# US 2019/0318008 A1 · Media selection based on learning past behaviors > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318008 A1 - Document ID: US20190318008A1 - Status: Published application - Kind: A1 - Application number: 15/954,866 - Filed: 2018-04-17 - Published: 2019-10-17 - Earliest claimed: 2018-04-17 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Luis Carlos Cruz Huertas; Rick A. Hamilton, II; Hari K. Narasimhamurthy; Edgar A. Zamora Duran - Web page: https://patentgrep.com/patent/US20190318008A1 ## CPC - G06F 16/435: Filtering based on additional data, e.g. user or group profiles - G06F 16/4387: {by the use of playlists} - G06N 5/02: Knowledge representation; Symbolic representation - G06N 5/04: Inference or reasoning models - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method, computer system, and a computer program product for selecting a media playlist based on learning past behaviors of a user is provided. The present invention may include receiving a plurality of current user data. The present invention may then include receiving a plurality of current external conditions data. The present invention may also include enriching a plurality of current raw data associated with the plurality of current user data, the plurality of user reactions to the media selections and the plurality of current external conditions data. The present invention may further include determining the plurality of current user data exceeds a threshold. The present invention may also include, in response to determining the threshold is exceeded, creating a dataset. The present invention may then include retrieving a media playlist. The present invention may further include sending the retrieved media playlist to a media device. ## Claims ### Claim 1 A method for selecting a media playlist based on learning past behaviors of a user, the method comprising: receiving a plurality of current user data associated with the user from a user device, wherein the received plurality of current user data associated with the user includes a plurality of user reaction data to a plurality of media selections corresponding with the user; receiving a plurality of current external conditions data associated with the user from the user device; enriching a plurality of current raw data associated with the received plurality of current user data, the received plurality of user reactions to the plurality of media selections and the received plurality of current external conditions data; determining the received plurality of current user data exceeds a threshold associated with the user; in response to determining that the received plurality of current user data exceeds the threshold, creating a dataset based on the determined plurality of current user data based on the exceeded threshold associated with the user; retrieving, from a records of learned user preferences and behaviors database and a combination of external digital devices, a media playlist based on the determined plurality of current user data exceeding the threshold associated with the user, wherein the retrieved media playlist alters the received plurality of current user data; and sending the retrieved media playlist to a media device associated with the user. ### Claim 2 (depends on 1) The method of claim 1, further comprising: determining that the retrieved media playlist fails to satisfy a user listening behavior; searching the records of learned user preferences and behaviors database to identify an alternate media playlist; retrieving the identified alternate media playlist, wherein the created dataset is utilized to match a user reaction with the retrieved alternate resulting media playlist; and sending the identified alternate media playlist to the media player associated with the user. ### Claim 3 (depends on 1) The method of claim 1, further comprising: receiving a plurality of training user data associated with the user from the user device; receiving a plurality of training external conditions data associated with the user on the user device; querying a plurality of media selections made by the user; enriching a plurality of raw training data associated with the received plurality of training user data, the queried plurality of media selections, and the received plurality of training external conditions data; correlating the enriched plurality of raw training data with the received plurality of training user data and the received plurality of training external conditions data to the queried plurality of media selections; and storing the correlated plurality of training user data and the correlated plurality of training external conditions data with the corresponding queried plurality of media selections in the records of learned user preferences and behaviors database. ### Claim 4 (depends on 3) The method of claim 3, further comprising: monitoring a plurality of reactions by the user based on the queried plurality of media selections; correlating the monitored plurality of reactions by the user to the corresponding queried plurality media selections; and storing the correlated plurality of reactions by the user with the corresponding queried plurality of media selections in the records of learned user preferences and behaviors database. ### Claim 5 (depends on 3) The method of claim 3, wherein receiving the plurality of training user data associated with the user on the user device, further comprises: utilizing a plurality of biometric devices and a plurality of biometric sensors associated with the mood, cognitive status and activity of the user. ### Claim 6 (depends on 3) The method of claim 3, wherein receiving the plurality of training external conditions data associated with the user on the user device, further comprises: utilizing a plurality of social media posts, a plurality of application program interfaces, and a plurality of data tracking services associated with the location, context and environmental conditions associated with the user. ### Claim 7 (depends on 4) The method of claim 4, wherein monitoring a plurality of reactions by the user based on the queried plurality of media selections, further comprises: utilizing a plurality of biometric devices and a plurality of biometric sensors associated with the mood, frustration level, cognitive status and activity of the user, and a plurality of social media posts associated with the user. ### Claim 8 A computer system for selecting a media playlist based on learning past behaviors of a user, comprising: one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising: receiving a plurality of current user data associated with the user from a user device, wherein the received plurality of current user data associated with the user includes a plurality of user reaction data to a plurality of media selections corresponding with the user; receiving a plurality of current external conditions data associated with the user from the user device; enriching a plurality of current raw data associated with the received plurality of current user data, the received plurality of user reactions to the plurality of media selections and the received plurality of current external conditions data; determining the received plurality of current user data exceeds a threshold associated with the user; in response to determining that the received plurality of current user data exceeds the threshold, creating a dataset based on the determined plurality of current user data based on the exceeded threshold associated with the user; retrieving, from a records of learned user preferences and behaviors database and a combination of external digital devices, a media playlist based on the determined plurality of current user data exceeding the threshold associated with the user, wherein the retrieved media playlist alters the received plurality of current user data; and sending the retrieved media playlist to a media device associated with the user. ### Claim 9 (depends on 8) The computer system of claim 8, further comprising: determining that the retrieved media playlist fails to satisfy a user listening behavior; searching the records of learned user preferences and behaviors database to identify an alternate media playlist; retrieving the identified alternate media playlist, wherein the created dataset is utilized to match a user reaction with the retrieved alternate resulting media playlist; and sending the identified alternate media playlist to the media player associated with the user. ### Claim 10 (depends on 8) The computer system of claim 8, further comprising: receiving a plurality of training user data associated with the user from the user device; receiving a plurality of training external conditions data associated with the user on the user device; querying a plurality of media selections made by the user; enriching a plurality of raw training data associated with the received plurality of training user data, the queried plurality of media selections, and the received plurality of training external conditions data; correlating the enriched plurality of raw training data with the received plurality of training user data and the received plurality of training external conditions data to the queried plurality of media selections; and storing the correlated plurality of training user data and the correlated plurality of training external conditions data with the corresponding queried plurality of media selections in the records of learned user preferences and behaviors database. ### Claim 11 (depends on 10) The computer system of claim 10, further comprising: monitoring a plurality of reactions by the user based on the queried plurality of media selections; correlating the monitored plurality of reactions by the user to the corresponding queried plurality media selections; and storing the correlated plurality of reactions by the user with the corresponding queried plurality of media selections in the records of learned user preferences and behaviors database. ### Claim 12 (depends on 10) The computer system of claim 10, wherein receiving the plurality of training user data associated with the user on the user device, further comprises: utilizing a plurality of biometric devices and a plurality of biometric sensors associated with the mood, cognitive status and activity of the user. ### Claim 13 (depends on 10) The computer system of claim 10, wherein receiving the plurality of training external conditions data associated with the user on the user device, further comprises: utilizing a plurality of social media posts, a plurality of application program interfaces, and a plurality of data tracking services associated with the location, context and environmental conditions associated with the user. ### Claim 14 (depends on 11) The computer system of claim 11, wherein monitoring a plurality of reactions by the user based on the queried plurality of media selections, further comprises: utilizing a plurality of biometric devices and a plurality of biometric sensors associated with the mood, frustration level, cognitive status and activity of the user, and a plurality of social media posts associated with the user. ### Claim 15 A computer program product for selecting a media playlist based on learning past behaviors of a user, comprising: one or more computer-readable storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising: receiving a plurality of current user data associated with the user from a user device, wherein the received plurality of current user data associated with the user includes a plurality of user reaction data to a plurality of media selections corresponding with the user; receiving a plurality of current external conditions data associated with the user from the user device; enriching a plurality of current raw data associated with the received plurality of current user data, the received plurality of user reactions to the plurality of media selections and the received plurality of current external conditions data; determining the received plurality of current user data exceeds a threshold associated with the user; in response to determining that the received plurality of current user data exceeds the threshold, creating a dataset based on the determined plurality of current user data based on the exceeded threshold associated with the user; retrieving, from a records of learned user preferences and behaviors database and a combination of external digital devices, a media playlist based on the determined plurality of current user data exceeding the threshold associated with the user, wherein the retrieved media playlist alters the received plurality of current user data; and sending the retrieved media playlist to a media device associated with the user. ### Claim 16 (depends on 15) The computer program product of claim 15, further comprising: determining that the retrieved media playlist fails to satisfy a user listening behavior; searching the records of learned user preferences and behaviors database to identify an alternate media playlist; retrieving the identified alternate media playlist, wherein the created dataset is utilized to match a user reaction with the retrieved alternate resulting media playlist; and sending the identified alternate media playlist to the media player associated with the user. ### Claim 17 (depends on 15) The computer program product of claim 15, further comprising: receiving a plurality of training user data associated with the user from the user device; receiving a plurality of training external conditions data associated with the user on the user device; querying a plurality of media selections made by the user; enriching a plurality of raw training data associated with the received plurality of training user data, the queried plurality of media selections, and the received plurality of training external conditions data; correlating the enriched plurality of raw training data with the received plurality of training user data and the received plurality of training external conditions data to the queried plurality of media selections; and storing the correlated plurality of training user data and the correlated plurality of training external conditions data with the corresponding queried plurality of media selections in the records of learned user preferences and behaviors database. ### Claim 18 (depends on 17) The computer program product of claim 17, further comprising: monitoring a plurality of reactions by the user based on the queried plurality of media selections; correlating the monitored plurality of reactions by the user to the corresponding queried plurality media selections; and storing the correlated plurality of reactions by the user with the corresponding queried plurality of media selections in the records of learned user preferences and behaviors database. ### Claim 19 (depends on 17) The computer program product of claim 17, wherein receiving the plurality of training user data associated with the user on the user device, further comprises: utilizing a plurality of biometric devices and a plurality of biometric sensors associated with the mood, cognitive status and activity of the user. ### Claim 20 (depends on 17) The computer program product of claim 17, wherein receiving the plurality of training external conditions data associated with the user on the user device, further comprises: utilizing a plurality of social media posts, a plurality of application program interfaces, and a plurality of data tracking services associated with the location, context and environmental conditions associated with the user.