Patent Issued for Voice interaction scripts (USPTO 11593067): United Services Automobile Association

2023 MAR 22 (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 11593067, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Maciolek, Michael J. (Boerne, TX, US), Whitaker, Charise Renee (San Antonio, TX, US).

This patent was filed on November 25, 2020 and was published online on February 28, 2023.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Voice-controlled personal assistants are used for many things such as telling a user the weather, playing a song, and reading an email. For example, a person can ask or state, “Alexa, what is the weather today?” and Alexa® can navigate the Internet, find the weather, and provide an appropriate spoken response (e.g., “It will be 70 degrees today”). Such services are helpful in some but not all situations.

“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: “People are increasingly finding and developing ways to simplify their lives. For example, people are using voice-controlled intelligent personal assistants to obtain information such as the weather and news, to order items, and to pay bills. Doing so saves the person from having to type on a computing device, locate a website or newsfeed and read the information. Although natural language processing technology is becoming increasingly better, some customers still experience frustration with the common misinterpretations and mistakes made by the machines during natural language processing. Additionally, not all requests are suitable for speaking a request or receiving a spoken answer. For example, information such as bank accounts and credit card balances are typically kept private. Moreover, sometimes users may wish to keep even the request for such information confidential.

“To address the above-mentioned issues, the technology described herein provides a system and method that can build and use scripts that request an activity (e.g., provide bank account balances) and create a script. The script can include preferences for information delivery (e.g., device, format) and can be called or activated by a customized voice command (e.g., “totals” or “I love the rain”) that is spoken to a virtual assistant. The virtual assistant can detect that the word or phrase and send the request to a server to determine which script should be called or the virtual assistant can identify the script. In some implementations, the user’s identity is sent with the request (e.g., the sending device is registered to the user, credentials are sent) and verified by analyzing voice biometrics (i.e., comparing voice biometrics of the user stating the customized voice command with previous versions of the user stating the customized voice command). The activity can be performed, and the results can be delivered to a device in a format indicated in the script (e.g., mobile device and text message, respectively). Thus, a person can state a request aloud using a virtual assistant and receive answers privately in a preferred format. Additionally, the user can select a customized voice command that is easily processed by the virtual assistant or server so that natural language processing errors are less likely to occur.

“In some implementations, the script is offered to be created in response to the user requesting the same activity more than one time. In other embodiments, the user receives a script creation offer for many or all requests. In some implementations, machine learning is used to analyze a set of scripts associated with the user. Based on the analysis, the user can receive script creation offers. In some implementations, menu options can be customized for the user based on the analysis.

“This disclosure describes systems and processes designed to provide users a platform to request and receive confidential information and keep such information confidential. Various embodiments may provide one or more of the following technological improvements: (1) reduce natural language processing errors by using voice-activated scripts; (2) reduce communications and overall processing power by authenticating a user using a customized voice command that is also used to make a substantive request; (3) increase security of account information; and (4) provide increased flexibility in device and format delivery options.

“In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present technology. It will be apparent, however, that embodiments of the present technology may be practiced without some of these specific details”

The claims supplied by the inventors are:

“1. A computerized method comprising: receiving, from a first device, two or more requests within a threshold time for an activity from a user; in response to receiving the two or more requests within the threshold time, causing an option to create a script for the activity to be displayed on a display of the first device; in response to a selection of the option to create the script for the activity; receiving, from the first device, a customized voice command for the script; identifying an indication of a delivering device, and a deliverable format; in response to identifying the indication of the delivering device, the deliverable format and the customized voice command, creating the script that includes a voice sample of the user, the customized voice command, the indication of the delivering device, and the deliverable format; receiving, from the user, the customized voice command that is spoken into a voice-controlled virtual assistant on a second device; identifying the script based on the spoken customized voice command; determining the activity, the delivering device, and the deliverable format based on the script; authenticating the user to receive results based on one or more voice characteristics in the spoken customized voice command matching the voice sample in the script; in response to determining the activity and authenticating the user, performing the activity; and sending the results of the activity to the delivering device in the deliverable format.

“2. The computerized method of claim 1, wherein causing the display of the option to create the script is in response to having previously received a same request for the activity from the user.

“3. The computerized method of claim 1, wherein the first device is a mobile device, wherein the delivering device is the mobile device.

“4. The computerized method of claim 1, wherein the deliverable format is one of: words spoken on the delivering device, a text message sent to the delivering device, an email accessible by the delivering device, a push notification sent to the delivering device, or a message delivered to an application accessible by the delivering device.

“5. The computerized method of claim 1, wherein the first device is a mobile device, wherein the script indicates that the delivering device is the mobile device and that the deliverable format is a text message.

“6. The computerized method of claim 1, further comprising authenticating the user based on a location of a device associated with the user.

“7. The computerized method of claim 1, further comprising: analyzing, using machine learning techniques, a set of scripts associated with the user; and offering to create scripts for additional activities based on the analysis.

“8. The computerized method of claim 1, further comprising: analyzing a set of scripts associated with the user; and customizing menu options for the user based on the analysis.

“9. The computerized method of claim 1, wherein the first device, the second device and the delivering device are the same device.

“10. 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: receiving, from a first device, two or more requests within a threshold time for an activity from a user; in response to receiving the two or more requests within the threshold time, causing an option to create a script for the activity to be displayed on a display of the first device; in response to a selection of the option to create the script for the activity; receiving, from the first device, a customized voice command for the script; identifying an indication of a delivering device, and a deliverable format; in response to identifying the indication of the delivering device, the deliverable format and the customized voice command, creating the script that includes a voice sample of the user, the customized voice command, the indication of the delivering device, and the deliverable format; receiving, from the user, the customized voice command that is spoken into a voice-controlled virtual assistant on a second device; identifying the script based on the spoken customized voice command; determining the activity, the delivering device, and the deliverable format based on the script; authenticating the user to receive results based on one or more voice characteristics in the spoken customized voice command matching the voice sample in the script; in response to determining the activity and authenticating the user, performing the activity; and sending the results of the activity to the delivering device in the deliverable format.

“11. The computing system of claim 10, wherein causing the display of the option to create the script is in response to having previously received a same request for the activity from the user.

“12. The computing system of claim 10, wherein the second device is a voice command device, and wherein the process further comprises: receiving, via the voice command device, the customized voice command; and sending the customized voice command to the first device.

“13. The computing system of claim 10, wherein the process further comprises authenticating the user based on a location of a device associated with the user.

“14. The computing system of claim 10, wherein the first device, the second device and the delivering device are the same device.

“15. A non-transitory computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to perform a process comprising: receiving, from a first device, two or more requests within a threshold time for an activity from a user; in response to receiving the two or more requests within the threshold time, causing an option to create a script for the activity to be displayed on a display of the first device; in response to a selection of the option to create the script for the activity; receiving, from the first device, a customized voice command for the script; identifying an indication of a delivering device, and a deliverable format; in response to identifying the indication of the delivering device, the deliverable format and the customized voice command, creating the script that includes a voice sample of the user, the customized voice command, the indication of the delivering device, and the deliverable format; receiving, from the user, the customized voice command that is spoken into a voice-controlled virtual assistant on a second device; identifying the script based on the spoken customized voice command; determining the activity, the delivering device, and the deliverable format based on the script; authenticating the user to receive results based on one or more voice characteristics in the spoken customized voice command matching the voice sample in the script; in response to determining the activity and authenticating the user, performing the activity; and sending the results of the activity to the delivering device in the deliverable format.

“16. The non-transitory computer-readable storage medium of claim 15, wherein the second device is a voice command device, and wherein the process further comprises: receiving, via the voice command device, the customized voice command; and sending the customized voice command to the first device.

“17. The non-transitory computer-readable storage medium of claim 15, wherein the process further comprises authenticating the user based on a location of a device associated with the user.”

For the URL and additional information on this patent, see: Maciolek, Michael J. Voice interaction scripts. U.S. Patent Number 11593067, filed November 25, 2020, and published online on February 28, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11593067)&db=USPAT&type=ids

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