Voice-based electric power customer service telephone traffic quality inspection system
A customer service and recording server technology, applied in the field of power customer service traffic quality inspection system, to avoid one-sidedness, reduce quantity, and objective system quality inspection
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0022] A voice-based power customer service traffic quality inspection system is divided into four modules, namely a server, a voice analysis system, a database, and an intelligent quality inspection system. figure 1 It is a structural schematic diagram of the voice-based power customer service traffic quality inspection system of the present invention.
[0023] The server is divided into recording server, index server and retrieval server. The recording server is the storage address of all call recordings generated by the customer service center of the power supply enterprise when serving customers, and is associated with the marketing work order to provide an effective data source for quality inspection. The recorded data is transmitted to the index building server cluster through the network, and the index server generates a corresponding index file for the input voice. The index file contains all the information in the voice and stores it in the retrieval server cluster. ...
Embodiment 2
[0029] The speech analysis system includes speech translation, scene segmentation, keyword recognition, emotion recognition, etc. Through voice translation, the acquired recording audio data is converted into structured text format data, and after being translated into structured text information data, it is conducive to recording positioning, problem detection, and convenient retrieval. Speech translation includes several steps such as preprocessing, feature extraction, and template training.
[0030] Specific as image 3 A schematic diagram of the speech translation module of the present invention is shown.
[0031]Preprocessing is usually divided into four steps: filtering, pre-emphasis, framing processing, and endpoint detection. Preprocessing is the preliminary processing of the speech signal. Since the performance of the speech recognition system is closely related to the external environment, noise interference, reverberation interference, etc. will have an unpredicta...
Embodiment 3
[0039] Intelligent voice quality inspection includes five steps: quality inspection setting, voice import, intelligent quality inspection, result display, and re-inspection scoring.
[0040] The specific process is as Figure 4 , as shown in the intelligent voice quality inspection flow chart of the present invention.
[0041] Quality inspection settings include rule settings and scoring settings. Quality inspection settings include:
[0042] (1) Keywords: Set keywords that require special attention during the quality inspection process. For example, in order to judge whether the customer service personnel speak politely during the call, you can set words such as "hello", "thank you", and "please" as keywords , forming a thesaurus. It is also possible to add words that are forbidden to be used by customer service staff when communicating with users, such as "don't know", "regardless", "complaint", etc. Through the quality inspection statistics of the frequency of keywords i...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More - R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com



