Bank of America Corporation

Venkata Karthik Ryali

Durga Prasad Kutthumolu

Sachin S Nagvekar

Laxma Gavinolla

Mukesh Singh

Priyanka K

Veerendra Gupta

A method includes generating a metaverse session, a first avatar of a first user, and a virtual advisor avatar. The first user is allowed access to the metaverse session using the first avatar. A voice query of the first user is received and analyzed to determine a preferred language/dialect of the first user, and an issue and a domain of the voice query. In response to determining that a language/knowledge server includes a response corresponding to the issue and the domain, the response is retrieved from the language/knowledge server. In response to determining that a language/dialect of the response matches the preferred language/dialect of the first user, a first voice response is generated from the retrieved response. The first voice response is in the preferred language/dialect of the first user. The first voice response is communicated to the first user using the virtual advisor avatar.

System and method for cross-domain and cross-linguistic knowledge-reinforced user servicing

A system receives job requests comprising associated job names and associated job parameters. The system performs a comparison of a job name and parameters for a first, second, and third job request with information of previously performed jobs and determines a first, second, and third amount of memory to perform the job requests. The system evaluates the first, second, and third amounts of memory with predetermined memory sizes to determine if the memory amounts exceed the predetermined memory sizes. The system negotiates with schedulers from one or more service provider networks to allocate memory from temporary memories for each amount of memory that exceeds the predetermined memory sizes. The system creates a prioritized queue comprising the first, second, and third received job requests for scheduler processing based upon the amounts of memory. The system can use a trained algorithmic model to predict the first, second, and third amounts of memories.

System for predicting memory resources and scheduling jobs in service-oriented architectures

A method includes encrypting a request received from a user device to generate an encrypted request. Encrypted data items are searched based on the encrypted request to identify desired encrypted data items. In response to determining that two or more encrypted data items of the desired encrypted data items have a same interaction identification, the two or more encrypted data items are locked and masked, and the masked two or more encrypted data items are removed. Algebraic operations are determined based on the encrypted request. An encrypted response is determined by performing the algebraic operations on the desired encrypted data items. The encrypted response is decrypted to obtain a decrypted response. An error is determined due to the algebraic operations performed on the desired encrypted data items. In response to determining that the error is less than an error threshold, the decrypted response is sent to the user device.

System and method for secure database management

Systems, computer program products, and methods are described herein for enhanced authentication using voice modulation matching. The present invention is configured to capture, via a first user input device, a digital audio stream of speech data of a first user; receive one or more identification credentials associated with the first user; encode the speech data to generate encoded speech data; query one or more data repositories using the encoded speech data; in response, retrieve, encoded speech data associated with a second user that matches the encoded speech data of the first user; determine that the first user has a familial relationship with the second user; generate an authentication token for the first user based on at least determining that the first user has a familial relationship with the second user; and record the authentication token for the first user in a distributed ledger associated with the second user.

System for enhanced authentication using voice modulation matching

A system includes a memory and a processor coupled to the memory. The processor receives a voice command from a first user to transfer a first amount of data objects from a first data file of the first user to a second data file of a second user. The processor generates a voice signature of the first user and further generates a virtual device in the virtual environment, wherein the virtual device comprises metadata relating to the transfer of the data objects. The processor presents the virtual device and the voice signature to the second user in the virtual environment. The processor receives a selection from the second user of the voice signature and plays the voice signature on a second user device of the second user. The processor receives an acknowledgement from the second user and initiates the requested transfer of data objects to the second user.

Growing community of inventors

Hyderabad Telangana, India

Venkata Karthik Ryali