# US 12,001,964 B2 · Artificial intelligence advisory systems and methods for behavioral pattern matching and language generation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,001,964 B2 - Document ID: US12001964B2 - Status: Granted - Kind: B2 - Application number: 18/115,831 - Filed: 2023-03-01 - Published: 2023-06-29 - Granted: 2024-06-04 - Earliest claimed: 2019-07-03 - Assignees: Kpn Innovations, LLC. - Applicants: Kpn Innovations, LLC. - Inventors: Kenneth Neumann - Web page: https://patentgrep.com/patent/US12001964B2 ## CPC - G06N 5/02: Knowledge representation; Symbolic representation - G06N 5/041: {Abduction} - G06F 16/3344: {using natural language analysis} - G06F 21/316: {by observing the pattern of computer usage, e.g. typical user behaviour} - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G16H 10/20: for electronic clinical trials or questionnaires - G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof - G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising - G16H 20/60: relating to nutrition control, e.g. diets - G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training - G16H 40/67: for remote operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H 80/00: ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring - G06F 40/35: Discourse or dialogue representation - G06F 40/56: Natural language generation - G06N 3/045: Combinations of networks - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract An artificial intelligence system for behavioral pattern matching and language generation includes at least a server. The system includes a behavior modification module operating on the at least a server, wherein the behavior modification module is designed and configured to receive at least a request for a behavior modification and generate a behavior modification model as a function of the at least a request for behavior modification. The system includes an artificial intelligence advisor operating on the at least a server, wherein the artificial intelligence advisor is configured to receive at least a user input from a user client device, generate at least a textual output using the behavior modification model and the at least a user input, and transmit the at least a textual output to the user client device. ## Claims ### Claim 1 An artificial intelligence system for providing a consultation for a user, the system comprising: a processor; and a memory containing instructions, the instructions configuring the processor to: extract one or more elements from a user input to detect a user query, wherein the user query comprises at least one of a conversational query and an informational query; detect a consultation event by matching one or more elements within the user query to a consultation action utilizing a consultation initiator which performs a machine learning operation on a machine-learning model, wherein performing the machine learning operation comprises: receiving a consultation training data set, wherein the consultation training data set comprises a plurality of word data and a plurality of phrase data correlated to categories of consultation events; training, iteratively, the machine-learning model using the consultation training data set and indicating the consultation event as a function of the trained machine-learning model and the word data and the phrase data; generate at least one textual output corresponding to at least one of the one or more elements within the user query, wherein the at least one textual output contains a category of the consultation event associated with an expert; store one or more of the at least one textual output, the user input, and the user query to a database; retrieve data corresponding to the stored one or more of the at least one textual output, the user input, and the user query from the database; and initiate the consultation by transmitting the retrieved data to the expert. ### Claim 2 (depends on 1) The artificial intelligence system of claim 1, wherein detecting the user query comprises applying a dependency parsing process to detect one or more syntactic elements within the user input. ### Claim 3 (depends on 1) The artificial intelligence system of claim 1, wherein the processor is further configured to store interactions between the user and other entities. ### Claim 4 (depends on 1) The artificial intelligence system of claim 1, wherein the user input and the at least one textual output are in a conversational language format. ### Claim 5 (depends on 1) The artificial intelligence system of claim 1, wherein at least one of the one or more elements of the user query are associated with a behavior. ### Claim 6 (depends on 5) The artificial intelligence system of claim 5, wherein the behavior is determined using metadata included in the user input. ### Claim 7 (depends on 5) The artificial intelligence system of claim 5, wherein the behavior is determined by correlating a plurality of different categories of the user input. ### Claim 8 (depends on 1) The artificial intelligence system of claim 1, wherein the expert is selected from an expert list based on one or more expert qualities associated with a behavior modification. ### Claim 9 (depends on 1) The artificial intelligence system of claim 1, wherein the expert is selected based on a user preference. ### Claim 10 (depends on 1) The artificial intelligence system of claim 1, wherein the textual output is generated based on a user history. ### Claim 11 An artificial intelligence method for providing consultation for a user, the method comprising: extracting, by a processor, one or more elements from a user input to detect a user query, wherein the user query comprises at least one of a conversational query and an informational query; detecting, by the processor, a consultation event by matching one or more elements within the user query to a consultation action utilizing a consultation initiator which performs a machine learning operation on a machine-learning model, wherein performing the machine learning operation comprises: receiving a consultation training data set, wherein the consultation training data set comprises a plurality of word data and a plurality of phrase data correlated to categories of consultation events; training, iteratively, the machine-learning model using the consultation training data set; and indicating the consultation event as a function of the trained machine-learning model and the word data and the phrase data; generating, by the processor, at least one textual output corresponding to at least one of the one or more elements within the user query, wherein the at least one textual output contains a category of the consultation event associated with an expert; storing, by the processor, one or more of the at least one textual output, the user input, and the user query to a database; retrieving, by the processor, data corresponding to the stored one or more of the at least one textual output, the user input, and the user query from the database; and initiating, by the processor, the consultation by transmitting the retrieved data to the expert. ### Claim 12 (depends on 11) The method of claim 11, wherein detecting the user query comprises applying a dependency parsing process to detect one or more syntactic elements within the user input. ### Claim 13 (depends on 11) The method of claim 11, further comprising storing, by the processor, interactions between the user and other entities. ### Claim 14 (depends on 11) The method of claim 11, wherein the user input and the at least one textual output are in a conversational language format. ### Claim 15 (depends on 11) The method of claim 11, wherein at least one of the one or more elements of the user query are associated with a behavior. ### Claim 16 (depends on 15) The method of claim 15, further comprising determining, by the processor, the behavior using metadata included in the user input. ### Claim 17 (depends on 15) The method of claim 15, further comprising determining, by the processor, the behavior by correlating a plurality of different categories of the user input. ### Claim 18 (depends on 11) The method of claim 11, further comprising selecting, by the processor, the expert from an expert list based on one or more expert qualities associated with a behavior modification. ### Claim 19 (depends on 11) The method of claim 11, further comprising selecting, by the processor, the expert based on a user preference. ### Claim 20 (depends on 11) The method of claim 11, further comprising generating, by the processor, the textual output based on a user history.