Sold by: Dynamic AI
Deployed on AWS
Free Trial
Detection of similarity of texts using mixed AI and statistical models
Overview
This model is designed for automation of business communication. Technical walk-through video describing how to use the model: https://youtu.be/rDdC0ekIBd4
It can serve as basis for classification, automatic responses and other uses. For example see the demo implementation for CRM in Customer Care: https://youtu.be/8f5-SpRfEcc Other demos are available on our website https://dynamic-ai.com
We used our own dataset as the test set to evaluate the accuracy of the proposed method. Test report and confusion matrix: https://docs.google.com/spreadsheets/d/1sBrIUqytH3kMD1eJgmJKIE2Nu50gVRTN1MvZ0_80XxI/edit#gid=399507084 Our system achieved an average accuracy of 95% on corpus of 232 messages.
Highlights
- Model is learning in real-time from every piece of input data and provides simple and easy to use interface for text categorization and similarity assessment. Number of messages it can consume is unlimited but message size is limited to 1000 characters.
- Powered by our Patented Genetic Coding engine with Evolutionary Core which is capable of assessing similarity between text data with argumentation of accuracy minimizing false positives.
- For ml.m5.4xlarge instance importing of 100-message categorized corpus takes 1hr. Prediction for a single message takes 3 to 30 seconds.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 60 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.4xlarge Inference (Batch) Recommended | Model inference on the ml.m5.4xlarge instance type, batch mode | $1.00 |
ml.m5.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.4xlarge instance type, real-time mode | $1.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $1.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $1.00 |
ml.c5.4xlarge Inference (Batch) | Model inference on the ml.c5.4xlarge instance type, batch mode | $1.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $1.00 |
ml.m4.4xlarge Inference (Real-Time) | Model inference on the ml.m4.4xlarge instance type, real-time mode | $1.00 |
ml.m5.2xlarge Inference (Real-Time) | Model inference on the ml.m5.2xlarge instance type, real-time mode | $1.00 |
ml.c5.4xlarge Inference (Real-Time) | Model inference on the ml.c5.4xlarge instance type, real-time mode | $1.00 |
ml.m4.2xlarge Inference (Real-Time) | Model inference on the ml.m4.2xlarge instance type, real-time mode | $1.00 |
Dimensions summary
You pay by the host hour for running this text similarity model on your chosen instance. Pricing splits into two modes: batch inference for processing grouped data, and real-time inference for live requests. Within each mode, you pick from five instance types (ml.m4.2xlarge, ml.m4.4xlarge, ml.m5.2xlarge, ml.m5.4xlarge, ml.c5.4xlarge). Larger or more capable instances carry different hourly rates. Cost scales with how many hours each instance runs. You select the mode and instance size that fit your workload, and billing follows actual usage.
Top-of-mind questions for buyers
One host hour covers one hour of an instance running the model. Batch dimensions bill only while a batch job processes. Real-time dimensions bill for each hour the inference endpoint stays deployed, even if it receives no requests. Charges stop when you shut down the instance or endpoint.
Batch mode runs the model against grouped data and bills host hours only during processing. Real-time mode keeps an endpoint live to answer requests as they arrive and bills every hour the endpoint stays up. Batch fits scheduled jobs; real-time fits continuous, on-demand scoring.
Each running instance bills separately at its own hourly rate. If you run multiple instances or sizes, their host hours add up on the same invoice. Your total depends on which instance types you run and how many hours each stays active.
dynamic-ai.com
Helpful?
Vendor refund policy
Not available.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This is bleeding-edge technology release and is highly experimental. It contains alpha-grade Genetic Core so accuracy and performance may differ from the Production version. There is no possibility to import or export the current state of the model.
Additional details
Inputs
- Summary
This model is expected to be run as real-time inference only and does not support batch transform. Unlike classical ML model, this product supports both making inference and training on the same deployed endpoint.
For detailed usage information please consult:
- Limitations for input type
- To achieve optimal performance the following limits should be met: - Each message should be up to 100 words and 1000 characters long. - Total number of messages in the system should not exceed 10 000.
- Input MIME type
- application/json
This is not a conventional ML model and uses custom interaction protocol built on top of JSON messages.
Please use a Python helper library provided to feed data in and get results.
https://github.com/Dynamic-AI/aws-sagemaker-examples/blob/master/src/v1/rent-a-car-corpus-small.txt
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
type | Input command for the model.
Available actions are implemented as functions of the Python helper library. | Type: Categorical
Allowed values: addMessage, addFeedback, getSimilarity, isReady, reset, restoreCheckpoint, saveCheckpoint | Yes |
Support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Use the NeoPulse® Framework to build custom deep learning models using data of all types: numeric, text, image, audio, and video.
https://tfhub.dev/google/universal-sentence-encoder-multilingual/1
Use Cohere's multilingual embedding model to map text to a semantic vector space, positioning text with a similar meaning in close proximity
Use the NeoPulse® Framework to build custom deep learning models using data of all types: numeric, text, image, audio, and video.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.