139, a natural language processing application 142, and other applications, services, processes, systems, engines, or functionality not discussed in detail herein.

The compliance detection application 139 can be executed to at least transcribe a call between at least an agent and a client to generate a transcript 121. The compliance detection application 139 can transcribe a call or discussion that is currently occurring or a call or discussion that has been recorded as a sound recording 118. The compliance detection application 139 can obtain one or more actions 130 corresponding to a workflow 124 followed in association for the call. The compliance detection application 139 can then identify sections of the transcript 121 using a natural language processing application 142. The compliance detection application 139 can obtain a compliance rule 115 and send a request to the natural language processing application 142 to determine that the compliance rule 115 has been violated and/or determine a confidence score for the likelihood that the compliance rule 115 has been violated. The compliance detection application 139 can then store a compliance violation 127 into a data store 112. The compliance detection application 139 can generate a user interface 148 for a compliance review device 106 and subsequently receive an outcome 137 for the compliance violation 127 from the compliance review device 106. The compliance detection application 139 can then store the outcome 137 in association with the compliance violation 127. Additional information regarding the compliance detection application 139 is further described in the discussion of FIG. 3.

The natural language processing application 142 can be executed to identify contextual nuances in the text of a transcript 121 and/or a sound recording 118. The natural language processing application 142 can be trained using various transcripts 121 of historical calls and their corresponding compliance violations 127. The natural language processing application 142 can use various techniques to identify and analyze the transcripts 121, such as syntactical analysis, lexical semantic analysis, relational semantic analysis, discourse and intent analysis, summarization, and other types of natural language processing analysis. The natural language processing application 142 can receive a request from the compliance detection application 139 to analyze a transcript 121 and/or identify a violation of a compliance rule 115 within a transcript 121. The natural language processing application 142 can analyze the transcript 121 to separate portions of the text into different categories or topics. The natural language processing application 142 can also receive a compliance rule 115 and a transcript 121 to subsequently identify a transcript segment 136 within the transcript 121 that likely violates the compliance rule 115. The natural language processing application 142 can identify what qualifies as a violation of the compliance rule 115 based on a regular expression or based on a natural language description of the rule, as previously discussed. The natural language processing application 142 can determine a confidence score for the likelihood that a compliance rule 115 has been violated. A confidence score can be some numeric value or combination of one or more numeric values. For example, a percentage or a decimal can be used to represent a confidence score. In at least another example, an integer value can count the number of times that the compliance rule 115 is likely violated, thus representing a value that increases the confidence that the value has been violated.

The compliance review device 106 can represent a plurality of client devices that can be coupled to the network 109. The compliance review device 106 can include a processor-based system such as a computer system. Such a computer system can be embodied in the form of a personal computer (e.g., a desktop computer, a laptop computer, or similar device), a mobile computing device (e.g., personal digital assistants, cellular telephones, smartphones, web pads, tablet computer systems, music players, portable game consoles, electronic book readers, and similar devices), media playback devices (e.g., media streaming devices, BluRay® players, digital video disc (DVD) players, set-top boxes, and similar devices), a videogame console, or other devices with like capability. The compliance review device 106 can include one or more displays 145, such as liquid crystal displays (LCDs), gas plasma-based flat panel displays, organic light emitting diode (OLED) displays, electrophoretic ink (“E-ink”) displays, projectors, or other types of display devices. In some instances, the display 145 can be a component of the compliance review device 106 or can be connected to the compliance review device 106 through a wired or wireless connection.

The compliance review device 106 can be configured to execute various applications, such as a compliance review application 152 or other applications. The compliance review application 152 can be executed in a compliance review device 106 to access network content served up by the computing environment 103 or other servers, thereby rendering a user interface 148 on the display 145. To this end, the compliance review application 152 can include a browser, a dedicated application, or another executable, and the user interface 148 can include a network page, an application screen, or another user mechanism for obtaining user input. User input can include the outcome 137 of a compliance violation 127. The compliance review device 106 can be configured to execute applications beyond the compliance review application 152, such as email applications, social networking applications, word processors, spreadsheets, or other applications.

Next, a general description of the operation of the various components of the network environment 100 is provided. To begin, the compliance detection application 139 can be executed to at least transcribe a call between at least an agent and a client to generate a transcript 121. The compliance detection application 139 can transcribe a call or discussion that is currently occurring or a call or discussion that has been recorded as a sound recording 118. The compliance detection application 139 can obtain one or more actions 130 corresponding to a workflow 124 followed in association for the call. The compliance detection application 139 can then identify sections of the transcript 121 using a natural language processing application 142. The compliance detection application 139 can obtain a compliance rule 115 and send a request to the natural language processing application 142 to determine that the compliance rule 115 has been violated and/or determine a confidence score for the likelihood that the compliance rule 115 has been violated. The compliance detection application 139 can then store a compliance violation 127 in a data store 112. The compliance detection application 139 can generate a user interface 148 for a compliance review device 106. The compliance review application 152 can receive the user interface 148 generated by the compliance detection application 139 and render the user interface 148 on the display 145. The user interface 148 can display one or more compliance violations 127 and the user interface 148 can be configured to prompt a compliance reviewer to enter an outcome 137 for the compliance violation 127. The compliance detection application 139 can subsequently receive an outcome 137 for the compliance violation 127 from the compliance review device 106. The compliance detection application 139 can then store the outcome 137 in association with the compliance violation 127. Additional information regarding the compliance detection application 139 is further described in the discussion of FIG. 3.

Referring next to FIG. 2, shown is a pictorial diagram of an example user interface 148 rendered by a compliance review device 106 in the network environment 100 of FIG. 1 according to various embodiments of the present disclosure. The user interface 148 can include a transcript segment 136, a compliance rule 115B that was violated, a sound recording segment 133, and a prompt to obtain an outcome 137. In at least some embodiments, the user interface 148 can include a confidence score relating to the likelihood that the compliance rule 115B was violated. The transcript segment 136 can include an identifier that represents the portion of the call that is being displayed. For example, in FIG. 2, there is the identifier “<call_start>” to identify that this is the beginning of the call between the client and agent. The identifiers could be a date, timestamp, or time since the start of the call identifier. Below the identifier in the transcript segment 136 are various statements that begin with either “Client” or “Agent” to identify the speaker of the statement. The transcript segment 136 ends in FIG. 2 with an ellipsis (“ . . . ”) to denote that the call continues further after this transcript segment 136. Various other identifiers can be used to identify the start or end of the call.

The user interface 148 can include the compliance rule 115B that was violated for the compliance violation 127. In FIG. 2, the compliance rule 115B is depicted as “Rule 05.22: Agent must identify that the call is being recorded.” The user interface 148 can also include the sound recording segment 133. Specifically, the user interface 148 can provide an affordance, such as a play button or a download link, which makes it possible for a compliance reviewer to hear the relevant portion of the sound recording 118.

Finally, the user interface 148 can include a prompt for the compliance reviewer to enter an outcome 137. The prompt can include a dropdown element that provides a list of predefined outcomes as previously discussed. Additionally, the prompt can include a free text entry section for the compliance reviewer to enter a brief note about the outcome 137 for the compliance violation 127. The prompt can then be submitted by clicking on the submit button or by using any standard form submission actions.

Referring next to FIG. 3, shown is a flowchart that provides one example of the operation of a portion of the compliance detection application 139. The flowchart of FIG. 3 provides merely an example of the many different types of functional arrangements that can be employed to implement the operation of the depicted portion of the compliance detection application 139. As an alternative, the flowchart of FIG. 3 can be viewed as depicting an example of elements of a method implemented within the network environment 100.

Beginning with block 303, the compliance detection application 139 can transcribe a call between at least an agent and a client to generate a transcript 121. The transcripts 121 can represent a text interpretation of the call or discussion between at least an agent and a client (or prospective client). In at least some embodiments, a transcript 121 can be generated by transcribing a call or discussion from a sound recording 118 of a call or discussion. In at least another embodiment, a transcript 121 can be generated by transcribing a call or discussion as it is actively occurring. In some embodiments, the compliance detection application 139 generate raw conversation text using a speech-to-text engine and subsequently provide additional context to the raw conversation text, such as identifying speakers or including timestamps. In some embodiments, emails, text messages, and/or other text content can be included in the transcript 121 such that a complete record of a call or discussion between an agent and client can be captured. In some embodiments, the compliance detection application 139 can identify one or more speakers in the call or discussion within the transcript 121 to provide context to the flow of the discussion or call. In at least one example, the transcript 121 can have a first speaker identified as an agent. Similarly, the transcript 121 can have a second speaker identified as a client. In some embodiments, the transcript 121 can include a date and timestamp corresponding to when each statement was made. In some embodiments, the transcript 121 can include a time counter that measures an amount of time that has elapsed since the start of the call or discussion (e.g., the number of seconds, minutes, and/or hours since the start of the call or discussion).

Next, at block 306, the compliance detection application 139 can obtain one or more actions 130 (also called an action log) that are associated with the call. The action log can represent various events captured during the call. In various embodiments, the action log can include time stamps that correspond to a point in the call where a specific action 130 was taken.

Continuing to block 309, the compliance detection application 139 can identify sections of the transcript 121. In at least one embodiment, the compliance detection application 139 can identify various sections based at least in part on the action log received at block 306. In such an embodiment, the denotation that an action 130 had occurred can identify that the agent has moved from one topic to another topic, which provides a point in time, which can be identified in the sound recording 118 and the transcript 121, that separates various topics. In some embodiments, the compliance detection application 139 can provide the transcript 121 to a natural language processing application 142 to identify various categories of discussion and the points in the transcript 121 where those discussions occurred. By splitting up the transcript into smaller segments, the natural language processing application 142 can potentially provide better results regarding whether a compliance rule 115 has been violated.

Next, at block 312, the compliance detection application 139 can obtain a compliance rule 115. In at least one embodiment, the compliance detection application 139 can obtain one or more compliance rules 115 to evaluate against the entire transcript 121. In at least some embodiments, the compliance detection application 139 can obtain the compliance rules 115 based on one or more topics of discussion or categories that were identified at block 309. Various compliance rules 115 can be obtained for each transcript 121.

Continuing to block 315, the compliance detection application 139 can determine that the compliance rule 115 has been violated. In at least one embodiment, the compliance detection application 139 can send a request to the natural language processing application 142 to evaluate the transcript 121 or a portion of the transcript 121 along with a compliance rule 115 to determine whether the compliance rule 115 has been violated. In at least another embodiment, the natural language processing application 142 can provide a confidence score that represents the likelihood of the compliance rule 115 being violated. The compliance detection application 139 can include a threshold amount to compare to the confidence score. The compliance detection application 139 can then compare the confidence score to the threshold amount to determine whether the compliance rule 115 has been violated.

In at least some embodiments, a compliance detection application 139 can determine whether a compliance rule 115 is violated by not reciting a word or phrase verbatim. In another example, an agent of the business must ask whether the client consents to receiving an email by reciting a specified script to ensure that the business does not violate the CAN-SPAM Act, which regulates how businesses can use email to communicate with people. In embodiments where an agent is required to recite a statement verbatim, the compliance rule 115 can include the exact statement that the agent must recite. In some embodiments, the compliance rule 115 can include a reference to the exact statement that the agent must recite rather than the exact statement itself. For example, the compliance rule 115 can include that the agent must recite the client's Miranda rights. The natural language processing application 142 can be trained to understand that certain language must be required when using the reference rather than the exact text itself.

In at least some embodiments, a compliance detection application 139 can determine whether a compliance rule 115 is violated when the compliance rule is contextual (non-verbatim). For instance, a compliance rule 115 can require that an agent advised a client how to contact customer support regarding their questions after the call, but such an explanation does not have to be recited verbatim to the client. For such compliance rules 115 that require non-verbatim statements to be made, the natural language processing application 142 can identify and characterize the conversation with the client to predict whether the compliance rule 115 has been violated. The natural language processing application 142 could also utilize intent classification on the transcript 121 to identify whether the compliance rule 115 has been violated.

In some embodiments, a compliance detection application 139 can determine whether a compliance rule 115 is violated when a statement is misleading. For example, in a call between a client and an agent, the agent may state that an “APR” or “Annual Percentage Rate” for a credit card will be a specified percentage (e.g., five percent, ten percent, etc.). However, such a statement could be misrepresenting an offer if that specific “APR” is an introductory rate (e.g., the rate will increase after a period of time), and the agent fails to inform the client about such an increase. In some embodiments, the compliance rule 115 can require that misrepresentations were explicitly stated. In some embodiments, the compliance rule 115 can require that omissions on statements that should have been stated count as a misrepresentation to the client. Omissions can be detected by the natural language processing application 142 as a result of being trained to find complete disclosures of information to clients.

In some embodiments, a compliance detection application 139 can determine whether a compliance rule 115 is violated when the compliance rule 115 contains as condition. For instance, when certain words or phrases are identified in the transcript 121, the compliance rule 115 would then be required to be evaluated. For instance, a compliance rule 115 could require a condition that the word “APR” or “Annual Percentage Rate” be discussed. In such an example, when “APR” or “Annual Percentage Rate” is stated, the compliance rule 115 could then require that certain statements be stated verbatim, that certain discussions be included in a non-verbatim fashion, and/or that certain statements be not misrepresented to the client, as previously discussed.

Next, at block 318, the compliance detection application 139 can store a compliance violation 127 into a data store 112. Once the compliance detection application 139 determines that a violation has occurred and/or that it is more likely to have occurred than not to have occurred by comparing the confidence score to the threshold amount, the compliance detection application 139 can store the relevant portions of the transcript 121, sound recordings 118 and compliance rules 115 as a compliance violation 127 in the data store 112. In at least some embodiments, the compliance detection application 139 can trim the transcript 121 to a transcript segment 136 of the relevant portion of the violation. Similarly, the compliance detection application 139 can trim, splice, or cut the sound recording 118 to a sound recording segment 133 of the relevant portion of the violation. The compliance detection application 139 can also store a copy of the compliance rule 115 or an identifier of the compliance rule in the compliance violation 127.

Continuing to block 321, the compliance detection application 139 can generate a user interface 148 for a compliance review device 106. An example of a user interface 148 that can be generated by the compliance detection application 139 is provided in FIG. 2. The user interface 148 can be configured to at least display the compliance violation 127, meaning that it can display the compliance rule 115B that is violated, display a transcript segment 136, and/or display an affordance to play either the sound recording 118 or the sound recording segment 133. In some embodiments, the user interface 148 can also be configured to prompt the compliance review device 106 to provide an outcome 137 for the compliance violation. Some embodiments the user interface 148 can be configured to prompt the compliance review device 106 to provide the outcome 137 via a predefined list of compliance violation outcomes, such as through a dropdown selector. In some embodiments, the user interface 148 can be configured to prompt the compliance review device 106 to provide the outcome 137 via a text entry form. Various form controls can be used to obtain information about the outcome 137.

Next, at block 324, the compliance detection application 139 can receive an outcome 137 for the compliance violation 127 from the compliance review device 106. And finally at block 327, the compliance detection application