The invention discloses a cloud computing platform server load balancing system and method, so as to overcome the defect that the current static load balancing technology cannot carry out dynamic adjustment according to the real-time condition of a load and the defect that a dynamic load balancing technology needs to additionally occupy system resources. According to the method, when a service request is received, a cloud computing platform selects a target server according to the number of requests which are processed and are being processed by each server in a cluster in recent preset unit time and the number of generated logs, and forwards the service request to the target server for processing. According to the embodiment of the invention, the load balancing can be effectively improved.

Cloud computing platform server load balancing system and method

The invention discloses a medical history transferring system based on voice recognition. The medical history transferring system based on voice recognition is composed of a voice collection unit, a cloud voice analysis and recognition unit, a medical history transferring unit and an output unit. A model is established by the cloud voice analysis and recognition unit through training conducted onvoice and a corresponding text and with the application of a tool kit of an HMM, so that a reasonable application side module is obtained; voice collected by the voice collection unit is sent into theapplication side module to be converted, a result obtained after conversion is transferred in a formatting and standardized mode through the medical history transferring unit, and finally an electronic medical history is output by the output unit. The medical history is transferred through a voice recognition system so that the work efficiency of doctors can be improved, paperless operation of medical history type-in can be achieved in a more environmentally friendly way

Medical history transferring system based on voice recognition

The invention provides a speech engine switching method, a mobile terminal and a server, which relate to the field of mobile communication technologies. The speech engine switching method is applied to the mobile terminal, and comprises the steps of: transmitting a speech engine switching request to the server; receiving instruction information of a currently-available target speech engine fed back by the server; and switching a current speech engine of the mobile terminal to the target speech engine according to the instruction information, and implementing speech service by using the target speech engine. The speech engine switching method solves the problems that speech service is interrupted or a speech assistant cannot be used when the speech engine is abnormal.

Speech engine switching method, mobile terminal and server

The invention discloses a system and a method for voice recognition based on cloud computation. The system comprises a voice data sending module, a voice data processing module, recognized text data sending module, a recognized text data processing module and a result text data sending module, and is characterized in that the voice data sending module is used for generating voice data according to voice of a user and sending the voice data to a voice recognition platform; the voice data processing module is used for acquiring the voice data and distributing a voice recognition server from a voice recognition server cluster according to a first distribution rule; the recognized text data sending module is used for sending recognized text data generated after recognition processing carried out by the current voice recognition server to a result matching platform; the recognized text data processing module is used for acquiring the recognized text data and distributing a result matching server from a result matching server cluster according to a second distribution rule; and the result text data sending module is used for sending result text data acquired after matching processing carried out by the current result matching server to a voice terminal. The system and the method disclosed by the invention enable a cloud terminal to respond to a large number of concurrent voice requests timely.

System and method for voice recognition based on cloud computation

The invention provides a voice quality detection method and device based on real-time conversation and electronic equipment. The voice quality detection method includes the steps that a real-time voice stream while the conversation is in progress is obtained; the obtained real-time voice stream is input into a pre-trained voice activity detection model to extract human voice segments from the real-time voice stream; and a vacant streaming automatic voice recognition resource is invoked to translate voice information in the human voice segments into text information. According to the embodiments of the voice quality detection method and device based on real-time conversation and the electronic equipment, the occupancy rate of the streaming automatic voice recognition resource in voice quality detection can be decreased, and thus the overall cost of voice quality detection is reduced.

Voice quality detection method and device based on real-time conversation and electronic equipment

The invention relates to a voice recognition system and method, in particular to a voice recognition system and method based on cloud. The voice recognition system comprises an intelligent voice input terminal, a load balancing server, a voice identification server cluster and a data base server cluster, wherein the intelligent voice input terminal is connected with the load balancing server, the load balancing server is connected with the voice identification server cluster, and the voice identification server cluster is connected with the data base server cluster. Because a cloud calculation technology is introduced to voice identification application services, the structure and the method can effectively solve the problems that the prior voice identification system is low in identification rate and causes slow concurrent access responses because of being limited in storage and calculation resources and improves comparison operation time, and adaptability of the voice recognition system and method is extended.

Luan Xin

Papers

Voice recognition system and method based on cloud