Artificial assistant system notifications
Artificial assistant system notification techniques are described that overcome the challenges of conventional search techniques. In one example, a user profile is generated to describe aspects of products or services learned through natural language conversations between a user and an artificial assistant system. These aspects may include price as well as non-price aspects such as color, texture, material, and so forth. To learn the aspects, the artificial assistant system may leverage spoken utterances and text initiated by the user as well as learn the aspects from digital images output as part of the conversation. Once generated, the user profile is then usable by the artificial assistant system to assist in subsequent searches.
1. A method implemented by a computing device, the method comprising:
generating, by the computing device, a user profile including an aspect model trained using machine learning based on initial natural language conversations between an artificial assistant system of the computing device and a user, the user profile identifying a first value of an aspect that resulted in successful conversion of a first product or service as part of the initial natural language conversations;
identifying, by the computing device, a second value of the aspect that resulted in unsuccessful conversion of a second product or service as part of a subsequent natural language conversation;
learning, automatically and without user intervention by the computing device, a first threshold value of the aspect using the aspect model trained using machine learning based on the first value and the second value of the aspect;
receiving, by the computing device, an indication of a third value of the aspect that resulted in unsuccessful conversion of a third product or service;
learning, automatically and without user intervention by the computing device, a second threshold value of the aspect using the aspect model trained using machine learning based on the third value of the aspect;
initiation, by the computing device, a search query including the aspect;
repeating, in a background of the computing device for the user, one or more searches automatically and without user intervention using the search query until a comparison of a value of the aspect of a search result of the repeated one or more searchs and the second threshold value of the aspect; and
outputting, by the artificial system of the computing device, a notification responsive to the determination that the triggering event has occurred.
2. The method implemented by the computing device as described in claim 1 , wherein the aspect is a non-price aspect, the non-price aspect including color, size, pattern, style, or material.
3. The method implemented by the computing device as described in claim 2 , wherein the non-price aspect is identified from a digital image output by the artificial assistant system of the computing device as part of the initial natural languarge conversations.
4. The method implemented by the computing device as described in claim 3 , wherein the search query including the aspect further includes a different product or service.
5. The method implemented by the computing device as described in claim 1 , wherein the aspect is a price and the second threshold value of the aspect is a threshold change in the price.
6. A computing device comprising:
a processing system; and
a memory to store instructions which, responsive to execution by the processing system, cause the processing system to implement an artificial assistant system to perform operations including:
generating a user profile including an aspect model trained using machine learning based on initial natural language conversations between an artificial assistant system of the computing device and a user, the user profile identifying a first value of an aspect that resulted in successful conversion of a first product or service as part of the initial natural language conversation;
identifying a second value of the aspect that resulted in unsuccessful conversion of a second product or service as part of a subsequent natural language conversation;
learning, automatically and without user intervention, a first threshold value of the aspect using the aspect model trained using machine learning based on the first value and the second value of the aspect;
receiving an indication of a third value of the aspect that resulted in unsuccessful conversion of a third product or service;
learning, automatically and without user intervention, a second threshold value of the aspect using the aspect model trained using machine learning based on the third value of the aspect;
initiating a search query including the aspect;
repeating, in a background of the computing device for the user, one or more searches automatically and without user intervention using the search query until a comparison of a value of the aspect of a search result of the repeated one or more searches and the second threshold value of the aspect; and
outputting, by the artificial assistant system, a notification responsive to the determination that the triggering event has occurred.
7. The computing device as described in claim 6 , wherein the aspect is a non-price aspect, the non-price aspect including color, size, pattern, style, or material.
8. The computing device as descrbed in claim 7 , wherein the non-price aspect is identified from a digital image output by the artificial assistant system of the computing device as part of the initial natural language conversations.
9. The computing device as described in claim 6 , wherein the search query including the aspect further includes a different product or service.
10. The computing device as described in claim 6 , wherein the aspect is a price and the second threshold value of the aspect is a threshold change in the price.
11. One or more non-transitory computer readable storage media storing instructions that, responsive to execution by a processing system, cause the processing system to implement an artificial assistant system to perform operations including:
generating a user profile including an aspect model trained using machine learning based on initial natural language conversations between an artificial assistant system and a user, the user profile identifying a first value of an aspect that resulted in successful conversion of a first product or service as part of the initial natural language conversations;
identifying a second value of the aspect that resulted in unsuccessful conversion of a second product or service as part of a subsequent natural language conversation;
learning, automatically and without user intervention, a first threshold value of the aspect using the aspect model trained using machine learning based on the first value and the second value of the aspect;
receiving an indication of a third value of the aspect that resulted in unsuccessful conversation of a third product or service;
learning, automatically and without user intervention, a second threshold value of the aspect using the aspect model trained using machine learning based on the third value of the aspect;
initiating a search query including the aspect;
repeating, in a background, one or more searches automatically and without user intervention using the search query until a determination that a triggering event has occurred, the triggering event based on a comparison of a value of the aspect of a search reslut of the repeated one or more searches and the second threshold value of the aspect; and
outputting, by the artificial assistant system, a notification responsive to the determination that the triggering event has occurred.
12. The one or more non-transitory computer readable storage media as described in claim 11 , wherein the aspect is a non-price aspect, the non-price aspect including color, size, pattern, style, or material.
13. The one or more non-transitory computer readable storage media as described in claim 12 , wherein the non-price aspect is identified from a digital image output by the artificial assistant system as part of the initial natural language conversations.
14. The one or more non-transitory computer readable storage media as described in claim 11 , wherein the search query including the aspect further includes a different product or service.
15. The one or more non-transitory computer readable storage medias as described in claim 11 , wherein the aspect is a price and the second threshold value of the aspect is a threshold change in the price.