Signal processing for making predictive determinations
In some examples, unstructured data is evaluated using a natural language processing model to output a set of subjective indicators. These subjective indicators are scored using a predictive model to determine whether a dependent user has or is likely to develop a particular condition such as a cellular abnormality.
1. A system comprising:
memory configured to store computer-executable instructions; and
one or more processors configured to access the memory to execute the computer-executable instructions to perform operations comprising:
accessing messages in a data stream, the messages originating from a plurality of computer systems in a computer network, the plurality of computer system comprising electronic devices that generate the messages to be transmitted via the computer network;
identifying first identified data from a first message from the accessed messages, and determining that the first identified data corresponds to a first entity, where the first message is from a first system of the plurality of computer systems;
identifying second identified data from a second message from the accessed messages, and determining that the second identified data also corresponds to the first entity, where the second message is from a second system of the plurality of computer systems;
aggregating data from the accessed messages determined to correspond to the first entity, the aggregated data comprising the first identified data and the second identified data;
selecting a subset of data from the aggregated data, including the first identified data and the second identified data;
generating a report corresponding to the first entity to comprise the selected subset of data, including:
ephemeral data from one or both of the first identified data and the second identified data that is tagged to be removed from the report at a predetermined time; and
persistent data from one or both of the first identified data and the second identified data that is not to be removed from the report at the predetermined time;
providing access to the report via one or more interfaces; and
removing the ephemeral data from the report based at least in part on the predetermined time.
2. The system as recited in claim 1 , the operations further comprising:
causing transmission of the report to one or more destination devices to facilitate the providing the access.
3. The system as recited in claim 2 , where the one or more destination devices correspond to one or both of the first system and the second system, and the report is transmitted to one or both of the first system and the second system.
4. The system as recited in claim 3 , the operations further comprising:
removing a portion of the report as a function of a requirement of the first system or the second system before transmitting the report to the first system or the second system.
5. The system as recited in claim 4 , the operations further comprising:
generating first de-identified data based at least in part on the first identified data; and
generating statistical data at least partially by aggregating the first de-identified data for the first entity with second de-identified data for a second entity.
6. The system as recited in claim 5 , where the transmission comprises the statistical data.
7. The system as recited in claim 6 , where the generating the report comprises generating a longitudinal history corresponding to the first entity, the report comprising the longitudinal history.
8. A computer-implemented method comprising:
accessing, by a computer system communicably couplable via a computer network with a plurality of computer systems comprising electronic devices that generate messages to be transmitted via the computer network toward a plurality of different destination devices, messages in a data stream, the messages originating from the plurality of computer systems in the computer network;
identifying, by the computer system, first identified data from a first message from the accessed messages, and determining that the first identified data corresponds to a first entity, where the first message is from a first system of the plurality of computer systems;
identifying, by the computer system, second identified data from a second message from the accessed messages, and determining that the second identified data also corresponds to the first entity, where the second message is from a second system of the plurality of computer systems;
aggregating, by the computer system, data from the accessed messages determined to correspond to the first entity, the aggregated data comprising the first identified data and the second identified data;
selecting, by the computer system, a subset of data from the aggregated data, including the first identified data and the second identified data;
generating, by the computer system, a report corresponding to the first entity to comprise the selected subset of data, including:
ephemeral data from one or both of the first identified data and the second identified data that is tagged to be removed from the report at a predetermined time; and
persistent data from one or both of the first identified data and the second identified data that is not to be removed from the report at the predetermined time;
providing, by the computer system, access to the report via one or more interfaces; and
removing, by the computer system, the ephemeral data from the report based at least in part on the predetermined time.
9. The computer-implemented method as recited in claim 8 , further comprising:
causing, by the computer system, transmission of the report to one or more destination devices to facilitate the providing the access.
10. The computer-implemented method as recited in claim 9 , where the one or more destination devices correspond to one or both of the first system and the second system, and the report is transmitted to one or both of the first system and the second system.
11. The computer-implemented method as recited in claim 10 , further comprising:
removing, by the computer system, a portion of the report as a function of a requirement of the first system or the second system before transmitting the report to the first system or the second system.
12. The computer-implemented method as recited in claim 11 , further comprising:
generating, by the computer system, first de-identified data based at least in part on the first identified data; and
generating, by the computer system, statistical data at least partially by aggregating the first de-identified data for the first entity with second de-identified data for a second entity.
13. The computer-implemented method as recited in claim 12 , where the transmission comprises the statistical data.
14. The computer-implemented method as recited in claim 13 , where the generating comprises generating a longitudinal history corresponding to the first entity based at least in part on the aggregated data, the report comprising the longitudinal history.
15. One or more non-transitory, machine-readable storage media comprising machine-executable instructions that, when executed by one or more processing devices, cause the one or more processing devices to perform operations comprising:
accessing messages in a data stream, the messages originating from a plurality of computer systems in a computer network;
identifying first identified data from a first message from the accessed messages, and determining that the first identified data corresponds to a first entity, where the first message is from a first system of the plurality of computer systems;
identifying second identified data from a second message from the accessed messages, and determining that the second identified data also corresponds to the first entity, where the second message is from a second system of the plurality of computer systems;
aggregating data from the accessed messages determined to correspond to the first entity, the aggregated data comprising the first identified data and the second identified data;
selecting a subset of data from the aggregated data, including the first identified data and the second identified data;
generating a report corresponding to the first entity to comprise the selected subset of data, including:
ephemeral data from one or both of the first identified data and the second identified data that is tagged to be removed from the report at a predetermined time; and
persistent data from one or both of the first identified data and the second identified data that is not to be removed from the report at the predetermined time;
providing access to the report via one or more interfaces; and
removing the ephemeral data from the report based at least in part on the predetermined time.
16. The one or more non-transitory, machine-readable storage media as recited in claim 15 , the operations further comprising:
causing transmission of the report to one or more destination devices to facilitate the providing the access.
17. The one or more non-transitory, machine-readable storage media as recited in claim 16 , where the one or more destination devices correspond to one or both of the first system and the second system, and the report is transmitted to one or both of the first system and the second system.
18. The one or more non-transitory, machine-readable storage media as recited in claim 17 , the operations further comprising:
removing a portion of the report as a function of a requirement of the first system or the second system before transmitting the report to the first system or the second system.
19. The one or more non-transitory, machine-readable storage media as recited in claim 18 , the operations further comprising:
generating first de-identified data based at least in part on the first identified data; and
generating statistical data at least partially by aggregating the first de-identified data for the first entity with second de-identified data for a second entity.
20. The one or more non-transitory, machine-readable storage media as recited in claim 19 , where the transmission comprises the statistical data.