Patent Issued for Predictive mapping for routing telephone calls (USPTO 11750744): United Services Automobile Association

2023 SEP 25 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- United Services Automobile Association (San Antonio, Texas, United States) has been issued patent number 11750744, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Daali, Amy (San Antonio, TX, US), Lopez, Mark Anthony (Helotes, TX, US), Medina, III, Reynaldo (San Antonio, TX, US), Williams, Kristopher (San Antonio, TX, US).

This patent was filed on August 31, 2022 and was published online on September 5, 2023.

From the background information supplied by the inventors, news correspondents obtained the following quote: “When a person calls an organization’s customer service phone number, he or she is routed to a customer service representative. To talk to the customer service process, the call routing system may request the person identify the reason for his or her call. In some cases, the call routing system may provide some options such as dialing a number for an option related to complaints. The call routing system may also request the person to enter some identifying information about him or her, such as a member number or a birthdate. After the person enters the requested information, the call routing system typically routes the person to the next available customer service representative.

“The techniques introduced here may be better understood by referring to the following Detailed Description in conjunction with the accompanying drawings, in which like reference numerals indicate identical or functionally similar elements. Moreover, while the technology is amenable to various modifications and alternative forms, specific embodiments have been shown by way of example in the drawings and are described in detail below. The intention, however, is not to limit the technology to the particular embodiments described. On the contrary, the technology is intended to cover all modifications, equivalents, and alternatives falling within the scope of the technology as defined by the appended claims.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “A conventional call routing system can randomly route a person’s call to a next available customer service representative based on a reason for the person’s call. For instance, the conventional call routing system can request a person to identify a reason for his or her call and can determine that the person is calling about credit card fraud. Based on this reason, the conventional call routing system can randomly select a next available customer service representative within the credit card fraud department to answer the person’s call. In some cases, such a random routing may provide a positive outcome for the person, but in some cases, the person may have a negative experience with the randomly selected customer service representative. By randomly routing the call to an available customer service representative, a conventional call routing system cannot predict whether its routing will result a good experience for the person.

“To overcome at least some of the issues described above for a conventional call routing system, this patent document describes systems, apparatus, and methods for routing telephone calls based on predictive mapping of a person calling to a customer service representative. The predictive mapping techniques used to map the person to the customer service representative can maximize the likelihood that the person will have a positive experience when talking to the mapped customer service representative. Alternatively, or additionally, the predictive mapping techniques used to map the person to the customer service representative can minimize the likelihood that the person will have a negative experience when talking to the mapped customer service representative. Thus, the technology identifies persons having the optimal personal compatibility for the given scenario to answer the telephone call.

“The predictive mapping techniques disclosed herein to identify the persons having optimal personal compatibility to answer the call can be based on any one or more of the following factors: (1) a sentiment score based on a topic of conversation (also known as topic modeling); (2) an experience score of the customer service representative with a topic of conversation; and (3) a performance score of the customer service representative in managing a topic of conversation. These factors and the predictive mapping using each of these factors are described in the sections below. The example headings for the various sections below are used to facilitate the understanding of the disclosed subject matter and do not limit the scope of the claimed subject matter in any way. Accordingly, one or more features of one section can be combined with one or more features of another section.

“I. Sentiment Scores for Topics or Topic Modeling”

The claims supplied by the inventors are:

“1. A method comprising: generating a plurality of sentiment scores associated with a plurality of topics, by: analyzing a plurality of sentences of conversations between users and call representatives, identifying at least one topic in respective sentences in the conversations, determining a sentiment sub-score for the respective sentences in the conversations associated with the at least one topic, and combining the sentiment sub-score of the respective sentences to create a sentiment score associated with the at least one topic; after completing generation of the plurality of sentiment scores, receiving, from a user device, an indication of the at least one topic selected via a telephone call; retrieving the sentiment score associated with the selected at least one topic from the plurality of sentiment scores; identifying at least one person for answering the telephone call based on the retrieved sentiment score and the selected at least one topic; and sending, to at least one computer associated with the at least one person, at least one message that indicates the selected at least one topic for answering the telephone call.

“2. The method of claim 1, further comprising: receiving, from additional user devices, indications of the at least one topic selected via a plurality of additional telephone calls; determining that a number of telephone calls having the sentiment score associated with the selected at least one topic exceeds a limit; identifying a plurality of persons available to answer the number of telephone calls, wherein the number of telephone calls are randomly distributed among the plurality of persons; and sending, to a plurality of computers associated with a plurality of persons, messages that indicates that the telephone call or at least one of the plurality of additional telephone calls is mapped to the plurality of persons.

“3. The method of claim 1, further comprising: receiving and analyzing a conversation between the at least one person and a user of the user device to determine a conversation score based on words used in the conversation, a tone of the conversation, a cadence of the conversation, or an amount of time of the conversation; and updating a performance score for the at least one person based on the conversation score.

“4. The method of claim 3, wherein the conversation score is determined by analyzing a set of words from a beginning portion of the conversation.

“5. The method of claim 3, wherein the performance score is determined based on an analysis of speech attributes of the at least one person on a prior telephone call involving the selected at least one topic.

“6. The method of claim 1, wherein a list of telephone calls to be answered by a plurality of persons is configured to be displayed on each of a plurality of computers, wherein the list of telephone calls includes the telephone call from the user device wherein the list of telephone calls is organized in an order of one or more telephone calls recommended for a person to one or more telephone calls not recommended for the person, and wherein the order is determined based on experience scores or performance scores related to a mapping between the person and topics associated with the list of telephone calls.

“7. The method of claim 1, further comprising: identifying the at least one topic in the plurality of sentences of the conversations between the users and the call representatives.

“8. A system comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the system to perform a process comprising: generating a plurality of sentiment scores associated with a plurality of topics, by: analyzing a plurality of sentences of conversations between users and call representatives, identifying at least one topic in respective sentences in the conversations, determining a sentiment sub-score for the respective sentences in the conversations associated with the at least one topic, and combining the sentiment sub-score of the respective sentences to create a sentiment score associated with the at least one topic; after completing generation of the plurality of sentiment scores, receiving, from a user device, an indication of the at least one topic selected via a telephone call; retrieving the sentiment score associated with the selected at least one topic from the plurality of sentiment scores; identifying at least one person for answering the telephone call based on the retrieved sentiment score and the selected at least one topic; and sending, to at least one computer associated with the at least one person, at least one message that indicates the selected at least one topic for answering the telephone call.

“9. The system according to claim 8, wherein the process further comprises: receiving, from additional user devices, indications of the at least one topic selected via a plurality of additional telephone calls; determining that a number of telephone calls having the sentiment score associated with the selected at least one topic exceeds a limit; identifying a plurality of persons available to answer the number of telephone calls, wherein the number of telephone calls are randomly distributed among the plurality of persons; and sending, to a plurality of computers associated with a plurality of persons, messages that indicates that the telephone call or at least one of the plurality of additional telephone calls is mapped to the plurality of persons.

“10. The system according to claim 8, wherein the process further comprises: receiving and analyzing a conversation between the at least one person and a user of the user device to determine a conversation score based on words used in the conversation, a tone of the conversation, a cadence of the conversation, or an amount of time of the conversation; and updating a performance score for the at least one person based on the conversation score.

“11. The system according to claim 10, wherein the conversation score is determined by analyzing a set of words from a beginning portion of the conversation.

“12. The system according to claim 10, wherein the performance score is determined based on an analysis of speech attributes of the at least one person on a prior telephone call involving the selected at least one topic.

“13. The system according to claim 8, wherein a list of telephone calls to be answered by a plurality of persons is configured to be displayed on each of a plurality of computers, wherein the list of telephone calls includes the telephone call from the user device wherein the list of telephone calls is organized in an order of one or more telephone calls recommended for a person to one or more telephone calls not recommended for the person, and wherein the order is determined based on experience scores or performance scores related to a mapping between the person and topics associated with the list of telephone calls.

“14. The system according to claim 8, wherein the process further comprises: identifying the at least one topic in the plurality of sentences of the conversations between the users and the call representatives.

“15. A non-transitory computer-readable medium storing instructions that, when executed by a computing system, cause the computing system to perform operations comprising: generating a plurality of sentiment scores associated with a plurality of topics, by: analyzing a plurality of sentences of conversations between users and call representatives, identifying at least one topic in respective sentences in the conversations, determining a sentiment sub-score for the respective sentences in the conversations associated with the at least one topic, and combining the sentiment sub-score of the respective sentences to create a sentiment score associated with the at least one topic; after completing generation of the plurality of sentiment scores, receiving, from a user device, an indication of the at least one topic selected via a telephone call; retrieving the sentiment score associated with the selected at least one topic from the plurality of sentiment scores; identifying at least one person for answering the telephone call based on the retrieved sentiment score and the selected at least one topic; and sending, to at least one computer associated with the at least one person, at least one message that indicates the selected at least one topic for answering the telephone call.

“16. The non-transitory computer-readable medium of claim 15, wherein the operations further comprise: receiving, from additional user devices, indications of the at least one topic selected via a plurality of additional telephone calls; determining that a number of telephone calls having the sentiment score associated with the selected at least one topic exceeds a limit; identifying a plurality of persons available to answer the number of telephone calls, wherein the number of telephone calls are randomly distributed among the plurality of persons; and sending, to a plurality of computers associated with a plurality of persons, messages that indicates that the telephone call or at least one of the plurality of additional telephone calls is mapped to the plurality of persons.

“17. The non-transitory computer-readable medium of claim 15, wherein the operations further comprise: receiving and analyzing a conversation between the at least one person and a user of the user device to determine a conversation score based on words used in the conversation, a tone of the conversation, a cadence of the conversation, or an amount of time of the conversation; and updating a performance score for the at least one person based on the conversation score.

“18. The non-transitory computer-readable medium of claim 17, wherein the conversation score is determined by analyzing a set of words from a beginning portion of the conversation.”

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

For the URL and additional information on this patent, see: Daali, Amy. Predictive mapping for routing telephone calls. U.S. Patent Number 11750744, filed August 31, 2022, and published online on September 5, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11750744)&db=USPAT&type=ids

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