Automated recommendation and curation of tasks for experiences
Systems and methods for generating and providing experience recommendations to members of a task facilitation service are provided. A task recommendation system can identify a set of experience recommendations within a geographic region. These experience recommendations are ordered based on a member profile. The ordered experience recommendations are provided such that one or more experience recommendations can be selected for presentation to the member. When the member selects an experience recommendation, tasks corresponding to the experience recommendation are generated and performance of these tasks is monitored. The member profile is updated based on the performance of these tasks, the selected experience recommendation, and feedback corresponding to performance of these tasks.
1. A computer-implemented method, comprising:
automatically detecting a request to identify one or more experience recommendations for a member, wherein the request is automatically detected by using natural language processing to evaluate different messages exchanged over an ongoing communications session between the member and a representative;
identifying a set of experience preferences associated with the member, wherein the set of experience preferences is identified based on a member profile;
identifying a set of available experiences implemented to generate different experience recommendations for reducing levels of stress associated with different members;
processing the set of available experiences and the set of experience preferences through a trained machine learning algorithm to generate a set of experience recommendations, wherein the trained machine learning algorithm is trained using a dataset of sample experience recommendations and sample member profiles, and wherein the set of experience recommendations corresponds to different available experiences selected according to the set of experience preferences;
providing the set of experience recommendations through the ongoing communications session;
evaluating new communications exchanged over the ongoing communications session to detect selection of an experience recommendation, wherein the selection is an indication of a request to curate a corresponding experience;
generating a project-specific interface associated with the corresponding experience, wherein the project-specific interface is generated to facilitate an experience-specific communications session, and wherein the experience-specific communications session and the ongoing communications session are distinct;
monitoring in real-time performance of one or more tasks corresponding to the experience recommendation;
obtaining, through the experience-specific communications session, feedback corresponding to the performance of the one or more tasks, wherein the feedback includes an indication of whether the one or more tasks resulted in a positive outcome and reduction in a level of stress associated with the member; and
updating the member profile and the trained machine learning algorithm according to the feedback, wherein the trained machine learning algorithm is updated to generate new experience recommendations that have a higher likelihood of being selected by different members.
2. The computer-implemented method of claim 1 , wherein the set of experience recommendations is generated based on experience recommendation scores corresponding to the different available experiences, and wherein an experience recommendation score corresponds to a likelihood of a corresponding experience recommendation being selected by the member.
3. The computer-implemented method of claim 1 , further comprising:
identifying a template corresponding to the experience recommendation selected by the member, wherein the template indicates additional information required from the member for the performance of the one or more tasks; and
automatically prompting the member through the experience-specific communications session to provide the additional information, wherein the member is automatically prompted without representative intervention.
4. The computer-implemented method of claim 1 , further comprising:
detecting rejection of another experience recommendation from the one or more experience recommendations; and
automatically updating the member profile based on the rejection to reduce a likelihood of other experience recommendations similar to the other experience recommendation being selected for the member.
5. The computer-implemented method of claim 1 , further comprising:
generating a set of task-specific interfaces corresponding to the one or more tasks, wherein the set of task-specific interfaces is accessible through the project-specific interface, and wherein a task-specific interface provides a task-specific communications session.
6. The computer-implemented method of claim 1 , further comprising:
processing the updated member profile through the trained machine learning algorithm to generate a new set of experience recommendations, wherein the updated member profile is processed without representative interaction.
7. The computer-implemented method of claim 1 , wherein obtaining the feedback further comprises:
automatically soliciting the member through the experience-specific communications session for the feedback.
8. A system, comprising:
one or more processors; and
memory storing thereon instructions that, as a result of being executed by the one or more processors, cause the system to:
automatically detect a request to identify one or more experience recommendations for a member, wherein the request is automatically detected by using natural language processing to evaluate different messages exchanged over an ongoing communications session between the member and a representative;
identify a set of experience preferences associated with the member, wherein the set of experience preferences is identified based on a member profile;
identify a set of available experiences implemented to generate different experience recommendations for reducing levels of stress associated with different members;
process the set of available experiences and the set of experience preferences through a trained machine learning algorithm to generate a set of experience recommendations, wherein the trained machine learning algorithm is trained using a dataset of sample experience recommendations and sample member profiles, and wherein the set of experience recommendations corresponds to different available experiences selected according to the set of experience preferences;
provide the set of experience recommendations through the ongoing communications session;
evaluate new communications exchanged over the ongoing communications session to detect selection of an experience recommendation, wherein the selection is an indication of a request to curate a corresponding experience;
generate a project-specific interface associated with the corresponding experience, wherein the project-specific interface is generated to facilitate an experience-specific communications session, and wherein the experience-specific communications session and the ongoing communications session are distinct;
monitor in real-time performance of one or more tasks corresponding to the experience recommendation;
obtain, through the experience-specific communications session, feedback corresponding to the performance of the one or more tasks, wherein the feedback includes an indication of whether the one or more tasks resulted in a positive outcome and reduction in a level of stress associated with the member; and
update the member profile and the trained machine learning algorithm according to the feedback, wherein the trained machine learning algorithm is updated to generate new experience recommendations that have a higher likelihood of being selected by different members.
9. The system of claim 8 , wherein the set of experience recommendations is generated based on experience recommendation scores corresponding to the different available experiences, and wherein an experience recommendation score corresponds to a likelihood of a corresponding experience recommendation being selected by the member.
10. The system of claim 8 , wherein the instructions further cause the system to:
identify a template corresponding to the experience recommendation selected by the member, wherein the template indicates additional information required from the member for the performance of the one or more tasks; and
automatically prompt the member through the experience-specific communications session to provide the additional information, wherein the member is automatically prompted without representative intervention.
11. The system of claim 8 , wherein the instructions further cause the system to:
detect rejection of another experience recommendation from the one or more experience recommendations; and
automatically update the member profile based on the rejection to reduce a likelihood of other experience recommendations similar to the other experience recommendation being selected for the member.
12. The system of claim 8 , wherein the instructions further cause the system to:
generate a set of task-specific interfaces corresponding to the one or more tasks, wherein the set of task-specific interfaces is accessible through the project-specific interface, and wherein a task-specific interface provides a task-specific communications session.
13. The system of claim 8 , wherein the instructions further cause the system to:
process the updated member profile through the trained machine learning algorithm to generate a new set of experience recommendations, wherein the updated member profile is processed without representative interaction.
14. The system of claim 8 , wherein the instructions that cause the system to obtain the feedback further cause the system to:
automatically solicit the member through the experience-specific communications session for the feedback.
15. A non-transitory, computer-readable storage medium storing thereon executable instructions that, as a result of being executed by a computer system, cause the computer system to:
automatically detect a request to identify one or more experience recommendations for a member, wherein the request is automatically detected by using natural language processing to evaluate different messages exchanged over an ongoing communications session between the member and a representative;
identify a set of experience preferences associated with the member, wherein the set of experience preferences is identified based on a member profile;
identify a set of available experiences implemented to generate different experience recommendations for reducing levels of stress associated with different members;
process the set of available experiences and the set of experience preferences through a trained machine learning algorithm to generate a set of experience recommendations, wherein the trained machine learning algorithm is trained using a dataset of sample experience recommendations and sample member profiles, and wherein the set of experience recommendations corresponds to one or more different available experiences selected according to the set of experience preferences;
provide the set of experience recommendations through the ongoing communications session;
evaluate new communications exchanged over the ongoing communications session to detect selection of an experience recommendation, wherein the selection is an indication of a request to curate a corresponding experience;
generate a project-specific interface associated with the corresponding experience, wherein the project-specific interface is generated to facilitate an experience-specific communications session, and wherein the experience-specific communications session and the ongoing communications session are distinct;
monitor in real-time performance of one or more tasks corresponding to the experience recommendation;
obtain, through the experience-specific communications session, feedback corresponding to the performance of the one or more tasks, wherein the feedback includes an indication of whether the one or more tasks resulted in a positive outcome and reduction in a level of stress associated with the member; and
update the member profile and the trained machine learning algorithm according to the feedback, wherein the trained machine learning algorithm is updated to generate new experience recommendations that have a higher likelihood of being selected by different members.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the set of experience recommendations is generated based on experience recommendation scores corresponding to the different available experiences, and wherein an experience recommendation score corresponds to a likelihood of a corresponding experience recommendation being selected by the member.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
identify a template corresponding to the experience recommendation selected by the member, wherein the template indicates additional information required from the member for the performance of the one or more tasks; and
automatically prompt the member through the experience-specific communications session to provide the additional information, wherein the member is automatically prompted without representative intervention.
18. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
detect rejection of another experience recommendation from the one or more experience recommendations; and
automatically update the member profile based on the rejection to reduce a likelihood of other experience recommendations similar to the other experience recommendation being selected for the member.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
generate a set of task-specific interfaces corresponding to the one or more tasks, wherein the set of task-specific interfaces is accessible through the project-specific interface, and wherein a task-specific interface provides a task-specific communications session.
20. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
process the updated member profile through the trained machine learning algorithm to generate a new set of experience recommendations, wherein the updated member profile is processed without representative interaction.
21. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions that cause the computer system to obtain the feedback further cause the computer system to:
automatically solicit the member through the experience-specific communications session for the feedback.