Automatic speech recognition (ASR) technology has been developed relatively mature, and general ASR engines have been widely used in transportation, medical, communication and other industries. However, due to non-independent homology of industry-specific vocabulary in the large-scale training corpus, there comes to low recognition accuracy of industry-specific vocabulary when the general ASR engines are applied to various subdivisions of industries. As compared with 16 kHz audio sampling rate in Internet environment, narrowband low sampling (8 kHz) of call center may result in more significant decrease of recognition accuracy of ASR. In order to improve the accuracy of speech recognition of industry-specific words, this paper proposes a translation optimization technology of ASR based on industry-specific vocabulary. Specifically, first, convolutional neural network model and deep neural network BERT model are used to predict word for corpus text data, and an industry-specific error correction vocabulary is generated. Next, in the production environment, a general ASR engine is used to perform initial transcription of telephone call voice data. Then, the transcribed text is corrected by using the Soft-Masked BERT model combined with the industry-specific error correction vocabulary, thus improving the accuracy of speech recognition. Finally, by using 12345 hotline customer service call voice data for modeling and testing, the proposed translation optimization technology is proved efficient in improving the accuracy of general ASR recognition by 10 percentage points with high error correction speed and good applicability.

With the deepening application of artificial intelligence technology in the field of customer service, telecommunications operators have raised higher standards for the accuracy of AI service knowledge recommendations. To enhance the efficiency and accuracy of knowledge recommendation in telecommunications operators' AI customer service systems, this paper proposed a large-scale customer service knowledge recommendation model driven by intent understanding. Firstly, the synonym and dialogue sequence keyword extraction model was employed to identify key terms in user queries. These keywords were then matched with questions in a standard question bank using semantic similarity comparison techniques to generate the most relevant standard questions. Additionally, a generative agent technology framework was utilized to construct and enrich the standard question bank, enabling the automatic generation of knowledge questions. The extracted standard questions were input into the ChatGLM2-6B large language model, which has been pre-trained and aligned with human preferences, further improving the accuracy of knowledge recommendations. The experimental results show that after the introduction of the standard question bank, the accuracy of the intelligent recommendation system in specific industry knowledge domains significantly increased from 74.8% to 85.9%. Multiple sets of comparative experimental results further validate the effectiveness of the strategy of establishing a standard question bank in improving accuracy. The large model discussed in this paper optimized the intelligent knowledge recommendation for operator AI customer service, providing new ideas and technical support for the knowledge recommendation in telecommunications operators' AI customer service systems. With this model, operators can more effectively understand and respond to customer inquiries, significantly enhancing the customer service experience.