Skip to main content



Reporting period: 2018-10-01 to 2019-09-30

A growing number of people talk to their smart phones to send e-mails and text messages, search directions or find information on the web. Our society is in a transition point where voice and natural-language understanding are suddenly at the forefront. Speech recognition market is expected to reach $9.97 Billion by 2022, whereas voice recognition market growth is expected to reach $1.99 Billion by 2022. At the same time, mobile usage is growing worldwide and so is mobile shopping. Smartphones play a major role in consumers’ lives, as they have become the default medium to access Internet not only for information or to socialize but also to shop. Conversational commerce is a trend emerged from the use of voice search via mobile personal assistants. However, e-commerce marketers must guarantee that they deliver a satisfying experience if they wish to survive. The introduction of voice search was just the beginning, consumers want now artificial virtual /digital assistants to be more helpful for a more enjoyable shopping experience. With the use of Artificial Intelligence (AI) and the combination of services, the e-commerce industry can offer a better shopping experience. Chatbots represent a huge opportunity because people are using messenger apps more than social networks.

PERTIMM detected a growing demand from Internet users and buyers for cost-effective, neutral and privacy-friendly services and from chatbot developers for platforms that support fast and cost effective chatbots development. The general objective of VOQAL.AI project is to accelerate the introduction of the first European multilingual collaborative and open-source platform for chatbot developers, which allows independency of GAFAs (Google, Apple, Facebook, Amazon) and guarantees data treatment and privacy. Different specific objectives were defined:

- To provide an enabled faster and cheaper development of bots and voice assistants.
- To allow the development of added-value chatbots (multilingual, cheaper, etc.).
- To respond to the European nations semantic and linguistic specificities through a platform capable of easily creating a structured interpretation of a natural language sentence.
- To create and consolidate a large and skilled community of contributors and moderatos that will be actively contributing towards the enlarging of the platform.
- To contribute to the EU industry independency of USA big players and avoid GAFAs hegemony.

The main conclusions of the project are the following:
- Creation of an open European multillingual collaborative platform compiling innovative features:
- Semantic open-source interpretation cartridges;
- A three-tiers structure which offers a power of expression that is exponentially greater than all other platforms;
- Automatic learning of interpretation rules by specific AI mechanisms integrated in the platform.
- Wide dissemination of project results among the main stakeholders
- Advance towards the final commercialisation of the platform

We are on the verge of launching the platform and many different communications have been prepared.
It can already be viewed at
The purpose of the work carried out has been to contribute to the achievement of the ultimate objective of the project, the development of the first European multilingual collaborative and open-source platform. For that purpose, the work has been divided into five different WPs, in which Pertimm has intensively worked during the project. All this work has resulted in different deliverables accurately reflecting all the actions performed.

From a project management point of view, Pertimm has worked mainly on the administrative, financial and technical management of the action and on the continuous reporting to the European Commission (EC).

From a more technical point of view, Pertimm has dedicated their efforts to the finalisation of the scaling up of the platform, mainly the addition of a tuning system and the AI learning system. On the other hand, Pertimm has also worked on the upgrade of the interfaces of contributors and moderators , the addition of plugins and the SDK and the validation of the platform with real end users. Pertimm has also finalised the development of a generic chatbot for e-commerce website and mobile app, i.e. the development of a prototype of an unplugged generic chatbot and vocal assistant for e-commerce.

Finally, Pertimm has dedicated huge efforts to the dissemination, communication and commercialisation of the platform, as well as to the monitoring of the markets and products for exploitation purposes. Pertimm has attended different international events during these 2 years where the presentation of their platform has been very successful and has also made contact with potential clients interested in the platform. Pertimm will continue to disseminate the results of the project after the end of the action, and will participate in 2 different events in Paris (France).
Over the years, dramatic changes in how we interact with computers have occurred. We went from flipping switches to stacking punch cards, typing away on hard copy and now, manipulating objects on a desktop using touch screens. Each transition has provided a greater ease of interaction. But, advances in speech recognition are completely changing the game: The idea of chatbots is decades old, but it exploded in 2016 when Facebook opened its Messenger platform to third-party developers.

Currently most of the speech-driven systems available are: 1) triggered task models (that do things for the user) or 2) call and response systems (just fun to interact with as entertainment). The trend is moving towards Intelligent Conversational UI (full-fledged dialogue systems with broad domain, a user can interact with it via speech and/or text and engage freely), that do not exist technically yet (only in movies or science fiction stories). Interfaces like Siri Alexa, Amy etc. come close to that. However, most NLI’s are domain specific and narrow, but even in that confined domain they don’t work well. Additionally, the technology is walled-off, proprietary, and secretive.

The main novelty of Pertimm’s platform in regards to existing platforms is derived from the following disruptive approach:

- Collaborative aspect of the platform;
- The semantic open-source interpretation cartridges, not only code;
- The form and genericity of the rules of interpretation: chatbots/conversational platforms currently available are based upon a two-tiers structure (intents and entities). VOQAL.AI is based upon a three-tiers structure (intents, interpretation rules, entities). This offers a power of expression that is exponentially greater than all other platforms;
- Multilingualism to progressively incorporate all EU languages;
- Automatic learning of interpretation rules by specific AI mechanisms integrated in the platform. Currently, conversational platforms help the bot developer by proposing examples of bots. Pertimm intends to take it to a whole new level by merging existing bots, recognizing that some bots can benefit from other bots in different areas (i.e. a car reservation bot can benefit from a hotel reservation bot).
- Data privacy: the IP address or mobile number of the users are never recorded. internal view agents that can been seen as a developer/moderator Logo home page