mosaicdatascience.com Open in urlscan Pro
162.159.135.42  Public Scan

Form analysis
1 forms found in the DOM

POST

<form enctype="multipart/form-data" method="post" class="frm-show-form  frm_pro_form " id="form_footercontact" data-token="be22ec5735fa6a8464b00cb0fa371b8d">
  <div class="frm_form_fields ">
    <fieldset>
      <legend class="frm_screen_reader">Have questions? Schedule a meeting below</legend>
      <h3 class="frm_form_title">Have questions? Schedule a meeting below</h3>
      <div class="frm_fields_container">
        <input type="hidden" name="frm_action" value="create">
        <input type="hidden" name="form_id" value="14">
        <input type="hidden" name="frm_hide_fields_14" id="frm_hide_fields_14" value="">
        <input type="hidden" name="form_key" value="footercontact">
        <input type="hidden" name="item_meta[0]" value="">
        <input type="hidden" id="frm_submit_entry_14" name="frm_submit_entry_14" value="ab48b5f6cb"><input type="hidden" name="_wp_http_referer" value="/2023/02/10/ai-enabled-voice-search-assistant-for-operating-manuals/">
        <div id="frm_field_129_container" class="frm_form_field form-field  frm_top_container">
          <div id="field_m84dl_label" class="frm_primary_label">Name <span class="frm_required" aria-hidden="true"></span>
          </div>
          <fieldset aria-labelledby="field_m84dl_label">
            <legend class="frm_screen_reader frm_hidden"> Name </legend>
            <div class="frm_combo_inputs_container" id="frm_combo_inputs_container_129" data-name-layout="first_last">
              <div id="frm_field_129-first_container" class="frm_form_field form-field frm_form_subfield-first  frm6" data-sub-field-name="first">
                <label for="field_m84dl_first" class="frm_screen_reader frm_hidden"> First </label>
                <input type="text" id="field_m84dl_first" value="" name="item_meta[129][first]" data-invmsg="Name is invalid" aria-invalid="false">
                <div class="frm_description" id="frm_field_129_first_desc">First</div>
              </div>
              <div id="frm_field_129-last_container" class="frm_form_field form-field frm_form_subfield-last  frm6" data-sub-field-name="last">
                <label for="field_m84dl_last" class="frm_screen_reader frm_hidden"> Last </label>
                <input type="text" id="field_m84dl_last" value="" name="item_meta[129][last]" data-invmsg="Name is invalid" aria-invalid="false">
                <div class="frm_description" id="frm_field_129_last_desc">Last</div>
              </div>
            </div>
          </fieldset>
        </div>
        <div id="frm_field_121_container" class="frm_form_field form-field  frm_required_field frm_top_container frm12 frm_first">
          <label for="field_p6sje" id="field_p6sje_label" class="frm_primary_label">Email <span class="frm_required" aria-hidden="true">*</span>
          </label>
          <input type="email" id="field_p6sje" name="item_meta[121]" value="" data-reqmsg="This field cannot be blank." aria-required="true" data-invmsg="Email is invalid" aria-invalid="false">
        </div>
        <div id="frm_field_130_container" class="frm_form_field form-field  frm_required_field frm_top_container frm6 frm_first">
          <label for="field_hx5r8" id="field_hx5r8_label" class="frm_primary_label">Title <span class="frm_required" aria-hidden="true">*</span>
          </label>
          <input type="text" id="field_hx5r8" name="item_meta[130]" value="" data-reqmsg="This field cannot be blank." aria-required="true" data-invmsg="Text is invalid" aria-invalid="false">
        </div>
        <div id="frm_field_131_container" class="frm_form_field form-field  frm_required_field frm_top_container frm6">
          <label for="field_jnvwq" id="field_jnvwq_label" class="frm_primary_label">Company <span class="frm_required" aria-hidden="true">*</span>
          </label>
          <input type="text" id="field_jnvwq" name="item_meta[131]" value="" data-reqmsg="This field cannot be blank." aria-required="true" data-invmsg="Text is invalid" aria-invalid="false">
        </div>
        <div id="frm_field_123_container" class="frm_form_field form-field  frm_top_container frm12 frm_first">
          <label for="field_ngfmw" id="field_ngfmw_label" class="frm_primary_label">Comments <span class="frm_required" aria-hidden="true"></span>
          </label>
          <textarea data-auto-grow="1" name="item_meta[123]" id="field_ngfmw" rows="1" data-invmsg="Paragraph is invalid" aria-invalid="false"></textarea>
        </div>
        <div id="frm_field_132_container" class="frm_form_field form-field  frm_none_container">
          <label for="g-recaptcha-response" id="field_v3w2m_label" class="frm_primary_label">Captcha <span class="frm_required" aria-hidden="true"></span>
          </label>
          <div id="field_v3w2m" class="frm-g-recaptcha" data-sitekey="6Lf6-SgkAAAAAOYRuRAuNorts9UL3K7uBZQk09ux" data-size="invisible" data-theme="light"></div>
        </div>
        <input type="hidden" name="item_key" value="">
        <div class="frm__6523f96540935">
          <label for="frm_email_14"> If you are human, leave this field blank. </label>
          <input id="frm_email_14" type="email" class="frm_verify" name="frm__6523f96540935" value="">
        </div>
        <input name="frm_state" type="hidden" value="FQi6/KGZhH4jGExf/L8yAX34Laeqq+Fbfroi5yODCiI=">
        <div class="frm_submit">
          <button class="frm_button_submit frm_final_submit" type="submit" formnovalidate="formnovalidate">Submit</button>
        </div>
      </div>
    </fieldset>
  </div>
  <p style="display: none !important;"><label>Δ<textarea name="ak_hp_textarea" cols="45" rows="8" maxlength="100"></textarea></label><input type="hidden" id="ak_js_1" name="ak_js" value="202">
    <script type="rocketlazyloadscript">document.getElementById( "ak_js_1" ).setAttribute( "value", ( new Date() ).getTime() );</script>
  </p>
</form>

Text Content

Toggle Navigation
 * Meet Mosaic
   * Customers
   * Who We Are
   * MDS Canada
   * NewsStay informed and inspired with the latest updates from Mosaic Data
     Science – your gateway to the dynamic world of AI and Machine Learning.
     Read up on our breakthroughs, milestones, and advancements, where we offer
     glimpses into our innovations, collaborations, and the ever-evolving
     landscape of AI. From new partnerships that redefine possibilities to
     groundbreaking discoveries that shape industries, our Company News keeps
     you connected to the pulse of progress.
   * More
     * Tools
     * Sustainability Statement
     * Employment
     * BlogsOur blogs are your gateway to a world of thought-provoking articles
       that navigate the complexities of AI, machine learning, and data-driven
       strategies. Authored by our team of data science experts, each blog post
       unveils a tapestry of knowledge, demystifying intricate concepts,
       unraveling industry trends, and offering fresh perspectives on the
       ever-evolving landscape of technology.
 * Strategy & Execution Services
   * Strategy
     * AI Transformation Consulting
     * Gen AI Readiness Assessment
     * Explainable AI & Bias Auditing
   * Execution
     * Rent a Data Scientist™
     * AI & ML Project Support
     * Mosaic Data Science AWS AI Services
 * Industries Served
   * Professional & Financial Services
   * Retail
   * CPG
   * Manufacturing
   * Pharma & BioTech
   * Oil & Gas
   * Utilities
   * Transportation & Logistics
   * Aviation
   * Healthcare & HealthTech
 * Capabilities
   * Machine Learning
     * NLP
     * Computer Vision
   * Artificial Intelligence
     * Neural Search
     * AI for IoT
   * Optimization
     * Scheduling
     * Supply Chain
   * Success Stories
     * Case StudiesSee our AI/ML deployments in action through our detailed case
       studies. Explore a curated selection of real-world scenarios, each
       meticulously dissected to showcase the transformative power of AI and
       machine learning. Delve into the strategies that drive efficiency,
       unearth hidden opportunities, and illuminate the path to informed
       decision-making. As you navigate through our case studies, you’ll witness
       firsthand how Mosaic Data Science translates data into actionable
       insights, propelling businesses into a future of success.
     * White PapersMosaic Data Science’s whitepapers are authored by our AI/ML
       experts, diving into groundbreaking research, meticulous analysis, and
       forward-thinking in AI and machine learning. Whether you’re seeking to
       comprehend the latest trends, demystify intricate technologies, or grasp
       the far-reaching implications of these innovations, our whitepapers are
       your gateway to informed decision-making.
 * Neural Search
 * Rent a Data Scientist™
 * Contact Us


AI-ENABLED VOICE SEARCH ASSISTANT FOR OPERATING MANUALS

PUBLISHED BY SEL GEROSA ON FEBRUARY 10, 2023FEBRUARY 10, 2023



SUMMARY

Mosaic built an AI-enabled voice search assistant using deep learning and
state-of-the-art language models to intelligently parse complex mechanical
operation manuals and return the desired search results.

TAKE OUR CONTENT TO GO



INTRODUCTION

With the expanding dominance of smart devices, voice search has been steadily
growing. Voice is changing how people interact with technology, especially with
the increasing preference to talk with assistant devices such as Alexa. Consider
a recent poll that states 68% of voice assistant users agree personal assistants
make their lives easier. Given this, it is not surprising that many believe
voice search will one day dominate the online search space. 

Businesses that produce complex mechanical products for their customers often
have to design and deliver a complex operating manual. If you have ever
purchased a new washing machine or dishwasher, you can sympathize with the page
thumbing through the accompanying documentation. Now, if you are a multinational
manufacturing organization operating complex machinery with technical manuals
that can run into the thousands – or even tens of thousands – of pages, the
problem grows in scale, and the need for a more streamlined process becomes
increasingly critical.  

The rise of transformer-based NLP architectures and Large Language Models allows
producers to build intelligent document processing solutions that scan lengthy
documents and return results to users’ questions. There is a unique combination
of art and science that must go into an intelligent document solution, as the
architect needs to not only understand how NLP algorithms work, but which models
are right for the task at hand as requirements tend to change based on the
desired outputs. That doesn’t even factor in the training pipelines, MLOPs, and
user acceptance required to have users trust the AI. Good thing there are
organizations like Mosaic Data Science that specialize in making these solutions
a reality for our customers!  

The Transformer model architecture. Input embeddings are passed to an attention
layer which are then passed to a feedforward layer. The output of the encoder is
passed to the decoder, which also includes an encoder-decoder attention layer.

In the following case study, Mosaic built a custom voice search solution using
deep learning and advanced language modeling techniques to improve a
manufacturing company’s customer experience with operator manual search. Mosaic
developed the search technology to be unique to the customer, offering more
benefits such as higher performance and more trustworthy results compared to an
off-the-shelf tool.  

PROBLEM  

Businesses that operate complex machinery spend significant time skimming
through hundreds or thousands of pages in engineering manuals, warranty books,
etc., searching for answers. A global industrial manufacturing firm noticed this
pain point and wanted to deliver a better customer experience by building a
digital assistant solution to help customers operate and maintain their
industrial power generation equipment. The idea was to enable users to query the
digital assistant through spoken commands and receive visual and verbal
responses to their search.  

The company turned to Mosaic Data Science for hands-on, flexible support in
building the underlying document processing and natural language search software
that would enable the company to make its technical manuals searchable and make
the digital assistant a reality. Throughout the project, Mosaic was a true
partner, offering data scientists with specific expertise in NLP techniques to
match the company’s specific needs.  

DEVELOPMENT PROCESS 

Mosaic laid out a design and development plan that is still ongoing, but thanks
to Mosaic’s deep learning expertise, the company has a working implementation
that they are already using today. The project was broken up into three
phases.  

PHASE 1  

The first part of the project focused on extracting the content of documents and
understanding the structure and relationships among the different data elements
in the documents. Mosaic’s data scientists leveraged cloud OCR tools and modern
NLP techniques for parsing technical documents and operation manuals. It was
critical to leverage the full spectrum of image processing, text analytics, and
deep learning to extract the unstructured information properly.  

Subcomponents of Intelligent Document Search | AI-Enabled Voice Search Assistant

Given the customer’s needs, the standard extraction and keyword-based indexing
of text elements were insufficient to meet requirements. The different data
elements required additional metadata to be properly contextualized. For
example, the same text could be shown in multiple sections, and the only
differentiator between the two pieces of text was the section hierarchy above
the text, making tracking of the section hierarchy critical. Non-textual
elements, such as images and tables, needed to be matched to relevant
descriptive text within these elements and in nearby document text. 

Mosaic leveraged NLP techniques to develop custom algorithms tailored to our
customer needs to parse text and expand the metadata associated with searchable
data elements by, e.g., tracking of full section hierarchy, identification of
captions, or description of images and tables in nearby text within the
appropriate section. 

 Sample of Document Content Extraction | AI-Enabled Voice Search Assistant

PHASE 2

Next, Mosaic indexed the extracted data elements to make them searchable. The
data was indexed in a full-text search engine. As opposed to relational
databases, search engines are designed to optimize the retrieval of individual
search results from large numbers of potential results.  

When ingesting data in a search engine there are important design decisions
which affect the performance of the system. One of them is the size of the text
elements (or search engines docs) being ingested. For example, input documents
can be ingested as full documents, sections, paragraphs, or sentences. The
former leads to search results being full documents vs specific portions or
elements of the documents. The best granularity is dependent on the use case,
whether the priority is to find the most relevant document or a more specific
answer within a large document. For use cases of this project, Mosaic divided
the text into passages, typically 3-5 sentences, and size was optimized using a
gold standard set of questions and answers provided by the customer.  

Traditional document search uses exact keyword matching, which ensures that
words in the search query are exactly matched in the returned response. However,
exact matching is unable to identify words with similar meaning or consider the
contextual meaning of the search query and search results to find the most
relevant answers. These limitations are overcome by using embedding-based
indices. Transformer-based deep learning models can generate vector
representations of individual words or sequences of words. These vectors, known
as embeddings, encode meaning and context and ensure that words or phrases with
similar meaning are represented by numerically similar vectors. Mosaic tuned
state-of-the-art transformer models using the customer’s technical documents and
created custom embedding-based indices to facilitate a more robust search and
increase search results performance. 

PHASE 3 

Next, Mosaic developed a custom search relevancy function to optimize the search
results. The team leveraged the keyword and embedding-based indices and the
contextual information (captions, document hierarchy, etc.) to build a custom
scoring function to identify and rank results for a given query. The scoring
function was validated and tuned against a gold standard set of questions and
answers. 

Throughout the entire effort, Mosaic recommended high-performing data
architecture tools and sustainable MLOps practices to ensure a flexible and
scalable solution.   

Smart Document Search Results | AI-Enabled Voice Search Assistant Visualization

CONCLUSION

Today, voice search is becoming the preferred search method. A recent report
revealed that 63% of individuals have utilized a voice-operated assistant using
devices such as their smart phone, household appliance, laptop, and TV. Given
this, many companies are exploring ways to integrate voice-enabled search
capabilities into their processes and offerings. Mosaic was able to help a
well-known leader in industrial manufacturing apply this concept to the creation
of an AI-enabled voice search assistant solution powered by NLP and deep
learning.  

The ability to parse through complex technical documents and return results that
users can trust is not only hugely beneficial for new sales & existing
customers; but the algorithms can be tuned for any number of outputs. If
internal product teams want to run a quality check on the manuals themselves, if
legal needs to flag certain clauses, etc., the custom build approach allows for
users to search for desired information with minimal tweaking.  

The solution was built custom to the needs of the manufacturer, as exemplified
by the tuning of the document parsing and indexing algorithms to unique
structure and content of their documents. Mosaic was able to deliver an
experience that customers currently use today when searching through manuals and
other documents for important information on their purchased equipment, saving
countless hours, promoting increased customer satisfaction rates and ensuring
the manufacturer remains competitive in its space.  

Categories: Case Studies
Tags: AI Success StoryAI/ML ProjectEnergy Machine LearningExplainableAIFeatured
Natural Language ProcessingGenAIManufacturing Machine LearningModel
DeploymentNeural Search EnginePractical AIRaDS SuccessRPA

--------------------------------------------------------------------------------


RELATED POSTS

CASE STUDIES

IOT MACHINE LEARNING MODELING FOR PRODUCT DEVELOPMENT

A hospitality technology disruptor was developing a new sensor suite to detect
when a guest was smoking inside a property and distinguish it from approved
activities such as cooking. They engaged Mosaic to build time
series classification models to identify and alert on smoking events from the
streaming sensor data.

CASE STUDIES

AI-POWERED MANUFACTURING OPTIMIZATION 

Using AI to analyze sensor data, Mosaic helped a renewable energy producer
optimize furnace temperature to improve wood pellet production efficiency by
reducing slag production and pressure buildup and providing control room
operators with easy-to-use recommendations for setting furnace controls.

CASE STUDIES

AI ENGINE DEVELOPMENT FOR REGIONAL HOMEBUILDING

Mosaic helped one of the US’s largest regional homebuilders deploy an artificial
intelligence engine that recommends the optimal community features based on
different geographic regions. The recommender delivers data-driven insights the
company can trust when planning, building, and positioning new communities.

 * LinkedIn
 * Twitter
 * Facebook
 * YouTube

RESOURCES

Case Studies

Rent a Data Scientist™

Mosaic Labs

Industry Expertise

About Us

Have questions? Schedule a meeting below


HAVE QUESTIONS? SCHEDULE A MEETING BELOW

Name
Name
First
First
Last
Last
Email *
Title *
Company *
Comments
Captcha

If you are human, leave this field blank.
Submit

Δ



--------------------------------------------------------------------------------

 * Privacy Policy

© 2023 All Rights Reserved.
This website uses cookies to improve your experience. We'll assume you accept
this policy as long as you are using this websiteXAcceptView Policy