Scirevance: Intelligent Knowledge Management Software

Scirevance: Intelligent Knowledge Management Software

Table of Contents

Are you curious about unlocking your organization’s untapped potential and accelerating decision-making? Count in High Peak. In the ever-growing market of knowledge management software, projected to reach USD 1.29 million in 2028, we have created an intelligent and AI-powered knowledge process platform.

This case study explores High Peak’s global expertise in developing and designing AI-driven customized solutions. We will showcase how this product extracts raw information and processes the same into meaningful and data driven stories. Let’s dive deep to understand better:

About our client

Our client, John Siniawski, is the CEO of Scirevance. John’s journey has been marked by decades of advocating for People, Processes, and Technology while breaking down silos and biases. His current milestone in this journey is Scirevance, a Knowledge Process Platform that optimizes processes, captures thoughts and enhances individual and enterprise capabilities. By valuing and sharing knowledge, John believes knowledge management software becomes a powerful legacy that empowers the future. Hence, Scirevance embraces technology and learning methodologies to turn information into actionable knowledge.

About the product

Scirevance is an advanced knowledge-processing software designed to provide users with optimal process optimization, efficient thought capture, and enhanced capabilities within their enterprises. Through the utilization of cutting-edge technologies and innovative learning methodologies, this knowledge management software fundamentally transforms the way document-fed information is understood. It streamlines the silos of organizing, analyzing, measuring, cultivating, and retaining knowledge bases assets. By integrating narrative intelligence, learning, and natural language processing (NLP), Scirevance enables real-time analysis and simplifies document management. Also, it empowers users to create comprehensive and successful reports right from the outset. 

More than just a standalone application, this top knowledge management software functions as a dynamic process platform. Our solution not only converts information into tangible knowledge but also equips your organization with unparalleled insights. By distinguishing itself from conventional data management tools, our specialization lies in effectively harnessing unstructured content. Thus, ensuring the preservation of every critical detail.

Key highlights

Knowledge Retention

Our platform goes beyond data storage. Our knowledge management software safeguards the collective wisdom of your team, capturing notes, statements, and various documents. Hence, ensuring continuity even with personnel changes.

Project Empowerment

Seamlessly applies historical knowledge to current projects. Also, easily trace the evolution of decisions, actions, and strategies for comprehensive context and strategic alignment.

Chronological Clarity

Effortlessly understand why, how, and when actions were taken. Visualize the entire timeline, fostering accountability, transparency, and informed decision-making.

Narrative Insights

Capture lessons learned through our narrative capability, fostering growth and optimization as you gain a deeper understanding of your processes.

You know, our client had an eye-opening moment when they stumbled upon some revealing stats from McKinsey and IDC. It turns out that employees spend a whopping 1.8 hours every day, that’s 9.3 hours per week on average, just searching and gathering information! Can you believe it? And that’s not all. Another report by IDC showed that knowledge workers spend about 2.5 hours per day, almost 30% of their workday, searching for information.

It was quite a shocker for them, but it also sparked an idea. He realized that if he could create a searchable record of knowledge, it could actually reduce the time employees waste on searching for company information by up to 35 percent! That’s huge in terms of productivity gains and efficiency.

So, that’s when HPS got to work on developing this incredible knowledge management software. His goal was clear: to help businesses streamline their processes, optimize the way they gather and manage information, and ultimately save valuable time for their employees. And you know what? 

The HPS team nailed it! Now, with our knowledge management software in place, legal entities can build powerful and winning case narratives without wasting precious hours on information searches. It’s a game-changer! It is an industry-agnostic software. Currently, the focus is on legal tech. Hence, lawyers around the globe can leverage Scirevance for its following capabilities:

Simplifying narrative building through powerful data visualization

Constructing a winning narrative arc relies on the trial lawyer’s ability to present facts and evidence in a way that alters each piece of evidence’s individual significance by merging it into a coherent story that resonates. This arc establishes a matter’s thematic thread that can be carried to the closing argument. 

Scirevance enables lawyers to go above fact-finding and build a compelling narrative that does more than sequence facts or tell events in a particular order. Also, the platform’s advanced note-taking and event identification features capture an individual lawyer’s unique process and present it through interactive chronologies and visualizations. Thus enabling lawyers and legal teams to structure the basis for their multifaceted arguments.

Accelerating matter investigation

Manually searching through a large amount of documentation drastically slows down the momentum of case investigation. It is also highly error-prone. Scirevance’s knowledge management software speeds up the case analysis process by transforming data into interactive visualizations that empower teams to identify hidden data patterns, discover new questions, and deliver actionable insights. Additionally, the platform consolidates all types of documents and acts as a library to retain them in a single place for easy retrieval and collaboration.

Intelligent mapping relationships between matter and documents

Because lawyers and legal teams deal with a lot of paperwork, the manual classification of documents is often resource-intensive and error-prone. Using artificial intelligence and natural language models, Scirevance helps lawyers find the correlation between multiple case attributes. It is done by providing simple yet powerful data visualizations and intuitive search capabilities. Hence, this helps them reduce the time taken to prepare for all litigation phases, increase efficiency, and free up staff.

Why did Scirevance first approach High Peak to build a powerful knowledge and intelligence augmentation system?

Dissatisfied with the state of knowledge management processes prevailing in the market and the cost associated with it—especially for businesses that are documentation-heavy in nature—Scirevance’s goal was to build a comprehensive platform for better document collection, processing, review, analysis, and visualization from the ground up for the legal industry. 

Hence, to solve this issue, Scirevance connected with High Peak Software to develop an analysis platform that empowers legal entities and lawyers to create powerful narratives and enhance the storytelling experiences with supporting data.

Every litigation matter has thousands of documents, such as emails, transcripts, briefs, contracts, and NDAs. Lawyers and legal professionals have to deal with large volumes of paperwork and documentation. Vetting and culling these documents takes multiple reviews, which are often time-consuming and costly.

Also, these activities include conducting extensive research, creating a chronology and timeline, fact-checking, documentation and review, and much more. A documentation backlog is created if the process to complete these tasks is not automated, smooth, and quick in returning actionable insights. 

In order to enable lawyers from small and medium law firms with a technology advantage, Scirevance wanted to create a self-learning knowledge management software to help legal teams:

The features include:
  • Dynamic process platform converting info to knowledge, empowering with unique insights. Expert in managing unstructured content for vital preservation.
  • Speed up the case investigation and analysis processes by transforming data into intuitive visualizations that empower lawyers to identify hidden patterns, discover new questions, and deliver actionable insights from day one.
  • Quickly understand the cases, and capture their thoughts and notes while enhancing their focus to develop a compelling narrative for clients. 
  • Manage a single source for all their matter-related documentation. Whether those are self-notes, documents from clients and oppositions, facts from any other related matter, or opinions from an external expert, every document is retrievable from one place on the device of their choice.
  • Access and highlight case-relevant information by obtaining accurate reports with custom-tailored interactive visualizations.
  • Easily handle more cases with less overhead by streamlining the document review and analysis process.
  • Retain institutional knowledge regardless of turnover or unforeseen disruptions. The platform acts as a library to retain all types of documentation in a single place for easy retrieval and collaboration.
  • Dynamic process platform converting info to knowledge, empowering with unique insights. Expert in managing unstructured content for vital preservation.

High Peak encountered and solved several technical and business challenges during product design and development.

Manual documentation process and information overload

A typical case would mean collecting thousands of documents consisting of scanned PDF files, native documents and emails, images, chat logs, and other related documentation. Relying on manual classification or overtly technical systems for such tasks is complex, resource-intensive, error-prone, and highly inefficient. 

Solving for an intuitive, scalable, and robust solution focusing on data security

Lawyers and law firms are constantly entrusted with highly sensitive information about their clients. As a course of their business, the need for effective data security is of critical importance. While solving the bottlenecks in the enhanced document analysis process, Scirevance wanted to ensure that their digital solution would be sophisticated yet easy to use while securely handling highly sensitive matter-related documents. At the same time, the solution should be built for scale and has to be robust enough, as vast volumes of data would be uploaded, processed, and extracted for analysis by the users. 

Designing a narrative-building automated e-discovery platform

The concept of storytelling, or narrative, is integral to any trial lawyer’s preparation. Building a narrative relies on the trial lawyer’s ability to present facts, issues, and evidence in a way that alters each piece of evidence’s individual significance by merging it into a coherent story that resonates. Also, our team needed to develop an end-to-end solution for lawyers and legal teams that goes beyond a mere e-discovery application to assist them with their trial preparation by constructing a compelling storyline. 

Complicated user interface

Within legal technology, we noticed that the tech development focus is entirely on the solution’s features, and user experience is not considered necessary compared to a checklist of capabilities. Moreover, based on our primary market research, we recognized a clear need for an intuitive e-discovery platform in the market, as e-discovery platforms with a non-intuitive user interface make it extremely challenging for non-technical users to adopt the application and its powerful features to reach their full potential.

A major challenge for our team at High Peak was to make sure that the application’s user experience and interface design were intuitive and easy to use. Thus, making the knowledge management software straightforward for lawyers to navigate and utilize the application swiftly.

Disconnected and unorganized offline workflows

Due to the multiple sources of matter-related information, offline workflows make it very difficult for the entire legal team to collaborate effectively. Information is unorganized and often present in silos, making the discovery process highly counterproductive. Therefore, it was critical for our team to make an integrated system that can act as a single source of truth and help end-users seamlessly adopt new digital workflows. 

Ambiguous presentation for seamless note-taking and referencing

The High Peak team faced a significant challenge in their document processing and analysis system when users uploaded files containing complex information, such as email conversations, events, or case-related content. The main issue was the extraction and presentation of relevant data for users to create notes and references in a seamless and intuitive manner.

When a user uploads a file, the High Peak system utilizes Natural Language Processing (NLP) to extract text data from the document. This extracted text was displayed as “process data.” However, the challenge arose when the extracted content included complex structures like tables or mixed content that could be interpreted as both text and tabular data. Users were unable to directly specify whether such content should be considered as text or a table, leading to confusion and potential misinterpretation of the document’s structure.

The High Peak team overcame this by introducing a dynamic view. Users could easily switch between extracted text and the original document, facilitating clearer understanding. This empowered users to select text, highlight content, and create meaningful notes, especially for legal purposes. This enhancement improved document analysis, usability, and overall user experience. This version showcases graphics from the document and displays tabular content. Importantly, you now possess the capability to effortlessly craft statements and notes. 

Based on the challenges faced by Scirevance’s team and aligning with the vision to make lawyer’s day-to-day processes more efficient, our partners at High Peak came up with an intelligence augmentation system to cut through the drawn-out process of document review and return end-users emphasis where it belongs – on winning the case.

Product discovery & ideation

At the very beginning, our team of engineers, data scientists, and project managers conducted various brainstorming sessions to understand and define the problem statement that our partner was trying to solve. After gathering the initial set of requirements from all the stakeholders at Scirevance and conducting an exhaustive competitive analysis, our team came up with the following:

  • An e-discovery platform that quickly identifies connections between documents, initiates review (TAR) helps lawyers deliver valuable insights faster, and
  • A knowledge process system that streamlines the matter analysis process and transforms the way legal teams interpret their data.

After the initial product rollouts (beta), we started conducting user interviews to understand how efficiently these solutions are helping our target audience. Consulting with subject matter experts made us quickly realize that the end-users are not comfortable using multiple and separate tools for their daily workflows. 

We also had to address the ease of user adoption, as our end-users would be moving from their traditional workflows to an integrated digital platform. Our research and focus groups suggested that combining our case analysis tool with an e-discovery platform, and ensuring its optimum user adoption would be the key to our success. 

Product strategy

We started again by rolling out case analytics features—particularly visualizations and search—to help lawyers with their analysis process while ensuring that the functions were correctly targeted. Furthermore, building an intuitive and easy-to-navigate interface was of utmost importance to increase product usability. 

To solve this, our team started building mock screens before rolling out any new feature. These mock screens are then shared with all the stakeholders, including end-users, for their feedback. The entire interface of the best knowledge management software is designed like that. Slowly and steadily, we started incorporating other appropriate functions into the platform based on industry-specific use cases.

Product-market fit

Our team at High Peak strongly believes that any product has to evolve constantly in order to be categorized as a product-market fit. Our AI-powered knowledge management software is continuously getting trained/retrained on a vast amount of data that is uploaded to our system. Additionally, our team keeps optimizing existing features and building new ones based on the vision of an all-inclusive platform. 

We also conducted focus groups to ensure we were set out in the right direction. We got our first win when a lawyer used the ‘Timeline’ and “Sentiment Analysis” features on our platform for the first time and got back to us by saying, “Not only do I know what somebody said, but now I also know how and when they said it in just a matter of minutes. This feature is going to change how lawyers traditionally function.” 

Product architecture

Our designed solution is built on the microservice-based architecture to ensure the platform is scalable, programming language & technology agnostic, provides better security & compliance, and can quickly process large data sets. One of the major highlights for our development team is that the current system is still running seamlessly on the initial architecture. 

Product design

To ensure smooth product adoption and a user-friendly experience, we designed our product interface to be highly intuitive and easy to use. Using artificial intelligence and natural language processing capabilities, the product continuously learns and evolves based on the lawyers’ input and adapts according to their workflows. Additionally, lawyers can create general notes and link them back to any matter in the system as required. Thus capturing their thought process and building a compelling narrative using simple yet powerful interactive data visualizations. 

Product development challenges

Building a novel product from scratch comes with its own set of challenges. They are as follows: 

  • Multiple iterations and approaches have to be considered while building every model, which is a resource-intensive process.
  • From a business standpoint, initially, the product usage wasn’t happening in the way that we’d expected.
  • Additionally, to help our client with the best ROI possible, we have a lean team in place working on all aspects of the product, from product ideation to server cost optimization. 

Product success

The product strategy evolved multiple times throughout its development, but our team at High Peak ensured that product development took place, keeping the end-users pain points in the center. As a result:

  • With an almost negligible marketing budget, our product has successfully onboarded multiple clients who are using it daily for e-discovery, narrative building, and case analysis needs. 
  • Consequently, the product usage has significantly increased compared to when we first started.
  • More and more potential customers have started talking about it, and our team is super excited to take it to the next level.
  • Our team is currently building new features based on documentation-specific extractions to provide specific outputs.
  • The platform is expandable to work in any domain and is currently getting tested in new open markets such as Hedge Funds.

Solutions/Modules

Notes

knowledge management software

The Notes feature now boasts enhanced flexibility. Originally tied to specific cases, it has evolved to accommodate versatile, generic notes applicable across matters. Users can tailor notes for client references or keep them private. Notably, notes can seamlessly transition between projects, optimizing contextual relevance. This feature allows comprehensive actions—creation, editing, and archiving—amplifying usability. The shift from generic to project-specific notes offers a cohesive narrative. This evolution underscores the platform’s commitment to adaptability, empowering users with a dynamic tool to weave coherent and insightful narratives throughout diverse projects.

Within our knowledge management software, the note-taking feature stands as a pivotal tool, offering two fundamental categories of notes with nuanced refinements. The broader classification encompasses general notes, serving as a versatile reservoir for diverse interactions. At the outset, it’s instrumental for initial client engagements or preliminary research, fostering comprehensive data capture.

By transitioning beyond mere note-taking, the knowledge management software facilitates seamless integration of these general notes across projects, streamlining the building process. It mirrors the quintessential professional workflow—initial note-taking, thorough analysis, synthesis, and culminating in a compelling narrative. This universally applicable framework caters to myriad sectors—healthcare, finance, consulting—while accommodating specific variations.

By meticulously documenting insights, narratives, and lessons, our platform empowers knowledge retention and efficient knowledge transfer. It ensures the legacy of expertise remains embedded within the organization, facilitating continuous growth and improvement. This approach, notably, echoes Pfizer’s success—a notable 15% increase in organizational efficiency attributed to note-taking capabilities.

Consolidated narratives

knowledge management software

The inclusion of a consolidated narrative serves a strategic purpose, enabling management to comprehensively review diverse projects and extract pertinent data. This feature facilitates targeted searches across projects, culminating in a generalized narrative. This narrative transcends individual projects, proving invaluable for client-specific contexts, presentations, or speeches. The knowledge management software further encompasses comprehensive client data, including contact details. As users delve into projects, they access team composition and project descriptions and conduct a thorough analysis. This dynamic capability remains closely tied to specific clients, elevating project insights and strategic decision-making within a client-centric framework.

Project/Trade

knowledge management software

USP: Introducing the “General Search” capability, our platform empowers users to conduct comprehensive searches spanning documents and visuals. While previously consolidated, we addressed a unique challenge involving email threads. Threads, representing distinct conversations, were processed individually, resulting in fragmented views. To resolve this, we bifurcated the display to enable distinct thread visualization. Each thread, previously treated as an individual file, is now presented as a cohesive entity. This refinement ensures that users can seamlessly navigate and comprehend entire email conversations. By clicking on a thread, users access a consolidated view, eliminating the previous fragmentation.

The transition from our initial version to the current iteration involved a comprehensive reimagining of the user interface. In the first version, the project list dominated the interface, lacking the open-close option. Our focal point was the project, evident by the landing page initially named “Matters.” Subsequent discussions, including insights from John, prompted a redesign. The updated view now emphasizes general notes upon login, catering to newly registered users. This thoughtful shift streamlines the onboarding process, enabling smoother interactions and note-taking during discussions, thereby enhancing user experience.

Our platform leverages cutting-edge technology to drive the “General Search” feature. At its core, we utilize Elastic Search—a robust and efficient search engine. This engine not only facilitates term-based searches but also incorporates synonyms through boosted terms. This strategic enhancement ensures a comprehensive and refined search experience.

Our process involves Natural Language Processing (NLP) to analyze and process data. The user’s search term is seamlessly integrated into Elastic Search, which acts as the central database. All processed data, including the encountered extracted information, resides within this repository. For instance, a search for “ammonia” triggers an expansive scan, exploring the term itself and its related synonyms.

knowledge management software

In a nutshell, the search functionality offers users dual perspectives. They can opt for a comprehensive overview, gain a high-level understanding of a topic, or zoom in to examine specific details. This versatility provides varied insights into a project, aiding comprehensive analysis and facilitating in-depth exploration. Users can seamlessly transition from a broad view to a granular focus, enhancing their grasp of project nuances and enabling effective learning and decision-making.

Note: The knowledge management software is integrated with Slack. It offers email and Slack thread analysis, reflecting evolving communication trends. While email remains useful for less urgent interactions, Slack’s immediacy suits real-time trading demands. Notes capture these exchanges, providing a chronology that aligns events with conversations. 

Extracting events from documents, though not flawless, enriches the timeline. Event extraction, a unique capability, shows promising results comparable to leading labs. As generative capabilities advance, finer precision is expected. This distinct feature enhances comprehension and historical context, bridging communication shifts for informed decision-making.

We designed and developed a smart and interactive matter management system to improve knowledge-driven work as well as to improve users’ general processes to optimize outcomes. As any matter involves multiple stakeholders, it operates on role-based access and caters to four types of users corresponding to their functionality: 

  • Global admin
  • Firm admin
  • Case owner
  • Team member

Once logged in, users can create projects and trades with attributes such as matter titles, dates, facts, notes, etc., and also invite collaborating users to participate in, contribute to, and access details and documents of a particular matter as per their requirement. Moreover, the applications record all the activities that a team member on the case has carried out. This makes collaboration between dynamic teams much easier.

knowledge management software

Sample | Overview of the Matter

Library- Automated document classification powered by self-learning algorithms saving thousands of manual hours

knowledge management software

Document classification tasks can be a massive bottleneck as they receive a large number of multiple document types to process. Before actually extracting data from these documents and organizing it afterward, they need to classify these documents into respective categories. Once a project is created, our system allows users to upload all kinds of documents, such as text, PDF, images, chat logs, etc., in bulk. 

Our knowledge management system software is powered by intelligent techniques such as Machine Learning and Deep Learning to effectively manage these documents with large amounts of unstructured information. These Machine Learning and Deep Learning models get better with time and help us make the document classification process much faster, more scalable, accurate, and cost-effective when compared with manual classification.

The Library in Scireavance serves as the central repository for all user-uploaded files. It is where users store, manage, and access their documents. Here’s a breakdown of its key features and recent updates:

File uploading and storage
  • Diverse File Formats: Scireavance allows users to upload a wide range of file formats, including PDF, DXT, DOC, DOCX, MSG (emails), and Excel files.
  • AWS S3 Bucket: All uploaded files are stored securely on the cloud using AWS S3 bucket, a file storage system provided by Amazon Web Services. This ensures data security and scalability.
File processing and analysis
  • NLP Processing and OCR: Upon upload, Scireavance employs Natural Language Processing (NLP) to analyze the files. It utilizes Optical Character Recognition (OCR) to extract text from various document types, making the content searchable and accessible for further analysis.
  • Elasticsearch database: The extracted text is stored in Elasticsearch, Scireavance’s primary database. This enables fast and efficient searching and retrieval of information.
  • Lambda for speed optimization: To enhance processing speed, especially for large files or batches of files, Scireavance utilizes Lambda. This serverless computing service from AWS creates instances based on file size and quantity, allowing parallel processing and faster completion times.
  • File movement: Previously, moving files between folders was a significant challenge in Scireavance. The Library Manager was implemented to solve this issue.
processed document

Sample | Processed Document

The primary objective of utilizing process data is to enable effective text selection and note creation, addressing the challenge of non-selectable PDF content. This functionality facilitates future case referencing. With the dynamic view, original PDF content becomes accessible, including table elements. This feature aims to enhance user experience by offering diverse views, supporting note creation, and ensuring seamless functionality. Any queries about this feature are welcomed.

pdf document

Sample | Original PDF Document

As users start uploading documents, it automatically detects various types of documents and categorizes them based on their formats. For example, if we upload different types of files like PDFs, images, Word documents, and emails into the system. The system can recognize what type of file it is automatically. Users of this enterprise knowledge management software can then access the files based on their format, folder structure, and type. Also, users can add a statement, note, and premise in the original uploaded document.

Library manager

The Library Manager is synonymous with Llama FS, the AI-powered file management system that uses the Llama large language model. This feature aims to help users better organize their files and folders within Scireavance. Here’s how it works:

  • Users can select multiple files and folders within the library that they wish to reorganize.
  • The content of the selected files, along with a summary of each file, is sent to the Llama model.
  • Scireavance developers have created specific prompts to instruct the model on how to analyze this information, taking into account the existing folder structure.
  • Based on these prompts, the model will suggest a new folder structure, including:
    • Renaming files: The model can suggest more descriptive file names based on the content. Importantly, the original file name will be retained and displayed alongside the new name, so users don’t lose track of their files.
    • Moving files to different folders: The model may suggest that some files belong in a different folder based on their content.
    • Creating new folders: The model can suggest creating new folders if the existing structure doesn’t adequately categorize the files.
  • The user is then presented with the suggested folder structure and can either accept or reject the changes.
  • If the user accepts the changes, the library will be restructured accordingly. However, this action cannot be reverted.

Visuals and Analytics Tab

Timeline

Previously, the system lacked the ability to associate uploaded files with specific dates and times for chronological organization. To address this, we’ve now incorporated a feature enabling users to attach dates to their file uploads, enhancing the timeline presentation. The Timeline feature captures data chronologically, showcasing the upload history of files. 

It provides comprehensive insights across different time periods. Users have the ability to retrieve specific information from desired dates, enhancing data retrieval efficiency. In this section, you’ll find a comprehensive list of documents, including PDFs, document versions, and more. 

Additionally, email files are tracked, with a count for each. Notably, we’ve introduced sentiment analysis powered by NLP. This analysis detects positive and negative sentiments within files, aiding users in understanding content nuances at a glance. Positive and negative sentiments are visually highlighted, providing valuable insights and facilitating efficient document assessment.

knowledge management software

Incorporating sentiment analysis introduces a nuanced dimension. The definition of positive and negative varies, molded by perspectives and roles. Whether legal, financial, or diverse fields, sentiment adapts – a positive statement can be negative in another context. Users wield control, adjusting system-indicated sentiments and facilitating a personalized outlook. 

Our approach entails harnessing AI within a curated information ecosystem, avoiding indiscriminate web scraping. Tailored AI sources, user-defined data, and a knowledge repository converge. This orchestrated synergy empowers multifaceted utilization – learning, compliance, strategizing, and presentation – a comprehensive suite deftly orchestrated for diverse industries.

Topic Clustering
Topic Clustering

Topic Clustering is a powerful tool for your case exploration. It caters to new users seeking clarity within the application. When faced with an unfamiliar case, users can seamlessly navigate to the topic clustering section. Here in our knowledge base management software, the tool identifies and presents the prominent subjects existing within the project. These topics are meticulously curated, capturing the essence of the case.

Upon selecting a topic, such as “feeling,” the tool conveniently compiles documents containing or related to that specific keyword. This approach allows users to gain a comprehensive understanding of the case’s content and intricacies. For newcomers and those seeking efficient comprehension, the Topic Clustering feature serves as a valuable gateway, enabling swift and insightful exploration of the case’s core themes and details. On clicking, the particular object opens the folder where the folder or the file is located.

Heat Maps

Also, in Visuals and Analytics, our Heat Maps offer a data visualization feature. Understand word relationships within your documents through a visual representation. This heat map illustrates word associations, aiding detailed analysis. This legal knowledge management software simplifies complex connections, empowering you to make informed decisions based on a comprehensive view of your case materials.

Relationships

The Relationships feature introduces a dynamic dimension crucial for understanding the intricate connections within your data. Imagine a scenario involving communication exchanges across different domains, each representing a distinct aspect. Consider, for instance, the Vegas domain, where files hold email conversations between diverse entities.

By interlinking these domains, we illuminate the intricate web of relationships. The personal knowledge management software meticulously maps out the senders and recipients of each email, portraying a comprehensive web of interactions. This visual representation unveils how domains communicate, allowing you to discern patterns and connections that might otherwise remain obscured.

In practical terms, this means when a user uploads a file—a crucial email conversation, perhaps—pertaining to a case, the knowledge management software intelligently identifies relationships across domains. This breakthrough ensures you can effortlessly capture notes for future reference, highlighting pivotal elements in depositions. Ultimately, this strategic enhancement empowers you to uncover critical insights, transforming seemingly disparate data into a cohesive and valuable resource for informed decision-making.

Communication analysis

In our pursuit of elevating efficiency and insight, we introduce a groundbreaking feature – the communication analysis with a top-level graphical display of the inner happenings within the tool. Imagine unraveling complex email threads with precision, not just deciphering content but identifying who was left out and, more importantly, why. 

A feature unparalleled in many competitions, this function brings a level of granularity that sets us apart. While others may offer basic categorizations, our tool uncovers the missing pieces, delving into the intricacies of a thread. This invaluable capability provides an edge, whether in legal cases, financial transactions, or collaborative projects, enabling users to swiftly identify shifts, disruptions, or even biases in communication dynamics. 

This breakthrough showcases our commitment to delivering a next-level game changer in the industry. Our tool’s prowess extends beyond thread analysis. The Chronologies feature, housing “Snippets,” enriches the understanding of documents. These carefully curated snippets highlight essential facts and statements, offering instant insights while maintaining direct access to the original document. 

This dual approach empowers users to not only craft precise summaries but also establish irrefutable linkages between their notes, arguments, and supporting documents. This seamless connection between analysis and evidence refines discussions, presentations, and narrative building, setting the stage for a more comprehensive and compelling approach.

Chronology Tab

Chronology

The Chronology tab emerges as a focal point, where the convergence of statements, notes, and premises unfolds seamlessly. This integrated canvas presents a panoramic view of the project’s progression, offering a cohesive narrative. Within this framework, the system extracts pivotal events and snippets from email files, providing contextual insights into significant moments.

By elevating user experience, the platform now offers the ability to generate generic statements, notes, and premises. This enhancement streamlines the assimilation of new document sets, optimizing contextual understanding. While not a novel feature, its refined interface simplifies note creation, resulting in an orderly compilation of notes, statements, and premises.

The Chronology tab in our knowledge management software embodies user-centric design, facilitating a structured approach to comprehending intricate case dynamics. This optimization embodies the fusion of functional efficacy and user-centered design, reinforcing the platform’s commitment to empowering case study endeavors.

Let’s look at the USP below

The system demonstrates its astuteness by discerning multiple instances of the same email event. Notably, it can identify events based on context without relying solely on dates or years. For instance, if an email mentions meeting “one week from now” or “one month later,” the system adeptly associates these events with their respective dates. This perceptive approach ensures accurate event filtering, as seen in phrases such as “travel any Thursday, Friday, and Sunday.” The system’s ability to decipher events within emails showcases its advanced understanding of contextual nuances.

Mechanism

The High Peak team undertook the task of implementing sentiment analysis by utilizing the Amazon reviews model, a classification system designed to determine the positivity or negativity of Amazon reviews. This model served as our foundational dataset. Subsequently, extensive annotations were conducted in-house to meticulously analyze each sentence within the context of the documents. 

Initial implementation involved numerous iterations with legal professionals, as differing perspectives and domain knowledge influenced sentiment judgments. Acknowledging the subjectivity, we developed a feature allowing users to manually highlight sentences and annotate their sentiments, addressing individual nuances. This iterative approach reflects our commitment to refining sentiment analysis accuracy within the diverse legal landscape.

User Services

Our user-centric approach is further exemplified through the User Services feature. A notable addition is the General Search function, enabling users to seamlessly explore across all projects. This novel capability enhances efficiency by swiftly retrieving relevant information. Additionally, the Invite section empowers users to effortlessly invite team members and collaborators to join the platform. 

Recognizing the importance of feedback, we’ve incorporated a dedicated Feedback section, fostering open communication and continuous improvement. This comprehensive User Services feature reflects our commitment to optimizing user experiences while fostering collaboration and growth within the application.

Accurate data extraction at scale using intelligent OCR techniques improving processing time

In most situations, documents are available in PDFs, native, or image form. Typically, data noise and quality elements pose a challenge to information extraction and data transformation from such documents. These include pen scribbles, watermarks, wrinkled, torn, discolored, smudged stamps imprinted on the text. Randomly occurring black and white grains, dark backgrounds, faded ink, printed with low-contrast or colored ink, and poor dpi of the scan. Furthermore, deriving inference from multiple related sentences in a clause or section is another challenge when processing matter-related documents.

We built an automated data extraction capability using Optical Character Recognition (OCR) technology to solve these specific data extraction problems. The knowledge management software involves AI models that are trained using a large amount of training data for handwritten text images and annotated actual text values. 

Using the OCR engine, printed or written text from an uploaded document or image file is converted into a machine-readable format. Accordingly, this extracted data is categorized by our deep learning algorithms and later used for data processing like editing or searching. For example, the algorithms can understand the extracted information presented in a DD/MM/YYYY format as a date.

Intelligent auto-summarization of emails creating short, easily digestible snippets of important information using NLP

Before going deep into any case, right from the first document itself, sometimes users want to take an overview or get to know a specific case attribute. To solve this use case, our team at High Peak came up with an auto summarization of email functionality.

Using Machine Learning and Natural Language Processing algorithms, our designed system analyzes the text in the documents and displays the summarized text in the form of snippets. A user can use the auto summarization feature to view a summarized version of all the emails in a thread—saving them a lot of time and effort. Additionally, information such as email threads and the number of emails can be viewed by the users working on the case.

Robust knowledge management system to store and protect all relevant and sensitive data under one roof

A well-functioning organization usually requires a well-functioning knowledge management system (KMS). With hundreds of documents associated with a single matter, our system provides effective content management, enabling users to organize all matter-related information and index it as clearly as they want.

The KMS comprises six main categories:

  • Statement: Any insights or conclusions derived from the matter-related documents can be stored as fact.
  • Notes: Our note-taking feature has evolved to offer both case-specific and adaptable note creation. Initially designed for case-relevant notes, we introduced “generic notes” for broader utility. Users can now create notes tailored to specific clients or private insights, fostering flexibility. Furthermore, notes can seamlessly transition between projects, streamlining organization and access. Users can easily convert generic notes into project-specific ones, ensuring a smooth shift from general to targeted relevance. With functionalities encompassing archiving, creation, and editing, this feature reflects our dedication to empowering efficient note-taking practices within the platform.
  • Premises: High-level and incident-level issues pertinent to the matter can be logged in this section of the KMS.
  • Library: Users can organize and store all the matter-related documents with the source feature. For instance, the number of processed files, unprocessed files, email threads, and so on. This feature enables users to have quick and immediate access to all necessary files in one place.
  • Tags 
knowledge management software

Our knowledge management software introduces a robust tagging mechanism. Users can now efficiently link related documents, creating meaningful associations. For instance, when dealing with documents concerning a specific individual, users can conveniently tag relevant files with the individual’s name. This streamlined approach allows for quick retrieval of essential information, simplifying the referencing process during depositions or other critical contexts.

Also read:- HighPeak’s Innovative RFID Tracking System
  • Narratives
Narratives

Users experience heightened control and organization in the narrative section, seamlessly integrating emails, facts, notes, and issues into a cohesive account. Vital for depositions, this feature enables exporting curated narratives, preserving the sequence for logical presentation. Users customize the arrangement, efficiently exporting a compiled document encompassing statements, notes, and premises. The former Fact, Notes, and Issues (FNIs) term adapts to evolving projects. In the legal world, our enhanced narrative empowers professionals, facilitating impactful, structured document presentations for crucial proceedings.

  • Utilities 
knowledge management software

The Utility tab offers enhanced convenience by consolidating vital features previously scattered across sections. Previously, functions like consolidated view, export, and reporting were located separately. To streamline accessibility, we grouped them under the Utility tab, providing a dedicated space for these essential tools. Notably, users can capture screenshots from the Timeline and Topic Clustering, which will be housed here alongside the Report section. 

This tab enables users to swiftly comprehend the chronological sequence of events within the timeline, including document uploads and case creation details. Additionally, users can generate comprehensive analytical reports encompassing created facts, notes, statements, and topic clustering insights. This dynamic feature integration, including the case-specific search capability, underscores our commitment to enhancing user efficiency and clarity.

Insights with generative AI

This feature, powered by a Llama 3 model, allows users to ask questions about selected files. The AI provides answers based on the context of the chosen documents. The system is designed to avoid hallucinations by stating “I don’t know” when it cannot find an answer within the provided content. Currently, only PDF and email files are supported for insights generation. There are plans to expand support to other file types, including Excel and it allows 30 selections now.

Working:

1. File Selection: The user can select the specific files they want to ask questions about. This can be done either by choosing files from the library or by uploading new files directly.

2. Question Input: The user inputs their question in natural language into the chat interface.

3. AI Processing: The Llama 3 large language model processes the question and analyzes the text extracted from the selected files to find relevant information.

4. Answer Generation: Llama 3 then generates a concise and informative answer to the user’s question based on the context provided in the selected files.

5. No Hallucination: If the model does not find relevant information within the selected documents to answer the question, it will explicitly state “I don’t know” instead of fabricating an answer.

  • Screenshot: While going through the processed documents, email threads, and data visualizations, users may take screenshots for future reference. These screenshots are stored and are available as and when required.

Intelligent search mechanism emulating natural language search with Boolean search as an add-on

Our knowledge management software includes an intelligent search mechanism with local and global search features. Built on Elasticsearch, it allows users to search and analyze hundreds of documents quickly and in near real-time. The users are provided with numerous search fields, including exact, proximity, domain, facts, notes, issues, tags, file extensions, entities, file metadata, and others. 

The knowledge process software also lets users leverage Boolean operators(AND, OR, & NOT) to construct the boolean search. Moreover, the advanced search mechanism also comes with the capability of highlighting the synonyms of input search terms and terms related to input search terms.

In addition, the user can also search for specific elements on a given tab/page using the local search feature.

Mark Review: enhancing document accountability and workflow

The “Mark Review” function in Scireavance aims to provide a clear distinction between simply viewing a document and completing a thorough review. While its exact implementation remains unclear from the sources, its core function is to allow users to mark a document as reviewed and apply a timestamp to record when the review occurred.

Here’s a more detailed breakdown of its intended purpose and potential benefits, drawing on John’s initial description and our conversation history:

  • Differentiation: The primary function is to create a visible difference between a document that has been opened or quickly scanned and one that has undergone a formal review process.
  • Timestamping: The timestamp associated with the review mark provides a record of when the review took place, aiding in tracking progress and accountability, especially in collaborative legal settings.
  • Accountability: By marking a document as reviewed, users acknowledge responsibility for its examination, which is valuable in legal contexts where meticulous documentation is crucial.
  • Workflow enhancement: This feature could potentially integrate with other Scireavance tools, such as the chronology or narrative building features. For example, a reviewed document could be automatically added to a case chronology, or its key findings could be easily incorporated into a narrative.

Intelligent bot integration to extract information from the web

This feature uses an RPA bot to automatically download documents from various websites based on predefined keywords and upload them into Scirevance.
Role-Based Access: Access to bot functionality is planned to be role-based, with permissions granted by super admins.
Paywall Website Access: The bot can access websites behind paywalls if provided with login credentials.
Duplicate Detection: The bot avoids downloading duplicate files by checking the database for existing files from the same website and keyword.

Technologies used

  • Front End: React, Javascript, Axios, D3, Recharts
  • Backend: Java, Mysql, Elasticsearch, Amazon s3, Aws Lambda
  • API Testing: Postman
  • NLP: StanfordCoreNLP, OpenCV, Tensorflow, Bert-TensorflowTika, Tesseract, Textract, CRFSuite

Upcoming Features

SME section

Anticipating future enhancements, our application is poised to introduce an innovative feature. We are exploring the inclusion of Subject Matter Experts (SMEs), esteemed professionals renowned for their expertise. 

This strategic addition will enable comprehensive project reviews, leveraging expert insights to elevate project outcomes. 

SMEs’ guidance will prove invaluable, enriching our platform with specialized knowledge and enhancing decision-making. Moreover, the application is undergoing advancements in scrape runs, further streamlining data collection and analysis.

Harness AI-powered knowledge: Choose High Peak to create your customized knowledge management software

In short, you can unlock the power of AI-driven knowledge management with High Peak! Our customized knowledge management software breaks silos, revolutionizing the way organizations work. Don’t miss out on this game-changing solution. Take your organization to new heights. Connect with our team and schedule a demo today!