Method for more accurately performing an autocomplete function

1. A method for autocompleting a textual input of a user, comprising:

receiving the textual input of the user via a user interface of a smartphone of the user;

generating a situational parameter relating to the user based on the textual input and on sensor data from a user sensor;

generating a temporal parameter based on the textual input and on the sensor data;

retrieving from a storage device historical textual input;

retrieving from the storage device historical sensor data relating to the situational parameter, wherein the historical sensor data that is retrieved is limited by the temporal parameter;

aggregating the historical textual input and the historical sensor data;

selecting a situational value relating to the situational parameter based on the historical textual input and the historical sensor data that have been aggregated;

generating a first list of words that the user is likely to input next based on the situational value that has been selected, wherein the words relate to the situational parameter;

ranking the words of the first list by probability that the user is intending to type each of the words; and

displaying to the user on the user interface a word ranked highest on the first list.

2. A method for autocompleting a textual input of a user, comprising:

receiving the textual input of the user via a user interface of a smartphone of the user;

generating a situational parameter relating to the user based on the textual input and on sensor data from a user sensor;

generating a temporal parameter based on the textual input and on the sensor data;

retrieving from a storage device historical textual input and historical sensor data relating to the situational parameter and the temporal parameter;

aggregating the historical textual input and the historical sensor data relating to the situational parameter and the temporal parameter;

selecting a situational value relating to the situational parameter based on the historical textual input and the historical sensor data that has been aggregated;

generating a first list of words that the user is likely to input next based on the situational value that has been selected, wherein the words relate to the situational parameter;

ranking the words of the first list by probability that the user is intending to type each of the words;

displaying to the user on the user interface a word ranked highest on the first list;

defining a time window in the past based on the situational parameter and the temporal parameter;

determining whether, for the user, a pre-existing model exists that relates the situational parameter to the time window;

using the pre-existing model, if the pre-existing model exists, to select the situational value relating to the situational parameter based on the historical textual input and the historical sensor data that has been aggregated;

aggregating the historical textual input and the historical sensor data relating to the situational parameter, if no pre-existing model exists, in time slots of equal length to the time window;

creating a language model, if no pre-existing model exists, using the historical textual input and the historical sensor data that has been aggregated; and

selecting, if no pre-existing model exists, the situational value relating to the situational parameter using the language model that has been created.

3. The method of claim 2 , wherein the words of the first list are ranked using the pre-existing model or the language model based on a combination of the probability of the user's intent and an association of the words with a targeted mental state of the user.

4. The method of claim 2 , further comprising:

receiving feedback from the user regarding the word displayed to the user on the user interface, wherein the feedback indicates whether the word is related to the situational parameter;

using the feedback to improve the pre-existing model, if the pre-existing model exists; and

using the feedback to create the language model, if no pre-existing model exists.

5. The method of claim 2 , wherein the language model is created in part using a characteristic of the user selected from the group consisting of: age, sex, ethnicity, demographic group, profession, personality type and medical condition indicated in electronic health records.

6. The method of claim 2 , further comprising:

retrieving from the storage device electronic health records relating to the user; and

using the pre-existing model to select the situational value based in part on the electronic health records.

7. The method of claim 1 , wherein the user sensor is selected from the group consisting of: a sensor on the smartphone of the user, a sensor on a wearable device of the user, and a sensor on a personal electronic device of the user.

8. The method of claim 1 , wherein the words of the first list are ranked based on a combination of the probability that the user is intending to type each of the words and an association of the words with a targeted mental state of the user.

9. A method for autocompleting a textual input of a user, comprising:

receiving the textual input of the user via a user interface of a smartphone of the user;

generating a situational parameter relating to the user based on the textual input and on sensor data from a user sensor;

generating a temporal parameter based on the textual input and on the sensor data;

retrieving from a storage device historical textual input and historical sensor data relating to the situational parameter and the temporal parameter;

aggregating the historical textual input and the historical sensor data relating to the situational parameter and the temporal parameter;

selecting a situational value relating to the situational parameter based on the historical textual input and the historical sensor data that has been aggregated;

generating a first list of words that the user is likely to input next based on the situational value that has been selected, wherein the words relate to the situational parameter;

ranking the words of the first list by probability that the user is intending to type each of the words;

displaying to the user on the user interface a word ranked highest on the first list;

generating a second list of words that the user is likely to input next based on the textual input of the user received via the user interface; and

merging the first list and the second list to generate an integrated list of words that the user is likely to input next, wherein the words of the integrated list are ranked by probability that the user is intending to type each word.

10. The method of claim 1 , wherein the time window is defined in part based on an explicit input by the user.

11. The method of claim 1 , wherein the situational parameter is generated in part based on a default value that is associated with the textual input.

12. The method of claim 1 , further comprising:

generating a second situational parameter based on the textual input;

retrieving historical textual input and historical sensor data relating to the second situational parameter; and

aggregating the historical textual input and the historical sensor data relating to the situational parameter and the second situational parameter.

13. The method of claim 1 , wherein the situational parameter relates to a characteristic selected from the group consisting of: a mood, a physical location, a surrounding environment, an activity level, and a social interaction.

14. The method of claim 1 , wherein the situational parameter involves a parameter related to the user selected from the group consisting of: a heart rate, a breathing rate, a GPS coordinate, a noise level experienced by the user, a light level experienced by the user, a time of day, a season, a distance traveled by the user, and a number of steps taken by the user.

15. The method of claim 1 , wherein the word displayed to the user on the user interface is selected from the first list based on an activity undertaken by the user in the past.

16. The method of claim 1 , wherein the word displayed to the user on the user interface is selected from the first list based on a predicted future activity of the user.

17. The method of claim 1 , wherein the storage device stores a database of electronic health records.

18. A system for autocompleting a textual input of a user, comprising:

a user interface on which the textual input is received from the user;

an analysis module that generates a situational parameter of the user and a temporal parameter based on the textual input;

a storage device from which the analysis module retrieves historical textual input and historical sensor data that relates to the situational parameter, wherein the historical sensor data that is retrieved is limited by the temporal parameter, wherein the analysis module aggregates the historical textual input and the historical sensor data;

a model-implementing module that selects a situational value from the situational parameter based on the historical textual input and the historical sensor data that has been aggregated; and

a situational autocomplete module that generates a list of words that the user is likely to input next based on the situational value that has been selected, wherein the words relate to the situational parameter, wherein the situational autocomplete module ranks the words of the list by probability that the user is intending to type each of the words, and wherein a word that is ranked highest on the list is displayed to the user on the user interface.

19. A system for autocompleting a textual input of a user, comprising:

a user interface on which the textual input is received from the user;

an analysis module that generates a situational parameter of the user and a temporal parameter based on the textual input;

a storage device from which the analysis module retrieves historical textual input and historical sensor data that relates to the situational parameter and the temporal parameter, wherein the analysis module aggregates the historical textual input and the historical sensor data relating to the situational parameter and the temporal parameter;

a model-implementing module that selects a situational value from the situational parameter based on the historical textual input and the historical sensor data that has been aggregated;

a situational autocomplete module that generates a list of words that the user is likely to input next based on the situational value that has been selected, wherein the words relate to the situational parameter, wherein the situational autocomplete module ranks the words of the list by probability that the user is intending to type each of the words, and wherein a word that is ranked highest on the list is displayed to the user on the user interface; and

a time window determining module that defines a time window in the past based on the temporal parameter and the situational parameter, wherein the model-implementing module determines whether, for the user, a pre-existing model exists that relates the situational parameter to the time window, wherein the model-implementing module uses the pre-existing model, if the pre-existing model exists, to selects the situational value, wherein the analysis module aggregates the historical textual input and the historical sensor data relating to the situational parameter, if no pre-existing model exists, in time slots of equal length to the time window, wherein the model-implementing module creates a language model, if no pre-existing model exists, using the historical textual input and the historical sensor data that has been aggregated, and wherein the analysis module selects, if no pre-existing model exists, the situational value relating to the situational parameter using the language model that has been created.

20. The system of claim 19 , wherein the words of the list are ranked using the pre-existing model or the language model based on a combination of the probability of the user's intent and an association of the words with a targeted mental state of the user.

21. The system of claim 19 , wherein the language model is created in part using a characteristic of the user selected from the group consisting of: age, sex, ethnicity, demographic group, profession, personality type and medical condition indicated in electronic health records.

22. The system of claim 18 , wherein the words of the list are ranked based on a combination of the probability that the user is intending to type each of the words and an association of the words with a targeted mental state of the user.

23. The system of claim 18 , wherein the situational parameter relates to a characteristic selected from the group consisting of: a mood, a physical location, a surrounding environment, an activity level, and a social interaction.

24. The system of claim 18 , wherein the situational parameter involves a parameter related to the user selected from the group consisting of: a heart rate, a breathing rate, a GPS coordinate, a noise level experienced by the user, a light level experienced by the user, a time of day, a season, a distance traveled by the user, and a number of steps taken by the user.

25. The system of claim 18 , wherein the word displayed to the user on the user interface is selected from the list based on an activity undertaken by the user in the past.

26. The system of claim 18 , wherein the word displayed to the user on the user interface is selected from the list based on a predicted future activity of the user.