Primal is the first artificial intelligence that synthesizes semantic data in real-time. We call our innovation, semantic synthesis.
Unlike analytical, data-driven solutions, Primal works effectively with very sparse data inputs, making it the only solution that can keep pace with today's diverse and exponentially growing online environments. It also directly incorporates inputs from end-users, making it an ideal solution for user modelling and personalization.
Primal's technology allow us to interact with unstructured and semi-structured content on the Internet as if the Web was already semantic. Online content is semantically annotated and organized using the individual semantic user models created by Primal, completely inverting conventional approaches.
This disruptive innovation is the product of over eight years of R&D. Primal is backed by a growing portfolio of intellectual property.
Much of the effort in semantic representation has been focused on annotating existing content. Creating this type of semantic layer over existing content is proving to be a daunting task due to the sheer glut of online content and the compounding effect in the volume of data needed to create machine-readable semantics.
Conventional solutions create this semantic data manually or derive it indirectly using large scale statistical analyses of existing content or user activity (big data). While the benefits of these approaches are well understood, they fail in environments where data acquisition and analysis is cost-prohibitive, such as the real-time Web and social media.
These conventional approaches are much too costly for even the largest organizations. Manual methods are prohibitively expensive at scale, so large projects necessarily rely on computing machinery. However, few companies possess the infrastructure or big data needed to represent the full breadth of individual interests.
(For more information on the problems and limitations with conventional approaches, see Where Big Data Fails … and Why.)
Primal works in the "long tail of big data" where existing approaches are cost-prohibitive. In these environments, the complexity of the underlying schema compromises the quality of the results generated through purely statistical approaches, while the overall scale of the environments makes ontological approaches prohibitively expensive.
Primal has developed an innovative approach to knowledge representation called semantic synthesis. Primal's technology produces semantic representations of user intentions as interest graphs.
The core differentiating aspect of our technology is its ability to synthesize semantic data in real-time, even if you don't have existing data to leverage.
Semantic synthesis surmounts two significant challenges: scalable semantics and personalization. Our approach is positioned between free text retrieval and ontology-supported querying, trading expressiveness and precision for scalability and individualization.
Our synthetic approach has a number of compelling benefits for personalization and user modelling at Web scale.
First and foremost is its scalability and cost structure. By synthesizing semantic representations as opposed to extracting and retrieving them, it avoids the extraordinary cost of modeling and annotating data in advance.
Secondly, ours is an inherently individualized approach to knowledge representation. The unique perspective of each and every individual user provides the essential context for semantic synthesis. By modeling user intentions, it provides a highly personalized mechanism for search and knowledge management applications.
Primal bridges the gap between the sparse expressions of interest provided by consumers and the rich, structured data needed to direct the activities of modern software.
Primal's interest graphs can be used as machine-readable inputs to a series of automated processes and software agents to get things done faster, easier, and simpler than with today's complex and costly solutions. In this way, Primal extends existing computer systems to perform highly personalized tasks for individual users.
Applications of Primal include personalized news and information services, software agents, multi-document summarization, semantic search, assembling experts and communities of interest, personal knowledge management, and social media monitoring and analytics.
Primal's technology is applied in large-scale (big data) environments where the underlying knowledge being represented is highly complex. Markets include Web scale personalization and user modelling, vertical and enterprise search, e-commerce, advertising, collaboration and social networking, and complex knowledge domains such as health.
Primal's flagship product is a cloud-based data service that delivers semantic user modeling and a framework for software agents to interact with the open Web.
The interest graphs generated by Primal are used as inputs to downstream search and knowledge management systems, allowing us to retrieve, aggregate, and filter unstructured sources.
Primal's synthesized interest graphs allow us to interact with unstructured and semi-structured content on the Internet as if the Web was already semantic. Real-time filtering is used to semantically annotate and organize online content using the individual interest graphs created by Primal.
The major difference here is that the content organization is discovered through the expectations of end-users, rather than being imposed by knowledge engineers in advance. In other words, Primal's interest graphs evolve as a by-product of this consumer-directed process, avoiding the bottleneck of semantic annotation that has frustrated efforts in the past.
The basic design pattern used in real-time Primal-powered applications. Note that the synthesis of semantic data is largely decoupled from the retrieval and annotation of content from the Web, fundamentally changing the cost-performance structure of the solution.
These interest graphs can be deleted immediately after the task has been completed, or they can be persisted as a knowledge-base for each individual end-user. This data can also be fed back into Primal, providing a learning mechanism. With each activity and task, the system becomes more attuned to the user's interests, just as a personal assistant becomes more helpful over time.
Unlike conventional semantic technologies, Primal automates the processes by which humans create formal semantic representations, as opposed to modeling representations of existing knowledge.
Much like human beings use words in combination with grammatical rules to form statements, semantic synthesis uses a vocabulary of atomic semantic data and a proprietary set of generative rules to synthesize semantic data, as shown in the figure below. Primal creates these machine-readable interest graphs on-demand, requiring only simple indicators of user interests.
Human beings do not retrieve their knowledge from knowledge bases, like conventional data-driven computing systems. Instead, we generate (synthesize) our statements on the fly.
We use a relatively small vocabulary of words (small data) in combination with grammatical rules (computational rules) to form more complex expressions.
Similarly, Primal has developed a computational approach to synthesize more complex semantic data from a much smaller "vocabulary" of proprietary data. Primal's technology uses its proprietary "grammar" of generative rules to synthesize complex semantic data ("expressions") in real-time.
Just as human vocabularies are a mix of common and specialized language, Primal's vocabularies can be easily and inexpensively expanded to include specialized areas of knowledge such as health, finance, and politics.
Primal's computational approach is what allows it to generate data for a limitless range of knowledge domains and applications. Primal creates this expressive, machine-readable semantic data on-demand.
Unlike conventional approaches, Primal's process starts with the end-user. It takes simple indicators of interests and uses this context to synthesize data structures that represent these interests in a way that machines can process. These user inputs are simple and intuitive word associations, congruent with the way people make meaning.
The interests of end-users may be expressed explicitly (as in a search query or a social profile) or implicitly (for example, based on the topics or tags associated with content of interest, or sensing data from a mobile device).
Primal's computational engine has both offline and real-time components: an analysis engine and a synthesis engine (see figure below).
The analysis engine drives the offline activities. This engine analyzes representative content and creates vocabularies of atomic semantic data, like the words in a dictionary. These vocabularies are used as the building blocks for more complex semantic representations in the real-time synthesis operations.
The real-time synthesis engine is where the vocabularies of atomic semantics are assembled into complex semantic representations as interest graphs.
The figure below illustrates Primal's technology platform in more detail:
Primal has a patent portfolio of 110 filings, 18 of which have been allowed or granted. Primal's applications span key geographic regions including USA, Canada, China, Japan, Israel, Australia and India
Primal's patent filings cover not only the foundational technology and architecture (e.g. semantic synthesis, software agents, etc.) but also targeted applications of these innovations in strategic markets such as search, advertising, mobile, social, etc. Here is a small sample of Primal's intellectual assets:
|US 7,596,574||Complex-Adaptive System for Providing Faceted Classification|
|US 7,606,781||System, Method and Computer Program for Facet Analysis|
|US 7,844,565||System, Method and Computer Program for Using a Multi-Tiered Knowledge Representation Model|
|US 7,849,090||System, Method and Computer Program for Faceted Classification Synthesis|
|US 7,860,817||System, Method and Computer Program for Faceted Analysis|
|US 8,010,570||System, Method and Computer Program for Transforming an Existing Complex Data Structure to Another Complex Data Structure|
|US 8,281,238||System, Method and Computer Program for Creating and Manipulating Data Structures Using an Interactive Graphical User Interface|
|AUS 2007291867||System, Method, and Computer Program for a Consumer Defined Information Architecture|