Back to results
US 11,886,816 B2Granted
Bot dialog manager
AssigneeProsper Funding LLC
InventorPaul Golding
Life of this patent
Estimating the term…
Abstract
A method manages bot dialogue. A user input is converted to a phrase vector. A set of identified tokens are identified by a token identification engine from the phrase vector. An unsupervised token is selected from the set of identified tokens. A supervised token is selected from the set of identified tokens. A voted token selected from the unsupervised token and the supervised token. A next token is identified based on a set of recent tokens that includes the voted token. The next token is presented as one of a voice communication and an email communication.
Claims20
A method comprising:
- converting a user input to a phrase vector;
- identifying, by a token identification engine, a set of identified tokens from the phrase vector;
- processing the set of identified tokens with an unsupervised scoring engine to select an unsupervised token from the set of identified tokens;
- processing the set of identified tokens with a supervised scoring engine to select a supervised token from the set of identified tokens;
- selecting a voted token from the unsupervised token selected with the unsupervised scoring engine and the supervised token selected with the supervised scoring engine, wherein the voted token is selected with a machine learning model trained to identify the voted token from the unsupervised token and the supervised token;
- identifying a next token based on a set of recent tokens that includes the voted token, wherein identifying the next token comprises:
- setting an explicit path state based on the voted token, and
- identifying, by a next token engine, the next token using the set of recent tokens, the explicit path state, and a recent path list;
- and
- presenting the next token as one of a voice communication and an email communication.
7 more elements
A system comprising:
- a processor;
- and
- a memory coupled to the processor,
- the memory comprising an application, wherein the application executes on the processor and is configured for:
- converting a user input to a phrase vector;
- identifying, by a token identification engine, a set of identified tokens from the phrase vector;
- processing the set of identified tokens with an unsupervised scoring engine to select an unsupervised token from the set of identified tokens;
- processing the set of identified tokens with a supervised scoring engine to select a supervised token from the set of identified tokens;
- selecting a voted token from the unsupervised token selected with the unsupervised scoring engine and the supervised token selected with the supervised scoring engine, wherein the voted token is selected with a machine learning model trained to identify the voted token from the unsupervised token and the supervised token;
- identifying a next token based on a set of recent tokens that includes the voted token, wherein identifying the next token comprises:
- setting an explicit path state based on the voted token, and
- identifying, by a next token engine, the next token using the set of recent tokens, the explicit path state, and a recent path list;
- and
- presenting the next token as one of a voice communication and an email communication.
11 more elements
One or more non-transitory computer readable mediums comprising computer readable program code for:
- converting a user input to a phrase vector;
- identifying, by a token identification engine, a set of identified tokens from the phrase vector;
- processing the set of identified tokens with an unsupervised scoring engine to select an unsupervised token from the set of identified tokens;
- processing the set of identified tokens with a supervised scoring engine to select a supervised token from the set of identified tokens;
- selecting a voted token from the unsupervised token selected with the unsupervised scoring engine and the supervised token selected with the supervised scoring engine, wherein the voted token is selected with a machine learning model trained to identify the voted token from the unsupervised token and the supervised token;
- identifying a next token based on a set of recent tokens that includes the voted token, wherein identifying the next token comprises:
- setting an explicit path state based on the voted token, and
- identifying, by a next token engine, the next token using the set of recent tokens, the explicit path state, and a recent path list;
- and
- presenting the next token as one of a voice communication and an email communication.
7 more elements
Dependencies are inferred from the claim text.