US-12620392-B2 - Initiating an action based on a voice message text generated from a voice message

US12620392B2US 12620392 B2US12620392 B2US 12620392B2US-12620392-B2

Abstract

From a mobile device a voice message text can be received for a voice message provided by a user for a phone call initiated by the user. Context information pertaining to the phone call can be received from the mobile device. Sentiment data can be generated by performing a sentiment analysis on the voice message text. A severity of an event to which the phone call pertains can be determined based on the context information and the sentiment data. An action can be selected based on the severity of the event to which the phone call pertains. Performance of the action can be initiated.

Inventors

Arif Ege Or
Tymoteusz Gedliczka
Umit Bektas
Aleksandra Szostak
Andrei Nosatîi

Assignees

INTERNATIONAL BUSINESS MACHINES CORPORATION

Dates

Publication Date: 20260505
Application Date: 20230905

Claims (20)

1 . A computer-implemented method, comprising: receiving, by a processor, from a mobile device, a voice message text for a first voice message provided by a user for a first phone call initiated by the user, wherein the receiving of the voice message text is based on the first phone call that is not connected to a target recipient device; receiving, by the processor, from the mobile device, context information pertaining to the first phone call; generating, by the processor, sentiment data by performing a sentiment analysis on the voice message text; determining, by the processor, a severity of an event to which the first phone call pertains based on the context information and the sentiment data; selecting, by the processor, an action based on the severity of the event to which the first phone call pertains; and initiating, by the processor, performance of the action, wherein the action includes: synthesizing a second voice message from the voice message text; initiating a second phone call to the target recipient device; and playing the synthesized second voice message to the target recipient device in the second phone call.
2 . The computer-implemented method of claim 1 , wherein the context information comprises data indicating a tone of a voice of the user in the first voice message.
3 . The computer-implemented method of claim 1 , wherein the context information comprises data indicating a speech pattern of spoken utterances of the user in the first voice message.
4 . The computer-implemented method of claim 1 , wherein the context information comprises data indicating a ratio of an acoustic volume of a voice of the user to an acoustic volume of ambient sounds detected by an input audio transducer of the mobile device.
5 . The computer-implemented method of claim 1 , wherein the context information comprises data indicating at least one unusual anomaly in physiological data of the user.
6 . The computer-implemented method of claim 1 , further comprising: classifying the severity of the event; and adding the event to a queue based on a classification of the severity of the event not being a highest severity, wherein the selecting of the action is based on a turn for the event in the queue being reached.
7 . The computer-implemented method of claim 6 , wherein the adding the event to the queue comprises adding to the queue the voice message text and the context information.
8 . A system, comprising: a processor programmed to initiate executable operations comprising: receiving, from a mobile device, a voice message text for a first voice message provided by a user for a first phone call initiated by the user, wherein the receiving of the voice message text is based on the first phone call that is not connected to a target recipient device; receiving, from the mobile device, context information pertaining to the first phone call; generating sentiment data by performing a sentiment analysis on the voice message text; determining a severity of an event to which the first phone call pertains based on the context information and the sentiment data; selecting an action based on the severity of the event to which the first phone call pertains; and initiating performance of the action, wherein the action includes: synthesizing a second voice message from the voice message text; initiating a second phone call to the target recipient device; and playing the synthesized second voice message to the target recipient device in the second phone call.
9 . The system of claim 8 , wherein the context information comprises data indicating a tone of a voice of the user in the first voice message.
10 . The system of claim 8 , wherein the context information comprises data indicating a speech pattern of spoken utterances of the user in the first voice message.
11 . The system of claim 8 , wherein the context information comprises data indicating a ratio of an acoustic volume of a voice of the user to an acoustic volume of ambient sounds detected by an input audio transducer of the mobile device.
12 . The system of claim 8 , wherein the context information comprises data indicating at least one unusual anomaly in physiological data of the user.
13 . The system of claim 8 , further comprising: classifying the severity of the event; and adding the event to a queue based on a classification of the severity of the event not being a highest severity, wherein the selecting of the action is based on a turn for the event in the queue being reached.
14 . The system of claim 13 , wherein the adding the event to the queue comprises adding to the queue the voice message text and the context information.
15 . A computer program product, comprising: one or more computer readable storage mediums having program code stored thereon, the program code stored on the one or more computer readable storage mediums collectively executable by a data processing system to initiate operations including: receiving, from a mobile device, a voice message text for a first voice message provided by a user for a first phone call initiated by the user, wherein the receiving of the voice message text is based on the first phone call that is not connected to a target recipient device; receiving, from the mobile device, context information pertaining to the first phone call; generating sentiment data by performing a sentiment analysis on the voice message text; determining a severity of an event to which the first phone call pertains based on the context information and the sentiment data; selecting an action based on the severity of the event to which the first phone call pertains; and initiating performance of the action, wherein the action includes: synthesizing a second voice message from the voice message text; initiating a second phone call to the target recipient device; and playing the synthesized second voice message to the target recipient device in the second phone call.
16 . A computer-implemented method, comprising: initiating, by a processor of a mobile device, a first phone call to a target recipient device; receiving, by the processor, from a telecommunications service, a call status indicator that indicates the first phone call is not connected to the target recipient device; outputting, by the processor, based on the receiving of the call status indicator that indicates the first phone call is not connected to the target recipient device, a prompt to a user to provide a first voice message; receiving, by the processor, based on the prompt to the user to provide the first voice message, the first voice message from the user; converting, by the processor, the first voice message to a voice message text; determining, by the processor, context information pertaining to the first phone call by analyzing the first voice message; and communicating, by the processor, the voice message text and the context information to the telecommunications service, wherein the telecommunications service determines a severity of an event to which the first phone call pertains based, at least in part, on the context information, selects an action based on the severity of the event to which the first phone call pertains, and initiates performance of the action, and the action includes: synthesizing a second voice message from the voice message text, initiating a second phone call to the target recipient device, and playing the synthesized second voice message to the target recipient device in the second phone call.
17 . The computer-implemented method of claim 16 , wherein the context information comprises data indicating a tone of a voice of the user in the first voice message.
18 . The computer-implemented method of claim 16 , wherein the context information comprises data indicating a speech pattern of spoken utterances of the user in the first voice message.
19 . The computer-implemented method of claim 16 , wherein the context information comprises data indicating a ratio of an acoustic volume of a voice of the user to an acoustic volume of ambient sounds detected by an input audio transducer of the mobile device.
20 . The computer-implemented method of claim 16 , wherein the context information comprises data indicating at least one unusual anomaly in physiological data of the user.

Description

BACKGROUND The present invention relates to mobile communications, and more specifically, to phone call processing. Mobile communication devices typically are configured to wirelessly communicate over mobile communication networks, for example cellular communication networks. An example of a mobile communication device is a smart phone, which is a portable computing device that combines mobile telephone functions and computing functions into one unit. For instance, smart phones can provide core functions, such as voice calls and text messaging, along with other computing functions. Mobile communication devices have become ubiquitous throughout much of the world. Indeed, many people consider such devices an essential part of modern living. In contrast to traditional landline telephones, mobile communication devices enable people to communicate from virtually anywhere they may travel, so long as their mobile communication devices are able to establish a wireless network connection. The use of mobile communication devices is particularly useful during emergencies. For example, if a person suffers a vehicle breakdown, that person can use their mobile communication device to call someone for assistance. Sometimes, however, mobile communication networks become congested, and phone calls that are placed may not go through. This can leave the person stranded until the network congestion eases. Moreover, target call recipients may be busy and not able to answer incoming calls, which also can result in the person being left stranded for some time. U.S. Pat. No. 10,069,965 B2 discloses a “method of maintaining audio communication in a congested communication channel.” “Instead of transmitting the speech from the sender to the receiver side, the speech is converted to text and sent as text data to the receiver side.” Similarly, U.S. Pat. No. 7,082,309 B2 discloses a “method for providing a call processing service wherein a short message can be transmitted to another party using a signaling channel in cases where a traffic channel cannot be allocated (for example, in traffic congestion state).” Merely sending the text to the receiver side, however, does not convey contextual information that may be important to convey a sense of urgency for a call. SUMMARY In one or more embodiments, a method includes receiving, from a mobile device, voice message text for a voice message provided by a user for a phone call initiated by the user. The method also can include receiving, from the mobile device, context information pertaining to the phone call. The method also can include generating sentiment data by performing a sentiment analysis on the voice message text. The method also can include determining, using a processor, a severity of an event to which the phone call pertains based on the context information and the sentiment data. The method also can include selecting an action based on the severity of the event to which the phone call pertains. The method also can include initiating performance of the action. A system can include a processor programmed to initiate executable operations. The executable operations can include one or more of the processes described for the above method. A computer program product includes a computer readable storage medium having program code stored thereon. The program code is executable by a data processing system to initiate operations. The operations can include one or more of the processes described for the above method. In one or more embodiments, a method can include initiating, by a mobile device, a phone call to a target recipient device. The method also can include receiving, from a telecommunications service, a call status indicator that indicates the phone call is not connected to the target recipient device. The method also can include responsive to receiving the call status indicator that indicates the phone call is not connected to the target recipient device, prompting the user to provide a voice message. The method also can include, responsive to prompting the user to provide the voice message, receiving the voice message from the user. The method also can include converting, by a processor of the mobile device, the voice message to voice message text. The method also can include determining context information pertaining to the phone call by analyzing the voice message. The method also can include communicating the voice message text and the context information to the telecommunications service. The telecommunications service can determine a severity of an event to which the phone call pertains based, at least in part, on the context information, select an action based on the severity of the event to which the phone call pertains, and initiate performance of the action. A mobile device includes a processor programmed to initiate executable operations. The executable operations can include one or more of the processes described for the above method. This Summary section is provi