FIELD: computer engineering.
SUBSTANCE: technical result is achieved by obtaining dialogue data, including text representations of dialogue pairs; obtaining data on facts, including textual representations of facts; identification from data on facts for a given dialogue pair of fact relating to it; creating a training data set, which includes a plurality of training digital objects, each of which includes textual representations: (i) a human request of a given dialogue pair; (ii) fact; and (iii) a human response of a given dialogue pair, responding to a human request; feeding the training data set to the chatbot system forcing the chatbot system to generate a machine-generated response; and optimizing difference between machine-generated response and human response, due to which the chatbot system is trained to generate machine-generated responses to user requests.
EFFECT: providing more natural responses to user requests, if, along with a given user request, the chatbot system can be configured to take into account a fact determined as relating to a given user request.
20 cl, 8 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND SYSTEM FOR RECOGNIZING USER'S SPEECH FRAGMENT | 2021 |
|
RU2808582C2 |
METHOD AND SYSTEM FOR CHECKING MEDIA CONTENT | 2022 |
|
RU2815896C2 |
METHOD AND SYSTEM FOR DIGITAL ASSISTANT TEXT GENERATION | 2022 |
|
RU2796208C1 |
METHOD AND SYSTEM FOR GENERATING TEXT | 2023 |
|
RU2817524C1 |
METHOD AND SERVER FOR TEACHING A NEURAL NETWORK TO FORM A TEXT OUTPUT SEQUENCE | 2020 |
|
RU2798362C2 |
METHOD AND SYSTEM FOR CONTROLLING DIALOGUE AGENT IN USER INTERACTION CHANNEL | 2019 |
|
RU2818036C1 |
METHOD AND SYSTEM FOR PROCESSING USER SPOKEN SPEECH FRAGMENT | 2019 |
|
RU2757264C2 |
METHOD OF CREATING MODEL FOR ANALYSING DIALOGUES BASED ON ARTIFICIAL INTELLIGENCE FOR PROCESSING USER REQUESTS AND SYSTEM USING SUCH MODEL | 2019 |
|
RU2730449C2 |
METHOD AND SYSTEM FOR GENERATING REQUESTS FOR ACCESSING NEURAL NETWORK LANGUAGE MODEL | 2024 |
|
RU2826816C1 |
METHOD AND SYSTEM FOR CLASSIFYING AN ELECTRONIC DEVICE USER | 2021 |
|
RU2795152C2 |
Authors
Dates
2024-05-31—Published
2023-05-23—Filed