System and method for advanced inventory management using deep neural networks

Abstract

A system and method for advanced inventory management using deep neural networks. The system may be disposed in a business establishment or it may be a cloud-based network comprising a one or more databases to store and retrieve including patron data, recipe data, business data, and inventory data, mobile and compute devices, staff and suppliers, one or more gateways for vendors and staff to interface with other third-party business, and an inventory analysis server. Taken together or in part, optimize organizational operations by predicting and optimizing key inventory decisions using artificial intelligence or other computerized methods around inventory management based upon a large amount of variables associated with the enterprise.

What is claimed is: 
     
         1 . A system for advanced inventory management, comprising:
 an inventory analysis server comprising at least a plurality of programming instructions stored in a memory of, and operating on at least one processor of, a computing device, wherein the plurality of programming instructions, when operating on the at least one processor, cause the computing device to:
 receive a plurality of stored and third-party data comprising inventory, patron, supplier, social media, and business information and use machine learning to:
 analyze at least a portion of the received data to determine the quantity of items to be purchased and to predict future inventory requirements; 
 analyze at least a portion of the received data to determine optimal inventory levels; 
 generate a plurality of inventory adjustment suggestions based on the determined quantity of times to be purchased, patron data, inventory data, and third-party data comprising at least one of: local news and events, current and forecasted weather, a social media posting, or a rating or review; 
 generate a smart shopping list based on the determined quantity of items to be purchased and the inventory adjustment suggestions; and 
 analyze at least a portion of the received data to determine a break-even point and to predict a dynamic point of reorder. 
 
   
     
     
         2 . The system of  claim 1 , wherein the received business data comprises at least one of: point of sale data for a plurality of sales transactions, accounts receivable information for a plurality of suppliers, accounts payable information for a plurality of suppliers, financial account information for a plurality of banking institutions, or time and location descriptors. 
     
     
         3 . The system of  claim 1 , wherein the retrieved inventory data comprises at least one of: a quantity of an item on-hand, a par level, a last re-order date, an expiration date, a shelf life value, or a forecasted reorder date; real-time third-party data, the real-time third-party data comprising at least one of: local news and events, current and forecasted weather, a social media posting, or a rating or review; and stored patron data comprising at least one of: a food item previously purchased, day and time data, weather conditions, local news and events, or preferences. 
     
     
         4 . The system of  claim 1 , wherein the inventory adjustment suggestions generate menu adjustments for a restaurant based on patron trends, inventory availability, and external events. 
     
     
         5 . The system of  claim 1 , wherein the machine learning comprises a long short term memory neural network. 
     
     
         6 . A method for advanced inventory management, comprising the steps of:
 receiving a plurality of stored and third-party data comprising inventory, patron, supplier, social media, and business information and use machine learning for the purpose of;   analyzing at least a portion of the received data to determine the quantity of items to be purchased and to predict future inventory requirements;   analyzing at least a portion of the received data to determine optimal inventory levels;   generating a plurality of inventory adjustment suggestions based on the determined quantity of times to be purchased, patron data, inventory data, and third-party data comprising at least one of: local news and events, current and forecasted weather, a social media posting, or a rating or review;   generating a smart shopping list based on the determined quantity of items to be purchased and the inventory adjustment suggestions; and   analyzing at least a portion of the received data to determine a break-even point and to predict a dynamic point of reorder.   
     
     
         7 . The method of  claim 6 , wherein the received business data comprises at least one of: point of sale data for a plurality of sales transactions, accounts receivable information for a plurality of suppliers, accounts payable information for a plurality of suppliers, financial account information for a plurality of banking institutions, or time and location descriptors. 
     
     
         8 . The method of  claim 6 , wherein the retrieved inventory data comprises at least one of: a quantity of an item on-hand, a par level, a last re-order date, an expiration date, a shelf life value, or a forecasted reorder date; real-time third-party data, the real-time third-party data comprising at least one of: local news and events, current and forecasted weather, a social media posting, or a rating or review; and stored patron data comprising at least one of: a food item previously purchased, day and time data, weather conditions, local news and events, or preferences. 
     
     
         9 . The method of  claim 6 , wherein the inventory adjustment suggestions generate menu adjustments for a restaurant based on patron trends, inventory availability, and external events. 
     
     
         10 . The method of  claim 6 , wherein the machine learning comprises a long short term memory neural network.