# US 10,121,211 B2 · Waste analysis system and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,211 B2 - Document ID: US10121211B2 - Status: Granted - Kind: B2 - Application number: 15/433,355 - Filed: 2017-02-15 - Published: 2018-08-16 - Granted: 2018-11-06 - Earliest claimed: 2017-02-15 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Timothy T. Bohn; Natalie N. Brooks Powell; Gary W. Crupi; Ho-Yiu Lam; David C. Martin; Sandhya ReddyVeera - Web page: https://patentgrep.com/patent/US10121211B2 ## CPC - G06Q 50/12: Hotels or restaurants - G06F 18/24: Classification techniques - G06F 40/295: Named entity recognition - G06N 5/04: Inference or reasoning models - G06N 5/046: Forward inferencing; Production systems - G06N 20/00: Machine learning - G06Q 10/06315: {Needs-based resource requirements planning or analysis} - G06Q 10/30: Administration of product recycling or disposal - G06T 7/0004: {Industrial image inspection} - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06V 10/56: relating to colour - G06V 10/764: using classification, e.g. of video objects - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G06T 2207/10024: Color image - G06T 2207/20076: Probabilistic image processing - G06T 2207/30128: Food products - G06T 2207/30242: Counting objects in image - G06V 20/68: Food, e.g. fruit or vegetables - G06V 2201/10: Recognition assisted with metadata - Y02W 90/00: Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - Y02W: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT ## Abstract Embodiments of the present invention provide techniques for identifying and quantifying waste in a process. Waste information is input via images and/or natural language. The amount of waste is estimated based on information in images and/or a natural language description. A computer-implemented technique extracts metadata on waste products from the images and/or natural language description. A variety of factors such as social media trends, weather, traffic, and/or sports schedules are evaluated by the computer and used in predicting the amount of waste that will occur. ## Claims ### Claim 1 A method for identifying waste in a process, comprising: receiving, by at least one computer, an image of one or more discarded products from a camera: performing, by the at least one computer, an object recognition process on the received image to identify the one or more discarded products within the image; acquiring, by the at least one computer, metadata relating to the one or more identified discarded products from the received image; recording, by the at least one computer, the metadata; analyzing, by the at least one computer, the metadata with a rules engine; determining, by the at least one computer, an overage amount of product as a function of the acquired metadata; deriving, by the at least one computer, a suggestion for waste reduction based on the determination; and generating, by the at least one computer, a report based on the recorded metadata, wherein the report includes the suggestion for waste reduction. ### Claim 2 (depends on 1) The method of claim 1, wherein the performing, by the at least one computer, the object recognition process on the received image comprises performing, by the at least one computer, an edge detection process. ### Claim 3 (depends on 2) The method of claim 2, wherein the performing, by the at least one computer, the object recognition process further comprises performing, by the at least one computer, a color analysis. ### Claim 4 (depends on 3) The method of claim 3, wherein the performing, by the at least one computer, the object recognition process further comprises using, by the at least one computer, one or more image classifiers. ### Claim 5 (depends on 1) The method of claim 1, further comprising acquiring, by the at least one computer, metadata for a food product. ### Claim 6 (depends on 1) The method of claim 1, further comprising performing, by the at least one computer, an object count process on the received image. ### Claim 7 (depends on 1) The method of claim 1, wherein the analyzing, by the at least one computer, the metadata with the rules engine comprises: receiving, by the at least one computer, sales data for a predetermined time duration from a point of sale system; and determining, by the at least one computer, an amount of used product during the predetermined time duration based on the received data; wherein the rules engine determines an overage amount of product as a function of the acquired metadata for the discarded product and a factor of the amount of used product. ### Claim 8 (depends on 5) The method of claim 5, wherein the acquiring, by the at least one computer, the metadata for a discarded product comprises: receiving, by the at least one computer, a natural language description of a discarded product; performing, by the at least one computer, a natural language analysis of the natural language description to identify one or more discarded products within the natural language description; and performing, by the at least one computer, an entity detection process for the natural language description. ### Claim 9 (depends on 8) The method of claim 8, wherein the natural language description comprises a speech fragment, and further comprising performing a speech-to-text process on the speech fragment prior to performing the natural language analysis. ### Claim 10 (depends on 8) The method of claim 8, wherein the performing, by the at least one computer, a natural language analysis includes performing, by the at least one computer, at least one of bigram processing, disambiguation, part-of-speech analysis, and anaphora resolution. ### Claim 11 (depends on 1) The method of claim 1, wherein the generating, by the at least one computer, the report further includes generating, by the at least one computer, an indicator of potential waste. ### Claim 12 (depends on 11) The method of claim 11, further comprising using, by the at least one computer, a social media trend to derive the indicator of potential waste. ### Claim 13 (depends on 11) The method of claim 11, further comprising using, by the at least one computer, a weather forecast to derive the indicator of potential waste. ### Claim 14 (depends on 11) The method of claim 11, further comprising using, by the at least one computer, a traffic report to derive the indicator of potential waste. ### Claim 15 (depends on 11) The method of claim 11, further comprising using, by the at least one computer, a sports team schedule to derive the indicator of potential waste. ### Claim 16 (depends on 1) The method of claim 1, wherein the generating, by the at least one computer, the report further includes generating, by the at least one computer, a substitution suggestion. ### Claim 17 (depends on 1) The method of claim 1, wherein the generating, by the at least one computer, the report further includes generating a process change suggestion. ### Claim 18 A computer system comprising: a processor; a memory coupled to the processor, the memory containing instructions, that when executed by the processor, perform the steps of: receiving an image of one or more discarded products from a camera; performing an object recognition process on the received image to identify the one or more discarded products within the image; acquiring metadata relating to the one or more identified discarded products from the received image; recording the metadata; analyzing the metadata with a rules engine; determining an overage amount of product as a function of the acquired metadata; deriving a suggestion for waste reduction based on the determination; and generating a report based on the recorded metadata, wherein the report includes the suggestion for waste reduction. ### Claim 19 A computer program product for identifying waste in a process, for an electronic computing device comprising a computer readable hardware storage device having program instructions embodied therewith, the program instructions executable by a processor to cause the electronic device to: receive an image of one or more discarded products from a camera; perform an object recognition process on the received image to identify the one or more discarded products within the image; acquire metadata relating to the one or more identified discarded products from the received image; record the metadata; analyze the metadata with a rules engine; determine an overage amount of product as a function of the acquired metadata; derive a suggestion for waste reduction based on the determination; and generate a report based on the recorded metadata, wherein the report includes the suggestion for waste reduction.