# US 10,769,377 B2 · Learning object/action pairs for recipe ingredients > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,377 B2 - Document ID: US10769377B2 - Status: Granted - Kind: B2 - Application number: 16/591,763 - Filed: 2019-10-03 - Published: 2020-01-30 - Granted: 2020-09-08 - Earliest claimed: 2016-02-08 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Donna K. Byron; Alexander Pikovsky; Florian Pinel; Timothy P. Winkler - Web page: https://patentgrep.com/patent/US10769377B2 ## CPC - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/295: Named entity recognition - G06F 40/211: Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars - G06F 40/253: Grammatical analysis; Style critique - G06F 40/30: Semantic analysis - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Aspects include learning object/action pairs for recipe ingredients. A method includes extracting an ingredient list that includes a plurality of entries from a recipe stored in an electronic format. Each of the plurality of entries includes one or more words. For each multi-word entry in the ingredient list, an ingredient associated with the entry is identified by comparing words contained in the entry to terms in a lexicon of cooking domain terms. It is determined whether an action corresponds to the identified ingredient. The determining includes parsing the entry to locate a verb that is associated with the identified ingredient. Based on determining that an action corresponds to the identified ingredient, a food item action pair that includes the identified ingredient and the located verb is output. ## Claims ### Claim 1 A method, comprising: receiving an ingredient list of a recipe stored in an electronic format in a corpus of recipes, the ingredient list including a plurality of entries, each of the entries comprising one or more words; for each multi-word entry in the ingredient list: identifying an ingredient associated with the entry, the identifying including comparing words contained in the entry to terms in a lexicon of cooking domain terms; determining whether an action corresponds to the identified ingredient, the determining including parsing the entry to locate a verb that is associated with the identified ingredient; and based on determining that an action corresponds to the identified ingredient, outputting a food item action pair that includes the identified ingredient and the located verb, wherein the located verb indicates that the action is performed on the identified ingredient and wherein the outputting is to a database; outputting at least one additional food item action pair for at least one of the multi-word entries in the ingredient list; and executing, at a computer, a recipe generator to automatically create a description of a new recipe not contained in the corpus of recipes using cognitive computing, the description of the new recipe including one of the food item action pairs. ### Claim 2 (depends on 1) The method of claim 1, wherein a plurality of ingredients are associated with at least one of the entries. ### Claim 3 (depends on 1) The method of claim 1, wherein the parsing includes using clause structure analysis to identify one or more modifiers of the identified ingredient. ### Claim 4 (depends on 3) The method of claim 3, wherein the parsing further includes identifying one of the one or more modifiers as a verb participle based, at least in part, on contents of a verb lexicon, and wherein the located verb corresponds to the verb participle. ### Claim 5 (depends on 3) The method of claim 3, wherein the parsing further includes identifying one of the one or more identifiers as a verb participle based, at least in part, on part of speech tags generated by a parser, and wherein the located verb corresponds to the verb participle. ### Claim 6 (depends on 1) The method of claim 1, wherein the identifying further includes at least one of: replacing a surface name of the ingredient that is contained in the entry with a semantic reference from the lexicon of cooking domain terms; and retaining an adjectival modifier as part of the identified ingredient. ### Claim 7 (depends on 1) The method of claim 1, further comprising: performing the receiving, identifying, determining, and outputting a food item action pair for a plurality of recipes in the corpus of recipes; and outputting a frequency count of each food item action pair that reflects a number of times that each food item action pair is output, wherein the frequency count is input to the recipe generator. ### Claim 8 A system, comprising: a memory having computer readable instructions; and a processor for executing the computer readable instructions, the computer readable instructions including: receiving an ingredient list of a recipe stored in an electronic format in a corpus of recipes, the ingredient list including a plurality of entries, each of the entries comprising one or more words; for each multi-word entry in the ingredient list: identifying an ingredient associated with the entry, the identifying including comparing words contained in the entry to terms in a lexicon of cooking domain terms; determining whether an action corresponds to the identified ingredient, the determining including parsing the entry to locate a verb that is associated with the identified ingredient; and based on determining that an action corresponds to the identified ingredient, outputting a food item action pair that includes the identified ingredient and the located verb, wherein the located verb indicates that the action is performed on the identified ingredient and wherein the outputting is to a database; outputting at least one additional food item action pair for at least one of the multi-word entries in the ingredient list; and executing a recipe generator to automatically create a description of a new recipe, not contained in the corpus of recipes, using cognitive computing, the description of the new recipe including one of the food item action pairs. ### Claim 9 (depends on 8) The system of claim 8, wherein a plurality of ingredients are associated with at least one of the entries. ### Claim 10 (depends on 8) The system of claim 8, wherein the parsing includes using clause structure analysis to identify one or more modifiers of the identified ingredient. ### Claim 11 (depends on 10) The system of claim 10, wherein the parsing further includes identifying one of the one or more modifiers as a verb participle based, at least in part, on contents of a verb lexicon, and wherein the located verb corresponds to the verb participle. ### Claim 12 (depends on 10) The system of claim 10, wherein the parsing further includes identifying one of the one or more identifiers as a verb participle based, at least in part, on part of speech tags generated by a parser, and wherein the located verb corresponds to the verb participle. ### Claim 13 (depends on 8) The system of claim 8, wherein the identifying further includes at least one of: replacing a surface name of the ingredient that is contained in the entry with a semantic reference from the lexicon of cooking domain terms; and retaining an adjectival modifier as part of the identified ingredient. ### Claim 14 (depends on 8) The system of claim 8, wherein the computer readable instructions further include: performing the receiving, identifying, determining, and outputting a food item action pair for a plurality of recipes in the corpus of recipes; and outputting a frequency count of each food item action pair that reflects a number of times that each food item action pair is output, wherein the frequency count is input to the recipe generator. ### Claim 15 A computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the computer processor to perform: receiving an ingredient list of a recipe stored in an electronic format, the ingredient list including a plurality of entries, each of the entries comprising one or more words; for each multi-word entry in the ingredient list: identifying an ingredient associated with the entry, the identifying including comparing words contained in the entry to terms in a lexicon of cooking domain terms; determining whether an action corresponds to the identified ingredient, the determining including parsing the entry to locate a verb that is associated with the identified ingredient; and based on determining that an action corresponds to the identified ingredient, outputting a food item action pair that includes the identified ingredient and the located verb, wherein the located verb indicates that the action is performed on the identified ingredient and wherein the outputting is to a database; outputting at least one additional food item action pair for at least one of the multi-word entries in the ingredient list; and executing a recipe generator to automatically create a description of a new recipe, not contained in the corpus of recipes, using cognitive computing, the description of the new recipe including one of the food item action pairs. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein a plurality of ingredients are associated with at least one of the entries. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the parsing includes using clause structure analysis to identify one or more modifiers of the identified ingredient. ### Claim 18 (depends on 17) The computer program product of claim 17, wherein the parsing further includes identifying one of the one or more modifiers as a verb participle based, at least in part, on contents of a verb lexicon, and wherein the located verb corresponds to the verb participle. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the identifying further includes at least one of: replacing a surface name of the ingredient that is contained in the entry with a semantic reference from the lexicon of cooking domain terms; and retaining an adjectival modifier as part of the identified ingredient. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the program instructions further cause the computer processor to perform: performing the receiving, identifying, determining, and outputting a food item action pair for a plurality of recipes in the corpus of recipes; and outputting a frequency count of each food item action pair that reflects a number of times that each food item action pair is output, wherein the frequency count is input to the recipe generator.