Publish and subscribe call center architecture
An example operation may include one or more of receiving an audio file from a public safety answering point (PSAP), the audio file comprising a recording of a telephone call, converting the audio file into a text file that comprises a transcript of the telephone call, identifying a keyword within the text file that is associated with a topic, and transmitting a portion of the text file of the telephone call to one or more subscribers that have registered with the topic.
1 . A method, comprising:
receiving a subscription to a topic;
receiving audio of a telephone call;
converting the audio into a transcript of at least a portion of the telephone call;
identifying a keyword associated with at least one of the telephone call or the transcript; and
forwarding one or more messages to emergency personnel, at least in part based on the identifying, wherein the one or more messages include a timestamp of the telephone call, and the one or more messages allow play of the audio of the telephone call.
2 . The method of claim 1 , wherein the one or more messages include at least a portion of the transcript.
3 . The method of claim 1 , further comprising:
recording the content of the telephone call.
4 . The method of claim 1 , further comprising:
notifying an emergency service of the topic.
5 . The method of claim 1 , further comprising:
using a machine-learning model to identify a text file as related to the topic.
6 . The method of claim 1 , wherein the one or more messages include a caller number of the telephone call.
7 . The method of claim 1 , wherein the topic is repeatedly mentioned within a plurality of calls, the plurality including the call.
8 . An apparatus, comprising:
a network interface that receives a subscription to a topic and receives audio of a telephone call; and
a processor configured to convert the audio into a transcript of at least a portion of the telephone call and to perform an identification of a keyword associated with at least one of the telephone call or the transcript, wherein the network interface forwards one or more messages to emergency personnel, at least in part based on the identification, and the one or more messages include a timestamp of the telephone call, the one or more messages allowing play of the audio of the telephone call.
9 . The apparatus of claim 8 , wherein the network interface notifies an emergency service of the topic.
10 . The apparatus of claim 8 , wherein the one or more messages include a caller number of the telephone call.
11 . A computer-readable medium encoded with instructions that, when executed by a processor, cause the processor to perform operations comprising:
receiving a subscription to a topic;
receiving audio of a telephone call;
converting the audio into a transcript of at least a portion of the telephone call;
identifying a keyword associated with at least one of the telephone call or the transcript; and
forwarding one or more messages to emergency personnel, at least in part based on the identifying, wherein the one or more messages include a timestamp of the telephone call, and the one or more messages allow play of the audio of the telephone call.
12 . The medium of claim 11 , the operations further comprising:
notifying an emergency service of the topic.
13 . The medium of claim 11 , wherein the one or more messages include a caller number of the telephone call.