventory tracking or counting} - G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract A system and method for controlling an automated process based on a time series of count data. The approach includes characterizing an observed time series of counts by modeling the underlying dynamics that give rise to the observed data, including evaluating the time series with a driver estimation process, wherein the driver estimation process identifies a model by an iterative process that includes: providing a probability model; and utilizing a combined MCMC and EM algorithm to determine a set of model parameters for the time series; outputting an estimated sequence of driver values based on the identified model; outputting a series of statistically plausible future counts, and controlling the automated process based on the estimated sequence of driver values. ## Claims ### Claim 1 A system for controlling a robot in an automated warehouse to stock shelves, comprising: a memory; and a processor coupled to the memory and configured to perform a process that includes: obtaining a time series of data associated with an intermittent demand for parts in the automated warehouse; evaluating the time series with a driver estimation process, wherein the driver estimation process estimates a driver for the time series with an iterative process that includes: providing a model space; and utilizing an Expectation/Maximization (EM) algorithm and a Markov Chain Monte Carlo (MCMC) algorithm to determine a probability model having set of model parameters within the model space; and generating an estimated sequence of driver values based on the model parameters, wherein the estimated sequence of driver values forms the driver; and processing the driver values to generate future demand scenarios; and controlling the automated warehouse based on the driver, including planning future inventory and deploying robots within the automated warehouse to stock shelves based on the future demand scenarios. ### Claim 2 (depends on 1) The system of claim 1, wherein the time series is obtained from a sensor unit. ### Claim 3 (depends on 2) The system of claim 2, wherein the sensor unit includes at least one of a proximity sensor, a temperature sensor, an accelerometer, an infrared sensor, a pressure sensor, a light sensor, an optical sensor, a smoke sensor, an electromechanical device, a Peripheral Component Interconnect (PCI) board, and an application programming interface. ### Claim 4 (depends on 1) The system of claim 1, wherein the intermittent demand includes mostly zeros. ### Claim 5 (depends on 1) The system of claim 1, wherein the model space comprises a Log-Gaussian Cox Process (LGCP) model. ### Claim 6 A method for controlling a robot to stock shelves in a warehouse, comprising: obtaining a time series of intermittent data from a sensor in the warehouse; evaluating the time series with a driver estimation process, wherein the driver estimation process estimates a driver for the time series with an iterative process that includes utilizing an Expectation/Maximization (EM) algorithm and a Markov Chain Monte Carlo (MCMC) algorithm to determine a probability model having set of model parameters within a model space; generating an estimated sequence of driver values based on the model parameters, wherein the estimated sequence of driver values forms the driver; processing the driver to generate future demand scenarios; and controlling the robot within the warehouse to stock shelves based on the future demand scenarios. ### Claim 7 (depends on 6) The method of claim 6, wherein the time series is obtained from a sensor unit. ### Claim 8 (depends on 7) The method of claim 7, wherein the sensor unit includes at least one of a proximity sensor, a temperature sensor, an accelerometer, an infrared sensor, a pressure sensor, a light sensor, an optical sensor, a smoke sensor, an electromechanical device, a Peripheral Component Interconnect (PCI) board, and an application programming interface. ### Claim 9 A system for re-ordering parts in an enterprise resource planning (ERP) system, comprising: a memory; and a processor coupled to the memory and configured to perform a process that includes: obtaining a time series of data associated with an intermittent demand for parts in the ERP system; evaluating the time series with a driver estimation process, wherein the driver estimation process estimates a driver for the time series with an iterative process that includes: providing a model space; utilizing an Expectation/Maximization (EM) algorithm and a Markov Chain Monte Carlo (MCMC) algorithm to determine a probability model having set of model parameters within the model space; and generating an estimated sequence of driver values based on the model parameters; processing the driver values to model future demand scenarios for the parts in the ERP system that are statistically similar but not identical to time series; and automatically re-ordering parts in the ERP system based on the future demand scenarios.