MLchartDataset catalogue

Patent · US10810371B2 · B2 · US

Adaptive, interactive, and cognitive reasoner of an autonomous robotic system

(11) Publication number
US10810371B2
(21) Application number
15/946,646
(22) Filing date
2018-04-05
(30) Priority date
2017-04-06
(43) Publication date
2020-10-20
(45) Date of grant
2020-10-20
(51) IPC
B25J 9/16; G06F 16/901; G06F 40/00; G06F 40/211; G06F 40/247; G06F 40/284; G06F 40/289; G06F 40/30; G06F 40/56; G06N 3/00; G06N 3/04; G06N 3/08; G06N 5/02; G06N 5/04
(52) CPC
  • G06F Electric digital data processing: 40/284, 16/9024, 40/211, 40/247, 40/289, 40/30, 40/56
  • B25J Manipulators; chambers provided with manipulation devices: 9/1658, 9/1694
  • G06N Computing arrangements based on specific computational models: 3/008, 3/042, 3/0427, 3/045, 3/0454, 3/0464, 3/08, 5/022, 5/04, 5/041
(73) Assignee
AIBRAIN CORP
(72) Inventors
SHINN HONG SHIK; HONG EUNMI; LIM BYOUNG-KWON; LEE CHEONGAN
(54) Title
Adaptive, interactive, and cognitive reasoner of an autonomous robotic system
(57) Abstract

An artificial intelligence problem is solved using an artificial intelligence memory graph data structure and a lexical database to identify supporting knowledge. A natural language input is received and classified into components. A starting node of an artificial intelligence memory graph data structure, which comprises one or more data nodes, is selected to begin a search for one or more supporting knowledge data nodes associated with the classified components. Starting at the starting node, the artificial intelligence memory graph data structure is searched using a lexical database to identify the one or more supporting knowledge data nodes. An artificial intelligence problem is identified and solved using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.

Full text
View on Google Patents

Claims (20)

  1. A method for solving an artificial intelligence problem, comprising: receiving a natural language input; processing the natural language input to classify components of the natural language input; selecting a starting node of an artificial intelligence memory graph data structure to begin a search for one or more supporting knowledge data nodes associated with the classified components, wherein the artificial intelligence memory graph comprises one or more data nodes; starting at the starting node, searching the artificial intelligence memory graph data structure using a lexical database to identify the one or more supporting knowledge data nodes, wherein the one or more identified supporting knowledge data nodes are identified by comparing subject-predicate-object lemma, parts of speech, and coreference results between the classified components and the one or more data nodes; identifying the artificial intelligence problem; and solving the artificial intelligence problem using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.
  2. The method of claim 1, further comprising recording the identified artificial intelligence problem and a determined solution in the artificial intelligence memory graph data structure.
  3. The method of claim 1, wherein the classified components of the natural language input include a subject-predicate-object triple.
  4. The method of claim 1, wherein the lexical database is used to identify a relationship between one of the classified components and at least one of the one or more supporting knowledge data nodes.
  5. The method of claim 4, wherein the relationship is a synonym relationship.
  6. The method of claim 4, wherein the relationship is a hypernym relationship.
  7. The method of claim 4, wherein the relationship is a derived hypernym relationship.
  8. The method of claim 1, wherein the artificial intelligence problem is solved using a case based reasoning module or an artificial intelligence planner.
  9. The method of claim 8, wherein the case based reasoning module matches the artificial intelligence problem to a case stored in the artificial intelligence memory graph data structure.
  10. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part, and the user part stores information associated with one or more of the following: a conversation history, or one or more cases for case based reasoning.
  11. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part, and the user part is searchable using a user identifier.
  12. The method of claim 1, wherein the lexical database is used to retrieve information related to a “what,” “where,” “who,” or “is” query.
  13. The method of claim 1, further comprising identifying a speaker responsible for the natural language input, wherein a user identifier of the identified speaker is used to select the starting node of the artificial intelligence memory graph data structure.
  14. The method of claim 1, wherein the one or more identified supporting knowledge data nodes are ranked.
  15. The method of claim 14, wherein a ranking is assigned to the one or more identified supporting knowledge data nodes based on a conversation time.
  16. The method of claim 1, wherein the one or more identified supporting knowledge data nodes are identified by filtering out data nodes with negative facts and negated facts.
  17. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part.
  18. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part, and the robotic system part includes data associated with a device configured to provide a software robot natural language interaction.
  19. A system for solving an artificial intelligence problem, comprising: a processor; and a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to: receive a natural language input; process the natural language input to classify components of the natural language input; select a starting node of an artificial intelligence memory graph data structure to begin a search for one or more supporting knowledge data nodes associated with the classified components, wherein the artificial intelligence memory graph comprises one or more data nodes; starting at the starting node, search the artificial intelligence memory graph data structure using a lexical database to identify the one or more supporting knowledge data nodes, wherein the one or more identified supporting knowledge data nodes are identified by comparing subject-predicate-object lemma, parts of speech, and coreference results between the classified components and the one or more data nodes; identify the artificial intelligence problem; and solve the artificial intelligence problem using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.
  20. A method for solving an artificial intelligence problem, comprising: receiving a natural language input; processing the natural language input to classify components of the natural language input; selecting a starting node of an artificial intelligence memory graph data structure to begin a search for one or more supporting knowledge data nodes associated with the classified components; starting at the starting node, searching the artificial intelligence memory graph data structure using a lexical database to identify the one or more supporting knowledge data nodes, wherein the one or more identified supporting knowledge data nodes are identified including by comparing subject-predicate-object lemma, parts of speech, and coreference results between the classified components and the one or more data nodes; identifying the artificial intelligence problem; and solving the artificial intelligence problem using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.

Description

Traditional robotic systems such as a voice artificial intelligence (AI) robot agent are capable of responding to generic queries. Examples of a query and response include asking and receiving a response for the current weather or movie show times. These queries typically rely on backend databases, such as weather or movie show times databases, to retrieve information. These queries, however, are often limited in their scope and result in a response that does not adapt to the user's historical context. For example, a user often desires to query information that the user has previously shared with the AI agent and to interact with the agent across multiple back-and-forth exchanges. Therefore, there exists a need for an autonomous robotic system that can participate in an interactive conversation that spans multiple queries and responses and also includes responses that are adapted to the context of previous conversations.

Various embodiments of the invention are disclosed in the following detailed description and the accompanying drawings. FIG. 1 is a flow diagram illustrating an embodiment of a process for responding to an input event using an adaptive, interactive, and cognitive reasoner. FIG. 2 is a flow diagram illustrating an embodiment of a process for responding to voice input using an adaptive, interactive, and cognitive reasoner with a voice response. FIG. 3 is a flow diagram illustrating an embodiment of a process for performing reasoning by an adaptive, interactive, and cognitive reasoner. FIG. 4 is a flow diagram illustrating an embodiment of a process for identifying supporting knowledge. FIG.

Citations (233)

  • US10068031B2
  • US10297253B2
  • US10318907B1
  • US10341304B1
  • US10395173B1
  • US10410328B1
  • US10418032B1
  • US10453117B1
  • US10514776B2
  • US10613527B2
  • US2003130827A1
  • US2004013295A1
  • US2004044657A1
  • US2004182614A1
  • US2004193322A1
  • US2004228456A1
  • US2005005266A1
  • US2005096790A1
  • US2005165508A1
  • US2005256882A1
  • US2006041722A1
  • US2006072738A1
  • US2006150119A1
  • US2006195407A1
  • US2007070069A1
  • US2007192910A1
  • US2007200920A1
  • US2008015418A1
  • US2008133052A1
  • US2008177683A1
  • US2008222077A1
  • US2008243305A1
  • US2009148034A1
  • US2009175545A1
  • US2009192968A1
  • US2010013153A1
  • US2010036802A1
  • US2010082513A1
  • US2010211340A1
  • US2010222957A1
  • US2011010013A1
  • US2011054689A1
  • US2011090787A1
  • US2011106436A1
  • US2011224828A1
  • US2011288684A1
  • US2011307435A1
  • US2012010900A1
  • US2012016678A1
  • US2012095619A1
  • US2012117005A1
  • US2012130270A1
  • US2012233152A1
  • US2012238366A1
  • US2013103195A1
  • US2013110764A1
  • US2013138425A1
  • US2013246430A1
  • US2013253977A1
  • US2013289984A1
  • US2013337916A1
  • US2014070947A1
  • US2014075004A1
  • US2014100012A1
  • US2014108303A1
  • US2014132767A1
  • US2014164533A1
  • US2014279807A1
  • US2014279971A1
  • US2014280210A1
  • US2014298358A1
  • US2014316570A1
  • US2015025708A1
  • US2015032254A1
  • US2015046181A1
  • US2015066520A1
  • US2015066836A1
  • US2015106308A1
  • US2015142704A1
  • US2015168954A1
  • US2015197007A1
  • US2015248525A1
  • US2015269139A1
  • US2015279348A1
  • US2015285644A1
  • US2015290795A1
  • US2015310446A1
  • US2015326832A1
  • US2015356144A1
  • US2015378984A1
  • US2016004826A1
  • US2016062882A1
  • US2016068267A1
  • US2016103653A1
  • US2016110422A1
  • US2016117593A1
  • US2016132789A1
  • US2016167226A1
  • US2016188595A1
  • US2016189035A1
  • US2016255969A1
  • US2016261771A1
  • US2016271795A1
  • US2016303738A1
  • US2016350685A1
  • US2016350930A1
  • US2016378752A1
  • US2016379092A1
  • US2016379106A1
  • US2016379120A1
  • US2016379121A1
  • US2017004199A1
  • US2017010830A1
  • US2017024392A1
  • US2017038846A1
  • US2017052905A1
  • US2017061302A1
  • US2017078224A1
  • US2017099200A1
  • US2017109355A1
  • US2017116187A1
  • US2017250930A1
  • US2017255884A1
  • US2017277619A1
  • US2017278110A1
  • US2017293610A1
  • US2017297588A1
  • US2017307391A1
  • US2017308521A1
  • US2017311863A1
  • US2017318919A1
  • US2017323285A1
  • US2017323356A1
  • US2017330106A1
  • US2017337620A1
  • US2018043532A1
  • US2018052876A1
  • US2018052913A1
  • US2018053114A1
  • US2018054507A1
  • US2018068031A1
  • US2018075403A1
  • US2018082230A1
  • US2018092559A1
  • US2018099846A1
  • US2018107917A1
  • US2018108443A1
  • US2018114111A1
  • US2018121098A1
  • US2018127211A1
  • US2018127212A1
  • US2018136615A1
  • US2018137155A1
  • US2018143634A1
  • US2018143978A1
  • US2018144208A1
  • US2018144248A1
  • US2018144257A1
  • US2018150740A1
  • US2018165518A1
  • US2018165625A1
  • US2018169865A1
  • US2018173459A1
  • US2018189269A1
  • US2018197275A1
  • US2018218266A1
  • US2018218472A1
  • US2018225281A1
  • US2018233141A1
  • US2018256989A1
  • US2018267540A1
  • US2018268699A1
  • US2018275677A1
  • US2018275913A1
  • US2018281191A1
  • US2018284735A1
  • US2018285359A1
  • US2018285595A1
  • US2018292827A1
  • US2018314603A1
  • US2018314689A1
  • US2018336271A1
  • US2018349485A1
  • US2018364045A1
  • US2019035083A1
  • US2019053856A1
  • US2019154439A1
  • US2019179329A1
  • US2019193273A1
  • US2019220774A1
  • US2019255703A1
  • US2019273619A1
  • US2019278796A1
  • US2019286996A1
  • US2019290209A1
  • US2019347120A1
  • US2019351558A1
  • US2019361457A1
  • US2019370096A1
  • US2019378019A1
  • US2020035110A1
  • US2020061839A1
  • US2020117187A1
  • US2020152084A1
  • US2020215698A1
  • US4638445A
  • US4815005A
  • US5581664A
  • US5761717A
  • US6542242B1
  • US6859931B1
  • US7386449B2
  • US7426500B2
  • US7545965B2
  • US7925605B1
  • US8073804B1
  • US8392921B2
  • US8495002B2
  • US8924011B2
  • US9239382B2
  • US9261978B2
  • US9373086B1
  • US9380017B2
  • US9424523B2
  • US9471668B1
  • US9555326B2
  • US9564149B2
  • US9568909B2
  • US9569425B2
  • US9659052B1
  • US9747901B1
  • US9792434B1
  • US9801517B2
Record as JSON 
{
  "publication_number": "US10810371B2",
  "country": "US",
  "kind": "B2",
  "title": "Adaptive, interactive, and cognitive reasoner of an autonomous robotic system",
  "abstract": "An artificial intelligence problem is solved using an artificial intelligence memory graph data structure and a lexical database to identify supporting knowledge. A natural language input is received and classified into components. A starting node of an artificial intelligence memory graph data structure, which comprises one or more data nodes, is selected to begin a search for one or more supporting knowledge data nodes associated with the classified components. Starting at the starting node, the artificial intelligence memory graph data structure is searched using a lexical database to identify the one or more supporting knowledge data nodes. An artificial intelligence problem is identified and solved using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.",
  "claims": [
    "1. A method for solving an artificial intelligence problem, comprising: receiving a natural language input; processing the natural language input to classify components of the natural language input; selecting a starting node of an artificial intelligence memory graph data structure to begin a search for one or more supporting knowledge data nodes associated with the classified components, wherein the artificial intelligence memory graph comprises one or more data nodes; starting at the starting node, searching the artificial intelligence memory graph data structure using a lexical database to identify the one or more supporting knowledge data nodes, wherein the one or more identified supporting knowledge data nodes are identified by comparing subject-predicate-object lemma, parts of speech, and coreference results between the classified components and the one or more data nodes; identifying the artificial intelligence problem; and solving the artificial intelligence problem using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.",
    "2. The method of claim 1, further comprising recording the identified artificial intelligence problem and a determined solution in the artificial intelligence memory graph data structure.",
    "3. The method of claim 1, wherein the classified components of the natural language input include a subject-predicate-object triple.",
    "4. The method of claim 1, wherein the lexical database is used to identify a relationship between one of the classified components and at least one of the one or more supporting knowledge data nodes.",
    "5. The method of claim 4, wherein the relationship is a synonym relationship.",
    "6. The method of claim 4, wherein the relationship is a hypernym relationship.",
    "7. The method of claim 4, wherein the relationship is a derived hypernym relationship.",
    "8. The method of claim 1, wherein the artificial intelligence problem is solved using a case based reasoning module or an artificial intelligence planner.",
    "9. The method of claim 8, wherein the case based reasoning module matches the artificial intelligence problem to a case stored in the artificial intelligence memory graph data structure.",
    "10. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part, and the user part stores information associated with one or more of the following: a conversation history, or one or more cases for case based reasoning.",
    "11. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part, and the user part is searchable using a user identifier.",
    "12. The method of claim 1, wherein the lexical database is used to retrieve information related to a “what,” “where,” “who,” or “is” query.",
    "13. The method of claim 1, further comprising identifying a speaker responsible for the natural language input, wherein a user identifier of the identified speaker is used to select the starting node of the artificial intelligence memory graph data structure.",
    "14. The method of claim 1, wherein the one or more identified supporting knowledge data nodes are ranked.",
    "15. The method of claim 14, wherein a ranking is assigned to the one or more identified supporting knowledge data nodes based on a conversation time.",
    "16. The method of claim 1, wherein the one or more identified supporting knowledge data nodes are identified by filtering out data nodes with negative facts and negated facts.",
    "17. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part.",
    "18. The method of claim 1, wherein the artificial intelligence memory graph data structure includes a robotic system part and a user part, and the robotic system part includes data associated with a device configured to provide a software robot natural language interaction.",
    "19. A system for solving an artificial intelligence problem, comprising: a processor; and a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to: receive a natural language input; process the natural language input to classify components of the natural language input; select a starting node of an artificial intelligence memory graph data structure to begin a search for one or more supporting knowledge data nodes associated with the classified components, wherein the artificial intelligence memory graph comprises one or more data nodes; starting at the starting node, search the artificial intelligence memory graph data structure using a lexical database to identify the one or more supporting knowledge data nodes, wherein the one or more identified supporting knowledge data nodes are identified by comparing subject-predicate-object lemma, parts of speech, and coreference results between the classified components and the one or more data nodes; identify the artificial intelligence problem; and solve the artificial intelligence problem using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure.",
    "20. A method for solving an artificial intelligence problem, comprising: receiving a natural language input; processing the natural language input to classify components of the natural language input; selecting a starting node of an artificial intelligence memory graph data structure to begin a search for one or more supporting knowledge data nodes associated with the classified components; starting at the starting node, searching the artificial intelligence memory graph data structure using a lexical database to identify the one or more supporting knowledge data nodes, wherein the one or more identified supporting knowledge data nodes are identified including by comparing subject-predicate-object lemma, parts of speech, and coreference results between the classified components and the one or more data nodes; identifying the artificial intelligence problem; and solving the artificial intelligence problem using the one or more identified supporting knowledge data nodes of the artificial intelligence memory graph data structure."
  ],
  "description_excerpt": "Traditional robotic systems such as a voice artificial intelligence (AI) robot agent are capable of responding to generic queries. Examples of a query and response include asking and receiving a response for the current weather or movie show times. These queries typically rely on backend databases, such as weather or movie show times databases, to retrieve information. These queries, however, are often limited in their scope and result in a response that does not adapt to the user's historical context. For example, a user often desires to query information that the user has previously shared with the AI agent and to interact with the agent across multiple back-and-forth exchanges. Therefore, there exists a need for an autonomous robotic system that can participate in an interactive conversation that spans multiple queries and responses and also includes responses that are adapted to the context of previous conversations.\n\nVarious embodiments of the invention are disclosed in the following detailed description and the accompanying drawings. FIG. 1 is a flow diagram illustrating an embodiment of a process for responding to an input event using an adaptive, interactive, and cognitive reasoner. FIG. 2 is a flow diagram illustrating an embodiment of a process for responding to voice input using an adaptive, interactive, and cognitive reasoner with a voice response. FIG. 3 is a flow diagram illustrating an embodiment of a process for performing reasoning by an adaptive, interactive, and cognitive reasoner. FIG. 4 is a flow diagram illustrating an embodiment of a process for identifying supporting knowledge. FIG.",
  "cpc": [
    "G06F 40/284",
    "B25J 9/1658",
    "B25J 9/1694",
    "G06F 16/9024",
    "G06F 40/211",
    "G06F 40/247",
    "G06F 40/289",
    "G06F 40/30",
    "G06F 40/56",
    "G06N 3/008",
    "G06N 3/042",
    "G06N 3/0427",
    "G06N 3/045",
    "G06N 3/0454",
    "G06N 3/0464",
    "G06N 3/08",
    "G06N 5/022",
    "G06N 5/04",
    "G06N 5/041"
  ],
  "ipc": [
    "B25J 9/16",
    "G06F 16/901",
    "G06F 40/00",
    "G06F 40/211",
    "G06F 40/247",
    "G06F 40/284",
    "G06F 40/289",
    "G06F 40/30",
    "G06F 40/56",
    "G06N 3/00",
    "G06N 3/04",
    "G06N 3/08",
    "G06N 5/02",
    "G06N 5/04"
  ],
  "assignees": [
    "AIBRAIN CORP"
  ],
  "inventors": [
    "SHINN HONG SHIK",
    "HONG EUNMI",
    "LIM BYOUNG-KWON",
    "LEE CHEONGAN"
  ],
  "filing_date": "2018-04-05",
  "publication_date": "2020-10-20",
  "grant_date": "2020-10-20",
  "priority_date": "2017-04-06",
  "application_number": "US-201815946646-A",
  "family_id": "63712659",
  "citations": [
    "US10068031B2",
    "US10297253B2",
    "US10318907B1",
    "US10341304B1",
    "US10395173B1",
    "US10410328B1",
    "US10418032B1",
    "US10453117B1",
    "US10514776B2",
    "US10613527B2",
    "US2003130827A1",
    "US2004013295A1",
    "US2004044657A1",
    "US2004182614A1",
    "US2004193322A1",
    "US2004228456A1",
    "US2005005266A1",
    "US2005096790A1",
    "US2005165508A1",
    "US2005256882A1",
    "US2006041722A1",
    "US2006072738A1",
    "US2006150119A1",
    "US2006195407A1",
    "US2007070069A1",
    "US2007192910A1",
    "US2007200920A1",
    "US2008015418A1",
    "US2008133052A1",
    "US2008177683A1",
    "US2008222077A1",
    "US2008243305A1",
    "US2009148034A1",
    "US2009175545A1",
    "US2009192968A1",
    "US2010013153A1",
    "US2010036802A1",
    "US2010082513A1",
    "US2010211340A1",
    "US2010222957A1",
    "US2011010013A1",
    "US2011054689A1",
    "US2011090787A1",
    "US2011106436A1",
    "US2011224828A1",
    "US2011288684A1",
    "US2011307435A1",
    "US2012010900A1",
    "US2012016678A1",
    "US2012095619A1",
    "US2012117005A1",
    "US2012130270A1",
    "US2012233152A1",
    "US2012238366A1",
    "US2013103195A1",
    "US2013110764A1",
    "US2013138425A1",
    "US2013246430A1",
    "US2013253977A1",
    "US2013289984A1",
    "US2013337916A1",
    "US2014070947A1",
    "US2014075004A1",
    "US2014100012A1",
    "US2014108303A1",
    "US2014132767A1",
    "US2014164533A1",
    "US2014279807A1",
    "US2014279971A1",
    "US2014280210A1",
    "US2014298358A1",
    "US2014316570A1",
    "US2015025708A1",
    "US2015032254A1",
    "US2015046181A1",
    "US2015066520A1",
    "US2015066836A1",
    "US2015106308A1",
    "US2015142704A1",
    "US2015168954A1",
    "US2015197007A1",
    "US2015248525A1",
    "US2015269139A1",
    "US2015279348A1",
    "US2015285644A1",
    "US2015290795A1",
    "US2015310446A1",
    "US2015326832A1",
    "US2015356144A1",
    "US2015378984A1",
    "US2016004826A1",
    "US2016062882A1",
    "US2016068267A1",
    "US2016103653A1",
    "US2016110422A1",
    "US2016117593A1",
    "US2016132789A1",
    "US2016167226A1",
    "US2016188595A1",
    "US2016189035A1",
    "US2016255969A1",
    "US2016261771A1",
    "US2016271795A1",
    "US2016303738A1",
    "US2016350685A1",
    "US2016350930A1",
    "US2016378752A1",
    "US2016379092A1",
    "US2016379106A1",
    "US2016379120A1",
    "US2016379121A1",
    "US2017004199A1",
    "US2017010830A1",
    "US2017024392A1",
    "US2017038846A1",
    "US2017052905A1",
    "US2017061302A1",
    "US2017078224A1",
    "US2017099200A1",
    "US2017109355A1",
    "US2017116187A1",
    "US2017250930A1",
    "US2017255884A1",
    "US2017277619A1",
    "US2017278110A1",
    "US2017293610A1",
    "US2017297588A1",
    "US2017307391A1",
    "US2017308521A1",
    "US2017311863A1",
    "US2017318919A1",
    "US2017323285A1",
    "US2017323356A1",
    "US2017330106A1",
    "US2017337620A1",
    "US2018043532A1",
    "US2018052876A1",
    "US2018052913A1",
    "US2018053114A1",
    "US2018054507A1",
    "US2018068031A1",
    "US2018075403A1",
    "US2018082230A1",
    "US2018092559A1",
    "US2018099846A1",
    "US2018107917A1",
    "US2018108443A1",
    "US2018114111A1",
    "US2018121098A1",
    "US2018127211A1",
    "US2018127212A1",
    "US2018136615A1",
    "US2018137155A1",
    "US2018143634A1",
    "US2018143978A1",
    "US2018144208A1",
    "US2018144248A1",
    "US2018144257A1",
    "US2018150740A1",
    "US2018165518A1",
    "US2018165625A1",
    "US2018169865A1",
    "US2018173459A1",
    "US2018189269A1",
    "US2018197275A1",
    "US2018218266A1",
    "US2018218472A1",
    "US2018225281A1",
    "US2018233141A1",
    "US2018256989A1",
    "US2018267540A1",
    "US2018268699A1",
    "US2018275677A1",
    "US2018275913A1",
    "US2018281191A1",
    "US2018284735A1",
    "US2018285359A1",
    "US2018285595A1",
    "US2018292827A1",
    "US2018314603A1",
    "US2018314689A1",
    "US2018336271A1",
    "US2018349485A1",
    "US2018364045A1",
    "US2019035083A1",
    "US2019053856A1",
    "US2019154439A1",
    "US2019179329A1",
    "US2019193273A1",
    "US2019220774A1",
    "US2019255703A1",
    "US2019273619A1",
    "US2019278796A1",
    "US2019286996A1",
    "US2019290209A1",
    "US2019347120A1",
    "US2019351558A1",
    "US2019361457A1",
    "US2019370096A1",
    "US2019378019A1",
    "US2020035110A1",
    "US2020061839A1",
    "US2020117187A1",
    "US2020152084A1",
    "US2020215698A1",
    "US4638445A",
    "US4815005A",
    "US5581664A",
    "US5761717A",
    "US6542242B1",
    "US6859931B1",
    "US7386449B2",
    "US7426500B2",
    "US7545965B2",
    "US7925605B1",
    "US8073804B1",
    "US8392921B2",
    "US8495002B2",
    "US8924011B2",
    "US9239382B2",
    "US9261978B2",
    "US9373086B1",
    "US9380017B2",
    "US9424523B2",
    "US9471668B1",
    "US9555326B2",
    "US9564149B2",
    "US9568909B2",
    "US9569425B2",
    "US9659052B1",
    "US9747901B1",
    "US9792434B1",
    "US9801517B2"
  ]
}

Record 776 of 5,000 in Patents full text (MLC-0201). Request the full dataset.