Paypal, Inc.

Alexander Yuryevich Shvid

Nikita Alekseyevich Lukyanenko

Venkata Ramana Varma Nadimpalli

Karl Anton Hennig

Vahini Pobbathi

Swathi Bangalore Ananthakumar

There are provided systems and methods for named entity recognition in chat dialogues for customer relationship management systems. A service provider, such as an electronic transaction processor for digital transactions, may provide live chat service channels for assistance through live agents and chatbot services. When interacting with these channels, a user may engage in a chat dialogue with live agents. This may include lines of texts corresponding to the exchanged messages and may include named entities for particular types or categories of words that refer to a particular object or thing. To identify these named entities, a natural language processor may utilize machine learning and other engines for named entity recognition in customer relationship management systems to highlight the named entities in live service chats. Agents of the systems may view content that identify the named entities and interact with the named entities to view descriptions.

Named entity recognition in chat dialogues for customer relationship management systems

Methods and systems are presented for providing an asynchronous communication system for facilitating computing services to computer nodes across multiple availability zones. Each computer node includes a client application configured to receive a service request and to generate a request file based on the service request. The client application uploads the request file to a folder hosted by a file sharing system and shared with a processing server. When a new request file is detected in the folder, the processing server downloads the request file from the file sharing system. Based on performing one or more computing services according to the request file, the processing server generates a response file including output data from the computing services. The processing server uploads the response file to the folder hosted by the file sharing system. The client application downloads the response file and presents the output data on a device.

Scalable messaging framework for providing machine learning services across multiple availability zones

There are provided systems and methods for sentence level dialogue summaries using unsupervised machine learning for keyword selection and scoring. A service provider, such as an electronic transaction processor for digital transactions, may provide live chat service channels for assistance through live agents and chatbot services. When interacting with these channels over a period of time, a user may create a dialogue with multiple different live agents and/or chatbots. These chat sessions may be asynchronous but have important and relevant information for future live agents to review. Thus, the service provider may provide a dialogue summarizer, which may summarize a dialogue automatically to a number of most relevant sentences. This may be done using an unsupervised machine learning system that utilizes different machine learning algorithms to select and rank keywords within the sentences. The sentences are then scored and highest scored sentences are output as a summary.

Sentence level dialogue summaries using unsupervised machine learning for keyword selection and scoring

Methods and systems are presented for providing a scalable communication framework for facilitating computing services to computer nodes across multiple availability zones. One or more communication servers act as a communication proxy for a processing server configured to perform the computing services. Upon receiving a service request from a computer node, the communication server establishes a synchronous communication session with the computer node. The communication server generates a request message and inserts the request message in a downstream queue accessible by the processing server. The processing server retrieves the request message from the downstream queue and performs the computing services based on the request message. Outputs from the computing services are encapsulated within a response message and then inserted in an upstream queue. The communication server extracts output data from the response message, and transmits the output data to the computer node via the synchronous communication session.

Methods and systems are presented for accessing various data values in a record stored in a data store independently from other data values in the record and without taking computationally expensive or storage-intensive procedures such as de-serializing a record based on a primary key. A data service module is provided to access each record in a data store, and generate for the records a table including a map of key-value pairs representing the data values in the records. When the data service module receives a request from an application for accessing a first data value in a first record, the data service module may retrieve a first key-value pair corresponding to the first data value in the first record without de-serializing the record. The data service module then provides a first value of the first key-value pair to the application.

Systems and methods for providing flexible data access

Methods and systems for providing a stateless application framework are presented. The stateless application framework is utilized by different applications for implementing different workflows. Each workflow may be associated with one or more state machine configurations representing the different states within the workflow. Upon receiving an indication of an event from an application, a stateless application module transmits a job request to a data processing engine based on a current state of the event. When a response is received from the data processing engine, the state application module determines whether the state of the event has been updated since transmitting the job request. If it is determined that the state has been updated, the stateless application module is configured to transmit another job request to the data processing engine based on the updated state of the event.

Systems and methods for providing services in a stateless application framework

Methods and systems for providing an external scheduler in a stateless application framework are presented. A first instance of a stateless application transmits a job request to a data processing engine, and submits a message to a messaging queue. The message indicates a task to be performed according to a delayed schedule. The first instance of the stateless application terminates after submitting the message. The messaging queue transmits the message to the stateless application framework according to the delayed schedule. Upon receiving the message, a second instance of the stateless application is instantiated. The second instance of the stateless application performs an action based on the message and terminates.

Growing community of inventors

San Jose, CA, United States of America

Alexander Yuryevich Shvid