Detailed Action
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of the Application and Claims
This action is in reply to the application filed on 8/22/2024.
This communication is the first action on the merits.
Claims 1-13 is/are currently pending and have been examined.
Claim Rejections – 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-13 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Claim 1 (similarly 13) recite, “A …-method for determining an agent proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof, the …-method comprising:
operating a Concurrent Sessions Handling Agent Proficiency (CSHAP) …, said CSHAP … comprising:
(a) operating an interactions … to retrieve one or more interactions and metadata thereof of the agent during a preconfigured period from the data store of interactions
wherein said one or more interactions were monitored and recorded to collect real-time data streams of each interaction in the one or more interactions and yield the metadata;
(b) for each interaction of the one or more retrieved interactions, determining if the interaction has been handled with concurrent different interactions during the preconfigured period via one or more channels types, based on the yielded metadata;
(c) for each determined interaction as handled with concurrent different interactions checking in the metadata if the interaction has one or more defocused events,
wherein the determining is based on a first key characteristics of defocused events and a second key characteristics of focus events, and
wherein defocused events are inactive-time events of an agent and a customer during the interaction and focused events are active-time events of the agent and the customer via a chat window;
(d) calculating a CSHAP score for the agent based on one or more attribute from the metadata of the interaction to provide an indication as to an ability of the agent to address different concurrent customer sessions via one or more channel types,
wherein the CSHAP is calculated based on a total number of concurrent different interactions handled by the agent during the preconfigured period, customer sentiment or feedback score for each interaction in the total number of concurrent different interaction, total time taken to handle each interaction and a total time of one or more focused events during each interaction in the total number of concurrent different interaction;
(e) storing the calculated CSHAP score in the data store of agents; and
(f) sending the CSHAP score to one or more …, to take one or more follow-up actions base on the CSHAP score.”
Analyzing under Step 2A, Prong 1:
The limitations regarding, …determining an agent proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof, the …-method comprising: operating a Concurrent Sessions Handling Agent Proficiency (CSHAP) …, said CSHAP … comprising: operating an interactions … to retrieve one or more interactions and metadata thereof of the agent during a preconfigured period from the data store of interactions…wherein said one or more interactions were monitored and recorded to collect real-time data streams of each interaction in the one or more interactions and yield the metadata; for each interaction of the one or more retrieved interactions, determining if the interaction has been handled with concurrent different interactions during the preconfigured period via one or more channels types, based on the yielded metadata; for each determined interaction as handled with concurrent different interactions checking in the metadata if the interaction has one or more defocused events, wherein the determining is based on a first key characteristics of defocused events and a second key characteristics of focus events, and …wherein defocused events are inactive-time events of an agent and a customer during the interaction and focused events are active-time events of the agent and the customer via a chat window; calculating a CSHAP score for the agent based on one or more attribute from the metadata of the interaction to provide an indication as to an ability of the agent to address different concurrent customer sessions via one or more channel types, wherein the CSHAP is calculated based on a total number of concurrent different interactions handled by the agent during the preconfigured period, customer sentiment or feedback score for each interaction in the total number of concurrent different interaction, total time taken to handle each interaction and a total time of one or more focused events during each interaction in the total number of concurrent different interaction; storing the calculated CSHAP score in the data store of agents; and sending the CSHAP score to one or more …, to take one or more follow-up actions base on the CSHAP score…, under the broadest reasonable interpretation, can include a human using their mind and using pen and paper to, …determining an agent proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof, the …-method comprising: operating a Concurrent Sessions Handling Agent Proficiency (CSHAP) …, said CSHAP … comprising: operating an interactions … to retrieve one or more interactions and metadata thereof of the agent during a preconfigured period from the data store of interactions…wherein said one or more interactions were monitored and recorded to collect real-time data streams of each interaction in the one or more interactions and yield the metadata; for each interaction of the one or more retrieved interactions, determining if the interaction has been handled with concurrent different interactions during the preconfigured period via one or more channels types, based on the yielded metadata; for each determined interaction as handled with concurrent different interactions checking in the metadata if the interaction has one or more defocused events, wherein the determining is based on a first key characteristics of defocused events and a second key characteristics of focus events, and …wherein defocused events are inactive-time events of an agent and a customer during the interaction and focused events are active-time events of the agent and the customer via a chat window; calculating a CSHAP score for the agent based on one or more attribute from the metadata of the interaction to provide an indication as to an ability of the agent to address different concurrent customer sessions via one or more channel types, wherein the CSHAP is calculated based on a total number of concurrent different interactions handled by the agent during the preconfigured period, customer sentiment or feedback score for each interaction in the total number of concurrent different interaction, total time taken to handle each interaction and a total time of one or more focused events during each interaction in the total number of concurrent different interaction; storing the calculated CSHAP score in the data store of agents; and sending the CSHAP score to one or more …, to take one or more follow-up actions base on the CSHAP score…; therefore, the claims are directed to a mental process.
Further, …determining an agent proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof, the …-method comprising: operating a Concurrent Sessions Handling Agent Proficiency (CSHAP) …, said CSHAP … comprising: operating an interactions … to retrieve one or more interactions and metadata thereof of the agent during a preconfigured period from the data store of interactions…wherein said one or more interactions were monitored and recorded to collect real-time data streams of each interaction in the one or more interactions and yield the metadata; for each interaction of the one or more retrieved interactions, determining if the interaction has been handled with concurrent different interactions during the preconfigured period via one or more channels types, based on the yielded metadata; for each determined interaction as handled with concurrent different interactions checking in the metadata if the interaction has one or more defocused events, wherein the determining is based on a first key characteristics of defocused events and a second key characteristics of focus events, and …wherein defocused events are inactive-time events of an agent and a customer during the interaction and focused events are active-time events of the agent and the customer via a chat window; calculating a CSHAP score for the agent based on one or more attribute from the metadata of the interaction to provide an indication as to an ability of the agent to address different concurrent customer sessions via one or more channel types, wherein the CSHAP is calculated based on a total number of concurrent different interactions handled by the agent during the preconfigured period, customer sentiment or feedback score for each interaction in the total number of concurrent different interaction, total time taken to handle each interaction and a total time of one or more focused events during each interaction in the total number of concurrent different interaction; storing the calculated CSHAP score in the data store of agents; and sending the CSHAP score to one or more …, to take one or more follow-up actions base on the CSHAP score…, are managing human agents’ ability to focus and proficiency at chatting with human customers, which are managing interactions between people, therefore the claims, are directed to certain methods of organizing human activities.
Additionally, …determining an agent proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof, the …-method comprising: operating a Concurrent Sessions Handling Agent Proficiency (CSHAP) …, said CSHAP … comprising: operating an interactions … to retrieve one or more interactions and metadata thereof of the agent during a preconfigured period from the data store of interactions…wherein said one or more interactions were monitored and recorded to collect real-time data streams of each interaction in the one or more interactions and yield the metadata; for each interaction of the one or more retrieved interactions, determining if the interaction has been handled with concurrent different interactions during the preconfigured period via one or more channels types, based on the yielded metadata; for each determined interaction as handled with concurrent different interactions checking in the metadata if the interaction has one or more defocused events, wherein the determining is based on a first key characteristics of defocused events and a second key characteristics of focus events, and …wherein defocused events are inactive-time events of an agent and a customer during the interaction and focused events are active-time events of the agent and the customer via a chat window; calculating a CSHAP score for the agent based on one or more attribute from the metadata of the interaction to provide an indication as to an ability of the agent to address different concurrent customer sessions via one or more channel types, wherein the CSHAP is calculated based on a total number of concurrent different interactions handled by the agent during the preconfigured period, customer sentiment or feedback score for each interaction in the total number of concurrent different interaction, total time taken to handle each interaction and a total time of one or more focused events during each interaction in the total number of concurrent different interaction; storing the calculated CSHAP score in the data store of agents; and sending the CSHAP score to one or more …, to take one or more follow-up actions base on the CSHAP score…., is mathematical concepts.
Accordingly, the claims are directed to a mental process, certain methods of organizing human activities, mathematical concepts, and thus, the claims are directed to an abstract idea under the first prong of Step 2A.
Analyzing under Step 2A, Prong 2:
This judicial exception is not integrated into a practical application under the second prong of Step 2A.
In particular, the claims recite the additional elements beyond the recited abstract idea identified under Step 2A, Prong 1, such as:
Claim 1, 13: computerized, module, chat window, applications, computerized-system comprising: one or more processors; a data store of interactions; a data store of agents; and a memory to store the data stores, said one or more processors are configured to
Claim 5: gamification application
Claim 8: Quality Management (QM) application
Claim 10: Automated Call Distribution (ACD) system
Claim 12: cloud computing environment
, and pursuant to the broadest reasonable interpretation, as an ordered combination, each of the additional elements are computing elements recited at high level of generality implementing the abstract idea, and thus, are no more than applying the abstract idea with generic computer components.
Further, these additional elements generally link the abstract idea to a technical environment, namely the environment of a computer and a call center, and the chat window is an additional element that can be overserved and evaluated by humans visually and mentally.
Additionally, with respect to, “…to retrieve…”, “…monitored and recorded to collect…”, “…storing…”, “…sending…”, these elements do not add a meaningful limitations to integrate the abstract idea into a practical application because they are extra-solution activity, pre and post solution activity - i.e. data gathering – “…to retrieve…”, “…monitored and recorded to collect…”, “…storing…”, data output – “…sending…”
Analyzing under Step 2B:
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception under Step 2B.
As noted above, the aforementioned additional elements beyond the recited abstract idea are not sufficient to amount to significantly more than the recited abstract idea because, as an order combination, the additional elements are no more than mere instructions to implement the idea using generic computer components (i.e. apply it).
Additionally, as an order combination, the additional elements append the recited abstract idea to well-understood, routine, and conventional activities in the field as individually evinced by the applicant’s own disclosure, as required by the Berkheimer Memo, in at least:
[0025]In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the disclosure. However, it will be understood by those of ordinary skill in the art that the disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, modules, units and/or circuits have not been described in detail so as not to obscure the disclosure.
[0034]According to some embodiments of the present disclosure, a computerized system, such as system 100A may include one or more processors 130, a data store, such as data store of interactions 120, a data store such as data store of agents 125, and a memory 110 to store the data stores. The one or more processors 130 may operate for each agent in the data store of agents 125, a module, such as Concurrent Sessions Handling Agent Proficiency (CSHAP) module 135, and such as module CSHAP 200 in Figs. 2A-2B.
[0074]According to some embodiments of the present disclosure, one application of the one or more applications may be a gamification application, a Quality Management (QM) application or an Automated Call Distribution (ACD) system, as shown in Fig. 1B.
[0075]According to some embodiments of the present disclosure, when system 100A is operating in a cloud computing environment, before operating the CSHAP module 135 the system 100A may further comprise selecting a tenant from a data store of tenants to operate the CSHAP module 135 for each agent in the data store of agents of the selected tenant.
[0078]According to some embodiments of the present disclosure, a computerized system, such as system 100B may include all the components of system 100A, which are one or more processors 130, a data store, such as data store of interactions 120, a data store such as data store of agents 125; and a memory 110 to store the data stores. The one or more processors 130 may operate for each agent in the data store of agents 125, a module, such as Concurrent Sessions Handling Agent Proficiency (CSHAP) module 135, and such as module CSHAP 200, in Figs. 2A-2B.
[0091]According to some embodiments of the present disclosure, one application of the one or more applications may be an Automated Call Distribution (ACD) system 140c.
[0092]According to some embodiments of the present disclosure, agents may have skills assigned based on their technical expertise such as basic support, advanced support, billing and the like. Interactions may be routed based on skill needed. The follow-up actions of the ACD system 140c based on the CSHAP score may be for example adding a new skill category such as network security issues, and updating the agent profile to include that skill or include that skill and remove an existing skill.
[0119] According to some embodiments of the present disclosure, a threshold may be provided by QM application 540 to check if the agent CSHAP score is below a threshold 530. When the CSHAP score is below the threshold the agent may need a coaching package assignment 550 which may be assigned out of existing packages by a user, such as a manager, e.g. coaching packages 560a-560c.
[00121]Similarly, it should be understood that, unless indicated otherwise, the illustrated order of execution of the operations represented by blocks of any flowchart referenced herein has been selected for convenience and clarity only. Operations of the illustrated method may be executed in an alternative order, or concurrently, with equivalent results. Such reordering of operations of the illustrated method should be understood as representing other embodiments of the illustrated method.
[00122]Different embodiments are disclosed herein. Features of certain embodiments may be combined with features of other embodiments; thus, certain embodiments may be combinations of features of multiple embodiments. The foregoing description of the embodiments of the disclosure has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure to the precise form disclosed. It should be appreciated by persons skilled in the art that many modifications, variations, substitutions, changes, and equivalents are possible in light of the above teaching. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the disclosure.
[00123]While certain features of the disclosure have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the disclosure.
Furthermore, as an ordered combination, these elements amount to generic computer components receiving or transmitting data over a network, performing repetitive calculations, electronic record keeping, and storing and retrieving information in memory, which, as held by the courts, are well-understood, routine, and conventional. See MPEP 2106.05(d).
Moreover, the remaining elements of dependent claims do not transform the recited abstract idea into a patent eligible invention because these remaining elements merely recite further abstract limitations that provide nothing more than simply a narrowing of the abstract idea recited in the independent claims.
Looking at these limitations as an ordered combination adds nothing additional that is sufficient to amount to significantly more than the recited abstract idea because they simply provide instructions to use a generic arrangement of generic computer components to “apply” the recited abstract idea, perform insignificant extra-solution activity, and generally link the abstract idea to a technical environment. Thus, the elements of the claims, considered both individually and as an ordered combination, are not sufficient to ensure that the claim as a whole amounts to significantly more than the abstract idea itself. Since there are no limitations in these claims that transform the exception into a patent eligible application such that these claims amount to significantly more than the exception itself, claims 1-13 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections – 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
Determining the scope and contents of the prior art.
Ascertaining the differences between the prior art and the claims at issue.
Resolving the level of ordinary skill in the pertinent art.
Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-13 is/are rejected under 35 U.S.C. 103 as being unpatentable by US Patent Publication to US20150334233A1 to O'Connor et al., (hereinafter referred to as “O'Connor”) in view of US Patent Publication to US20180091654A1 to Miller et al., (hereinafter referred to as “Miller”)
As per Claim 1, O'Connor teaches: A computerized-method for determining an agent proficiency when addressing concurrent customer sessions via one or more channel types and utilization thereof, the computerized-method comprising: ([0036]-[0052])
operating a Concurrent Sessions Handling Agent Proficiency (CSHAP) module, said CSHAP module comprising: ([0052]-[0055])
(a) operating an interactions module to retrieve one or more interactions and metadata thereof of the agent during a preconfigured period from the data store of interactions (in at least [0006] contact center occupancy is measured by the percentage of time an agent is working within a given interval. In traditional contact centers, the only media capability an agent is using is voice via telephone calls. Occupancy often refers to information such as talk time and after call work time as periods that constitute work time. An agent's occupancy is a measure of how efficiently an agent's time is used. If an agent today were to work constantly from login to logout, the agent would be 100% occupied. [0037] FIG. 1 shows an illustrative embodiment of a multimodal contact center, in accordance with one embodiment of the present invention. A contact center 100 comprises a central server 110, a set of data stores or databases 114 containing contact or customer related information and other information that can enhance the value and efficiency of the contact processing [0049] FIG. 2 depicts an agent handling multiple simultaneous contacts of various media capabilities or modes. A media capability is a form of media communication and includes a communication channel. Media capabilities may include, but are not limited to, a web capability, a text capability, a voice capability and/or a video capability. The media capabilities may vary in characteristics like bandwidth requirement, the latency of support (i.e., how close to real-time, immediacy, responsiveness, etc.), the level of participation by the agent, usage of other system resources, and so forth. [0052] FIG. 3 illustrates an exemplary embodiment of a block diagram to illustrate various modules of a contact center system 300 determining occupancy of an agent with simultaneous multimodal contacts, in accordance with an embodiment of the present invention. The contact center system 300 may include multiple modules to determine the occupancy of agents in the system. Multiple modules may determine the occupancy of an agent handling multiple simultaneous contacts using a variety of media capabilities. [0077] the occupancy baseline, which is used to determine when an agent is 100% occupied, may be reevaluated by a relearning module 310. The call center system administrator and/or supervisor may input and determine the baseline values for the parameters. The relearning module 310 may learn from the agents in the system to determine and reevaluate the baseline values. The relearning module 310 may monitor one or more agents to reevaluate the parameters or weights. The relearning module 310 may adjust the parameters. The relearning module 310 may teach itself to reevaluate the parameters based on how busy the agents in the call center system are in responding to customer contacts. For example, the multimodal occupancy score of a group of agents may be collected and used as feedback into the contact center system to provide relearning. [0078] The feedback may allow a redefinition of what 100% occupancy looks like and represents. This can then be used to adjust an agent's multimodal occupancy score. The relearning module 310 may monitor one or more agents to reevaluate one or more of the parameters associated with a media capability and/or contact. In an embodiment, a processor may be used to monitor the agents. In an embodiment, the relearning module could be controlled by a supervisor. In an embodiment, the values could be automatically fed back into the system so the relearning module 310 will self learn what 100% occupied looks like to the contact call center system. Alternatively, a blend of the supervisor control and the relearning may be used. For example, if an agent is 85% busy, but is still easily taking on new simultaneous contacts, then the current multimodal occupancy score may be revised by the relearning module 310. [0084] At step 504, a media capability may be determined for each contact received by the agent. The agent may receive a plurality of contacts and a media capability may be determined for each contact received. The media capability of a contact may include, but is not limited to, a voice capability, a video capability, a text capability or an email. In an embodiment, the contacts simultaneously handled by an agent may have one or more different capabilities. In an alternate embodiment, the contacts simultaneously handled by an agent may have one or more of the same capabilities. For example, the agent may handle four contacts that all have web chat capabilities. Alternatively, the agent may handle two contacts. One of those contacts may have an email capability and the other contact may have a web chat capability. [0085] At step 506, one or more parameters associated with the media capability of each contact may be determined. In an embodiment, for each contact, one or more parameters are determined based on one or more of the contact, the media capability and the agent. For example, the media capability may be a text capability. One parameter may be the volume of text received and/or sent by the agent. The contact center system may determine a word length at which an agent is 100% occupied. This determined word length may be divided by the actual word length over a time interval to determine a parameter. The parameter may later be used to determine the multimodal occupancy score. In another example, the media capability may be a voice capability. The parameter may be the conversation length of the conversation between the customer and the agent. The contact center system may determine a conversation length at which an agent is 100% occupied. This determined conversation length may be divided by the actual conversation length over a time interval to determine a parameter used to determine the multimodal occupancy score.)
wherein said one or more interactions were monitored and recorded to collect real-time data streams of each interaction in the one or more interactions and yield the metadata; (in at least [0050] The customer contacts 202A-D sent to the multimodal contact center system 204 may include a variety of media capabilities. Customer contact 202A may include a voice capability. The voice capability may include a voice call. The contact center system 204 may route the voice call to agent 206A. Customer contact 202B may include a web capability. The web capability may include, but is not limited to, a web chat. Additionally, customer contacts 202C and 202 D may include a text capability such as, but not limited to, an email. The contact center system 204 may determine whether the incoming contact has a web capability or an email capability and may send it to an agent based on the agents' occupancy and/or whether the agent also has that capability. In an embodiment, an agent may be determined to have a multimodal occupancy score of 90% by handling a customer phone call 202A. The contact center system 204 may determine the agent does not have the ability to handle another contact as the phone call will keep the agent occupied. In an alternative embodiment, agent may be determined to have a multimodal occupancy score of 100% by handling a customer phone call 202A to ensure the agent is not given another contact. [0078] The feedback may allow a redefinition of what 100% occupancy looks like and represents. This can then be used to adjust an agent's multimodal occupancy score. The relearning module 310 may monitor one or more agents to reevaluate one or more of the parameters associated with a media capability and/or contact. In an embodiment, a processor may be used to monitor the agents. In an embodiment, the relearning module could be controlled by a supervisor. In an embodiment, the values could be automatically fed back into the system so the relearning module 310 will self learn what 100% occupied looks like to the contact call center system. Alternatively, a blend of the supervisor control and the relearning may be used. For example, if an agent is 85% busy, but is still easily taking on new simultaneous contacts, then the current multimodal occupancy score may be revised by the relearning module 310. [0083] At step 502, the method may monitor a plurality of multimodal contacts simultaneously handled by an agent. The contact center system may monitor the contacts handled by an agent in order to determine a multimodal occupancy score of an agent. As the contacts are multimodal, an agent is not necessarily completely occupied based on a single contact. Instead, an agent may need to handle two or more contacts simultaneously in order for the agent to remain sufficiently occupied. In an embodiment, the agent may want to have their multimodal occupancy score at a predetermined level over a time interval. For example, the agent may want a multimodal occupancy score of 85% for a day of work.)
(b) for each interaction of the one or more retrieved interactions, determining if the interaction has been handled with concurrent different interactions during the preconfigured period via one or more channels types, based on the yielded metadata; (in at least [0083] At step 502, the method may monitor a plurality of multimodal contacts simultaneously handled by an agent. The contact center system may monitor the contacts handled by an agent in order to determine a multimodal occupancy score of an agent. As the contacts are multimodal, an agent is not necessarily completely occupied based on a single contact. Instead, an agent may need to handle two or more contacts simultaneously in order for the agent to remain sufficiently occupied. In an embodiment, the agent may want to have their multimodal occupancy score at a predetermined level over a time interval. For example, the agent may want a multimodal occupancy score of 85% for a day of work. [0084] At step 504, a media capability may be determined for each contact received by the agent. The agent may receive a plurality of contacts and a media capability may be determined for each contact received. The media capability of a contact may include, but is not limited to, a voice capability, a video capability, a text capability or an email. In an embodiment, the contacts simultaneously handled by an agent may have one or more different capabilities. In an alternate embodiment, the contacts simultaneously handled by an agent may have one or more of the same capabilities. For example, the agent may handle four contacts that all have web chat capabilities. Alternatively, the agent may handle two contacts. One of those contacts may have an email capability and the other contact may have a web chat capability.)
(c) for each determined interaction as handled with concurrent different interactions checking in the metadata if the interaction has one or more defocused events, (in at least [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score.)
wherein the determining is based on a first key characteristics of defocused events and a second key characteristics of focus events, and (in at least [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0081] in FIG. 4 may have four chat windows open. However, the agent can only type in a single window at a time so the window in which the agent in typing is the in-focus contact and the other windows are out of focus contacts. Based on the calculation discussed below, occupancy score for the in-focus contact may be 70% and the out of focus contact could add 5% each to the agent's occupancy score giving the agent a total multimodal occupancy score of 85%. Accordingly, multiple open contacts increase the occupancy of the agent, but the main component of the occupancy of the agent is determined by the in-focus contact.)
wherein defocused events are inactive-time events of an agent and a customer during the interaction and focused events are active-time events of the agent and the customer via a chat window; (in at least [0081] in FIG. 4 may have four chat windows open. However, the agent can only type in a single window at a time so the window in which the agent in typing is the in-focus contact and the other windows are out of focus contacts. Based on the calculation discussed below, occupancy score for the in-focus contact may be 70% and the out of focus contact could add 5% each to the agent's occupancy score giving the agent a total multimodal occupancy score of 85%. Accordingly, multiple open contacts increase the occupancy of the agent, but the main component of the occupancy of the agent is determined by the in-focus contact. [0088] a focus weight may be used to determine the multimodal occupancy score for an agent. The focus weight may be determined for each contact. The contact center system may determine a focus weight for an in-focus contact and a focus weight for one or more out of focus contacts. The in-focus contact may be the contact which the agent is currently responding. The other contacts, in which the agent is not currently interacting, are the out of focus contacts. In an embodiment, the focus weight may be based at least on one of the skill of the agent and the media capability. The focus weight may be different for a contact based on the media capability.)
(d) calculating a CSHAP score for the agent based on one or more attribute from the metadata of the interaction to provide an indication as to an ability of the agent to address different concurrent customer sessions via one or more channel types, (in at least [0089] At step 508, a multimodal occupancy score of the agent may be calculated based on the one or more parameters for each of the plurality of multimodal contacts. The multimodal occupancy score may be calculated based on the parameters associated with the media capability for each contact. The multimodal occupancy score may be used as a metric to determine the percentage of time that an agent is working within a time interval.)
wherein the CSHAP is calculated based on a total number of concurrent different interactions handled by the agent during the preconfigured period, customer sentiment or feedback score for each interaction in the total number of concurrent different interaction, … time taken to handle each interaction and a … time of one or more focused events during each interaction in the total number of concurrent different interaction; (in at least [0050] an agent may be determined to have a multimodal occupancy score of 90% by handling a customer phone call 202A. The contact center system 204 may determine the agent does not have the ability to handle another contact as the phone call will keep the agent occupied. In an alternative embodiment, agent may be determined to have a multimodal occupancy score of 100% by handling a customer phone call 202A to ensure the agent is not given another contact. [0051] The contact center system 204 may route the web capability of customer contact 202B to agent 206B. The contact center system 204 may determine the agent 206B has a multimodal occupancy score of 75% based on handling the web chat contact 202B. The contact center system 204 may determine the agent has the ability to handle another customer contact with a different media capability. The contact center system 204 may determine that having agent 206B handle the first email contact 202C gives agent 206B a multimodal occupancy score of an additional 5% and may also send a second email contact 202D, which gives agent 206B a multimodal occupancy score of an additional 10%. After assigning agent 206B the web chat contact 202B, a first email contact 202C and a second email contact 202D, agent 206B may have a total multimodal occupancy score of 90% (75%+5%+10%). [0057] The volume of text parameter may refer to the amount of incoming text an agent must read as well as the amount of outgoing text an agent must type to a customer. In an embodiment, the volume of incoming text may be affected by the textual sentiment of the customer, as an angry customer is more likely to write a high volume of text the agent needs to read. Additionally, the angry customer may require the agent to type more in order to settle or comfort the angry customer. For example, an angry customer may spend five minutes typing in a chat window and the agent must read this text. The agent also has to respond to all the points made in the text by the angry customer. As a result, the volume of text parameter may be high and the contact may require more time from the agent than a non-angry contact. The multimodal occupancy score of the agent may be increased due to the high volume of text parameter. An increased multimodal occupancy score means the agent can handle fewer additional contacts in order to allow the agent to focus on the web chat with the angry customer. In alternate embodiments, customers may have large volumes of text, regardless of their textual sentiment, and the multimodal occupancy score may be determined based on the length of the customer's volume of text parameter. [0059] the media capability module 306 may include a conversation length module 314. A conversation length module 314 may determine a conversation length parameter to calculate a multimodal occupancy score of an agent. The conversation length module 314 may use the conversation length parameter for a contact with a voice capability. The length of a conversation may refer to one or more of the agent speaking and/or the customer speaking. For example, if the customer is verbose, the agent may need to be on the phone longer than if the customer is succinct. The length of the conversation parameter may affect the multimodal occupancy score of the agent. Additionally, if the customer asks questions that are very time consuming for an agent to answer, then the length of the conversation parameter may be longer and will affect the multimodal occupancy score of the agent. [0061] The difficulty weight module 316 may determine a difficulty weight for the contact handled by the agent. The difficultly weight module 316 may take into account the difficulty for an agent in processing the contact. For example, processing a survey may be considered to be less difficult than processing a complaint. In an embodiment, the textual sentiment for a contact with a text capability may be used in determining the difficulty of the contact. The textual sentiment refers to how a customer uses language written to the agent. The textual sentiment may be important in a difficulty weight as an angry customer is more difficult to process and/or more stressful to deal with for an agent than a happy customer. This is because an angry customer is harder for an agent to emotionally deal with than a happy customer as an agent is often yelled at but needs to remain calm when speaking with the customer. In an embodiment, the textual sentiment may contribute to the overall difficulty weight determined by the difficulty weight module 316. [0067] an agent may handle multiple customers at a time via web chat. However, an agent only writes on a single window at a time. As such, the window which is written on by the agent is the in-focus contact and the other windows are the out of focus contacts. In an embodiment, a first focus weight for an in-focus contact may be greater than a second focus weight for an out of focus contact. The total focus weight of an agent may be determined by the focus weight module 320. In an embodiment, the focus weights may add to the value of 1. The customer may have three simultaneous contacts. The in-focus contact may be given a focus weight of 0.6. The other two out of focus contacts may be each given a focus weight of 0.2. Thus the total of the three focus weights is 1. Alternatively, the focus weights may add to numbers greater or less than 1. [0070] the chat sessions 4 times and sending 20 words over a predetermined text interval, the chat sessions are a separation weight of 1 and each chat session may have a difficulty weight of 1. Each time the chat is in-focus, the focus weighting may be a focus weight of 0.8 with the out of focus window having a focus weight of 0.2. The multimodal occupancy score may be calculated as: Occupancy of an agent for a single contact=((Contact switches/4)*(Words per text interval/20)*(Difficulty weight)*(Depth of separation weight)*(Focus weight)*100% [0072] in order to determine the multimodal occupancy score of the agent over the time interval, the multimodal occupancy score calculation must be completed for each simultaneous contact handled by the agent. In the above example, there are two chats. The occupancy score above is shown for a single chat. In the example, the chat which was used to determine the multimodal occupancy score of the agent was the in-focus chat and given a weight of 1. The multimodal occupancy score may now be determined for the out of focus chat. In an embodiment, the multimodal occupancy score of the other chat may be 5%. As such, the total multimodal occupancy score of the agent over the time interval may be 85% (80%+5%). [0073] The multimodal occupancy score may change when the agent switches from one contact to another. The contact switch module 304 may indicate when an agent switches from one contact to another. When an agent switches from one contact to another contact, an agent may become more occupied as the agent will need to ramp-up on the current contact. As a result, the multimodal occupancy score of the agent may increase for a predetermined number of intervals after a predetermined number of intervals have passed. The agent may only experience the increase in the multimodal occupancy score after a certain interval of time has passed in order to prevent an agent from unnecessarily switching between contacts to increase the multimodal occupancy score of that agent. [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0083] At step 502, the method may monitor a plurality of multimodal contacts simultaneously handled by an agent. The contact center system may monitor the contacts handled by an agent in order to determine a multimodal occupancy score of an agent. As the contacts are multimodal, an agent is not necessarily completely occupied based on a single contact. Instead, an agent may need to handle two or more contacts simultaneously in order for the agent to remain sufficiently occupied. In an embodiment, the agent may want to have their multimodal occupancy score at a predetermined level over a time interval. For example, the agent may want a multimodal occupancy score of 85% for a day of work. [0085] The contact center system may determine a word length at which an agent is 100% occupied. This determined word length may be divided by the actual word length over a time interval to determine a parameter. The parameter may later be used to determine the multimodal occupancy score. In another example, the media capability may be a voice capability. The parameter may be the conversation length of the conversation between the customer and the agent. The contact center system may determine a conversation length at which an agent is 100% occupied. This determined conversation length may be divided by the actual conversation length over a time interval to determine a parameter used to determine the multimodal occupancy score. [0088] a focus weight may be used to determine the multimodal occupancy score for an agent. The focus weight may be determined for each contact. The contact center system may determine a focus weight for an in-focus contact and a focus weight for one or more out of focus contacts. The in-focus contact may be the contact which the agent is currently responding. The other contacts, in which the agent is not currently interacting, are the out of focus contacts. In an embodiment, the focus weight may be based at least on one of the skill of the agent and the media capability. The focus weight may be different for a contact based on the media capability. [0089] At step 508, a multimodal occupancy score of the agent may be calculated based on the one or more parameters for each of the plurality of multimodal contacts. The multimodal occupancy score may be calculated based on the parameters associated with the media capability for each contact. The multimodal occupancy score may be used as a metric to determine the percentage of time that an agent is working within a time interval.)
(e) storing the calculated CSHAP score in the data store of agents; and (in at least [0078] The feedback may allow a redefinition of what 100% occupancy looks like and represents. This can then be used to adjust an agent's multimodal occupancy score. The relearning module 310 may monitor one or more agents to reevaluate one or more of the parameters associated with a media capability and/or contact. In an embodiment, a processor may be used to monitor the agents. In an embodiment, the relearning module could be controlled by a supervisor. In an embodiment, the values could be automatically fed back into the system so the relearning module 310 will self learn what 100% occupied looks like to the contact call center system. Alternatively, a blend of the supervisor control and the relearning may be used. For example, if an agent is 85% busy, but is still easily taking on new simultaneous contacts, then the current multimodal occupancy score may be revised by the relearning module 310.)
(f) sending the CSHAP score to one or more applications, to take one or more follow-up actions base on the CSHAP score. (in at least [0029] a system having an ACD or other similar contact processing switch, the present invention is not limited to any particular type of communication system switch or configuration of system elements. [0036] The term “switch” or “server” as used herein should be understood to include a Private Branch Exchange (PBX), an ACD, an enterprise switch, or other type of communications system switch or server, as well as other types of processor-based communication control devices such as media servers, computers, adjuncts, etc. [0040] The switch 130 and/or server 110 can be any architecture for directing contacts (i.e., customers) to one or more communication devices. In some embodiments, the switch 130 may perform load-balancing functions by allocating incoming or outgoing contacts among a plurality of logically and/or geographically distinct contact centers. Illustratively, the switch and/or server may be a modified form of the subscriber-premises equipment sold by Avaya Inc. under the names Definity™ Private-Branch Exchange (PBX)-based ACD system, MultiVantage™ PBX, Communication Manager™, S8300™ media server and any other media servers, SIP Enabled Services™, Intelligent Presence Server™, and/or Avaya Interaction Center™, and any other products or solutions offered by Avaya or another company. [0050] The customer contacts 202A-D sent to the multimodal contact center system 204 may include a variety of media capabilities. Customer contact 202A may include a voice capability. The voice capability may include a voice call. The contact center system 204 may route the voice call to agent 206A. Customer contact 202B may include a web capability. The web capability may include, but is not limited to, a web chat. Additionally, customer contacts 202C and 202 D may include a text capability such as, but not limited to, an email. The contact center system 204 may determine whether the incoming contact has a web capability or an email capability and may send it to an agent based on the agents' occupancy and/or whether the agent also has that capability. In an embodiment, an agent may be determined to have a multimodal occupancy score of 90% by handling a customer phone call 202A. The contact center system 204 may determine the agent does not have the ability to handle another contact as the phone call will keep the agent occupied. In an alternative embodiment, agent may be determined to have a multimodal occupancy score of 100% by handling a customer phone call 202A to ensure the agent is not given another contact. [0051] The contact center system 204 may route the web capability of customer contact 202B to agent 206B. The contact center system 204 may determine the agent 206B has a multimodal occupancy score of 75% based on handling the web chat contact 202B. The contact center system 204 may determine the agent has the ability to handle another customer contact with a different media capability. The contact center system 204 may determine that having agent 206B handle the first email contact 202C gives agent 206B a multimodal occupancy score of an additional 5% and may also send a second email contact 202D, which gives agent 206B a multimodal occupancy score of an additional 10%. After assigning agent 206B the web chat contact 202B, a first email contact 202C and a second email contact 202D, agent 206B may have a total multimodal occupancy score of 90% (75%+5%+10%). [0064] the difficulty weight module 316 may modify the difficultly weight based on the skill level of an agent. For example, a highly skilled agent may have less difficulty handling a particular contact than a less skilled agent. As such, the difficulty weight may be adjusted based on the agent's skill level. A highly skilled agent may decrease the difficulty weight while a newly trained and less skilled agent may increase the difficulty weight. For example, for a particular contact, a less skilled agent may have a difficulty weight of 1 based on the contact while a more skilled agent may have a difficulty weight of 0.5 based on the same contact. As such, the more skilled agent may have a lower multimodal occupancy score, as a result of the lower difficulty weight, and the more skilled agent may be available to take on additional contacts. [0066] an agent switching from a first call with a programmer to a second call with a lawyer requires a different use of language and skills. As such, it may be more difficult for an agent to switch from talking to a programmer to talking to a lawyer than for an agent to switch from talking to a programmer to talking to another programmer. Similarly, the switching of an agent from a complaint contact to a sales contact may have a large depth of separation weight. However, a switch between a support contact and a complaint contact may have a small depth of separation weight. The depth of separation weight may be adjusted and increased from a regular depth of separation weight in order to take into account a difficult switch between contacts when determining the multimodal occupancy score of the agent. [0073] The multimodal occupancy score may change when the agent switches from one contact to another. The contact switch module 304 may indicate when an agent switches from one contact to another. When an agent switches from one contact to another contact, an agent may become more occupied as the agent will need to ramp-up on the current contact. As a result, the multimodal occupancy score of the agent may increase for a predetermined number of intervals after a predetermined number of intervals have passed. [0076] The contact switch module may also determine a catch-up time interval the agent remains at the multimodal occupancy score of 100%. In an embodiment, the contact switch module may provide a baseline amount of time that an agent remains at the catch-up multimodal occupancy score. In an embodiment, the amount of time the agent remains at the catch-up multimodal occupancy score may be based, at least in part, on a skill level of the agent. An agent with a higher skill level will have a shorter interval at the catch-up multimodal occupancy score than a less skilled agent. The more skilled agent may have a shorter interval as the more skilled agent will be able to more quickly get caught-up on the more difficult contact. For example, the contact switching module 304 may determine that the agent can remain at the catch-up multimodal occupancy score for 15 seconds. However, the contact switching module 304 may determine that a highly skilled agent can only remain at the catch-up multimodal occupancy score for 10 seconds. Accordingly, after the predetermined time interval at the catch-up multimodal occupancy score of 100%, the agent may return to multimodal occupancy score of 93.5% for the second contact. [0077] the occupancy baseline, which is used to determine when an agent is 100% occupied, may be reevaluated by a relearning module 310. The call center system administrator and/or supervisor may input and determine the baseline values for the parameters. The relearning module 310 may learn from the agents in the system to determine and reevaluate the baseline values. The relearning module 310 may monitor one or more agents to reevaluate the parameters or weights. The relearning module 310 may adjust the parameters. The relearning module 310 may teach itself to reevaluate the parameters based on how busy the agents in the call center system are in responding to customer contacts. For example, the multimodal occupancy score of a group of agents may be collected and used as feedback into the contact center system to provide relearning. [0078] The feedback may allow a redefinition of what 100% occupancy looks like and represents. This can then be used to adjust an agent's multimodal occupancy score. The relearning module 310 may monitor one or more agents to reevaluate one or more of the parameters associated with a media capability and/or contact. In an embodiment, a processor may be used to monitor the agents. In an embodiment, the relearning module could be controlled by a supervisor. In an embodiment, the values could be automatically fed back into the system so the relearning module 310 will self learn what 100% occupied looks like to the contact call center system. Alternatively, a blend of the supervisor control and the relearning may be used. For example, if an agent is 85% busy, but is still easily taking on new simultaneous contacts, then the current multimodal occupancy score may be revised by the relearning module 310.)
Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller:
…total time… (in at least [0063] monitor and to evaluate the quality of contact center agents' interactions with customers. The automatic analysis or automatic evaluation may be performed on metadata associated with the interaction (such as the length of the interaction in minutes and the number of transfers between different agents of the contact center) as well as the content of the interaction (e.g., an analysis of the text transcripts of the interaction to detect keywords or phrases), and the automatic evaluation of the interaction may be used to generate one or more evaluation scores representing the agent's performance during the interaction. [0072] The metadata of the interaction includes portions of the interaction that are not readily user-modifiable. These may include, for example, identifiers of the agent and customer involved in the interaction (e.g., phone numbers, email addresses, assigned customer numbers or agent numbers, etc.), timestamps of various messages, the number of messages sent in the interaction (e.g., the number of messages sent in a text chat or the number of email messages exchanged), the length (e.g., in minutes) of an audio and/or video interaction, customer feedback regarding the interaction (e.g., net promoter score), and the like. [0087] metadata may include the number of transfers of the interaction between agents, customer feedback (e.g., a net promoter score (NPS) or survey data), the time of day of the interaction, and conversation length (e.g., the number of chat messages sent, the number of emails sent, the total amount of text sent between the customer and agent, the duration of the text chat session or the audio or video conference). [0088] the interaction feature extractor 174 represents qualitative features using one-hot encoding (e.g., the presence or absence of a particular feature, such as whether or not an interaction was transferred). In some embodiments, quantitative data is encoded with quantile discretization (e.g., binning numerical data into groups). For example, interactions that were less than 5 minutes long may be put into one bin, interactions that were 5 to 15 minutes long may be put into another bin, and interactions that were over 15 minutes long may be put into a third bin, and the features relating to the length of the interaction may merely indicate which bin the interaction fell into [0103] the automatically computed evaluations from multiple interactions are compared as an aggregate against threshold conditions. For example, a time window may be specified where all automatically computed evaluations of interactions involving a particular agent falling within a time window are aggregated, and the aggregated scores for the agent during the time window are compared against the various threshold conditions. In still other embodiments of the present invention, all of the automatically computed interactions for a particular agent are aggregated and compared against various time windows.)
At the time the invention was filed, it would have been obvious for one of ordinary skill in the art to have modified the teachings of O'Connor, as taught by Miller above, with a reasonable expectation of success if arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make this modification to the teachings of O'Connor with the motivation of, …improve the efficiency of the hardware supporting a contact center, such as by reducing the number of interactions that are stored in the mass storage device 126 by discarding or deleting uninteresting interactions, as determined through the automatic analysis of the interactions, and thereby making more efficient use of data storage space within the contact center systems… to detect deviations in the agent's performance from history, which may show signs of worsening performance (and resulting in the automatic scheduling of additional training) or improving performance (where the agent may be sent a message congratulating him or her on the improvement and encouraging continued progress)…. a quality monitoring process will monitor the performance of an agent by evaluating the interactions that the agent participated in for events such as whether the agent was polite and courteous, whether the agent was efficient, and whether the agent proposed the correct solutions to resolve a customer's issue….., as recited in Miller.
As per Claim 2, O'Connor teaches: The computerized-method of claim 1, wherein the first key characteristics of the defocused events are at least one of:
(i) the agent has switched from the chat window with the customer to a second chat window with a second customer; (in at least [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0081] in FIG. 4 may have four chat windows open. However, the agent can only type in a single window at a time so the window in which the agent in typing is the in-focus contact and the other windows are out of focus contacts. Based on the calculation discussed below, occupancy score for the in-focus contact may be 70% and the out of focus contact could add 5% each to the agent's occupancy score giving the agent a total multimodal occupancy score of 85%. Accordingly, multiple open contacts increase the occupancy of the agent, but the main component of the occupancy of the agent is determined by the in-focus contact.)
(ii) messages and user actions within the chat window are intermittent, wherein the second key characteristics of the focused events are at least one of: (in at least [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0081] in FIG. 4 may have four chat windows open. However, the agent can only type in a single window at a time so the window in which the agent in typing is the in-focus contact and the other windows are out of focus contacts. Based on the calculation discussed below, occupancy score for the in-focus contact may be 70% and the out of focus contact could add 5% each to the agent's occupancy score giving the agent a total multimodal occupancy score of 85%. Accordingly, multiple open contacts increase the occupancy of the agent, but the main component of the occupancy of the agent is determined by the in-focus contact.)
(i) user actions within the chat window with the customer to send messages; and (in at least [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0081] in FIG. 4 may have four chat windows open. However, the agent can only type in a single window at a time so the window in which the agent in typing is the in-focus contact and the other windows are out of focus contacts. Based on the calculation discussed below, occupancy score for the in-focus contact may be 70% and the out of focus contact could add 5% each to the agent's occupancy score giving the agent a total multimodal occupancy score of 85%. Accordingly, multiple open contacts increase the occupancy of the agent, but the main component of the occupancy of the agent is determined by the in-focus contact.)
(ii) the messages and actions are continuous and consistent within the chat window, and wherein the user actions are at least one of: actively typing, responding, and interacting. (in at least [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0081] in FIG. 4 may have four chat windows open. However, the agent can only type in a single window at a time so the window in which the agent in typing is the in-focus contact and the other windows are out of focus contacts. Based on the calculation discussed below, occupancy score for the in-focus contact may be 70% and the out of focus contact could add 5% each to the agent's occupancy score giving the agent a total multimodal occupancy score of 85%. Accordingly, multiple open contacts increase the occupancy of the agent, but the main component of the occupancy of the agent is determined by the in-focus contact.)
As per Claim 3, O'Connor teaches: The computerized-method of claim 1,
wherein the CSHAP module is operating every preconfigured duty cycle. (in at least [0006] contact center occupancy is measured by the percentage of time an agent is working within a given interval. In traditional contact centers, the only media capability an agent is using is voice via telephone calls. Occupancy often refers to information such as talk time and after call work time as periods that constitute work time. An agent's occupancy is a measure of how efficiently an agent's time is used. If an agent today were to work constantly from login to logout, the agent would be 100% occupied. [0037] FIG. 1 shows an illustrative embodiment of a multimodal contact center, in accordance with one embodiment of the present invention. A contact center 100 comprises a central server 110, a set of data stores or databases 114 containing contact or customer related information and other information that can enhance the value and efficiency of the contact processing [0049] FIG. 2 depicts an agent handling multiple simultaneous contacts of various media capabilities or modes. A media capability is a form of media communication and includes a communication channel. Media capabilities may include, but are not limited to, a web capability, a text capability, a voice capability and/or a video capability. The media capabilities may vary in characteristics like bandwidth requirement, the latency of support (i.e., how close to real-time, immediacy, responsiveness, etc.), the level of participation by the agent, usage of other system resources, and so forth. [0052] FIG. 3 illustrates an exemplary embodiment of a block diagram to illustrate various modules of a contact center system 300 determining occupancy of an agent with simultaneous multimodal contacts, in accordance with an embodiment of the present invention. The contact center system 300 may include multiple modules to determine the occupancy of agents in the system. Multiple modules may determine the occupancy of an agent handling multiple simultaneous contacts using a variety of media capabilities. [0084] At step 504, a media capability may be determined for each contact received by the agent. The agent may receive a plurality of contacts and a media capability may be determined for each contact received. The media capability of a contact may include, but is not limited to, a voice capability, a video capability, a text capability or an email. In an embodiment, the contacts simultaneously handled by an agent may have one or more different capabilities. In an alternate embodiment, the contacts simultaneously handled by an agent may have one or more of the same capabilities. For example, the agent may handle four contacts that all have web chat capabilities. Alternatively, the agent may handle two contacts. One of those contacts may have an email capability and the other contact may have a web chat capability. [0085] At step 506, one or more parameters associated with the media capability of each contact may be determined. In an embodiment, for each contact, one or more parameters are determined based on one or more of the contact, the media capability and the agent. For example, the media capability may be a text capability. One parameter may be the volume of text received and/or sent by the agent. The contact center system may determine a word length at which an agent is 100% occupied. This determined word length may be divided by the actual word length over a time interval to determine a parameter. The parameter may later be used to determine the multimodal occupancy score. In another example, the media capability may be a voice capability. The parameter may be the conversation length of the conversation between the customer and the agent. The contact center system may determine a conversation length at which an agent is 100% occupied. This determined conversation length may be divided by the actual conversation length over a time interval to determine a parameter used to determine the multimodal occupancy score.)
As per Claim 4, O'Connor teaches: The computerized-method of claim 1, wherein the calculating of the CSHAP score for the agent is based on formula (I):
PNG
media_image1.png
137
772
media_image1.png
Greyscale
whereby:
N is a total number of concurrent different interactions handled by an agent during the preconfigured period, (in at least [0072] in order to determine the multimodal occupancy score of the agent over the time interval, the multimodal occupancy score calculation must be completed for each simultaneous contact handled by the agent. In the above example, there are two chats. The occupancy score above is shown for a single chat. In the example, the chat which was used to determine the multimodal occupancy score of the agent was the in-focus chat and given a weight of 1. The multimodal occupancy score may now be determined for the out of focus chat. In an embodiment, the multimodal occupancy score of the other chat may be 5%. As such, the total multimodal occupancy score of the agent over the time interval may be 85% (80%+5%). [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0085] At step 506, one or more parameters associated with the media capability of each contact may be determined. In an embodiment, for each contact, one or more parameters are determined based on one or more of the contact, the media capability and the agent. For example, the media capability may be a text capability. One parameter may be the volume of text received and/or sent by the agent. The contact center system may determine a word length at which an agent is 100% occupied. This determined word length may be divided by the actual word length over a time interval to determine a parameter. The parameter may later be used to determine the multimodal occupancy score. In another example, the media capability may be a voice capability. The parameter may be the conversation length of the conversation between the customer and the agent. The contact center system may determine a conversation length at which an agent is 100% occupied. This determined conversation length may be divided by the actual conversation length over a time interval to determine a parameter used to determine the multimodal occupancy score.)
CSi is Customer Sentiment or feedback score for an interaction, (in at least [0061] The difficulty weight module 316 may determine a difficulty weight for the contact handled by the agent. The difficultly weight module 316 may take into account the difficulty for an agent in processing the contact. For example, processing a survey may be considered to be less difficult than processing a complaint. In an embodiment, the textual sentiment for a contact with a text capability may be used in determining the difficulty of the contact. The textual sentiment refers to how a customer uses language written to the agent. The textual sentiment may be important in a difficulty weight as an angry customer is more difficult to process and/or more stressful to deal with for an agent than a happy customer. This is because an angry customer is harder for an agent to emotionally deal with than a happy customer as an agent is often yelled at but needs to remain calm when speaking with the customer. In an embodiment, the textual sentiment may contribute to the overall difficulty weight determined by the difficulty weight module 316.)
Ti is … time taken to handle an interaction, (in at least [0072] in order to determine the multimodal occupancy score of the agent over the time interval, the multimodal occupancy score calculation must be completed for each simultaneous contact handled by the agent. In the above example, there are two chats. The occupancy score above is shown for a single chat. In the example, the chat which was used to determine the multimodal occupancy score of the agent was the in-focus chat and given a weight of 1. The multimodal occupancy score may now be determined for the out of focus chat. In an embodiment, the multimodal occupancy score of the other chat may be 5%. As such, the total multimodal occupancy score of the agent over the time interval may be 85% (80%+5%). [0085] At step 506, one or more parameters associated with the media capability of each contact may be determined. In an embodiment, for each contact, one or more parameters are determined based on one or more of the contact, the media capability and the agent. For example, the media capability may be a text capability. One parameter may be the volume of text received and/or sent by the agent. The contact center system may determine a word length at which an agent is 100% occupied. This determined word length may be divided by the actual word length over a time interval to determine a parameter. The parameter may later be used to determine the multimodal occupancy score. In another example, the media capability may be a voice capability. The parameter may be the conversation length of the conversation between the customer and the agent. The contact center system may determine a conversation length at which an agent is 100% occupied. This determined conversation length may be divided by the actual conversation length over a time interval to determine a parameter used to determine the multimodal occupancy score.)
FTi is … time of one or more focused events during an interaction (in at least [0070] Each time the chat is in-focus, the focus weighting may be a focus weight of 0.8 with the out of focus window having a focus weight of 0.2. The multimodal occupancy score may be calculated as: Occupancy of an agent for a single contact=((Contact switches/4)*(Words per text interval/20)*(Difficulty weight)*(Depth of separation weight)*(Focus weight)*100% [0080] FIG. 4 depicts a diagram of an exemplary terminal of an agent simultaneously handling multiple contacts, in accordance with one embodiment of the present invention. The computing device 400 may include four simultaneous contacts 401, 402, 403 and 404. In an embodiment, all four contacts may be of the same media capability. For example, all four contacts may be textual contacts, such as, but not limited to, text messages. An agent may have multiple open textual contacts. However, only one of those contacts can be in-focus and receive the text typed by an agent at a given time. The single contact in-focus will have the greatest impact on the occupancy of the agent. The out of focus contacts will have a lesser impact. However, all the open contacts that are handled by the agent will contribute to the agent's multimodal occupancy score. [0085] At step 506, one or more parameters associated with the media capability of each contact may be determined. In an embodiment, for each contact, one or more parameters are determined based on one or more of the contact, the media capability and the agent. For example, the media capability may be a text capability. One parameter may be the volume of text received and/or sent by the agent. The contact center system may determine a word length at which an agent is 100% occupied. This determined word length may be divided by the actual word length over a time interval to determine a parameter. The parameter may later be used to determine the multimodal occupancy score. In another example, the media capability may be a voice capability. The parameter may be the conversation length of the conversation between the customer and the agent. The contact center system may determine a conversation length at which an agent is 100% occupied. This determined conversation length may be divided by the actual conversation length over a time interval to determine a parameter used to determine the multimodal occupancy score.)
Weffective is an effective weighting factor of concurrent channel requests based on formula II: (in at least [0071] an agent may currently have 2 chats, type 32 words per text interval, a difficulty weight of 1.25, a depth of separation weight of 0.08 and a focus weight of 1. Using the above equation, the occupancy score of the agent for a single chat may equal (2/4)*(43/20)*1.25*0.8*1*100%=80%)
PNG
media_image2.png
43
125
media_image2.png
Greyscale
whereby:
𝑊𝑖 is a weighting factor of each channel type. (in at least [0051] The contact center system 204 may route the web capability of customer contact 202B to agent 206B. The contact center system 204 may determine the agent 206B has a multimodal occupancy score of 75% based on handling the web chat contact 202B. The contact center system 204 may determine the agent has the ability to handle another customer contact with a different media capability. The contact center system 204 may determine that having agent 206B handle the first email contact 202C gives agent 206B a multimodal occupancy score of an additional 5% and may also send a second email contact 202D, which gives agent 206B a multimodal occupancy score of an additional 10%. After assigning agent 206B the web chat contact 202B, a first email contact 202C and a second email contact 202D, agent 206B may have a total multimodal occupancy score of 90% (75%+5%+10%). [0062] the textual sentiment, the difficultly weight module 316 may also include the media capability in the determination of the difficulty weight. For example, a contact with an email capability may be considered to be more difficult for an agent than a contact with a web chat capability. In an embodiment, the difficulty weight of an email or chat may be calculated using the total word count or any other existing difficult weight formulas. [0087] a separation weight may be used to determine the multimodal occupancy score for an agent. A separation weight may be determined for each contact. A separation weight may be applied to determine the agent's multimodal occupancy score when an agent switched from a first contact to a second contact. The depth of separation weight module may be determined when an agent changes from one contact to another. In an embodiment, the depth of separation weight may be determined based on the media capability of the first contact when compared to the media capability of the second contact. In another embodiment, the depth of separation weight may be determined based on the type or contact type. Based on the depth of separation, the separation weight may be adjusted and increased from a regular depth of separation weight of one in order to take into account the more difficult depth of separation weights when determining the occupancy of the agent.)
Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller:
…total time… (in at least [0063] monitor and to evaluate the quality of contact center agents' interactions with customers. The automatic analysis or automatic evaluation may be performed on metadata associated with the interaction (such as the length of the interaction in minutes and the number of transfers between different agents of the contact center) as well as the content of the interaction (e.g., an analysis of the text transcripts of the interaction to detect keywords or phrases), and the automatic evaluation of the interaction may be used to generate one or more evaluation scores representing the agent's performance during the interaction. [0072] The metadata of the interaction includes portions of the interaction that are not readily user-modifiable. These may include, for example, identifiers of the agent and customer involved in the interaction (e.g., phone numbers, email addresses, assigned customer numbers or agent numbers, etc.), timestamps of various messages, the number of messages sent in the interaction (e.g., the number of messages sent in a text chat or the number of email messages exchanged), the length (e.g., in minutes) of an audio and/or video interaction, customer feedback regarding the interaction (e.g., net promoter score), and the like. [0087] metadata may include the number of transfers of the interaction between agents, customer feedback (e.g., a net promoter score (NPS) or survey data), the time of day of the interaction, and conversation length (e.g., the number of chat messages sent, the number of emails sent, the total amount of text sent between the customer and agent, the duration of the text chat session or the audio or video conference). [0088] the interaction feature extractor 174 represents qualitative features using one-hot encoding (e.g., the presence or absence of a particular feature, such as whether or not an interaction was transferred). In some embodiments, quantitative data is encoded with quantile discretization (e.g., binning numerical data into groups). For example, interactions that were less than 5 minutes long may be put into one bin, interactions that were 5 to 15 minutes long may be put into another bin, and interactions that were over 15 minutes long may be put into a third bin, and the features relating to the length of the interaction may merely indicate which bin the interaction fell into [0103] the automatically computed evaluations from multiple interactions are compared as an aggregate against threshold conditions. For example, a time window may be specified where all automatically computed evaluations of interactions involving a particular agent falling within a time window are aggregated, and the aggregated scores for the agent during the time window are compared against the various threshold conditions. In still other embodiments of the present invention, all of the automatically computed interactions for a particular agent are aggregated and compared against various time windows.)
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 5, O'Connor teaches: The computerized-method of claim 1,
wherein one application of the one or more applications is …. (in at least [0040] The switch 130 and/or server 110 can be any architecture for directing contacts (i.e., customers) to one or more communication devices. In some embodiments, the switch 130 may perform load-balancing functions by allocating incoming or outgoing contacts among a plurality of logically and/or geographically distinct contact centers. Illustratively, the switch and/or server may be a modified form of the subscriber-premises equipment sold by Avaya Inc. under the names Definity™ Private-Branch Exchange (PBX)-based ACD system, MultiVantage™ PBX, Communication Manager™, S8300™ media server and any other media servers, SIP Enabled Services™, Intelligent Presence Server™, and/or Avaya Interaction Center™, and any other products or solutions offered by Avaya or another company.)
Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller:
wherein one application of the one or more applications is a gamification application (in at least [0066] directed to the automatic assignment of agent training or coaching sessions to agents based on one or more automatically computed evaluation scores of the agent's performance, thereby allowing for faster feedback and more rapid correction of agent behavior. [0068] FIG. 2, the quality management server 170 may include a quality prediction module 172 and an interaction feature extractor 174. In the embodiment shown, the quality prediction module 172 may receive requests to predict an evaluation score for a recorded interaction. The request may come from the call recording server 158, which may also provide the recorded interaction to be evaluated from the mass storage device 126. The quality management server 170 may also include a quality service 176, which is configured to provide a user interface (e.g., a web server providing a web application) for human supervisors to perform evaluations of interactions and to score the interactions based on evaluation criteria. These manually generated evaluation scores may also be provided to the quality prediction module 172 in order to train quality prediction models. [0116] scheduling, automatically, additional training sessions for agents for which the system has automatically detected problems or other procedural noncompliance in the agent's interactions. As noted above, the automatically extracted features and the prediction models may be used to detect and score agent behavior during the interaction along a variety of different evaluation parameters (e.g., professionalism, script compliance, knowledge of particular products, and the like). As such, targeted training sessions may be assigned to the agent to correct the detected problems. [0120] The controller may then compare the predicted performance with the automatically evaluated performance on a recent interaction with to detect deviations in the agent's performance from history, which may show signs of worsening performance (and resulting in the automatic scheduling of additional training) or improving performance (where the agent may be sent a message congratulating him or her on the improvement and encouraging continued progress).)
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 6, Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller: The computerized-method of claim 5,
wherein the one or more follow-up actions of the gamification application based on the CSHAP score, is providing at least one reward or recognition to the agent. (in at least [0120] The controller may then compare the predicted performance with the automatically evaluated performance on a recent interaction with to detect deviations in the agent's performance from history, which may show signs of worsening performance (and resulting in the automatic scheduling of additional training) or improving performance (where the agent may be sent a message congratulating him or her on the improvement and encouraging continued progress))
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 7, Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller: The computerized-method of claim 6,
wherein the at least one reward or recognition to the agent is provided to the agent, when the CSHAP score is above a predefined threshold or between a predefined range. (in at least [0110] As noted above, some interactions may be more “interesting” in that they contain agent behavior that does not comply with standards or that they contain extraordinarily good agent behavior. As discussed above, the automatic scoring of an interaction may provide an indication as to whether a particular interaction is interesting or not. For example, the controller may tag an interaction as being “interesting” if one or more scores of the interaction is significantly outside the typical range of scores in the environment (e.g., more than two standard deviations from the mean score). For example, a particularly low score on an interaction may be an indication of flagging performance by an agent, or may indicate unusual, difficult interaction for the agent to handle (e.g., a particularly belligerent and/or irrational customer). [0119] the condition is a z-score threshold or standard score. In particular, the controller may calculate the Gaussian distribution across all agents' prediction scores in the contact center over a specific time range, and if a particular agent's average z-score (which may be a running score over time) is below a threshold, then a condition is met for assigning training to the agent. [0120] The controller may then compare the predicted performance with the automatically evaluated performance on a recent interaction with to detect deviations in the agent's performance from history, which may show signs of worsening performance (and resulting in the automatic scheduling of additional training) or improving performance (where the agent may be sent a message congratulating him or her on the improvement and encouraging continued progress))
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 8, O'Connor teaches: The computerized-method of claim 1,
wherein one application of the one or more applications is ….. (in at least [0040] The switch 130 and/or server 110 can be any architecture for directing contacts (i.e., customers) to one or more communication devices. In some embodiments, the switch 130 may perform load-balancing functions by allocating incoming or outgoing contacts among a plurality of logically and/or geographically distinct contact centers. Illustratively, the switch and/or server may be a modified form of the subscriber-premises equipment sold by Avaya Inc. under the names Definity™ Private-Branch Exchange (PBX)-based ACD system, MultiVantage™ PBX, Communication Manager™, S8300™ media server and any other media servers, SIP Enabled Services™, Intelligent Presence Server™, and/or Avaya Interaction Center™, and any other products or solutions offered by Avaya or another company.)
Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller:
wherein one application of the one or more applications is a Quality Management (QM) application (in at least [0066] directed to the automatic assignment of agent training or coaching sessions to agents based on one or more automatically computed evaluation scores of the agent's performance, thereby allowing for faster feedback and more rapid correction of agent behavior. [0068] FIG. 2, the quality management server 170 may include a quality prediction module 172 and an interaction feature extractor 174. In the embodiment shown, the quality prediction module 172 may receive requests to predict an evaluation score for a recorded interaction. The request may come from the call recording server 158, which may also provide the recorded interaction to be evaluated from the mass storage device 126. The quality management server 170 may also include a quality service 176, which is configured to provide a user interface (e.g., a web server providing a web application) for human supervisors to perform evaluations of interactions and to score the interactions based on evaluation criteria. These manually generated evaluation scores may also be provided to the quality prediction module 172 in order to train quality prediction models. [0116] scheduling, automatically, additional training sessions for agents for which the system has automatically detected problems or other procedural noncompliance in the agent's interactions. As noted above, the automatically extracted features and the prediction models may be used to detect and score agent behavior during the interaction along a variety of different evaluation parameters (e.g., professionalism, script compliance, knowledge of particular products, and the like). As such, targeted training sessions may be assigned to the agent to correct the detected problems. [0120] The controller may then compare the predicted performance with the automatically evaluated performance on a recent interaction with to detect deviations in the agent's performance from history, which may show signs of worsening performance (and resulting in the automatic scheduling of additional training) or improving performance (where the agent may be sent a message congratulating him or her on the improvement and encouraging continued progress).)
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 9, Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller: The computerized-method of claim 8,
wherein the one or more follow-up actions of the QM application based on the CSHAP score is automatically assigning a coaching program when the CSHAP score is below a predefined threshold. (in at least [0119] the condition is a z-score threshold or standard score. In particular, the controller may calculate the Gaussian distribution across all agents' prediction scores in the contact center over a specific time range, and if a particular agent's average z-score (which may be a running score over time) is below a threshold, then a condition is met for assigning training to the agent. [0120] The controller may then compare the predicted performance with the automatically evaluated performance on a recent interaction with to detect deviations in the agent's performance from history, which may show signs of worsening performance (and resulting in the automatic scheduling of additional training) or improving performance (where the agent may be sent a message congratulating him or her on the improvement and encouraging continued progress)) [0122] automatically monitoring the quality of an agent's performance and automatically assigning training to the agent based on meeting particular conditions, such as automatically computed scores failing to meet minimum standards.)
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 10, O'Connor teaches: The computerized-method of claim 1,
wherein one application of the one or more applications is an Automated Call Distribution (ACD) system. (in at least [0029] a system having an ACD or other similar contact processing switch, the present invention is not limited to any particular type of communication system switch or configuration of system elements. Those skilled in the art will recognize the disclosed techniques may be used in any communication application in which it is desirable to provide improved contact processing. [0040] The switch 130 and/or server 110 can be any architecture for directing contacts (i.e., customers) to one or more communication devices. In some embodiments, the switch 130 may perform load-balancing functions by allocating incoming or outgoing contacts among a plurality of logically and/or geographically distinct contact centers. Illustratively, the switch and/or server may be a modified form of the subscriber-premises equipment sold by Avaya Inc. under the names Definity™ Private-Branch Exchange (PBX)-based ACD system, MultiVantage™ PBX, Communication Manager™, S8300™ media server and any other media servers, SIP Enabled Services™, Intelligent Presence Server™, and/or Avaya Interaction Center™, and any other products or solutions offered by Avaya or another company. [0066] an agent switching from a first call with a programmer to a second call with a lawyer requires a different use of language and skills. As such, it may be more difficult for an agent to switch from talking to a programmer to talking to a lawyer than for an agent to switch from talking to a programmer to talking to another programmer. Similarly, the switching of an agent from a complaint contact to a sales contact may have a large depth of separation weight. However, a switch between a support contact and a complaint contact may have a small depth of separation weight. The depth of separation weight may be adjusted and increased from a regular depth of separation weight in order to take into account a difficult switch between contacts when determining the multimodal occupancy score of the agent. [0076] The contact switch module may also determine a catch-up time interval the agent remains at the multimodal occupancy score of 100%. In an embodiment, the contact switch module may provide a baseline amount of time that an agent remains at the catch-up multimodal occupancy score. In an embodiment, the amount of time the agent remains at the catch-up multimodal occupancy score may be based, at least in part, on a skill level of the agent. An agent with a higher skill level will have a shorter interval at the catch-up multimodal occupancy score than a less skilled agent. The more skilled agent may have a shorter interval as the more skilled agent will be able to more quickly get caught-up on the more difficult contact. For example, the contact switching module 304 may determine that the agent can remain at the catch-up multimodal occupancy score for 15 seconds. However, the contact switching module 304 may determine that a highly skilled agent can only remain at the catch-up multimodal occupancy score for 10 seconds. Accordingly, after the predetermined time interval at the catch-up multimodal occupancy score of 100%, the agent may return to multimodal occupancy score of 93.5% for the second contact. [0077] the occupancy baseline, which is used to determine when an agent is 100% occupied, may be reevaluated by a relearning module 310. The call center system administrator and/or supervisor may input and determine the baseline values for the parameters. The relearning module 310 may learn from the agents in the system to determine and reevaluate the baseline values. The relearning module 310 may monitor one or more agents to reevaluate the parameters or weights. The relearning module 310 may adjust the parameters. The relearning module 310 may teach itself to reevaluate the parameters based on how busy the agents in the call center system are in responding to customer contacts. For example, the multimodal occupancy score of a group of agents may be collected and used as feedback into the contact center system to provide relearning. [0078] The feedback may allow a redefinition of what 100% occupancy looks like and represents. This can then be used to adjust an agent's multimodal occupancy score. The relearning module 310 may monitor one or more agents to reevaluate one or more of the parameters associated with a media capability and/or contact. In an embodiment, a processor may be used to monitor the agents. In an embodiment, the relearning module could be controlled by a supervisor. In an embodiment, the values could be automatically fed back into the system so the relearning module 310 will self learn what 100% occupied looks like to the contact call center system. Alternatively, a blend of the supervisor control and the relearning may be used. For example, if an agent is 85% busy, but is still easily taking on new simultaneous contacts, then the current multimodal occupancy score may be revised by the relearning module 310.)
As per Claim 11, O'Connor teaches: The computerized-method of claim 10,
wherein the one or more follow-up actions of the ACD system based on the CSHAP score includes changing attributes of routing skills of the agent. (in at least [0029] a system having an ACD or other similar contact processing switch, the present invention is not limited to any particular type of communication system switch or configuration of system elements. Those skilled in the art will recognize the disclosed techniques may be used in any communication application in which it is desirable to provide improved contact processing. [0040] The switch 130 and/or server 110 can be any architecture for directing contacts (i.e., customers) to one or more communication devices. In some embodiments, the switch 130 may perform load-balancing functions by allocating incoming or outgoing contacts among a plurality of logically and/or geographically distinct contact centers. Illustratively, the switch and/or server may be a modified form of the subscriber-premises equipment sold by Avaya Inc. under the names Definity™ Private-Branch Exchange (PBX)-based ACD system, MultiVantage™ PBX, Communication Manager™, S8300™ media server and any other media servers, SIP Enabled Services™, Intelligent Presence Server™, and/or Avaya Interaction Center™, and any other products or solutions offered by Avaya or another company. [0064] the difficulty weight module 316 may modify the difficultly weight based on the skill level of an agent. For example, a highly skilled agent may have less difficulty handling a particular contact than a less skilled agent. As such, the difficulty weight may be adjusted based on the agent's skill level. A highly skilled agent may decrease the difficulty weight while a newly trained and less skilled agent may increase the difficulty weight. For example, for a particular contact, a less skilled agent may have a difficulty weight of 1 based on the contact while a more skilled agent may have a difficulty weight of 0.5 based on the same contact. As such, the more skilled agent may have a lower multimodal occupancy score, as a result of the lower difficulty weight, and the more skilled agent may be available to take on additional contacts. [0066] an agent switching from a first call with a programmer to a second call with a lawyer requires a different use of language and skills. As such, it may be more difficult for an agent to switch from talking to a programmer to talking to a lawyer than for an agent to switch from talking to a programmer to talking to another programmer. Similarly, the switching of an agent from a complaint contact to a sales contact may have a large depth of separation weight. However, a switch between a support contact and a complaint contact may have a small depth of separation weight. The depth of separation weight may be adjusted and increased from a regular depth of separation weight in order to take into account a difficult switch between contacts when determining the multimodal occupancy score of the agent. [0076] The contact switch module may also determine a catch-up time interval the agent remains at the multimodal occupancy score of 100%. In an embodiment, the contact switch module may provide a baseline amount of time that an agent remains at the catch-up multimodal occupancy score. In an embodiment, the amount of time the agent remains at the catch-up multimodal occupancy score may be based, at least in part, on a skill level of the agent. An agent with a higher skill level will have a shorter interval at the catch-up multimodal occupancy score than a less skilled agent. The more skilled agent may have a shorter interval as the more skilled agent will be able to more quickly get caught-up on the more difficult contact. For example, the contact switching module 304 may determine that the agent can remain at the catch-up multimodal occupancy score for 15 seconds. However, the contact switching module 304 may determine that a highly skilled agent can only remain at the catch-up multimodal occupancy score for 10 seconds. Accordingly, after the predetermined time interval at the catch-up multimodal occupancy score of 100%, the agent may return to multimodal occupancy score of 93.5% for the second contact. [0077] the occupancy baseline, which is used to determine when an agent is 100% occupied, may be reevaluated by a relearning module 310. The call center system administrator and/or supervisor may input and determine the baseline values for the parameters. The relearning module 310 may learn from the agents in the system to determine and reevaluate the baseline values. The relearning module 310 may monitor one or more agents to reevaluate the parameters or weights. The relearning module 310 may adjust the parameters. The relearning module 310 may teach itself to reevaluate the parameters based on how busy the agents in the call center system are in responding to customer contacts. For example, the multimodal occupancy score of a group of agents may be collected and used as feedback into the contact center system to provide relearning. [0078] The feedback may allow a redefinition of what 100% occupancy looks like and represents. This can then be used to adjust an agent's multimodal occupancy score. The relearning module 310 may monitor one or more agents to reevaluate one or more of the parameters associated with a media capability and/or contact. In an embodiment, a processor may be used to monitor the agents. In an embodiment, the relearning module could be controlled by a supervisor. In an embodiment, the values could be automatically fed back into the system so the relearning module 310 will self learn what 100% occupied looks like to the contact call center system. Alternatively, a blend of the supervisor control and the relearning may be used. For example, if an agent is 85% busy, but is still easily taking on new simultaneous contacts, then the current multimodal occupancy score may be revised by the relearning module 310.)
As per Claim 12, O'Connor teaches: The computerized-method of claim 1,
… to operate the CSHAP module for each agent in the data store of agents of the selected tenant. (in at least [0037] FIG. 1 shows an illustrative embodiment of a multimodal contact center, in accordance with one embodiment of the present invention. A contact center 100 comprises a central server 110, a set of data stores or databases 114 containing contact or customer related information and other information that can enhance the value and efficiency of the contact processing, and a plurality of servers, namely a voice mail server 118, an Interactive Response unit (e.g., IVR) 122, and other servers 126, a switch 130, a plurality of working agents operating packet-switched communication devices 134-1 to N such as computer work stations or personal computers, and/or circuit-switched communication devices 138-1 to M, all interconnected by a communication network such as local area network (“LAN”) 142 and/or wide area network (“WAN”). The servers can be connected via optional communication lines 146 to the switch 130. As will be appreciated, the other servers 126 can also include a scanner that is normally not connected to the switch 130 or Web server, VoIP software, video call software, voice messaging software, an IP voice server, a fax server, a web server, an email server, and the like. The switch 130 is connected via a plurality of trunks 150 to the Public Switch Telephone Network or PSTN 154 and via link(s) 152 to the second communication devices 138-1 to M. A gateway 158 is positioned between the server 110 and the packet-switched network 162 to process communications passing between the server 110 and the network 162. [0049] FIG. 2 depicts a block diagram of a contact center system determining occupancy of an agent with simultaneous multimodal contacts, in accordance with one embodiment of the present invention. In an embodiment, contacts 203A-D may be sent from customers to the contact center system 204 using a variety of media capabilities. In contrast to the traditional systems where an agent only handled a single contact at a time, FIG. 2 depicts an agent handling multiple simultaneous contacts of various media capabilities or modes. A media capability is a form of media communication and includes a communication channel. Media capabilities may include, but are not limited to, a web capability, a text capability, a voice capability and/or a video capability. The media capabilities may vary in characteristics like bandwidth requirement, the latency of support (i.e., how close to real-time, immediacy, responsiveness, etc.), the level of participation by the agent, usage of other system resources, and so forth. For example, an email capability uses relatively little bandwidth and there may be a moderately high tolerance for latency. In contrast, a voice capability uses relatively more bandwidth and a video capability uses even more bandwidth. Media capabilities may be contacts in the form of emails, web chats, instant messages, phone calls and video calls. In an embodiment, the agent may be able to simultaneously handle one or more of voice, chat, email and/or other media capabilities of contacts.)
Although implied, O'Connor does not expressly disclose the following limitations, which however, are taught by Miller,
wherein when the computerized-method is operating in a cloud computing environment, before operating the CSHAP module the computerized-method is further comprising selecting a tenant from a data store of tenants to operate the CSHAP module for each agent in the data store of agents of the selected tenant. (in at least [0041] the contact center may operate as a hybrid system in which some components of the contact center system are hosted at the contact center premise and other components are hosted remotely (e.g., in a cloud-based environment). The contact center may be deployed in equipment dedicated to the enterprise or third-party service provider, and/or deployed in a remote computing environment such as, for example, a private or public cloud environment with infrastructure for supporting multiple contact centers for multiple enterprises. The various components of the contact center system may also be distributed across various geographic locations and computing environments and not necessarily contained in a single location, computing environment, or even computing device. [0058] The contact center system may also include a call recording server 158 configured to record interactions, including voice calls, text chats, emails, and the like. The recorded interactions may be stored in the mass storage device 126, in addition to other types of data. In some embodiments, the mass storage device includes multiple storage devices (e.g., multiple hard drives or solid state drives). In some embodiments of the present invention, the mass storage device 126 is abstracted as a data storage service, which may be a cloud based service such as Amazon Simple Storage Service (S3) or Google Cloud Storage. [0124] the same underlying quality prediction 172 and feature extraction 174 modules may be used by different tenants in a multi-tenant environment, where individual requests for extracting features or performing predictions may be associated with particular identifiers (e.g., identifiers of particular contact centers and/or enterprises), where the identifiers are used to select the particular prediction models trained for the corresponding tenant. [0127] The various servers may be located on a computing device on-site at the same physical location as the agents of the contact center or may be located off-site (or in the cloud) in a geographically different location, e.g., in a remote data center, connected to the contact center via a network such as the Internet. In addition, some of the servers may be located in a computing device on-site at the contact center while others may be located in a computing device off-site, or servers providing redundant functionality may be provided both via on-site and off-site computing devices to provide greater fault tolerance. In some embodiments of the present invention, functionality provided by servers located on computing devices off-site may be accessed and provided over a virtual private network (VPN) as if such servers were on-site, or the functionality may be provided using a software as a service (SaaS) to provide functionality over the internet using various protocols, such as by exchanging data using encoded in extensible markup language (XML) or JavaScript Object notation (JSON).)
The reason and rationale to combine O'Connor and Miller is the same as recited above.
As per Claim 13 for A system (see at least O'Connor [0036]-[0052]), substantially recite the subject matter of Claim 1 and are rejected based on the same reasoning and rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PO HAN (Max) LEE whose telephone number is (571) 272-3821. The examiner can normally be reached on Monday - Thursday, 9 AM-6:30 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Rutao Wu can be reached on (571) 272-6045. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PO HAN LEE/Primary Examiner, Art Unit 3623