Patent Issued for Methods and systems for codeless chatbot development (USPTO 11699431): Allstate Solutions Private Limited

2023 AUG 02 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventor Shepal, Chinmayee (Maharashtra, IN), filed on September 8, 2021, was published online on July 11, 2023.

The patent’s assignee for patent number 11699431 is Allstate Solutions Private Limited (Bangalore, India).

News editors obtained the following quote from the background information supplied by the inventors: “A chatbot is a software application that can automate conversations and interact with individuals through messaging platforms. A chatbot may be programmed to respond to an intent of the individual with whom the chatbot is interacting in a conversation such that the chatbot prompts the individual to provide information necessary to fulfill the intent.

“Because chatbots may be associated with a particular intent and intent fulfillment, chatbots may engage in similar conversations with regard to their associated intent and intent fulfillment. Likewise, similarities in conversation style between chatbots may lead to redundant programming of chatbots. Moreover, developing chatbots with programming code may involve complex issues of software development and/or configuration. Therefore, a need exists for methods and systems for more efficient and streamlined chatbot development.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventor’s summary information for this patent: “In accordance with one embodiment of the present disclosure, a system for intelligent codeless chatbot development includes a chatbot comprising an artificial intelligence neural network model and a natural language processing tool, one or more processors, one or more memory components communicatively coupled to the one or more processors and the chatbot, and machine-readable instructions stored in the one or more memory components. The machine-readable instructions may cause the one or more processors to implement an iterative process to automatically develop a chatbot conversation for a conversation designer by receiving, with the chatbot, a conversation design input of one or more conversation design inputs from the conversation designer, and identify, with the natural language processing tool, an intent based on the conversation design input. The machine-readable instructions may also cause the one or more processors to generate, with the artificial intelligence neural network model, a development event based on the intent, and retrieve a conversation chat flow from a set of conversation chat flows of a code sheet based on the development event, the code sheet comprising a set of conversations, the set of conversation chat flows, and a set of rules for code retrieval based on the set of conversations and the set of conversation chat flows. The machine-readable instructions may further cause the one or more processors to automatically retrieve a chatbot computer program code based on the conversation chat flow and the set of rules from the code sheet, and repeat the iterative process to develop the chatbot conversation until the chatbot computer program code is automatically retrieved from a code repository for each conversation design input of the one or more conversation design inputs from the conversation designer.

“In accordance with another embodiment of the present disclosure, a system for intelligent codeless chatbot development includes a chatbot comprising an artificial intelligence neural network model and a natural language processing tool, one or more processors, one or more memory components communicatively coupled to the one or more processors and the chatbot, and machine-readable instructions stored in the one or more memory components. The machine-readable instructions may cause the one or more processors to implement an iterative process to automatically develop a chatbot conversation for a conversation designer by receiving, with the chatbot, a conversation design input of one or more conversation design inputs from the conversation designer, and identify, with the natural language processing tool, an intent based on the conversation design input. The machine-readable instructions may also cause the one or more processors to generate, with the artificial intelligence neural network model, a development event based on the intent, and retrieve a conversation chat flow from a set of conversation chat flows of a code sheet based on the development event, the code sheet comprising a set of conversations, the set of conversation chat flows, and a set of rules for code retrieval based on the set of conversations and the set of conversation chat flows, wherein each conversation chat flow is based on an associated intent, and wherein each conversation chat flow comprises a set of prompts for identification of information to generate a fulfillment of the associated intent. The machine-readable instructions may further cause the one or more processors to automatically retrieve a chatbot computer program code based on the conversation chat flow and the set of rules from the code sheet, and repeat the iterative process to develop the chatbot conversation until the chatbot computer program code is automatically retrieved from a code repository for each conversation design input of the one or more conversation design inputs from the conversation designer.

“In accordance with yet another embodiment of the present disclosure, a method for intelligent codeless chatbot development includes implementing, via a processor, an iterative process to automatically develop a chatbot conversation for a conversation designer by receiving, with a chatbot comprising an artificial intelligence neural network model and a natural language processing tool, a conversation design input of one or more conversation design inputs from the conversation designer, and identifying, with the natural language processing tool, an intent based on the conversation design input. The method also includes generating, with the artificial intelligence neural network model, a development event based on the intent, and retrieving, via the processor, a conversation chat flow from a set of conversation chat flows of a code sheet based on the development event, the code sheet comprising a set of conversations, the set of conversation chat flows, and a set of rules for code retrieval based on the set of conversations and the set of conversation chat flows. The method further includes automatically retrieving, via the processor, a chatbot computer program code based on the conversation chat flow and the set of rules from the code sheet, and repeating the iterative process to develop the chatbot conversation until the chatbot computer program code is automatically retrieved from a code repository for each conversation design input of the one or more conversation design inputs from the conversation designer.

“Although the concepts of the present disclosure are described herein with primary reference to chatbots, it is contemplated that the concepts will enjoy applicability to any software development platform or environment for a developed software application.”

The claims supplied by the inventors are:

“1. A system for intelligent codeless chatbot development, the system comprising: a chatbot comprising an artificial intelligence neural network model and a natural language processing tool; one or more processors; one or more memory components communicatively coupled to the one or more processors and the chatbot; and machine-readable instructions stored in the one or more memory components that cause the one or more processors to perform at least the following: implement an iterative process to automatically develop a chatbot conversation for a conversation designer by receiving, with the chatbot, a conversation design input of one or more conversation design inputs from the conversation designer; identify, with the natural language processing tool, an intent based on the conversation design input; generate, with the artificial intelligence neural network model, a development event based on the intent; retrieve a conversation chat flow from a set of conversation chat flows of a code sheet based on the development event, the code sheet comprising a set of conversations, the set of conversation chat flows, and a set of rules for code retrieval based on the set of conversations and the set of conversation chat flows; automatically retrieve a chatbot computer program code based on the conversation chat flow and the set of rules from the code sheet; and repeat the iterative process to develop the chatbot conversation until the chatbot computer program code is automatically retrieved from a code repository for each conversation design input of the one or more conversation design inputs from the conversation designer.

“2. The system of claim 1, wherein the artificial intelligence neural network model is trained on a set of historical conversation data and a set of historical fulfillment data corresponding to the set of historical conversation data.

“3. The system of claim 1, wherein the machine-readable instructions further cause the one or more processors to: generate one or more prompts to the conversation designer by the chatbot to accept or reject each chatbot computer program code retrieved based on the conversation chat flow and the set of rules from the code sheet.

“4. The system of claim 3, wherein the machine-readable instructions further cause the one or more processors to: train the artificial intelligence neural network model using machine learning based on the chatbot computer program code, acceptance or rejection of each chatbot computer program code, or combinations thereof.

“5. The system of claim 1, wherein each conversation chat flow is based on an associated intent, and wherein each conversation chat flow comprises a set of prompts for identification of information to generate a fulfillment of the associated intent.

“6. The system of claim 5, wherein the machine-readable instructions further cause the one or more processors to: compress, with the artificial intelligence neural network model, the conversation chat flow retrieved from the set of conversation chat flows such that the conversation chat flow contains fewer prompts than prior to retrieval.

“7. The system of claim 1, wherein to retrieve the code sheet, the machine-readable instructions further cause the one or more processors to: parse the code sheet into a computer program code format.

“8. The system of claim 1, wherein the machine-readable instructions further cause the one or more processors to: generate a lambda event based on the development event; select a conversation from the set of conversations, the conversation chat flow, and one or more rules from the set of rules from the code sheet for code retrieval based on the lambda event; convert the conversation, the conversation chat flow, and the one or more rules into a data interchange format; transmit the conversation, the conversation chat flow, and the one or more rules to a cloud platform based on the lambda event; and automatically retrieve the chatbot computer program code based on the data interchange format from the cloud platform.

“9. The system of claim 8, wherein the machine-readable instructions further cause the one or more processors to: cache the conversation, the conversation chat flow, and the one or more rules for a subsequent development event.

“10. A system for intelligent codeless chatbot development, the system comprising: a chatbot comprising an artificial intelligence neural network model and a natural language processing tool; one or more processors; one or more memory components communicatively coupled to the one or more processors and the chatbot; and machine-readable instructions stored in the one or more memory components that cause the one or more processors to perform at least the following: implement an iterative process to automatically develop a chatbot conversation for a conversation designer by receiving, with the chatbot, a conversation design input of one or more conversation design inputs from the conversation designer; identify, with the natural language processing tool, an intent based on the conversation design input; generate, with the artificial intelligence neural network model, a development event based on the intent; retrieve a conversation chat flow from a set of conversation chat flows of a code sheet based on the development event, the code sheet comprising a set of conversations, the set of conversation chat flows, and a set of rules for code retrieval based on the set of conversations and the set of conversation chat flows, wherein each conversation chat flow is based on an associated intent, and wherein each conversation chat flow comprises a set of prompts for identification of information to generate a fulfillment of the associated intent; automatically retrieve a chatbot computer program code based on the conversation chat flow and the set of rules from the code sheet; and repeat the iterative process to develop the chatbot conversation until the chatbot computer program code is automatically retrieved from a code repository for each conversation design input of the one or more conversation design inputs from the conversation designer.

“11. The system of claim 10, wherein the artificial intelligence neural network model is trained on a set of historical conversation data and a set of historical fulfillment data corresponding to the set of historical conversation data.

“12. The system of claim 10, wherein the machine-readable instructions further cause the one or more processors to: generate one or more prompts to the conversation designer by the chatbot to accept or reject each chatbot computer program code retrieved based on the conversation chat flow and the set of rules from the code sheet.

“13. The system of claim 12, wherein the machine-readable instructions further cause the one or more processors to: train the artificial intelligence neural network model using machine learning based on the chatbot computer program code, acceptance or rejection of each chatbot computer program code, or combinations thereof.

“14. The system of claim 10, wherein the machine-readable instructions further cause the one or more processors to: compress, with the artificial intelligence neural network model, the conversation chat flow retrieved from the set of conversation chat flows such that the conversation chat flow contains fewer prompts than prior to retrieval.

“15. A method for intelligent codeless chatbot development, the method comprising: implementing, via a processor, an iterative process to automatically develop a chatbot conversation for a conversation designer by receiving, with a chatbot comprising an artificial intelligence neural network model and a natural language processing tool, a conversation design input of one or more conversation design inputs from the conversation designer; identifying, with the natural language processing tool, an intent based on the conversation design input; generating, with the artificial intelligence neural network model, a development event based on the intent; retrieving, via the processor, a conversation chat flow from a set of conversation chat flows of a code sheet based on the development event, the code sheet comprising a set of conversations, the set of conversation chat flows, and a set of rules for code retrieval based on the set of conversations and the set of conversation chat flows; automatically retrieving, via the processor, a chatbot computer program code based on the conversation chat flow and the set of rules from the code sheet; and repeating the iterative process to develop the chatbot conversation until the chatbot computer program code is automatically retrieved from a code repository for each conversation design input of the one or more conversation design inputs from the conversation designer.

“16. The method of claim 15, wherein the artificial intelligence neural network model is trained on a set of historical conversation data and a set of historical fulfillment data corresponding to the set of historical conversation data.

“17. The method of claim 15, further comprising: generating one or more prompts to the conversation designer by the chatbot to accept or reject each chatbot computer program code retrieved based on the conversation chat flow and the set of rules from the code sheet.

“18. The method of claim 17, further comprising: training the artificial intelligence neural network model using machine learning based on the chatbot computer program code, acceptance or rejection of each chatbot computer program code, or combinations thereof.

“19. The method of claim 15, further comprising: compressing, with the artificial intelligence neural network model, the conversation chat flow retrieved from the set of conversation chat flows such that the conversation chat flow contains fewer prompts than prior to retrieval.”

There are additional claims. Please visit full patent to read further.

For additional information on this patent, see: Shepal, Chinmayee. Methods and systems for codeless chatbot development. U.S. Patent Number 11699431, filed September 8, 2021, and published online on July 11, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11699431)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)