Abstract: Techniques are described for performing estimations based on image analysis. In some implementations, one or more images may be received of at least portion(s) of a physical object, such as a vehicle. The image(s) may show damage that has occurred to the portion(s) of the physical object, such as damage caused by an accident. The image(s) may be transmitted to an estimation engine that performs pre-processing operation(s) on the image(s), such as operation(s) to excerpt one or more portion(s) of the image(s) for subsequent analysis. The image(s), and/or the pre-processed image(s), may be provided to an image analysis service, which may analyze the image(s) and return component state information that describes a state (e.g., damage extent) of the portion(s) of the physical object shown in the image(s). Based on the component state information, the estimation engine may determine a cost estimate to repair and/or replace damaged component(s).

Abstract: Techniques are described for generating metrics about an individual's experience. One of the method describes providing, by at least one processor, the session record as input to at least one computer-processable model that determines, based on the session record, at least one metric for the service session, the at least one model having been trained, using machine learning and based at least partly on survey data for previous service sessions, to provide the at least one metric associated with the individual's experience. The method includes associating, by at least one processor, the metric of the individual's experience with the individual. The method also includes communicating, by at least one processor, the at least one metric for presentation through a user interface of a computing device.

Abstract: Techniques are described for performing estimations based on image analysis. In some implementations, one or more images may be received of at least portion(s) of a physical object, such as a vehicle. The image(s) may show damage that has occurred to the portion(s) of the physical object, such as damage caused by an accident. The image(s) may be transmitted to an estimation engine that performs pre-processing operation(s) on the image(s), such as operation(s) to excerpt one or more portion(s) of the image(s) for subsequent analysis. The image(s), and/or the pre-processed image(s), may be provided to an image analysis service, which may analyze the image(s) and return component state information that describes a state (e.g., damage extent) of the portion(s) of the physical object shown in the image(s). Based on the component state information, the estimation engine may determine a cost estimate to repair and/or replace damaged component(s).

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data from previous service sessions between service representative(s) and individual(s). Training data may include, for previous service session(s), a session record (e.g., audio record) of the session and a set of survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that is a combination of a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data such as communications from previous service sessions between service representative(s) and individual(s), and survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that combines a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network. Individuals can be clustered according to the metric(s) and/or other factors, and the cluster(s) can be employed for routing incoming service requests.

Abstract: Techniques are described for generating metrics about an individual's experience. One of the method describes providing, by at least one processor, the session record as input to at least one computer-processable model that determines, based on the session record, at least one metric for the service session, the at least one model having been trained, using machine learning and based at least partly on survey data for previous service sessions, to provide the at least one metric associated with the individual's experience. The method includes associating, by at least one processor, the metric of the individual's experience with the individual. The method also includes communicating, by at least one processor, the at least one metric for presentation through a user interface of a computing device.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data from previous service sessions between service representative(s) and individual(s). Training data may include, for previous service session(s), a session record (e.g., audio record) of the session and a set of survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that is a combination of a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for coordinating callers with customer service representatives. One of the methods includes in response to receiving identification information from a caller, selecting a virtual machine from a plurality of virtual machines, the virtual machine configured to generate a virtual user interface for an application executing on the virtual machine. The method includes populating the virtual user interface with information about the caller based on the received identification information. The method includes sharing the virtual user interface with an application executing on a computer of a customer service representative. The method includes connecting the caller with the customer service representative.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media are used for coordinating callers with customer service representatives. One of the methods includes identifying a number of callers. The method also includes dynamically adjusting a number of customer service representatives based on the number of callers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a coordinating callers with customer service representatives is described. One of the methods includes identifying a number of callers. The method also includes dynamically adjusting a number of customer service representatives based on the number of callers.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data such as communications from previous service sessions between service representative(s) and individual(s), and survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that combines a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network. Individuals can be clustered according to the metric(s) and/or other factors, and the cluster(s) can be employed for routing incoming service requests.

Abstract: A method includes in response to receiving identification information from a caller, selecting a virtual machine from a plurality of virtual machines, the virtual machine configured to generate a virtual user interface for an application executing on the virtual machine. The method includes populating the virtual user interface with information about the caller based on the received identification information. The method includes sharing the virtual user interface with an application executing on a computer of a customer service representative. The method includes connecting the caller with the customer service representative.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media are used for coordinating callers with customer service representatives. One of the methods includes identifying a number of callers. The method also includes dynamically adjusting a number of customer service representatives based on the number of callers.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data from previous service sessions between service representative(s) and individual(s). Training data may include, for previous service session(s), a session record (e.g., audio record) of the session and a set of survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that is a combination of a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network.