A resilient network call management framework that automatically detects slow Application Programming Interfaces (APIs) at downstream dependent applications based on constantly measuring and monitoring the response time coming from such applications. Once a slow API has been identified, the framework provides the capability to temporarily shut down (otherwise referred to herein as, “short-circuit”) the network call path associated therewith until the monitoring determines that the response time is back to an acceptable level (i.e., returns to a healthy status). Implemented in conjunction with a shared services server hosting different service applications, processing by the framework may be limited to only those service applications or network calls deemed non-critical, such that, critical service applications or network calls are not subjected to being shut down regardless of response time.

A computer-implemented method of for optimizing cellular network performance including identifying a plurality of voice call records stored on an application server in a first type of cellular network. The method includes analyzing call data associated with the plurality of voice call records, and identifying a set of fall back voice call records. The call data for each voice call record of the set of fall back voice call records includes a fall back indicator indicating that each voice call was initiated using a second type of cellular network. The method includes analyzing cause codes in the call data associated with the set of fall back voice call records and determining, based on the cause codes, a value for at least one KPI associated with the second type of cellular network.

A method for call processing and related products are provided. The method is applicable to an electronic device. The method includes the following. A movement speed of the electronic device is obtained, in response to the electronic device entering a call mode. A movement road section of the electronic device is determined, in response to the movement speed being higher than a first threshold. A target communication quality value of the electronic device is obtained according to the movement speed and the movement road section. Connect to a preset wireless network, in response to the target communication quality value being less than a second threshold, and a call is maintained with a call peer through the preset wireless network.

Disclosed is a method of determining call quality for a contact centre. A call is initialised between a customer agent and a contact centre agent, with the customer agent connecting to the call at a point of presence having a selectable geographic location. Monitoring information is received, for the call, measured at the customer agent, the contact centre agent and a contact centre service provider connecting the call between the customer agent and the contact centre agent. Quality of the call is determined from the monitoring information collected from the customer agent, the contact centre agent and the contact centre service provider.

A communication system for processing a call includes control logic and at least one machine learning model generating call classifiers from outputs of an audio signal processor and a natural language processor operated on the call. Heuristic logic transforms the call classifiers into weighted sub-metrics for the call, and aggregate normalized Gaussian logic transforms the weighted sub-metrics into a metric control that may be applied as a feedback signal to adapt the operation of the control logic. The control logic in turn may adapt the behavior of an agent, automated voice attendant, or a template utilized in a call flow.

A communication server detects a first communication request from a first caller device to a second caller device. The communication server detects a second communication request from the second caller device to the first caller device. The first communication request and the second communication request both occur within a threshold time period. The communication server establishes, without additional input from the first caller device and the second caller device, an active session in response to the first communication request. The active session is established between the first caller device and the second caller device. The communication server dismisses the second communication request.

A system and method for calculating a journey excellence score (JES) for a customer journey in a contact center, including, during a training phase: representing each of a plurality of tagged customer journeys by a list of attributes and a value associated with each of the attributes, wherein each of the tagged customer journeys is tagged with respect to a dissatisfaction indicator, and training a model using the plurality of tagged customer journeys, based on the associated values and tags, to generate model weights; and at runtime: obtaining the customer journey; representing the customer journey by the list of attributes and a value associated to each of the attributes; and calculating the JES for the customer journey by applying the model weights to the associated values.

A computer-implemented method includes generating at least one call detail record for each call initiated on a communication network, aggregating the call detail records generated over a predetermined time period to provide an aggregated call detail record, and calculating a call set up failure rate for the calls from the aggregated call detail record, wherein the call set up failure rate is a measure of the amount of calls that failed prior to ringing at a called party's device. The computer-implemented method further includes adjusting parameters of the communication network when the call set up failure rate is above a threshold.

A device, system and method for transmitting notifications based on indications of effectiveness for previous notifications is provided. A public-safety answering point (PSAP) device transmits, to first communication devices, a first notification of a given type, associated with a first public-safety incident. The PSAP device, subsequent to transmitting the first notification, tracks indications of effectiveness of the first notification determined from one or more of: PSAP call traffic; locations and/or responses of the first communication devices and/or PSAP-related data retrieved from one or more servers external or internal to a PSAP system. The PSAP device transmits, to second communication devices, a second notification of the given type, the second notification associated with a second public-safety incident; one or more of the second notification and transmitting of the second notification being modified, relative to the first notification, based on the one or more indications of effectiveness.

A computer-implemented method of for optimizing cellular network performance including identifying a plurality of voice call records stored on an application server in a first type of cellular network. The method includes analyzing call data associated with the plurality of voice call records, and identifying a set of fall back voice call records. The call data for each voice call record of the set of fall back voice call records includes a fall back indicator indicating that each voice call was initiated using a second type of cellular network. The method includes analyzing cause codes in the call data associated with the set of fall back voice call records and determining, based on the cause codes, a value for at least one KPI associated with the second type of cellular network.