Skip to main content

Archives: All Ads

All Ads

Improving data harvesting/collection for AgFlow by leveraging Natural Language Processing (NLP) and Machine Learning (ML) techniques

Requester: AgFlow S.A. (AgFlow)
Anyone following agricultural commodities currently has no other choice but to source key market information from data lakes of news articles, reports, or analyses that come in many different formats and require much effort to process.

AgFlow is changing how the industry gets access to crucial market information by harvesting various datasets out of these data lakes, structuring them, standardizing them, and serving them through an easy-to-use interface that transforms tedious-to-process information into actionable data. So far, we have achieved to streamline data harvesting for tabular formats. However, contextual information is still tricky to extract without employing legions of market analysts/journalists who would spend their day reading agricultural commodities market news articles, reports, or analyses to highlight trends.

Using Natural Language Processing (NLP) techniques within our ecosystem, we will extract key market data in a scalable way, enrich our database, and enhance our extrapolation models powered by Machine Learning (ML) to serve our users through our platform.

Daten-basierte Services im Maschinenbau

Wie können die erhobenen Daten für Services v.a. im predictive Maintenance Bereich genutzt wer-den? Wie kann darauf aufbauend ein Service System entwickelt und operativ effizient betrieben werden, um Wert für die Kunden (value creation) und die Anbieterin (value capturing) zu schaffen?

Reimagine the access to technical documentation with the support of artificial intelligence

Many manufacturers own miscellaneous inventory product documentation in need of supply to their customers and users. For an efficient retrieval in a content delivery system (CDS), these documents should be first labeled with respect to classification standards relevant for a given industry. However, due to the lack of resources in Technical Editing departments, this classification is often missing, incomplete or follows non-standardized procedures and, as a result, valuable information in the product documentation cannot be discovered in a CDS.

In this project, we aim to approach the problem of large-scale access to product documentation by leveraging the methods of artificial intelligence (AI) for automated document classification. Our goal is to automatically generate metadata for ca. 100’000 documents and make them easily accessible via digital media. We are looking for industry partners seeking to make the information in the company’s product documentation discoverable, and willing to share product documentation with the research partner for experiments. The industry partner(s) will benefit by having its documentation labeled and ready for use in a CDS, and by increasing its digital offer with the developed document discovery tool. Furthermore, we are looking for both complementary industry partners – service or software sector – and research partners to improve applied knowledge. These complementary industry partners might benefit from scaling the solution and providing it to the market.


Conventions of Innosuisse funding projects are the participant concept, not only in terms of content, but also on the administrative-financial level in return gaining the scientific knowledge and expertise of one or several research partners. The contribution of potential industry partner(s) consists of providing non-classified inventory product documentation, being interested in the application or implementation of a Content Delivery Portal and sharing entrepreneurial know how. Financially, the project costs are partially incurring within your company and shall be covering at least same the amount as the funding offered by Innosuisse, of which at least 10% shall cover your research partner’s expenses in terms of a cash contribution.


The planned project intends to be an application-based study where research institutions will work together with at least one industry partner. During this Innosuisse project, we will conduct a qualitative and quantitative text analysis of inventory product documentation. The purpose of this project is to identify the most effective way to automatically produce metadata within a certain classification standard (e.g. iiRDS or VDI 2770). We are also planning to develop a chatbot as a user- friendly interface for document search in a CDS, translating queries in natural language into machine- readable search requests, allowing the future users to interact with the search engine in a comfortable manner.

Economical value for the industry partner (s) is estimated in securing a competitive standing as innovative company e.g. concerning user friendliness or linguistically simplified access resulting in potential revenue and reputation increase. On one hand, the aspired solution is intended to be applicable with the existing resources in Technical Editing, on the other hand, the digital offer might potentially increase customer acquisition, customer satisfaction as well as customer retention. A social value is anticipated for users who could directly profit from the digital supply in terms of optimized language access. An overall economic, social benefit might be gained by actively promoting the automated processes by digitalization in technical communication. As a result of this digital shift, actual challenges like the increasing complexity in the working environment accompanied by the growing skills demand or the prospective labor shortage might be partly resolved.

INSIGHTS APP – Collective Intelligence-based Leadership and Ideation Service

Collaborative cultures of cooperation will determine future success in public management. Digitization offers new technical possibilities in communication, collaboration and (political) leadership. If we succeed in combining innovation with the creation of democratic values at eye level, citizens, public administration, and their employees and leaders will all benefit. The key to success lies in the digital integration and participation of all people involved.
INSIGHTS effectively combines the elements of integration, participation and digitization, focuses on an agile network and puts people in their respective roles at the heart of attention. We achieve more when we work not just alongside or with each other, but for each other in a network. In this way, we feel connected to everyone and engage more effectively in finding the best solutions together. Only those who experience their own actions and doings as meaningful and who have creative freedom in the fulfillment of their tasks or thereby feel that they are part of a larger whole will be able to fully contribute their performance and innovation potential to others – regardless of whether it is an employee, a leader, an entire department or a citizen.
For employees and leaders, integration, participation and digitization are essential in today’s home office reality to ensure full performance and potential development as well as mental health issues through an appreciation-based and motivation-based corporate culture. Today, employees already have changed expectations of their working environment. Discipline, hierarchy and silo structures are being replaced by concepts such as collaboration, democratic decision-making processes and participation. The leadership behavior of leaders who meet these new values is already strategically important today.
Citizens are motivated to participate digitally via app in important decision-making processes and to make their personal contribution, especially in areas in which they are directly or indirectly affected.
For citizens, this offers an ideal opportunity to get involved directly and at any time for their own interests. For the administrative authority a perfect possibility to reach the desired citizen contact fast and straightforward – for more acceptance of the decided actions, a foresight of the emerging (risk) topics and interests of the citizens, the communication of respect, which they can show to the citizens and therefore create trust in the administrative authority. Being close to the citizens is thus not just a slogan, but a plannable activity of the administrative authority.

INSIGHTS uses the implicit knowledge and experience of all roles, whether employees, leaders or citizens through collective intelligence and mobilizes their creative and implementing power for the best solutions. Everyone is always heard equally on important questions, projects, strategies and already implemented decisions, shares their own opinion completely independently without any external pressure or bias and votes anonymously with their knowledge and experience on the ideas and solutions developed by means of preference comparison – in real time. At the same time, new innovative answers to existing questions can be continuously fed into the knowledge pool by everyone – for the sake of employees, leaders, the administrative authority, individual departments and the citizens alike.
Employees can use INSIGHTS for their personal questions and concerns in times of home office, find a buddy, coach or mentor for future collaboration, have a personal or professional exchange, find solutions for a current problem, get their own food for thought or complete their own ideas and make them better.
Leaders and department heads can use INSIGHTS for their management activities as a basis for solutions to existing problems to be worked out, as an early warning system and indicator of what the employees are concerned with, for the very important corporate culture work through involvement and transparency of the employees being managed and creation of a “WE feeling”.

Call for participation
HR can feel the pulse of the organizational corporate culture, conduct satisfaction surveys for upcoming or completed projects, extract direct learnings from them, use them as an indicator of how
the effective psychological health of employees is going, use them as an early warning system and transparent foresight of what issues are coming and more.
Administrators are roles that are allowed to ask questions and are also open to employees, leaders, department heads, and departments, but not to the citizens. Administrators can split their own organization into sub-organizations and launch their own protected collaborative democratic collective- intelligence-based surveys in these rooms without having to re-register. Create rooms for employees, management circles, customer surveys, administrative management, citizens, associations, departments and inform their stakeholders everytime via notification when new questions and answers are available.
The citizens will not be administrators. They are digitally “interviewed” by selected administrators. The citizens can be invited as a user to all collaborative surveys or make their own proposals to the administrative management.
The features:

  • Cross-organizational and cross-departmental structure
    Different sub-structures or parallel internal and external stakeholder groups can be handled at
    the same time.
  • Digital (political) leadership à
    For administrative management, employees, leaders, HR and the citizens.
  • Digital employee coaching and mentoring service
    For employees and HR.
  • Duplications
    We solve duplications through the algorithm.
  • Digital (political) opinion survey
    For administrative management, employees, leaders, HR and the citizens.
  • Collaborative culture of cooperation
    Innovative responses that constantly evolve like Wikipedia.
  • No bias
    There are no multiple-choice answers, clearing the way for innovation.
  • Protection of one’s own thinking power
    The opinions of others are not seen at the time of voting. Each respondent shares their own
    personal opinion without outside influence.
  • Psychological safety
    Full independence and anonymity of all stakeholders for the best solutions. No influence by
    the “loudest”.
  • No up- or downvoting
    We effectively protect against manipulation by comparing preferences.
  • Reporting of inappropriate posts
    We make sure that any “disqualifying” responses can be filtered out.
  • No data loss due to early terminated survey
    We always collect as much and as little information as each respondent is willing to give.
  • Motivation & appreciation of all stakeholders
    Democratic integration and participation leads to full innovation and solutions not yet known.
    Everything that is important for upcoming decisions, strategies or projects.
  • Everyone gets a chance to speak
    Even those who would otherwise not express their views.
  • High innovation power
    Through collaboration and collective intelligence.
  • Democracy and transparency
    During and after completion of the collaborative survey, no one can take corrective action. The
    survey is documented and transparent to all stakeholders.
  • User identification
    Each user is validated by their mobile phone.

Create synthetic data using cutting-edge deep learning


We live in a data driven generation where big data, data mining and artificial intelligence are revolutionizing the ways we obtain value from data. The challenge is that both, private companies and public entities, have no way to easily share this data internally or externally. The main hurdles are:

  • Compliance laws
  • Fears of data misuse
  • Patient / client privacy
  • Inability to transfer data securely
  • High costs for data curation or similar

Syntheticus – our SaaS platform – tackles these hurdles using cutting-edge deep learning. Our platform allows users to generate synthetic data which is anonymous, maintains the same properties as the original and hence can be used for data insights, analysis and sharing.

Syntheticus is the 1st Swiss platform dedicated to generating synthetic data. Our collaborations with Swiss academical institutions enables us to be at the forefront of research. We envision a global market and we’re open for every industry that is dealing with confidential data.

According to a new report from analyst firm Forrester, the move AI 2.0 is being driven by five areas of AI advancement. – one of those five advancements is synthetic data. Forrester believes synthetic data can be used to accelerate the development of new AI solutions, improve the accuracy of AI models, and protect sensitive data. It is currently being used in autonomous vehicles, financial services, insurance and pharmaceutical firms, and computer vision vendors(

Requested support:

Syntheticus is the first platform for hosting multiple models for synthetic data generation. The open source models allow for complete transparency and traceability.This approach allows us to continually add state-of-the-art models based on the latest research.

We are looking to appoint a research partner to advance the research in these topics (synthetic data for formats like tabular, time-series, relational, image, audio, text, etc) in order to implement the models into our platform Syntheticus within a joint Innosuisse project.

Download call as a PDF

Extended Geospatial Data Cube

Extended Geospatial Data Cube- searching for project partners Geospatial data are widely used as explanatory variables for large-scale data analysis and modeling. Many data sources are available today, some of them with high spatial or even temporal resolution
and impressive data quality. However, the potential of using these sources is underachieved. Possible reasons are data costs, but even more a lack of user knowledge or the unhandy data formats.

In the field of satellite data, the new platform SwissDataCube addresses these problems. It offers preprocessed satellite data in a data cube with a uniform spatial resolution (regular grid over Switzerland).

As of Spring 2021 Swisstopo is making its basic geodata freely available (OGD). A large part of this data is available in vector formats and its use is tricky and time-consuming.

The goal is to expand the SwissDataCube with the data from Swisstopo (and other federal offices) and make this geodata accessible to a large target group. The goal is a data cube which:

  • covers Switzerland as a whole
  • provides all data layers in a uniform resolution (first 100m, then 10m, 1m)
  • is based on high quality data sets
  • is updated regularly
  • can be used via an API (Application Programming Interface), for download, as geoservices or as linked data

Intended contents in the extended data cube are:

  • data derived from the elevation model (height, slope, curvature, exposition)
  • percentage of forest / sealed area / cultivated land / …
  • proximity to public transport / hospital / supermarket / …
  • time series such as hours of sunshine / rain / snow / wind / …
  • population, et cetera

The company is looking for pilot users who use the data cube for their analyzes and who participate in the prioritization of the data variables. They are also open to other ideas or contributions.
If you are interested and want to contribute with your company, send an email to (Deadline February 24, 2021), stating

  • Which data levels and resolution are most valuable for you?
  • Do you have already a specific test case in mind? If yes, in which field is it situated?
  • What form of participation are you interested in
    • As project partner, investing manpower or cash and in return influencing (prioritizing) the project?
    • As implementor of a test case?
    • As pilot customer, purchasing access to the data cube
  • Are you willing to implement a test case or would you prefer to contribute with a cash contribution?
  • Could you participate in a Shaping workshop in March?