The application underlying this decision relates to measuring communication skills of crew members. However, the European Patent Office refused to grant a patent since claim 1 mainly addresses the improvement of calculating a (non-technical) property, namely the prosodic accomodation of two crew members during a conversation. Here are the practical takeaways of the decision T 2689/18 (Measuring communication skills of crew members/Trinity College Dublin) of January 25, 2022 of Technical Board of Appeal 3.4.03:

Key takeaways

Improving the quality of a (non-technical) output from a (technical) signal processing procedure cannot contribute to the technical character of an invention.

The invention

The application underlying the present decision mainly concerns the measuring of specific communication skills (e.g., prosodic accomodation) from a recorded conversation between at least two crew members (cf. paras. [0001] and [0014] of the application).

Fig. 4 of WO 2015/014956 A1

Here is how the invention is defined in claim 1 of the main request:

  • Claim 1 (Main Request)

Is it technical?

Both the Board in charge and the Appellant agreed that the closest prior art document D1 fails to disclose the following two features of claim 1:

1. Two recorded audio traces from two participants in a conversation are compared with each other in order to provide a rating for each of the at least two participants as well as a joint rating for the at least two participants together, and

2. The calculation of the correlation coefficient is based on a time window, the default length of which is extended to include the speech utterance of each crew member it its entirety.

The Appellant argued that adjusting the default length, which is extended to include the speech utterance of each crew member in its entirety, by flexibly varying a time window used in the calculation of the correlation, would result in a better resolution of the correlation coefficient.

However, the Board considered both features as non-technical. Regarding the first feature of measuring the skills based on comparing their recorded audio traces, the Board argued as follows:

1.1 Comparing and analysing two audio traces (signals) instead of only one as disclosed in D1 is carried out using the same, generally know signal processing techniques. Otherwise indicating details are not provided in the application.

1.2 The specified prosodic parameters used in the analysis are based on speech utterance and are as such non-technical. The reason for this is that they involve a mixture of administrative, psychological and mental acts. The same reasoning applies to the numerical rating resulting from the signal processing of the two audio traces.

1.3 Moreover, the aural detection of the crew’s behaviour does not go beyond the computer-implementation of a equivalent analysis by a human. An increased objectivity of the ranking arises purely from the computer-implementation itself due to the straightforward automation by the computer.

Regarding the second feature concerning the default length of the moving time window, the Board outlined:

2.1 The choice of the length as well as the positioning of the window are purely subjective choices that have no technical influence on the calculation of the correlation coefficient or the statistical modelling technique. Instead, only the quality of the calculated coefficient is improved. Given that the rating has no technical meaning, obtaining a “better” or “more accurate” rating has no technical meaning as well. Consequently, the choice of the length of the time window is seen as a choice based on an administrative consideration, a scheme of performing a mental act or a mathematical method, all of which are non-technical.

Despite the lack of a further technical effect, the Board also responded to the Appellant’s argument that the definition of the “default length” is of a flexible or extendable nature:

2.2 The wording of said feature, namely the “default length is extended to include the speech utterance of each crew member in its entirety” does not necessarily express the appellant’s interpretation that the moving time window is of a flexible or extendable nature. According to the definition of claim 1, it can be understood that the “default length” is adjusted according to the entire duration of the speech utterance of each participant once at the beginning of the statistical modelling. From this, one cannot conclude that the window length is flexibly varied and extended during the course of the analysis. There is also no passage of the application which defines the exact meaning of the term. In fact, the term is used only once in the entire description (para. [0049]) and in a very similar wording. Accordingly, a flexibly variable time duration cannot be unequivocally derived.

Since both differentiating features are considered as non-technical, they cannot contribute to an inventive step over D1.

Therefore, the Board dismissed the appeal due to lack of inventive step.

More information

You can read the whole decision here: T 2689/18 (Measruing communication skills of crew members/Trinity College Dublin) of January 25, 2022.

Stay in the loop

Never miss a beat by subscribing to the email newsletter. Please see our Privacy Policy.

Privacy policy *
* = Required field

Please share this article if you enjoyed it!