18 results about "Call volume" patented technology

Aspects of the present disclosure relate to coordinating conversations with an "active talk bar" displayed on an XR device for an artificial reality (XR) environment, whose control bar for voice conversations continuously exists in multiple XR experiences. A user can create a voice call with other users of a plurality of XR devices, end the call, manage participants of the call, adjust call volume, and the like through the active call bar. Users may also view which XR experiences other users within the group are accessing and may invite them to join their XR experience. The active talk bar may continuously exist on the user interface as the user moves between the experience and the application. In addition, no matter where other users are located, the users can continue voice communication in different experiences, that is, the users can participate in the voice communication without being located in the same experience.

A machine learning model (e.g., including a deep learning neural network) with learned embeddings is applied to time series data with associated metadata to obtain predictions of the time series value. For example, a call volume in a period of time may be predicted based on call volume data for a sequence of time bins in a window of preceding time. Time bins may be associated with respective metadata, such as day of week, hour of day, day of month, holiday, part of business cycle, weather, and / or tide. These pieces of metadata may be mapped to embedding vectors using trained embedding functions. The resulting embedding vectors may be input to a neural network along with the corresponding time series data (e.g., call volumes) to make a prediction for future time bin. For example, the prediction may be used to provision servers in a network infrastructure.

This application provides a method, apparatus, and computer-readable storage medium for constructing a call volume prediction model. The method includes: obtaining the total call volume before the transfer from a first call center and the total call volume before the transfer from a second call center; obtaining the transfer ratio of the first call center within a first time period, where the transfer ratio is the ratio of the target call volume to the total call volume before the transfer from the first call center; determining call transfer information from the first call center to the second call center within the first time period based on the total call volume before the transfer from the first call center and the transfer ratio; summing the total call volume before the transfer from the second call center and the call transfer information to reconstruct the first historical call volume information of the second call center, obtaining the reconstructed target historical call volume data; and constructing a target call volume prediction model based on the target historical call volume data. The embodiments of this application result in higher prediction accuracy for the reconstructed call volume prediction model.

Various methods and processes, apparatuses or systems, and media for forecasting of service level indicator (SLI) metrics using deep learning algorithms in order to detect anomalies and to provide accurate alerts to users are disclosed. The method includes: receiving information that relates to an incoming call volume for a particular queue from among a set of queues; analyzing, by using a model, the first information in order to determine a set of SLI metrics that relate to the queue; generating a forecast of one or more of the SLI metrics for the queue; and displaying, via a graphical user interface, information that relates to the forecast.

This application provides an API service management method, apparatus, device, medium, and program product, relating to the field of big data technology. The method comprises: processing API requests corresponding to multiple subsets based on an API service architecture to obtain task execution results; the API service architecture including at least one of an access layer, a control layer, and an execution layer; collecting business data and traffic volume data corresponding to the API requests; obtaining a comprehensive health score and API call volume prediction value for the subsets based on historical data, the business data, and the traffic volume data; and performing differentiated traffic volume allocation for the multiple subsets based on the comprehensive health score and the predicted API call volume value. This application improves API service resource utilization and response efficiency.

The invention relates to the technical field of data transmission, and discloses a service-based wireless Internet of Things terminal adaptive channel competition and scheduling method, which comprises the following steps of: after service data is acquired, matching service priority, processing data volume and resource calling volume; determining a first channel competition coefficient based on the service priority, marking a to-be-selected channel, and calculating a second channel competition coefficient by combining the average data volume and the average call volume of the service data in the to-be-selected channel; and weighting to obtain a comprehensive competition coefficient, selecting a final channel according to the sequence, and selecting a channel of which the transmission frequency is lower than a reference value if the difference is equal. According to the method, service differentiation self-adaptive scheduling is realized, the transmission quality of high-priority services is guaranteed preferentially, the channel conflict probability is effectively reduced, the utilization rate of wireless spectrum and channel resources is improved, and the network transmission efficiency and reliability are optimized.

This application provides a procurement forecasting method, apparatus, device, and computer-readable storage medium. The method includes: determining a first estimated call volume of data resources in the next ordering cycle based on the ordering data, ordering attribute information, and configuration attribute information of each ordering object in the current ordering cycle; determining a second estimated call volume of data resources in the next ordering cycle based on the historical call volume corresponding to each historical ordering cycle within a preset historical time period; determining a target estimated volume based on the first and second estimated call volumes; and determining a predicted procurement volume of data resources based on the target estimated volume, the historical call volume corresponding to each historical ordering cycle, and the already procured amount of data resources. This improves the accuracy of the target estimated volume, thereby improving the accuracy of the predicted procurement volume. Cyclic forecasting according to the ordering cycle avoids waste caused by premature procurement and disruption to normal use by ordering users due to late procurement, thus improving the accuracy of procurement timing.

A method for synchronizing agent staffing and customer call volume in a contact center estimates the number of agents to staff the contact center during a future time period and uses historical data to estimate the number of customer calls expected during the future time period. The method performs a first comparison of the number of agents to the expected customer call volume for the future time period and then determines at least one preferred contact center callback window. The method communicates with the customer to request at least one preferred customer-selected callback time and performs a second comparison to provide the customer with a suggested callback time selected to synchronize the customer call volume with the number of agents, the preferred contact center callback window, and the preferred customer-selected callback time, thereby improving the customer experience and contact center efficiency.

The application relates to the field of visual technology, in particular to a visual doorbell based on face recognition, which comprises a doorbell body, the front of the doorbell body is provided with a camera and a doorbell button, the doorbell body is provided with a doorbell system, the doorbell system comprises a face collection module, the face collection module is arranged on an outdoor unit and is used for capturing a visitor's face image in real time, a local recognition engine, a built-in pre-stored face database, feature extraction and identity matching of the collected image, a dynamic response unit, a differentiated response strategy is triggered according to a recognition result, when the recognition result is that the visitor is an authorized user, the dynamic response unit automatically unlocks the access control and pushes personalized welcome information to an indoor terminal, when the recognition result is that the visitor is an unauthorized person, the dynamic response unit starts real-time alarm and records a visitor behavior video, a cloud collaborative module, data synchronization with the local recognition engine, remote update of the face database and the recognition algorithm are supported, the visual doorbell based on face recognition automatically enhances the call volume and the interface display brightness for the old users, and a voice assistant is activated to guide the children.

The invention relates to the technical field of data processing, and discloses an incoming line voice volume prediction method, device, equipment and medium, which can be applied to the financial and medical fields, and the method comprises the following steps: obtaining historical incoming line voice volume data, carrying out data formatting processing, carrying out holiday attribute identification and feature expansion processing, and obtaining a voice volume feature data set; training and reasoning an incoming line day volume prediction model by using the volume characteristic data set, and performing date and time period volume modeling preparation processing to obtain a time period volume modeling data set; and performing time period distribution prediction on the time period speech volume modeling data set, performing incoming line time period speech volume reduction calculation, and outputting an incoming line speech volume prediction result. In the invention, aiming at the problem that the existing incoming line volume prediction accuracy is low, incoming line time period volume reduction calculation can be carried out according to the calculated time period proportion prediction result, so that the incoming line volume prediction result is output, and the incoming line volume prediction accuracy is improved.

The present invention relates to the technical field of call volume prediction, and in particular to a data-sharing API call volume prediction method, apparatus and device. In the method, a VMD algorithm is used to decompose a time sequence of an original call volume so as to reduce data instability and random fluctuations and enhance a prediction effect of a model; in view of the problems of weak feature extraction capability and low prediction accuracy of a single model, a convolutional neural network (CNN) is combined with long short-term memory (LSTM) to enhance the capability of extracting sequence features and improve sequence prediction accuracy; and an improved particle swarm optimization algorithm is used to enhance the global and local search capabilities of particles at different stages during iteration and enhance the capability of searching for optimal hyperparameters of a CNN-LSTM prediction model, thereby improving prediction accuracy and generalization. The present invention is suitable for prediction tasks of data-sharing API call volume in large-sample scenarios.

The embodiment of the invention discloses an outbound processing method, device and equipment, a computer readable medium and a program product. A specific embodiment of the method comprises the following steps: in response to determining that an outbound call processing stage corresponding to a future time period is not in a cold start stage, generating a predicted outbound call volume and a to-be-processed outbound call volume according to an outbound call index information set corresponding to a current moment; in response to determining that the average idle duration of the seat is greater than the preset average idle duration of the seat, generating outbound adjustment information according to the average idle duration of the seat and the preset average idle duration of the seat; according to the outbound adjustment information, the predicted outbound volume and the to-be-processed outbound volume, generating an actual outbound volume for the future time period; and according to the actual call-out volume, executing call-out processing for the call-out processing stage in a future time period. The implementation mode is related to intelligent customer service, and the outbound call efficiency of the seat can be improved.

A microservices cloud environment features improved workload orchestration based on enhanced runtime performance predictions. The present disclosure provides solutions that can be implemented in a microservices development pipeline (e.g., a continuous integration and continuous delivery (CI / CD) pipeline), with the solutions enabling improved characterization of a true runtime performance of a microservice when deployed in a production, or user-facing, environment. Deployment of a microservice within the production environment is performed more optimally by characterizing the microservice via performance data collected specific to the production environment, and not to any other environment in the CI / CD pipeline. The environment-specific characterization of a microservice is based on predictions that link both workload type (e.g., compute-intensive, memory-intensive, network-intensive) and call volume. According to its characterization, a microservice can be re-assigned, after its initial deployment in a non-optimized node group, to an optimized node group in anticipation of the microservice's predicted peak call time.

This application provides an incoming call volume control method and an electronic device. The method includes: An electronic device determines to start a detection based on a state of a display screen, a state of an optical proximity sensor, and an incoming call situation. During the detection, if target biological feature information is detected by the electronic device, the electronic device may adjust an incoming call volume. Therefore, a convenient and fast incoming call volume adjustment mode is provided, which enables a user to adjust the incoming call volume without operating the electronic device. Moreover, the electronic device starts the detection when a specific condition is satisfied, thereby effectively reducing power consumption while ensuring time relevancy and high efficiency of the detection.

An emergency management system (EMS) generates a likelihood of a 911 service outage for a public safety access point (PSAP). The EMS receives supplemental call data for mobile devices that initiated 911 calls to a public safety answering point (PSAP). The EMS generates a 911 call volume metric for the 911 calls. The EMS receives a number of queries from the PSAP for a portion of the supplemental call data that corresponds to the 911 call volume metric. The EMS tracks the number of queries received from the PSAP. The EMS determines the likelihood of a 911 service outage for the PSAP based on the 911 call volume metric and the number of queries received. The EMS notifies the PSAP of the likelihood of the 911 service outage (e.g., with an outage score).

The application provides a call method and related equipment, and relates to the technical field of terminal equipment. The call method comprises the following steps: in response to a first operation of a first user, displaying a first volume control interface and a second volume control interface, the first volume control interface corresponding to a second user in call with the first user, the second volume control interface corresponding to a third user in call with the first user, the first volume control interface comprising a first control, and the second volume control interface comprising a second control; in response to a second operation of the first user on the first control, adjusting the call volume of the second user, and / or in response to a second operation of the first user on the second control, adjusting the call volume of the third user. By using the method, the electronic equipment can adjust the call volume of one or more specified users in response to user operation during the call, solve the problem that the volume adjustment mode of the existing electronic equipment is too single, and improve the call experience of the user.

The application relates to a method and system for automatically constructing a stress test service model, and belongs to the field of software testing. The method collects and analyzes log information of a tested service by constructing a log collection platform and a log aggregation and analysis platform, obtains hourly service call distribution information and daily service call distribution information of the tested service in a first preset time period, and aggregates and calculates an average call volume model M1 in hourly units. Meanwhile, the highest call volume model M2 and the model M3 with the largest call volume difference are aggregated and calculated in daily units. The model M2, the model M3 and the average call volume model M1 are combined to respectively calculate the service TPS structure with the highest call volume and the service TPS structure with the largest call volume difference, and the TPS proportion of each service is configured in a stress test script. The application enables a tester to obtain an actual production service model, accurately specify the TPS distribution of a corresponding service, and simulate a stress test scene conforming to the actual production situation.

The invention relates to a call prediction method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring basic information, call behavior characteristics and call event characteristic tags of a to-be-called user and call text data corresponding to a to-be-matched product; extracting interest perception features, negative perception features and identity features of the to-be-called user in the call text data based on the call prediction model; according to a call prediction model, performing quantification processing on the interest perception feature, the negative perception feature and the identity feature to obtain a call quantification result, and according to the call quantification result, determining an initial call strategy of the to-be-called user; and performing time prediction on the basic information, the call behavior characteristics and the call event characteristic labels based on a call prediction model to obtain an interval period and call time, and updating the initial call strategy according to the interval period and the call time to obtain a target call strategy. By adopting the method, the accuracy of the call prediction method can be improved.