Parsing electronic conversations for presentation in an alternative interface

1. A computer-implemented method comprising:

identifying two or more objects in an electronic chatting thread between a plurality of participants, the electronic chatting thread comprising a plurality of objects, wherein the plurality of objects are of different media types, the two or more objects include a non-verbal object, and the non-verbal object is one of an image, an animated image, an emoji, or a video;

grouping the two or more objects into two or more object groups by their different media types, wherein each object group contains at least one object;

programmatically analyzing the electronic chatting thread based on the two or more object groups to determine a conversational structure of the electronic chatting thread conversation;

applying conversational framing to the two or more object groups based on the conversational structure of the electronic chatting thread by generating (a) a textual description of the non-verbal object and (b) within the electronic chatting thread, inserting one or more interstitial conversational framing portions between a pair of object groups, the one or more interstitial conversational framing portions descriptive of a relationship between the pair of object groups;

generating a voice interface conversational presentation that includes a verbal representation of the textual description of the non-verbal object; and

providing the voice interface conversational presentation configured for output by an audio output device.

2. The computer-implemented method of claim 1 , wherein identifying the two or more objects includes identifying one or more verbal objects.

3. The computer-implemented method of claim 2 , wherein grouping the two or more objects includes:

grouping sequential verbal objects;

grouping sequential non-verbal objects; and

retaining sequence information of the electronic chatting thread.

4. The computer-implemented method of claim 1 , wherein applying conversational framing includes inserting an introductory conversational framing portion at a beginning of the voice interface conversational presentation.

5. The computer-implemented method of claim 4 , wherein the introductory conversational framing portion includes identification of one or more participants in the electronic chatting thread.

6. The computer-implemented method of claim 1 , wherein applying conversational framing includes inserting a conclusory conversational framing portion between a last object group and a preceding object group, wherein the preceding object group immediately precedes the last object group.

7. The computer-implemented method of claim 1 , wherein identifying the two or more objects within the electronic chatting thread includes programmatically analyzing an encoding of objects in the electronic chatting thread.

8. The computer-implemented method of claim 1 , wherein applying conversational framing includes one or more of expanding shorthand text, leaving shorthand text in place, and replacing shorthand text with text of another language.

9. The computer-implemented method of claim 1 , wherein applying conversational framing includes converting a graphical symbol to a textual description of the graphical symbol.

10. The computer-implemented method of claim 1 , further comprising:

presenting an audio query to a user when a determination is made that an operational context indicates that voice interface presentation is a suitable form of presentation;

receiving an audio response to the audio query; and

based on the audio response, causing the voice interface conversational presentation to be output from the audio output device.

11. The computer-implemented method of claim 1 , wherein the electronic chatting thread includes a text portion and at least one of a graphical symbol or a uniform resource locator.

12. The computer-implemented method of claim 1 , further comprising:

determining a context of a device;

causing the voice interface conversational presentation to be output via the audio output device when the context of the device is one for which voice output is suitable; and

causing the electronic chatting thread to be displayed on a display device when the context of the device is one for which visual display is suitable.

13. A system comprising:

one or more processors coupled to a non-transitory computer readable medium having stored thereon software instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including:

identifying two or more objects in an electronic chatting thread between a plurality of participants, the electronic chatting thread comprising a plurality of objects, wherein the plurality of objects are of different media types, the two or more objects include a non-verbal object, and the non-verbal object is one of an image, an animated image, an emoji, or a video;

grouping the two or more objects into two or more object groups by their different media types, wherein each object group contains at least one object;

programmatically analyzing the electronic chatting thread based on the two or more object groups to determine a conversational structure of the electronic chatting thread;

applying conversational framing to the two or more objects based on the conversational structure of the electronic chatting thread by generating (a) a textual description of the non-verbal object and (b) within the electronic chatting thread, inserting one or more interstitial conversational framing portions between a pair of object groups, the one or more interstitial conversational framing portions descriptive of a relationship between the pair of object groups;

generating an alternative interface conversational presentation that includes a verbal representation of the textual description of the non-verbal object; and

providing the alternative interface conversational presentation having at least a portion configured for output by a non-display output device.

14. The system of claim 13 , wherein identifying the two or more objects includes identifying one or more verbal objects.

15. The system of claim 13 , wherein identifying the two or more objects includes programmatically analyzing an encoding of the two or more objects.

16. A non-transitory computer readable medium having stored thereon software instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:

identifying two or more objects in an electronic chatting thread between a plurality of participants, the electronic chatting thread comprising a plurality of objects, wherein the plurality of objects are of different media types, the two or more objects include a non-verbal object, and the non-verbal object is one of an image, an animated image, an emoji, or a video;

grouping the two or more objects into two or more object groups by their different media types, wherein each object group contains at least one object;

programmatically analyzing the electronic chatting thread based on the two or more object groups conversation to determine a conversational structure of the electronic chatting thread conversation;

applying conversational framing to the two or more objects based on the conversational structure of the electronic chatting thread conversation by generating (a) a textual description of the non-verbal object and (b) within the electronic chatting thread, inserting one or more interstitial conversational framing portions between a pair of object groups, the one or more interstitial conversational framing portions descriptive of a relationship between the pair of object groups;

generating an alternative interface conversational presentation that includes a verbal representation of the textual description of the non-verbal object; and

providing the alternative interface conversational presentation having at least a portion configured for output by a non-display output device.

17. The non-transitory computer readable medium of claim 16 , wherein identifying the two or more objects includes identifying one or more verbal objects.

18. The non-transitory computer readable medium of claim 16 , wherein grouping the two or more objects includes:

grouping sequential verbal objects;

grouping sequential non-verbal objects; and

retaining sequence information of the electronic chatting thread.

19. The non-transitory computer readable medium of claim 16 , wherein applying conversational framing includes inserting an introductory conversational framing portion at a beginning of the alternative interface conversational presentation.

20. The non-transitory computer readable medium of claim 19 , wherein the introductory conversational framing portion includes identification of one or more participants in the electronic chatting thread.