Patent Issued for Data access system for representatives (USPTO 11206329): United Services Automobile Association

2022 JAN 12 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventors Adam, Patrick (Helotes, TX, US), Anaruk, Andrew L. (San Antonio, TX, US), Fernandez, Gabriel Carlos (San Antonio, TX, US), Goos, Benjamin (San Antonio, TX, US), Maldonado, Ana (San Antonio, TX, US), filed on January 7, 2021, was published online on December 21, 2021.

The patent’s assignee for patent number 11206329 is United Services Automobile Association (San Antonio, Texas, United States).

News editors obtained the following quote from the background information supplied by the inventors: “Companies constantly try to find the proper amount of data access for employees. That is, employees need to have enough access to perform their job duties but generally do not need access to all information. Data access for employees such as customer service representatives is becoming increasingly important as privacy becomes a further concern for companies.

“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.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventors’ summary information for this patent: “As privacy becomes a focus for many companies, companies that store customer information are being forced to control data access to customer information. That is, some employees have access to customer data while others will have little or no access to customer data. There are easy cases in which access does not need to be granted to employees. For example, property inspectors do not need access to the homeowner’s personal information such as social security number, mortgage, employment status and birthday. However, a customer or member service representative (“representative”) may, during the course of a call with a customer, need access to various information to better serve the customer.

“Current systems lack to the technology to adequately protect customer information and allow representatives to perform their job duties. Current systems provide access to all customer information to representatives, regardless of the type of information being requested or discussed. While convenient, providing such uncontrolled access can cause issues. For example, in some circumstances, representatives may use the information carelessly or nefariously. Should the representative notice something interesting in the customer’s profile, the representative may review the user’s social media pages or finances out of curiosity. In other circumstances, the representative could collect a customer’s information and sell it or otherwise partake in illegal activities. Even if the representative does nothing with the customer data, providing access to the customer data can put the company and/or employee at risk of claims. Another issue of providing unlimited customer data to representatives is that fraudsters may trick the representative into giving out customer data. For example, a fraudster may ask the representative about some of the customer’s past or personal information to use in other scenarios (e.g., “What color was my last Honda?” or “What birth date do you have for me in the system?”). In many cases, much of the user’s personal information is not relevant to the call (e.g., the user’s birth date, social security number).

“Systems and methods disclosed herein address the challenge of adequately protecting customer information and yet allowing a representative to perform his or her duties. In some embodiments, an organization receives a call from a user. The call can be received by an interactive voice response (IVR) system and the user can provide identification and, in some cases, authentication information. The IVR system can determine the subject matter the user is calling about (e.g., home insurance, property claim). When the call is routed to a representative, the system can monitor the call between the user and the representative. The user can have an associated profile with data about the user (e.g., birthday, family members, salary, employment status, products or services with the organization). Such data can be locked such that the representative cannot access the data. As the user and the representative converse, the system can continuously convert the speech from the call into text. The system can determine an intent of the call and what information the representative needs to know based on an analysis of the text. A portion of the data form the user’s profile can be unlocked based on the determined intent of the call. Such unlocked data can be displayed on a display screen of the representative or the representative can access the unlocked data in another way. As the user and the representative continue conversing, additional data can be unlocked as needed.

“The user may request additional information about a product or about himself or herself that is outside of the initial subject matter of the call. Assuming the data is unlocked, the representative can provide such information to the user. As the conversation continues and the speech is determined and analyzed for intent, the system can indicate to the representative the information by flashing the information on the screen or highlighting a certain portion of the screen or bringing up an automated chat box with the answer.

“If, on the other hand, the user asks for information that is still part of the locked data, the representative can ask the user to provide authentication data (e.g., birthday) to further verify the user’s identity before handing out additional or more sensitive information. The authentication data can be input into a one-way function such as a hash function. The system can compare the output of the authentication data after being hashed with the output of previously provided and hashed data using the same hash function. If the outputs (hashes) are the same, then the user has provided correct information and the user’s trust level has been elevated such that additional data can be unlocked and displayed on the representatives display screen or otherwise provided to the representative. Thus, the sensitive data can stay protected if the user cannot provide the proper credentials. In response to the user not providing the proper authentication information, the call can be transferred to a fraud unit or other service equipped to handle calls needing additional authentication.”

The claims supplied by the inventors are:

“1. A computerized method comprising: monitoring a call between a user and a representative regarding a subject matter, wherein the user has a profile with data relating to the user, and wherein the data is locked such that the representative cannot initially access the data; at multiple points during the call, converting, by a processor, audio from the call between the user and the representative on the call, into text; determining an intent of the call based on the text; generating a list of products or services potentially of interest to the user based on the profile of the user and the determined intent of the call; unlocking a portion of the data based on the list of products or services such that the representative can access the unlocked portions of the data; and displaying the unlocked portion of the data and the list of products or services potentially of interest to the user on a display screen of the representative during the call, wherein a locked portion of data is obscured to the representative.

“2. The computerized method of claim 1, further comprising: training a model to determine, based on text from multi-party speech inputs of multiple calls, call intents; wherein the analyzing the text includes applying the model to the text.

“3. The computerized method of claim 1, further comprising: receiving, from the user, a request for information relating to the user; and in response to the information being part of the locked portion of the data, requesting authentication information from the user.

“4. The computerized method of claim 3, further comprising: receiving, from the user, the authentication information; inputting the received authentication information into a one-way function; and verifying the received authentication information based on a comparison of an output of the one-way function with an output of the authentication information previously input into the one-way function.

“5. The computerized method of claim 4, further comprising: in response to verifying the received authentication information, unlocking an additional portion of the locked portion of the data; and displaying the unlocked additional portion of the data on the display screen of the representative.

“6. The computerized method of claim 3, further comprising: receiving, from the user, the authentication information; inputting the received authentication information into a one-way function; comparing an output of the one-way function with an output of the authentication information previously input into the one-way function; determining, based on the comparison, the output of the one-way function does not match the output of the authentication information; and transferring the call to a different representative based on the output of the one-way function not matching the output of the authentication information.

“7. A non-transitory, computer-readable medium storing instructions that, when executed by a computing system, cause the computing system to perform operations comprising: monitoring a call between a user and a representative regarding a subject matter, wherein the user has a profile with data relating to the user, and wherein at least part of the data is locked such that the representative cannot initially access the locked part of the data; at multiple points during the call, converting, by a processor, audio from the call between the user and the representative on the call, into text; determining an intent of the call based on the text; generating a list of products or services potentially of interest to the user based on the profile and the determined intent of the call; unlocking a portion of the data based on the list of products or services such that the representative can access the unlocked portions of the data; and displaying the unlocked portion of the data and the list of products or services potentially of interest to the user on a display screen of the representative during the call, wherein a locked portion of data is obscured to the representative.

“8. The non-transitory, computer-readable medium of claim 7, wherein the operations further comprise: training a model to determine, based on text from multiple speech inputs, intents; wherein the analyzing the text includes applying the model to the text.

“9. The non-transitory, computer-readable medium of claim 7, wherein the operations further comprise: receiving, from the user, a request for information relating to the user; and in response to the information being part of the locked portion of the data, requesting authentication information from the user.

“10. The non-transitory, computer-readable medium of claim 9, wherein the operations further comprise: receiving, from the user, the authentication information; verifying the received authentication information based on a comparison of the authentication information with previously stored authentication information.

“11. The non-transitory, computer-readable medium of claim 10, wherein the operations further comprise: in response to verifying the received authentication information, unlocking an additional portion of the locked portion of the data; and displaying the unlocked additional portion of the data on the display screen of the representative.

“12. The non-transitory, computer-readable medium of claim 9, wherein the operations further comprise: receiving, from the user, the authentication information; determining the authentication information is not valid; and in response to determining the authentication information is not valid, transferring the call to a different representative.

“13. A computing system comprising: one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to perform a process comprising: monitoring a call between a user and a representative regarding a subject matter, wherein the user has a profile with data relating to the user, and wherein at least part of the data is locked such that the representative cannot initially access the locked part of the data; at multiple points during the call, converting, by a processor, audio from the call between the user and the representative on the call, into text; determining an intent of the call based on the text; generating a list of products or services potentially of interest to the user based on the profile and the determined intent of the call; unlocking a portion of the data based on the list of products or services such that the representative can access the unlocked portions of the data; and displaying the unlocked portion of the data and the list of products or services potentially of interest to the user on a display screen of the representative during the call, wherein a locked portion of data is obscured to the representative.

“14. The computing system according to claim 13, wherein the process further comprises: training a model to determine, based on text from multiple previous calls, call intents; wherein the analyzing the text includes applying the model to the text.

“15. The computing system according to claim 13, wherein the process further comprises: receiving, from the user, a request for information relating to the user; and in response to the information being part of the locked portion of the data, requesting authentication information from the user.

“16. The computing system according to claim 15, wherein the process further comprises: receiving, from the user, the authentication information; inputting the received authentication information into a one-way function; and verifying the received authentication information based on a comparison of an output of the one-way function with an output of the authentication information previously input into the one-way function.

“17. The computing system according to claim 16, wherein the process further comprises: in response to verifying the received authentication information, unlocking an additional portion of the locked portion of the data; and displaying the unlocked additional portion of the data on the display screen of the representative.”

For additional information on this patent, see: Adam, Patrick. Data access system for representatives. U.S. Patent Number 11206329, filed January 7, 2021, and published online on December 21, 2021. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=11206329.PN.&OS=PN/11206329RS=PN/11206329

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