	US 12,229,510 B2
	Named entity recognition in chat dialogues for customer relationship management systems
Nikita Alekseyevich Lukyanenko, San Jose, CA (US); and Alexander Shvid, Las Vegas, NV (US)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PAYPAL, INC., San Jose, CA (US)
Filed on Aug. 31, 2021, as Appl. No. 17/463,361.
Prior Publication US 2023/0069587 A1, Mar. 2, 2023
Int. Cl. G06F 40/279 (2020.01); G06F 40/35 (2020.01)

CPC G06F 40/279 (2020.01) [G06F 40/35 (2020.01)]

20 Claims

1. A system comprising:

a non-transitory memory; and

one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:

accessing a chat dialogue between a user and a chat service of a customer relationship management (CRM) system for a service provider associated with the system, wherein the chat dialogue comprises a plurality of words in a plurality of word groupings;

determining a past chat dialogue between the user and an assistance type provided to the user via a communication channel for the chat service of the CRM system, wherein the past chat dialogue indicates the assistance type previously used by the user and one or more named entities interacted with by the user, wherein the assistance type is associated with a service application provided by the service provider for use by the user, and wherein communication channel provides digital communications for the chat service of the CRM system;

performing a named entity recognition (NER) operation on the plurality of words using a machine learning (ML) model trained based on the assistance type and the communication channel, wherein the NER operation identifies the one or more named entities in the chat dialogue based on one or more of the plurality of words;

determining an interaction with the one or more named entities by the user and a time associated with the interaction based on the performing the NER operation and the chat dialogue;

determining one or more labels for the one or more named entities, wherein the one or more labels are specific to the assistance type and the communication channel;

determining additional data for the one or more named entities based the one or more labels and the interaction at the time, wherein the additional data includes one or more past interactions at one or more past times by the user with the merchant that correspond to the interaction;

generating a description of the one or more named entities in a format compatible with a user interface displaying visual chat data for the chat dialogue based on the interaction and the additional data; and

outputting the visual chat data having the one or more named entities marked with the one or more labels and selectable to view the description, wherein the visual chat data comprise one or more processes to view the additional data for the one or more named entities in the chat dialogue.