Systems and methods of searching communications
Systems and methods for searching communications may include receiving a selection from a user of at least one of an acoustic characteristic, a language characteristic, or a category, accessing a database comprising a plurality of communications, the plurality of communications labeled with acoustic characteristics, language characteristics, and categories, restricting the plurality of communications to a subset of the plurality of communications including the user's selection of the at least one acoustic characteristic, language characteristic, or category, generating at least one of a word cloud or a tree for presenting a plurality of topics identified in the subset of the plurality of communications, and receiving a selection of one of the plurality of topics, the receiving causing a display of a further subset of the subset of the plurality of communications, the further subset having the selected topic.
1 . A method, comprising:
receiving a selection from a user of at least one of an acoustic characteristic, a language characteristic, or a category;
accessing a database comprising a plurality of communications, the plurality of communications labeled with acoustic characteristics, language characteristics, and categories;
restricting the plurality of communications to a subset of the plurality of communications including the user's selection of the at least one of the acoustic characteristic, the language characteristic, or the category;
generating a word cloud for presenting a plurality of topics identified in the subset of the plurality of communications, wherein the plurality of topics presented in the word cloud are selectable by the user;
receiving a selection of one of the plurality of topics presented in the word cloud by the user;
in response to the receiving, causing a display of a further subset of the subset of the plurality of communications corresponding to the selected one of the plurality of topics presented in the word cloud, and
the display including a textual display of:
the selected one of the plurality of topics,
the further subset of the subset of the plurality of communications corresponding to the selected one of the plurality of topics, and
at least one of the acoustic characteristics, the language characteristics, or the categories of the further subset of the subset of the plurality of communications;
receiving at least one of a search term or a selection of one of the categories of the further subset of the subset of the plurality of communications;
further limiting the textual display by filtering the further subset of the subset of the plurality of communications according to the at least one of the search term or the selected one of the categories; and
filtering a false positive communication from the further subset of the subset of the plurality of communications by identifying a specified offending phrase in the false positive communication and requiring additional evidence that the false positive communication corresponds to the selected one of the plurality of topics,
wherein the additional evidence includes another indication in the false positive communication that the false positive communication corresponds to the selected one of the plurality of topics, and the method further comprises receiving an input from the user of the specified offending phrase.
2 . The method of claim 1 , further comprising filtering at least one of the plurality of communications or the subset of the plurality of communications using metadata.
3 . The method of claim 2 , wherein the metadata is at least one of a speaker name, a speaker type, a communication type, an agent data, an agent grouping, a call handling location, a time and date of a call, a department, a skill or queue, a pertinent IVR path data, another category, or a call length.
4 . The method of claim 1 , wherein the at least one category is at least one of a language pattern, a keyword, a phrase, a non-word symbol, an emotion, a behavior, a reason, a procedure, a competitor, a dissatisfaction, an agitation, a satisfaction, an escalation, an empathy, a repeat contact, a transferred call, or a politeness.
5 . The method of claim 1 , wherein the at least one acoustic characteristic is at least one of a silence block, a duration of a silence, a stress of words, an aggregated stress of a plurality of words, an emphasis, an agitation, a tempo, a change in tempo, a gain in volume or energy of words, a tone, an overtalk, a time lag between words or symbols, a time dependency between key words or phrases, any set of words spoken in any order within a specified time frame, a proximity to an event, a specified amount of time between at least two specified events, an inter-word timing, an inter-word sequencing, an inter-word distance, an inflexion of words, or a temporal pattern.
6 . The method of claim 5 , wherein at least one of the at least two specified events is an escalation attempt, a use of profanity, a sales opportunity, or a compliance violation.
7 . The method of claim 5 , wherein at least one of the at least two specified events is an occurrence of an item in a list for the at least one category.
8 . The method of claim 5 , wherein the specified amount of time is selectively variable.
9 . The method of claim 5 , wherein the specified amount of time is a time period before one of the at least two specified events.
10 . The method of claim 5 , wherein the specified amount of time is a time period after one of the at least two specified events.
11 . The method of claim 1 , wherein the at least one language characteristic is a language pattern comprising at least one of an order of occurrence of words, an order of occurrence of words within a time frame, a Boolean relationship of words, words at a specific location in the subset, or a proximity of a topic.
12 . The method of claim 1 , wherein the display of the further subset of the subset of the plurality of communications includes, for each communication of the further subset of the subset of the plurality of communications, an indication of at least one of a confidence, an agent score, a duration, or a date, and the method further comprises:
receiving an input from the user to sort the display of the further subset of the subset of the plurality of communications according to at least one of the confidence, the agent score, the duration, or the date; and
causing the display of the further subset of the subset of the plurality of communications to be sorted according to the at least one of the confidence, the agent score, the duration, or the date.
13 . The method of claim 1 , wherein the further subset of the subset of the plurality of communications include a plurality of telephone conversations, and the display includes a textual display of at least some of the telephone conversations.
14 . The method of claim 1 , wherein a degree of commonality among the plurality of topics is expressed by at least one of a font size, a font characteristic, or a color.
15 . The method of claim 1 , wherein the filtered further subset of the subset of the plurality of communications includes communications from multiple channels of communication.
16 . A system, comprising:
a user interface configured to receive a selection from a user of at least one of an acoustic characteristic, a language characteristic, or a category of a plurality of communications; and
a processor in communication with the user interface, the processor programmed to:
access a database comprising the plurality of communications, the plurality of communications labeled with acoustic characteristics, language characteristics, and categories;
restrict the plurality of communications to a subset of the plurality of communications including the user's selection of the at least one acoustic characteristic, language characteristic, or category;
generate a word cloud for presenting a plurality of topics identified in the subset of the plurality of communications, wherein a degree of commonality among the plurality of topics is expressed by at least one of a font size, a font characteristic, or a color, and wherein the plurality of topics presented in the word cloud are selectable by the user;
receive a selection of one of the plurality of topics presented in the word cloud by the user;
in response to the receiving, causing a display of a further subset of the subset of the plurality of communications corresponding to the selected one of the plurality of topics presented in the word cloud, and
the display including a textual display of:
the selected one of the plurality of topics, the further subset of the subset of the plurality of communications corresponding to the selected one of the plurality of topics, and
at least one of the acoustic characteristics, the language characteristics, or the categories of the further subset of the subset of the plurality of communications;
receive at least one of a search term or a selection of one of the categories of the further subset of the subset of the plurality of communications;
further limit the textual display by filtering the further subset of the subset of the plurality of communications according to the at least one of the search term or the selected one of the categories; and
filter a false positive communication from the further subset of the subset of the plurality of communications by identifying a specified offending phrase in the false positive communication and requiring additional evidence that the false positive communication corresponds to the selected one of the plurality of topics,
wherein the additional evidence includes another indication in the false positive communication that the false positive communication corresponds to the selected one of the plurality of topics, and the processor is further programmed to receive an input from the user of the specified offending phrase.
17 . The system of claim 16 , wherein the processor is further programmed to filter at least one of the plurality of communications or the subset of the plurality of communications using metadata.
18 . The system of claim 17 , wherein the metadata is at least one of a speaker name, a speaker type, a communication type, an agent data, an agent grouping, a call handling location, a time and date of a call, a department, a skill or queue, a pertinent IVR path data, another category, or a call length.
19 . The system of claim 16 , wherein the at least one category is at least one of a language pattern, a keyword, a phrase, a non-word symbol, an emotion, a behavior, a reason, a procedure, a competitor, a dissatisfaction, an agitation, a satisfaction, an escalation, an empathy, a repeat contact, a transferred call, or a politeness.
20 . The system of claim 16 , wherein the at least one acoustic characteristic is at least one of a silence block, a duration of a silence, a stress of words, an aggregated stress of a plurality of words, an emphasis, an agitation, a tempo, a change in tempo, a gain in volume or energy of words, a tone, an overtalk, a time lag between words or symbols, a time dependency between key words or phrases, any set of words spoken in any order within a specified time frame, a proximity to an event, a specified amount of time between at least two specified events, an inter-word timing, an inter-word sequencing, an inter-word distance, an inflexion of words, or a temporal pattern.
21 . The system of claim 20 , wherein at least one of the at least two specified events is an escalation attempt, a use of profanity, a sales opportunity, or a compliance violation.
22 . The system of claim 20 , wherein at least one of the at least two specified events is an occurrence of an item in a list for the at least one category.
23 . The system of claim 20 , wherein the specified amount of time is selectively variable.
24 . The system of claim 20 , wherein the specified amount of time is a time period before one of the at least two specified events.
25 . The system of claim 20 , wherein the specified amount of time is a time period after one of the at least two specified events.
26 . The system of claim 16 , wherein the language characteristic is a language pattern comprising at least one of an order of occurrence of words, an order of occurrence of words within a time frame, a Boolean relationship of words, words at a specific location in the subset, or a proximity of a topic.