Granted Patent B2

US 12,657,597 · App. 18/198,246 · Granted Jun 16, 2026

Inventors: Israel Oliveira (Porto Alegre, BR); Cristian Basilio (Porto Alegre, BR); Douglas Parnoff (Porto Alegre, BR); Leandro Pereira (Porto Alegre, BR)

Assignee: ADP, Inc.

G06Q30/0203G06F40/20G06Q10/0637G06Q10/105H04L51/02

Abstract

Claims (84)

1 . A method for analyzing chatbot dialogs, comprising:

transmitting, by a data processing system comprising a processor coupled with memory, via a network, a question from an administrator device to a chatbot corresponding to a client device to generate a dialog between the chatbot and the client device;

receiving, by the data processing system via the network, a response to the transmitted question from the client device for inclusion in the dialog;

determining, by the data processing system, that the response corresponds to a response trigger corresponding to the question;

transmitting, by the data processing system via the network, responsive to determining that the response corresponds to the response trigger, a chatbot response for inclusion in the dialog, to the client device providing the response;

determining, by the data processing system, that the chatbot response does not include a second question regarding the response corresponding to the response trigger;

storing, by the data processing system, the dialog comprising the question, the response, the chatbot response, and an identifier in a dialog database;

analyzing, by the data processing system, the dialog, which comprises the question, the response, and the chatbot response, using an artificial intelligence component executing at least one of speech recognition, speech-to-text conversion, natural language processing, pattern recognition, data statistics analysis, sentiment analysis, anomaly detection, question and answer classification, or root cause analysis;

generating, by the data processing system, insights based on the analyzed dialog, wherein the insights comprise at least i) a root cause of at least one of an issue, a sentiment, a concern, a complaint, or a problem and ii) one or more solutions to the root cause;

displaying, by the data processing system, the insights in a dashboard on a display of the administrator device; and

transmitting, by the data processing system, using an application programming interface, in response to a level of certainty in the root cause being greater than a certainty threshold, a control signal to a temperature control system of a building, to cause the temperature control system to modify the temperature of a room in the building to resolve the root cause using the one or more solutions to the root cause.

2 . The method of claim 1 , further comprising:

receiving, by the data processing system via the network, the question and the response trigger corresponding to the question from the administrator device.

3 . The method of claim 1 , further comprising:

extracting, by the data processing system, relevant information from the dialog based on the analysis.

4 . The method of claim 1 , further comprising:

analyzing, by the data processing system, the dialog using the artificial intelligence component to generate a structured dialog.

5 . The method of claim 1 , further comprising:

analyzing, by the data processing system, the dialog using the artificial intelligence component to generate a structured dialog; and

generating, by the data processing system, the insights based on the structured dialog generated using the artificial intelligence component.

6 . The method of claim 1 , further comprising:

determining, by the data processing system, that a third question has been received from the administrator device responsive to displaying the insights in the dashboard; and

transmitting, by the data processing system, the third question to the client device for inclusion in the dialog.

7 . The method of claim 1 , further comprising:

receiving, by the data processing system, a plurality of responses to the question from a plurality of client devices, wherein the response and one or more of the plurality of responses include the complaint about the temperature;

generating, by the data processing system, insights based on the analyzed dialog and the analyzed plurality of responses, wherein the insights comprise i) the room of the building, ii) the root cause includes a complaint about the temperature in the room based on the response and the one or more of the plurality of responses, and iii) the one or more solutions include modifying the temperature of the room;

determining, by the data processing system, based on the analyzed dialog and the analyzed plurality of responses, the level of certainty of the root cause; and

transmitting, by the data processing system, the control signal based on the insights.

8 . The method of claim 1 , wherein the response includes an indication of a possible threat, the insights include a room, the root cause includes a security issue, and the one or more solutions to the root cause include locking a door, further comprising:

locking, by the data processing system, based on the insights, the door corresponding to the room to resolve the root cause using the one or more solutions to the root cause.

9 . The method of claim 1 , further comprising:

generating, by the data processing system, a communication corresponding to the response, based on the generated insights; and

transmitting, by the data processing system, the communication to a second client device.

10 . The method of claim 1 , further comprising:

extracting, by the data processing system, based on analyzing the dialog, a first indication from the response and a second indication from the response, wherein the first indication includes at least one of intense heat levels, heavy amounts of smoke, and fire, and the second indication includes a room;

generating, by the data processing system, the insights based on the analyzed dialog, the first indication, and the second indication, wherein the insights comprise i) the root cause, including a fire issue and ii) the one or more solutions, including controlling a fire suppression system; and

controlling, by the data processing system, based on the insights, the fire suppression system in the room to resolve the root cause using the one or more solutions to the root cause.

11 . A method to control an external system, comprising:

transmitting, by a data processing system comprising a processor coupled with memory, via a network, a question from an administrator device to a chatbot corresponding to a client device to generate a dialog between the chatbot and the client device;

receiving, by the data processing system via the network, a response to the transmitted question from the client device for inclusion in the dialog, wherein the response includes an indication of a possible threat;

determining, by the data processing system, that the response corresponds to a response trigger corresponding to the question;

transmitting, by the data processing system via the network, responsive to determining that the response corresponds to the response trigger, a chatbot response for inclusion in the dialog, to the client device providing the response;

determining, by the data processing system, that the chatbot response does not include a second question regarding the response corresponding to the response trigger;

storing, by the data processing system, the dialog comprising the question, the response, the chatbot response, and an identifier in a dialog database;

analyzing, by the data processing system, the dialog, which comprises the question, the response, and the chatbot response, using an artificial intelligence component executing at least one of speech recognition, speech-to-text conversion, natural language processing, pattern recognition, data statistics analysis, sentiment analysis, anomaly detection, question and answer classification, or root cause analysis;

generating, by the data processing system, insights based on the analyzed dialog, wherein the insights comprise at least i) a root cause of at least one of an issue, a sentiment, a concern, a complaint, or a problem and ii) one or more solutions to the root cause, wherein the root cause includes a security issue and the one or more solutions to the root cause include locking a door to a room; and

controlling, by the data processing system, the external system, based on the generated insights, to lock the door corresponding to the room to resolve the root cause using the one or more solutions to the root cause.

12 . The method of claim 11 , further comprising:

receiving, by the data processing system via the network, the question and the response trigger corresponding to the question from the administrator device.

13 . The method of claim 11 , further comprising:

extracting, by the data processing system, relevant information from the dialog based on the analysis.

14 . The method of claim 11 , further comprising:

analyzing, by the data processing system, the dialog using the artificial intelligence component to generate a structured dialog.

15 . The method of claim 11 , further comprising:

analyzing, by the data processing system, the dialog using the artificial intelligence component to generate a structured dialog; and

generating, by the data processing system, the insights based on the structured dialog generated using the artificial intelligence component.

16 . The method of claim 11 , further comprising:

receiving, by the data processing system, a plurality of responses to the question from a plurality of client devices, wherein the response and one or more of the plurality of responses include the complaint about a temperature;

generating, by the data processing system, insights based on the analyzed dialog and the analyzed plurality of responses, wherein the insights comprise i) the room of a building, ii) the root cause includes a complaint about the temperature in the room based on the response and the one or more of the plurality of responses, and iii) the one or more solutions include modifying the temperature of the room; and

determining, by the data processing system, based on the analyzed dialog and the analyzed plurality of responses, a level of certainty of the root cause;

wherein controlling the external system comprises:

transmitting, by the data processing system, using an application programming interface, in response to the level of certainty being greater than a certainty threshold, a control signal to a temperature control system of the building, to cause the temperature control system to modify the temperature of the room to resolve the root cause using the one or more solutions to the root cause.

17 . The method of claim 11 , further comprising:

generating, by the data processing system, a communication corresponding to the response, based on the generated insights; and

transmitting, by the data processing system, the communication to the external system.

18 . The method of claim 11 , further comprising:

controlling, by the data processing system, the external system, based on the generated insights, wherein the external system is a fire suppression system associated with the response.

19 . The method of claim 11 , further comprising:

extracting, by the data processing system, based on analyzing the dialog, a first indication from the response and a second indication from the response, wherein the first indication includes at least one of intense heat levels, heavy amounts of smoke, and fire, and the second indication includes a room;

generating, by the data processing system, the insights based on the analyzed dialog, the first indication, and the second indication, wherein the insights comprise i) the root cause, including a fire issue and ii) the one or more solutions, including controlling a fire suppression system; and

controlling, by the data processing system, in response to generating the insights, the fire suppression system in the room to resolve the root cause using the one or more solutions to the root cause.

20 . A system, comprising:

one or more processors, coupled with memory, to:

transmit, via a network, a question from an administrator device to a chatbot corresponding to a client device to generate a dialog between the chatbot and the client device;

receive, via the network, a response to the transmitted question from the client device for inclusion in the dialog;

determine that the response corresponds to a response trigger corresponding to the question;

transmit, via the network, responsive to determining that the response corresponds to the response trigger, a chatbot response for inclusion in the dialog, to the client device providing the response;

determine that the chatbot response does not include a second question regarding the response corresponding to the response trigger;

store the dialog comprising the question, the response, the chatbot response, and an identifier in a dialog database;

analyze the dialog using an artificial intelligence component executing at least one of speech recognition, speech-to-text conversion, natural language processing, pattern recognition, data statistics analysis, sentiment analysis, anomaly detection, question and answer classification, or root cause analysis;

extracting, based on analyzing the dialog, a first indication from the response and a second indication from the response, wherein the first indication includes at least one of intense heat levels, heavy amounts of smoke, and fire, and the second indication includes a room

generate insights based on the analyzed dialog, the first indication, and the second indication, wherein the insights comprise at least i) a root cause of at least one of an issue, a sentiment, a concern, a complaint, or a problem and ii) one or more solutions to the root cause, wherein the root cause includes a fire issue and the one or more solutions include controlling a fire suppression system;

display the insights in a dashboard on a display of the administrator device; and

control, based on the insights, the fire suppression system in the room to resolve the root cause using the one or more solutions to the root cause.

Continuity (2)

References Cited (30)