Systems and methods for a two-tier machine learning model for generating conversational responses
地域：
VA
VA McLean
摘要
Methods and systems are described for generating dynamic conversational responses using two-tier machine learning models. The dynamic conversational responses may be generated in real time and reflect the likely goals and/or intents of a user. The two-tier machine learning model may include a first tier that determines an intent cluster based on a feature input, and a second tier that determines a specific intent from the cluster.
說明書
This application is a continuation of U.S. patent application Ser. No. 16/908,116, filed Jun. 22, 2020. The content of the foregoing application is incorporated herein in its entirety by reference.
The invention relates to generating dynamic conversational responses using two-tier machine learning models.
In recent years, the amount and uses of interactive programs has risen considerably. In tandem with this rise, is the need to have human-like interactions and/or create applications that mimic the tone, cadence, and speech patterns of humans. Additionally, in order to fulfill user-interaction requirements, these applications need to be helpful, and thus respond intelligently by providing relevant responses to user inputs, whether these inputs are received via text, audio, or video input.
權(quán)利要求
What is claimed is:1. A system for generating dynamic conversational responses using two-tier machine learning models, the system comprising:cloud-based storage circuitry configured to:store a first machine learning model, wherein the first machine learning model is trained to select an intent cluster from a plurality of intent clusters based on user actions, and wherein each intent cluster of the plurality of intent clusters corresponds to a respective intent of a user following a first user action; and store a second machine learning model, wherein the second machine learning model is trained to select a specific intent from a plurality of specific intents of a selected intent cluster based, and wherein each specific intent of the plurality of specific intents corresponds to a respective specific intent of the user following the first user action; cloud-based control circuitry configured to:receive the first user action during a conversational interaction with a user interface; determine, using the first machine learning model, a conversion detail or information from a user account of the user; select the second machine learning model, from a plurality of machine learning models, based on the intent cluster selected from the plurality of intent clusters, wherein each intent cluster of the plurality of intent clusters corresponds to a respective machine learning model from the plurality of machine learning models; select, using the second machine learning model, a dynamic conversational response from a plurality of dynamic conversational responses based on a second output; and cloud-based input/output circuitry configured to:generate the dynamic conversational response during the conversational interaction. 2. A method for generating dynamic conversational responses using two-tier machine learning models, the method comprising:receiving a first user action during a conversational interaction with a user interface; generating, using a first machine learning model, a first output based on the first user action, wherein the first machine learning model is trained to select an intent cluster from a plurality of intent clusters based on user actions, and wherein each intent cluster of the plurality of intent clusters corresponds to a respective intent of a user following the first user action; generating, using a second machine learning model, a second output from a second machine learning model based on the first output, wherein the second machine learning model is trained to select a specific intent from a plurality of specific intents of the selected intent cluster, and wherein each specific intent of the plurality of specific intents corresponds to a respective specific intent of the user following the first user action; selecting a dynamic conversational response from a plurality of dynamic conversational responses based on the second output; and generating, at the user interface, the dynamic conversational response during the conversational interaction. 3. The method of claim 2 , further comprising of selecting the second machine learning model, from a plurality of machine learning models, based on the intent cluster selected from the plurality of intent clusters, wherein each intent cluster of the plurality of intent clusters corresponds to a respective machine learning model from the plurality of machine learning models. 4. The method of claim 2 , further comprising: determining the plurality of intent clusters based on similar feature inputs similar characteristics of the users. 5. The method of claim 2 , wherein the first machine learning model is a supervised machine learning model, and wherein the second machine learning model is a supervised machine learning model. 6. The method of claim 2 , wherein the first machine learning model is a factorization machine model, and wherein the second machine learning model is an artificial neural network model. 7. The method of claim 2 , further comprising of clustering available specific intents into the plurality of intent clusters. 8. The method of claim 2 , further comprising:receiving a first labeled feature input, wherein the first labeled feature input is labeled with a known intent cluster for the first labeled feature input; and training the first machine learning model to classify the first labeled feature input with the known intent cluster. 9. The method of claim 2 , wherein a first feature input is a conversion detail or information from a user account of the user. 10. The method of claim 2 , wherein a first feature input indicates a time at which the user interface was launched. 11. The method of claim 2 , wherein a first feature input indicates a webpage from which the user interface was launched. 12. A non-transitory computer-readable medium for generating dynamic conversational responses using two-tier machine learning models, comprising of instructions that, when executed by one or more processors, cause operations comprising:receiving a first user action during a conversational interaction with a user interface; generating, using a first machine learning model, a first output based on the first user action, wherein the first machine learning model is trained to select an intent cluster from a plurality of intent clusters based on user actions, and wherein each intent cluster of the plurality of intent clusters corresponds to a respective intent of a user following the first user action; generating a second output, using a second machine learning model, based on the first output, wherein the second machine learning model is trained to select a specific intent from a plurality of specific intents of the selected intent cluster, and wherein each specific intent of the plurality of specific intents corresponds to a respective specific intent of the user following the first user action; selecting a dynamic conversational response from a plurality of dynamic conversational responses based on the second output; and generating, at the user interface, the dynamic conversational response during the conversational interaction. 13. The non-transitory computer-readable medium of claim 12 , further comprising of instructions that cause further operations comprising of selecting the second machine learning model, from a plurality of machine learning models, based on the intent cluster selected from the plurality of intent clusters, wherein each intent cluster of the plurality of intent clusters corresponds to a respective machine learning model from the plurality of machine learning models. 14. The non-transitory computer-readable medium of claim 12 , further comprising of instructions that cause further operations comprising determining the plurality of intent clusters based on similar feature inputs similar characteristics of the users. 15. The non-transitory computer-readable medium of claim 12 , wherein the first machine learning model is a supervised machine learning model, and wherein the second machine learning model is a supervised machine learning model. 16. The non-transitory computer-readable medium of claim 12 , wherein the first machine learning model is a factorization machine model, and wherein the second machine learning model is an artificial neural network model. 17. The non-transitory computer-readable medium of claim 12 , further comprising of instructions that cause further operations comprising of clustering available specific intents into the plurality of intent clusters. 18. The non-transitory computer-readable medium of claim 12 , further comprising of instructions that cause further operations comprising:receiving a first labeled feature input, wherein the first labeled feature input is labeled with a known intent cluster for the first labeled feature input; and training the first machine learning model to classify the first labeled feature input with the known intent cluster. 19. The non-transitory computer-readable medium of claim 12 , wherein a first feature input is a conversion detail or information from a user account of the user. 20. The non-transitory computer-readable medium of claim 12 , wherein a first feature input indicates a time at which the user interface was launched or a webpage from which the user interface was launched.
意見反饋
使用該功能遇到問題