Music – Instruments – Electrical musical tone generation
Reexamination Certificate
2001-07-02
2002-09-17
Fletcher, Marlon T. (Department: 2837)
Music
Instruments
Electrical musical tone generation
C084S600000, C084S615000, C084S649000, C084S653000
Reexamination Certificate
active
06452083
ABSTRACT:
DESCRIPTION
The present invention relates to an incremental sequence completion system and method designed to compute e.g. music sequences in a variety of different contexts and situations, including: Internet adaptive or interactive radio, digital audio broadcasting (DAB) with intelligent scheduling, music recommendation systems, and other innovative Electronic Music Distribution (EMD) services in general. These sequences are generated “iteratively”, step by step. The present invention also concerns a system or server adapted to implement such a method.
Advances in networking and transmission of digital multimedia data have made it possible to provide users with huge catalogues of information, such as music catalogues. These advances thus raise not only the problem of distribution, but also the problem of choosing the desired information among huge catalogues.
Such new developments raise music selection problems which may depend on users' aims or those of content providers. Although modelling a user's goal in accessing music is very complex, two basic elements, i.e. desire of repetition and desire of surprise, can be identified.
The desire of repetition means that people want to listen to music they already know, or similar to what they already know. Sequences of repeating notes create expectations of the same notes to occur. On the other hand, the desire for surprise is a key to understanding music at all levels of perception.
Of course, these two desires are contradictory, and the issue in music selection is precisely to find the right compromise: provide users with items they already know, or items they do not know but would probably like.
From the viewpoint of record companies, the goal of music delivery is to achieve a better exploitation of the catalogue. Indeed, record companies have problems with the exploitation of their catalogue using standard distribution schemes. For technical reasons, only a small part of the catalogue is actually “active”, i.e. proposed to users, in the form of easily available products. More importantly, the analysis of music sales shows clearly decreases in the sales of albums, and short-term policies based on selling many copies of a limited number of items (hits) are no longer efficient. Additionally, the sales of general-purpose “samplers” (e.g. “Best of love songs”) are no longer profitable, because users already have the hits, and do not want to buy CDs in which they like only a fraction of the titles. Instead of proposing a small number of hits to a large audience, a natural solution is to increase diversity by proposing more customised albums to users.
The system according to the present invention allows to compute one step in the music sequence generation process. When implementing the inventive system, the server typically receives repeated calls to provide full-fledged EMD services.
For instance, a user may compute the choice of an initial music title by using a device or system of the invention. He thereby starts the procedure from an empty sequence. The system then computes a next title using a sequence containing the first computed title, etc. The system computes only the “best next item”, sometimes referred to here as “bext”, of a given sequence of items. This allows to compute different kinds of continuations, and to take into account possible changes in the user's taste, or in the sequence heard.
The system according to the present invention takes into account two main parameters:
1) a context of what is listened to, given by a sequence of items that is supposed to have already been heard by the user; and
2) a user profile, defining the taste of the user.
Typically, the items are music titles, and the sequences of music programs composed of a sequence of titles, e.g. interactive Internet Radio and “on-demand” music compilations.
The system produces the “best next item”, i.e. “bext”: Here, the term “bext” means the item proposed by the server which should satisfy two criteria: 1) conforming to the user's taste, and 2) being consistent within the given context (defined by the sequence).
The main innovative idea of the present invention resides in combining two elements, i.e. 1) an incremental sequence completion system and 2) a standard-user profiling system. The term completion is well known in the field of computing, and refers to the technique of completing by anticipation a sequence of which the first elements are given as an input.
The method in accordance with the present invention is capable of operating interactively. In other words, the user (recipient of the sequence) can send data to the server during the course of a sequence generation to modify the selections to follow in the sequence. These data can e.g. correspond to parameters that form the user profile. A dialogue can thereby be established between the user and the server of the sequence: the server delivers an item of the sequence and the user may, in response, indicate his or her appreciation of that item, e.g. through user profile parameters. The response is taken into account by the server to modify—if needs be—the corresponding profile accordingly. In this way, the server can evolve in real time by such interactions with the user to provide an increasingly accurate choice of best next items in the sequence, and thereby effect an optimised completion through a better anticipation of the next item of the sequence likely to satisfy the user.
In the present invention, the term “database” is used for designating any collection of data, e.g. covering both pre-stored data and dynamically stored data. There are many situations in which it is necessary or desirable to create a sequence of items (e.g. music titles) from a collection of items for which data are available. It is also important that a created sequence is “coherent”, i.e. there should exist a particular relationship between attributes (or descriptors) of the items which constitute a sequence. Typically, the attributes of the items, components of the sequence, should not be too dissimilar, especially for successive items in the same sequence.
A system for producing “coherent” sequences of items in a particular order is known from patent document EP-A-0 961 209. However, this patent deals specifically with sequences having a length that is initially fixed, i.e. known a priori.
The items are generally stored in a database and described in terms of data pairs, each pair respectively consisting of an attribute and the corresponding value. The problem of creating the desired fixed length sequence is treated as “Constraint Satisfaction Programming (CSP)”, also disclosed in the above EP application. The sequence to be obtained is specified by formulating a collection of constraints holding on items in the database. Each constraint describes a particular property of the sequence, and the sequence can be specified by any number of constraints.
The items in the database exhibit a particular generic format with associated taxonomies for at least some of the attribute values. Also, the constraints are specified out of a predetermined library of generic constraint classes which have been specially formulated. The special constraint classes allow the expression of desired properties of the target sequence, notably properties of similarity between groups of items, properties of dissimilarity and properties of cardinality. These constraint classes enable the properties of coherent sequences to be expressed in a particularly simple manner.
It is the combination of the use of a generic format for items in the database and the special constraint classes which makes it possible to use CSP solution techniques to solve the combinatorial problem of building an ordered collection of elements satisfying a number of constraints.
Much work has been carried out in user recommendation systems. Most of this work is based on the idea of managing user “profiles”, using some sort of collaborating filtering approach (for instance, the FireFly technology). Similarity measures between profiles allow to compute the close
Cazaly Daniel
Pachet François
Fletcher Marlon T.
Frommer William S.
Frommer & Lawrence & Haug LLP
Simon Darren M.
Sony France S.A.
LandOfFree
Incremental sequence completion system and method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Incremental sequence completion system and method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Incremental sequence completion system and method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2859617