Smart Service Solutions AI: AI-driven Multimodal Search for Home Appliance Support

[{“box”:0,”content”:”n[if 992 equals=”Open Access”]n

n

n

n

Open Access

nn

n

n[/if 992]n[if 2704 equals=”Yes”]n

n

Notice

nThis is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.n

n[/if 2704]n

n

Year : 2025 [if 2224 equals=””]23/09/2025 at 11:01 AM[/if 2224] | [if 1553 equals=””] Volume : 15 [else] Volume : 15[/if 1553] | [if 424 equals=”Regular Issue”]Issue : [/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] 03 | Page : 27 43

n

n

nn

n

n

n

    By

    n

    [foreach 286]n

    n

    Sunitha Abburu, Sundaresan Poovalingam,

    n t

  • n

    n[/foreach]

    n

n[if 2099 not_equal=”Yes”]n

    [foreach 286] [if 1175 not_equal=””]n t

  1. Advanced Engineering Group, Strategic Technology Group, Infosys, Bangalore, Infosys, Bangalore, Karnataka, Karnataka, India, India

    2. n[/if 1175][/foreach]

n[/if 2099][if 2099 equals=”Yes”][/if 2099]n

n

Abstract

n

n

nThe global home appliance services market is projected to reach USD 1,203.11 billion by 2032, driven by smart household appliances. Essential services like installations, maintenance, and repairs ensure optimal performance and longevity, leading to higher customer satisfaction and loyalty. The service station partner ecosystem is crucial for ongoing support and profitability. However, challenges such as identifying the right manuals, finding relevant parts, and providing accurate instructions must be addressed to enhance operational efficiency and maintain brand reputation. An AI-based solution can streamline the identification of manuals, parts, service stations and troubleshooting steps for home appliances by processing text, voice and images. This AI-based solution integrates Neo4j for data management and Multimodal Search with Retrieval-Augmented Generation (RAG) to enhance technician support for home appliance services. Neo4j efficiently organizes and retrieves comprehensive data of various home appliances, parts, and manuals, service stations, while the RAG system provides precise, contextually relevant instructions. The multimodal RAG system is particularly important as it leverages both text and images from manuals, ensuring technicians receive detailed, accurate guidance with visual aids such as drawings and diagrams. This approach significantly improves service efficiency, customer satisfaction, and operational effectiveness, and increases business. Evaluation metrics such as answer relevancy, context precision, and context recall validate the system’s performance.nn

n

n

n

Keywords: AI, multimodal RAG, Neo4j, large language models (LLMs), multimodal large language models (MLLMs) home appliances, service

n[if 424 equals=”Regular Issue”][This article belongs to Journal of Instrumentation Technology & Innovations ]

n

[/if 424][if 424 equals=”Special Issue”][This article belongs to Special Issue under section in Journal of Instrumentation Technology & Innovations (joiti)][/if 424][if 424 equals=”Conference”]This article belongs to Conference [/if 424]

n

n

n

How to cite this article:
nSunitha Abburu, Sundaresan Poovalingam. [if 2584 equals=”][226 wpautop=0 striphtml=1][else]Smart Service Solutions AI: AI-driven Multimodal Search for Home Appliance Support[/if 2584]. Journal of Instrumentation Technology & Innovations. 28/07/2025; 15(03):27-43.

n

How to cite this URL:
nSunitha Abburu, Sundaresan Poovalingam. [if 2584 equals=”][226 striphtml=1][else]Smart Service Solutions AI: AI-driven Multimodal Search for Home Appliance Support[/if 2584]. Journal of Instrumentation Technology & Innovations. 28/07/2025; 15(03):27-43. Available from: https://journals.stmjournals.com/joiti/article=28/07/2025/view=0

nn

n

n[if 992 equals=”Open Access”]Full Text PDF[/if 992]n

n

n[if 992 not_equal=”Open Access”]n

n

n[/if 992]n

nn

nnn

n[if 379 not_equal=””]nn

Browse Figures

n

n

n[foreach 379]

figures

[/foreach]n

n

n

n[/if 379]

n

n

n

n

n

References n

n[if 1104 equals=””]n

Nabijonova IBQ. Navigating the Complexities of Teaching Foreign Languages in Inclusive Education. Proceedings of the International Scientific-Practical Conference; 2024 May 22; Tashkent. Session IV. Innovative and integrative problems of foreign language development in a multilingual environment. 2024. p. 675-8. doi:10.5281/zenodo.11420636.

Nasir M, Rajkumari Y, Adil M. After-sales service and brand reputation: a case of kitchen appliance industry. Int J Qual Serv Sci. 2024 Aug 27; 16(3): 413–31.

Lin CJ, Chen CC. Factors Influencing Consumer Buying Behavior for Smart Home Technologies.

Yin J, Krotova T. Sustainability strategies in home appliance design. In: VI International Scientific “ ”; ; y , y University of Technologies and Design. p. 241–4. [Ukrainian].

Sandoval RG, Rivadeneira I, Andy Lagos O, Luis Alarcon C, Diego Montenegro C. Bioethical and Medical-Legal Challenges in Multimodal Cancer Treatment: Addressing Misinformation and Informal, Unregistered Advice. SRC/JMHC-357. J Med Healthcare. 2024; 6(10): 2–9.

Ravanelli M, Parcollet T, Bengio Y. The pytorch-kaldi speech recognition toolkit. In ICASSP 2019- 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2019 May 12; 6465–6469.

Sarmah B, Mehta D, Hall B, Rao R, Patel S, Pasquali S. Hybridrag: Integrating knowledge graphs and vector retrieval augmented generation for efficient information extraction. In Proceedings of the 5th ACM International Conference on AI in Finance. 2024 Nov 14; 608–616.

Liang L, Bo Z, Gui Z, Zhu Z, Zhong L, Zhao P, Sun M, Zhang Z, Zhou J, Chen W, Zhang W. Kag: Boosting llms in professional domains via knowledge augmented generation. In Companion Proceedings of the ACM on Web Conference 2025. 2025 May 8; 334–343.

He Z, Yu J, Guo B. Execution time prediction for cypher queries in the neo4j database using a learning approach. Symmetry. 2022 Jan 1; 14(1): 55.

Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G. Learning transferable visual models from natural language supervision. In International conference on machine learning, PmLR. 2021 Jul 1; 8748–8763.

Geng S, Yuan J, Tian Y, Chen Y, Zhang Y. HiCLIP: Contrastive language-image pretraining with hierarchy-aware attention. arXiv preprint arXiv:2303.02995. 2023 Mar 6.

Chen X, Wu Z, Liu X, Pan Z, Liu W, Xie Z, Yu X, Ruan C. Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811. 2025 Jan 29.

Reimers N, Gurevych I. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084. 2019 Aug 27.

Ahmadian A, Ahmed M, Alammar J, Alizadeh M, Alnumay Y, Althammer S, Arkhangorodsky A, Aryabumi V, Aumiller D, Avalos R, Aviv Z. Command A: An Enterprise-Ready Large Language Model. CoRR. 2025 Jan 1.

nn[/if 1104][if 1104 not_equal=””]n

    [foreach 1102]n t

  1. [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]

    2. n[/foreach]

n[/if 1104]

n

nn[if 1114 equals=”Yes”]n

n[/if 1114]

n

n

[if 424 not_equal=””]Regular Issue[else]Published[/if 424] Subscription Original Research

n

n

[if 2146 equals=”Yes”][/if 2146][if 2146 not_equal=”Yes”][/if 2146]n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n[if 1748 not_equal=””]

[else]

[/if 1748]n

n[if 1746 equals=”Retracted”]n

n

n

n

[/if 1746]n[if 4734 not_equal=””]

n

n

n

[/if 4734]n

n

Volume 15
[if 424 equals=”Regular Issue”]Issue[/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] 03
Received 20/06/2025
Accepted 08/07/2025
Published 28/07/2025
Retracted
Publication Time 38 Days

n

n

46

nn

n

Login

n
My IP
n

PlumX Metrics

nn

n

n

n[if 1746 equals=”Retracted”]n

[/if 1746]nnn

nnn”}]