看见音乐

Baidao’s data empowers to see music and creates a new intelligent customer service experience.

Customer background

KANJIAN | Kanjian Music was founded in 2012. It is committed to using technology to build a new digital infrastructure for the music industry, reshaping the efficiency chain from creation to application. It provides a digital platform for the music industry that integrates music creation, protection, distribution, management, and commercial application. It uses technology to provide a new generation of architectural presets for the music industry, accelerates the digital upgrade of the industry, helps ecological partners access the future, releases creative value, and promotes the sustainable development of the creative industry.

As of 2021, the platform facilitates the global transfer of over 20 million music and sound assets worldwide, covering the digital content assets of over 1 million musicians, more than 100,000 companies and institutions globally. It empowers creators to achieve autonomous control of their content assets, as well as decentralized distribution and settlement capabilities across global channels. It intelligently connects to over 300 major music channels worldwide, and intelligently distributes and supplies music to more than 36 types of industries and scenarios globally, while also providing digital operation solutions.

Business requirements and challenges

With the growth of See Music’s business, its customer service needs also increase accordingly. The Contact Center is an important way for many enterprises to interact with their customers. However, ensuring a perfect user experience brings more challenges to enterprises.

Some common business challenges faced by the Kanjian Music Call Center include: meeting the growing customer demands, reducing the high operating costs, improving customer satisfaction, etc. AI and Machine Learning (ML) offer significant opportunities for improvement in call centers.

With the rapid development of AI technology, the application of artificial intelligence in various industries is becoming more and more widespread. The music industry is no exception. More and more music companies are starting to use Contact Center Artificial Intelligence (CCAI) to enhance the customer experience and reduce operating costs.

Kanjian Music hopes to build an intelligent CCAI system. This system can meet routine needs such as automatically replying to common questions, recommending music according to customers’ preferences, and handling customer complaints.

solution

The overall goal of this plan is to use Google Cloud’s Dialogflow, Machine Learning, and AI products to build an intelligent Contact Center for the music industry, meeting customer needs and improving customer service efficiency.

This solution will use Dialogflow to build a conversational AI bot, which is used to recommend music based on users’ preferences, handle common customer questions and simple needs. As the project gradually expands, in the future, this solution will also use AI products such as Google Cloud Speech-to-Text and Natural Language API for functions like speech recognition and natural language understanding, in order to further enhance the understanding ability and processing efficiency of the AI bot. The introduction of AI products can identify customer emotions and concerns by analyzing call records and customer feedback. These insights can be used to guide agent training, personalize interactions, and address any issues that may lead to customer dissatisfaction. In addition, ML can be used to predict customer churn and identify potential risks, enabling the call center to take proactive actions to retain customers and improve their experience.

By introducing ML, various tasks can be automated to help achieve the goals of reducing operational costs and enhancing the customer experience. For common needs such as recommending favorite music to users, it is no longer practical to rely on manual services. Technical means such as AI and ML must be used for support.

Google partner Baidao Data helped the IT team of KanJian Music conduct a detailed analysis of the cost investment plan and optimization solutions for the cloud – based business of Google Cloud Technology. At the same time, it provided very good answers and business solutions to various problems and requirements. During the transformation process, some Google Cloud products were used to assist KanJian Music in designing the architecture of the call center, improving the old architecture, enabling customers to lean towards automated management on the call center platform, and maintaining the stable operation of the system. Its professional and meticulous service support left a deep impression on customers.

The core of building a call center with Dialogflow

Dialogflow is a natural language understanding (NLU) platform under Google Cloud, which can be used to build applications such as chatbots and intelligent assistants. It can help enterprises build natural and smooth conversational interfaces. Dialogflow has powerful features, including:

• Intent recognition: Identify the user’s intent and map it to the corresponding conversation flow.
• Entity recognition: Identify key information in conversations, such as names, dates, times, etc.
• Context understanding: Remember the conversation history and provide more accurate responses based on the context.

The AI robot of the See Music Call Center is implemented in the following ways:

• Collect and organize data: Collect data on songs that users have listened to multiple times or “liked”.
• Build intents and entities: Use Dialogflow to define intents and entities and train based on data.
• Design the dialogue flow: Design the dialogue flow, match it according to intents and entities, and achieve intelligent conversations for AI robots.
• Data matching: By analyzing features such as the style and danceability of the songs that users like, match song data that users may like and recommend the data to users.

In addition to Dialogflow, Google Cloud also offers a range of AI products, such as:

• Google Cloud Speech-to-Text：Convert speech to text.
• Google Cloud Text-to-Speech：Convert text to speech.
• Google Cloud Translation：Support translation in multiple languages.

In future system iterations, these AI products can be used together with Dialogflow to build a more powerful CCAI solution for See Music.

See Music built a conversational interface using Dialogflow and trained models to recognize user intents and entities. Then, they integrated Dialogflow with Google Cloud Cloud Functions to call the trained models via REST/loading the model.

The architecture diagram is as follows:

Building an Enterprise-Level Data Warehouse with BigQuery

BigQuery is a powerful and comprehensive cloud – native data warehouse and analytics engine of Google Cloud. It is a serverless data analytics solution where users don’t need to manage the infrastructure and configuration, and can focus solely on data and analysis. At the same time, BigQuery has the ability to scale elastically, automatically adapting to large – scale datasets and concurrent queries, ensuring high – performance and low – latency query results. BigQuery utilizes distributed computing and column – based storage technologies, which endows it with excellent query performance. It can handle billions or even trillions of rows of data and return query results within seconds or even sub – seconds, accelerating the data analysis and decision – making process. Moreover, BigQuery can be easily and tightly integrated with other Google Cloud services and tools, such as Google Cloud Storage, Dataproc, Dataflow, etc. Data can be effortlessly imported into BigQuery for analysis, and query results can be exported to other services for further processing. 

In the past, the storage of data used for music analysis was extremely messy. Data was stored in various ways, such as local machine rooms and MySQL databases. This led to the need to design multiple data pipelines for data analysis, making the entire data analysis platform extremely bloated. After using BigQuery, Kan Jian Music can have a unified data warehouse, and the design of data processing pipelines will be more streamlined. Moreover, with the powerful query performance of BigQuery, data can be pre – processed quickly, shortening the data cleaning cycle. 

Some analytical data does not require complex processing and can be directly applied to data reports after being processed by BigQuery. Combining BigQuery with Looker Studio can quickly generate reports and obtain some preliminary information in advance.

Use the elastic scaling capabilities of the cloud to build a powerful and stable display platform.

With the elastic scaling capabilities of Google Cloud, it provides a highly flexible resource management and scalability for the data display platform of KanJian Music, enabling it to adapt to the constantly changing display scale and traffic demands. The display platform can automatically adjust the scale and capacity of resources according to actual needs. This means that during the peak period of viewing display reports, the platform can rapidly expand to ensure stable performance and user experience; while during the off-peak period, the platform can automatically reduce resources to save costs. This flexibility not only provides efficient resource utilization but also guarantees the stability and reliability of the data display platform.

Google Cloud also provides advanced security and reliability guarantees. Data is backed up and redundantly stored in the cloud to prevent data loss and corruption. At the same time, the security measures and access control mechanisms of Google Cloud ensure that the content of the display platform and user data are fully protected.

Use the product

• Compute Engine
• Dialogflow
• Vertex AI
• Cloud Functions
• Google Cloud Storage
• BigQuery

Customer benefits

Note: [All the following statistical data are from the statistical results of the customer background]

• Shorten call handling time and waiting time. ML – powered chatbots and virtual assistants can significantly reduce call handling time by dealing with simple questions and requests and making personalized recommendations based on users’ historical listened songs.
• After using BigQuery, See Music has a unified data warehouse, which makes data management more standardized.
• Improve the network connection stability by 20% through Google’s high-quality dedicated network.
• Scale on demand according to the business development speed, achieve zero latency in hardware procurement, configuration, and maintenance, and also save 30% of the labor cost.