Knowledge design
Expertmaker toolkit offer simple to use tools and functionality for creating powerful search solutions
The Expertmaker toolkit offers extensive functionality. You can use it to capture and model knowledge, transform and analyze data and solutions, use it to manipulate data and much more.
The AI solvers are made to make it easy to integrate the data and to make it easy to model your knowledge around the data.
The following solvers are offered with the Expertmaker toolkit 4.0:
The similarity solver is ideal for finding the best match. It is very useful for recommendations and discovery solutions. Together with keyword search it can offer very high precision search. It is a very useful solver that can be applied in a lot of contexts.
The value solver is ideal for e-commerce. It is a directional solver that will find the best possible match given that e.g. price is lower than a certain level or that some other intent is met. It can be used together with keyword.
The reverse solver will find the most similar product based on one or more products that have been identified. The benefit is that it actually looks for the most similar profile whereas most competing solutions base similarity on statistical data which is very sensitive to volumes and data quality.
The diagnostic solver is a tree solver that can be used to solve a number of challenges ranging from diagnosing problems and illnesses to consultative selling and customer care solutions. It can also be used as part of an interactive user experience and other process related solutions. This makes it very useful in many situations. The diagnostic solver opens up for a lot of online B2B solutions that up to now have not been available online. Other process related sales like banking and insurance products can also benefit from this solver.
The probability solver is tree solver that can help solve very complex problems and is usually applied where you need to analyze large amount of data. It can visualize the results so that they can be validated and understood. This solver is very useful in medical solutions for both prediction and analysis. It can help find patterns and support other solutions. It can also be used in other complex situations like B2B sales processes.
The classify solver is a solver for grouping and classifying. It is very useful for situations where the data is very complex and it is hard to find the relevant patterns. By teaching the solver it can achieve very high precision. It can for example be used for classifying illnesses or be used in virtual assistants helping people with for example information overload.
The estimate solver is a numerical solver for predicting a single numerical answer. It can for example be used when identifying profiles, ages and timings. This can be very useful for designing smart homepages or as support and input to other solvers.
The text classifier is a solver for extracting data and classifying unstructured text. This is very useful most texts available online or in intranets are unstructured have no meta-data attached to them. The text classifier can be used together with several of the other solvers.
Expertmaker also offers classic keyword search functionality, which is not a solver but a feature, that can be applied to the solutions stand alone or together with the other solvers.
The following solvers are available in Expertmaker v 4.0:
- Similarity
- Value
- Reverse
- Diagnostic
- Probablitity
- Classify
- Estimate
- Text classifier
- Keyword search
Easy to use
Artificial Intelligence may sound powerful but difficult to work with. Expertmaker has spent a lot of time making it really very easy to use. The driver behind Expertmaker has alwasy been to make AI so simple to use that anyone should be able to build a search solution. There is no need for programming skills or AI experience to build a basic solution. However, for the advanced user, it is also possible to build very advanced solutions.
The user interface is similar to a spread sheet program.
Easy to use toolkit
Knowledge modeling
People automatically learn from and understand information and data. With software it is not automatic, you have to make it understand. We call that knowledge modeling, which effectively means that you capture knowledge from a person, an expert, data or other source around a topic. Then you teach the software based on the relevant knowledge and experience. This may sound complicated but it isn’t. With the help of the toolkit it is very easy to do this.
Features and functions
As knowledge and intelligence is at the center of the solutions created it is important to be able to work with the data and models. The toolkit offers a wide range of features and functions for analyzing and managing the solutions.
The functionality offered is designed to make it simple to use them. The toolkit offer extensive visualization support to make it easier to understand and manupilate the data and knowledge.
The toolkit also offers a number of functions and features that help analyze and model the solutions such as:
- Consistency automation
- Simple data propagation
- Basic quantitative statistics
- Incremental sorting and filtering
- Data visualization: multi-dimensional overview, decision trees
- Transformations: aggregation, splits, reductions, etc.
- Dimensionality reduction
- General complexity reduction
