{"id":1154225,"date":"2025-11-06T05:00:00","date_gmt":"2025-11-06T13:00:00","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/?p=1154225"},"modified":"2025-11-05T08:31:51","modified_gmt":"2025-11-05T16:31:51","slug":"when-industry-knowledge-meets-pike-rag-the-innovation-behind-signifys-customer-service-boost","status":"publish","type":"post","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/blog\/when-industry-knowledge-meets-pike-rag-the-innovation-behind-signifys-customer-service-boost\/","title":{"rendered":"When industry knowledge meets PIKE-RAG: The innovation behind Signify\u2019s customer service boost"},"content":{"rendered":"\n
\"Three<\/figure>\n\n\n\n

As a world leader in connected LED lighting products, systems, and services, Signify (formerly Philips Lighting) serves not only everyday consumers but also a large number of professional users who have stringent requirements for technical specifications and engineering compatibility. Faced with thousands of product models, complex component parameters, and technical documentation spanning multiple versions, delivering accurate, professional answers efficiently has become a core challenge for Signify\u2019s knowledge management system.<\/p>\n\n\n\n

To address this challenge, Signify (opens in new tab)<\/span><\/a> collaborated with Microsoft Research Asia<\/a> on a proof-of-concept (PoC) using PIKE-RAG technology<\/a>, integrating it into their upgraded knowledge management system built on Microsoft Azure. The result: a 12% improvement in answer accuracy.<\/p>\n\n\n\n

Challenges of applying RAG in lighting<\/h2>\n\n\n\n

In an era where AI is rapidly transforming how enterprises manage information, Signify recognized the strategic importance of precise and efficient knowledge systems. It adopted large AI models and retrieval-augmented generation (RAG) techniques to better support its wide range of customer inquiries.<\/p>\n\n\n\n

Yet applying RAG to lighting scenarios involving professional users presented unique challenges. Product data spanned multimodal documents, unstructured tables, and complex product parameters, demanding continuous customization that slowed development and limited scalability. Despite improvements through keyword tuning, system optimization, and refined prompts, Signify sought more advanced approaches to further raise accuracy and reliability.<\/p>\n\n\n\n

Seeking to unlock greater value from its knowledge management system, Signify began exploring more suitable technical solutions that are better aligned with their professional use cases. Upon learning that PIKE-RAG had been successfully applied in domains like healthcare and law, significantly improving information accuracy, Signify worked with Microsoft Research Asia on a PoC of PIKE-RAG on Microsoft Azure.<\/p>\n\n\n\n

How PIKE-RAG addressed Signify\u2019s pain points<\/h2>\n\n\n\n

Compared to traditional RAG, PIKE-RAG efficiently retrieves textual information and also understands multimodal content like charts and tables. Its built-in domain adaptation module quickly learns reasoning patterns aligned with specific domains to generate responses that are consistent with engineering contexts. These differentiated advantages stem from PIKE-RAG\u2019s unique approach to understanding and processing professional knowledge. In Signify\u2019s use case, this manifests in three key areas:<\/p>\n\n\n\n

Multimodal document parsing and learning of industry-specific reasoning patterns<\/h3>\n\n\n\n

Signify\u2019s product documentation includes diverse formats, such as nonstandard tables (e.g., comparison charts of voltage ranges under different currents) and circuit diagrams (e.g., driver power limits). Traditional systems often fail to process this information effectively\u2014either ignoring it or extracting disorganized text fragments.<\/p>\n\n\n\n

PIKE-RAG integrates Microsoft Research Asia\u2019s Document Intelligence technology with Microsoft Azure OpenAI models to accurately identify table structures and parse key parameters in circuit diagrams. For example, when a customer service agent queries, \u201cWhat is the output voltage of a specific driver model at 0.15A current,\u201d the system automatically locates the curve chart in the document and infers a range of 40\u201354V based on the current interval\u2014an area where traditional systems frequently err, due to their inability to \u201cread\u201d diagrams.<\/p>\n\n\n\n

End-to-end knowledge loop, eliminating reliance on erroneous data sources<\/h3>\n\n\n\n

Enterprise knowledge systems often integrate data from multiple sources, which can lead to discrepancies, especially when database updates are not fully synchronized. PIKE-RAG captures diverse information sources and establishes citation relationships, supporting complex reasoning tasks that rely on multi-source data.<\/p>\n\n\n\n

In other words, PIKE-RAG can directly use original documents as data sources, efficiently parsing and understanding product manuals and PDF charts. By extracting key information from these text- and graphic-rich documents, PIKE-RAG enables more efficient and trustworthy knowledge retrieval.<\/p>\n\n\n\n

Dynamic task decomposition and multi-hop reasoning for precise answers to complex questions<\/h3>\n\n\n\n

Traditional RAG systems typically follow a \u201cone question, one answer\u201d model and struggle with multi-step reasoning. In Signify\u2019s lighting domain, customer inquiries often involve multi-level associations. PIKE-RAG dynamically decomposes user questions into executable subtasks and solves them through multi-hop reasoning. For example, when asked, \u201cList all bases compatible with the G8 series lamps,\u201d if no document directly provides the answer, PIKE-RAG\u2019s reasoning proceeds as follows:<\/p>\n\n\n\n

Step 1: The system identifies implicit knowledge. One document notes that the G7 and G8 series have identical dimensions and that all bases compatible with the G7 series are also compatible with the G8 series. <\/p>\n\n\n\n

Step 2: Based on this, the system retrieves the base list for the G7 series. <\/p>\n\n\n\n

Step 3: Since the list uses abbreviations, the system searches for a table that maps abbreviations to full names and generates a complete list of G8-compatible bases. <\/p>\n\n\n\n

Through this automated multi-hop reasoning, the system delivers accurate and complete answers.<\/p>\n\n\n\n

\"Figure
Figure 1: PIKE-RAG orchestrates and integrates heterogeneous information in multi-source and multimodal environments. <\/figcaption><\/figure>\n\n\n\n

Testing showed that the PIKE-RAG-powered knowledge management platform provided a significant advantage. It achieved a 12% improvement in performance compared with the original system.<\/p>\n\n\n\n

These results were achieved without any question-specific customization, only algorithmic optimization, demonstrating precise knowledge matching and generation. As the system continues to learn and integrate Signify\u2019s proprietary knowledge, accuracy is expected to improve further.<\/p>\n\n\n\n

\u201cIn the PoC for our product specification insight tool, PIKE-RAG helped us significantly improve the original system\u2019s performance. This will enhance overall customer satisfaction. We\u2019re currently evaluating PIKE-RAG\u2019s application path from multiple angles, including technical implementation, cost control, and future adaptability, and we look forward to deepening our collaboration with Microsoft Research Asia to drive further innovation,\u201d said Haitao Liu, head of Signify Research China.<\/p>\n\n\n\n

\u201cIt\u2019s also worth noting that the researchers at Microsoft Research Asia demonstrated strong industry knowledge and rigorous scientific methodology. They proactively studied and analyzed the issues, tracing and clarifying the root causes of our issues to make PIKE-RAG better suited to Signify\u2019s real-world needs.\u201d<\/p>\n\n\n\n

Beyond lighting: Generalization across industries<\/h2>\n\n\n\n

In Signify\u2019s successful test, PIKE-RAG demonstrated strong generalization capabilities in complex industrial scenarios, enabling rapid cross-domain adaptation. Its three core strengths are:<\/p>\n\n\n\n