Computer implemented method for the automated analysis or use of data
AssigneeUnlikely Artificial Intelligence Limited
InventorsWilliam Tunstall-Pedoe, Finlay Curran, Harry Roscoe, Robert Heywood
Life of this patent
Estimating the term…
Abstract
A computer implemented method for the automated analysis or use of data is implemented by a voice assistant. The method comprises the steps of: (a) storing in a memory a structured, machine-readable representation of data that conforms to a machine-readable language (‘machine representation’); the machine representation including representations of user speech or text input to a human/machine interface; and (b) automatically processing the machine representations to analyse the user speech or text input.
Claims28
A computer implemented method for the automated analysis or use of data, comprising the steps of:
- (a) storing in a non-transitory computer-readable medium a structured, machine-readable representation of data that conforms to a machine-readable language, in which the data relates to user speech or text information input to a human/machine interface;
- (b) automatically processing the structured machine-readable representation to analyse the user speech or text information;
- (c) identifying a first wake word in the analysed user speech or text information, and initiating processing in response to identifying the first wake word, and entering a privacy-preserving state after the initiating processing;
- and
- (d) after entering the privacy-preserving state, identifying a second wake word in the analysed user speech or text information, and continuing processing in response to identifying the second wake word, wherein the second wake word is sufficiently long or unusual that a false recognition of the second wake word is significantly more improbable than a false recognition of the first wake word;
- in which a neural architecture is used to generate the machine-readable language and the neural architecture utilises recurrent neural networks or long short-term memories (LSTMs) or attention mechanisms or transformers.
A computer implemented method for the automated analysis or use of data, comprising the steps of:
- (a) storing in a non-transitory computer-readable medium a structured, machine-readable representation of data that conforms to a machine-readable language;
- in which the data includes input data relating to user speech or text information input to a human/machine interface, and in which the structured representation of data includes one or more tenets, statements or other rules defining objectives or motives;
- (b) automatically processing the structured machine-readable representation to analyse the user speech or text information;
- (c) automatically selecting, deciding on or executing actions;
- and the method further includes the steps of:
- (i) analysing a potential action to determine whether executing the action would optimize or otherwise affect achievement or realization of those tenets, statements or other rules;
- (ii) automatically selecting, deciding on or executing actions only if the actions optimize or otherwise positively affect the achievement or realization of those tenets, statements or other rules;
- in which a neural architecture is used to generate the machine-readable language and the neural architecture utilises recurrent neural networks or long short-term memories (LSTMs) or attention mechanisms or transformers.
Dependencies are inferred from the claim text.