LINEAR UNSUPERVISED METHOD OF CLASSIFICATION STABLE ON
THE ORDER OF OBJECTS
The invention relates to a linear unsupervised method of classification stable on the order of objects.
It more generally relates to automatic classification techniques known under the term "clustering".
It is notably used in the fields of "Data Mining" and "Text Mining" for "knowledge discovery", with no prior assumptions, in large databases. This data can be of the structured type when dealing with behavioral or demographics data, for example, or of the unstructured type when dealing with textual data.
Starting from a database formed from a set (or population) of n objects
described by a set of m descriptors (or variables), the automatic classification consists in structuring these objects in the form of very homogeneous classes (or groups). This homogeneity means that two objects of the same class must be more similar to (or resemble) one another than two objects belonging to two different classes.
The formation of these classes will allow groups of objects with similar profiles or themes to be easily detected depending on whether the data is of the structured or unstructured type.
This problem has too many permutations and combinations to be solved by an exact method. For this reason, heuristic algorithms that are less costly in terms of processing time and machine resources have been generated in order to-find approximate solutions to it.
Some of these heuristic algorithms offer solutions by arbitrarily fixing the number of classes, whereas others propose a hierarchy having partitions with a variable number of classes.
For example, the following heuristic algorithms may be mentioned:
• The methods of the "mobile centers" type, such as "k-means", dynamic clustering, etc....
• The methods of hierarchical classification (increasing or decreasing)
• The methods of the "first leader" type, etc.

Examples for various unsupervised methods of classification are given in the following references: 1) Saporta G. (1990), Probabilites, Analyse de donnees et Statistique, Technip: 2) Lebart and al (1995), Multidimensional exploratory statistics, Dunod: 3) Hartigan, J. (1975), Clustering Algorithms, John Wiley and Sons, New York, NY, US.
The methods of the "mobile centers" and hierarchical classification type arbitrarily fix a number of classes. On the other hand, the methods of the "first leader" type require a similarity threshold to be fixed and are dependent on the order in which the objects are taken into account. Indeed, they may lead to completely different results depending on the order in which the objects are arranged. Nevertheless, they do allow large quantities of data to be processed within reasonable times. However, in order to achieve this performance, these methods require the maximum number of classes to be fixed at a very small number with respect to the number of objects.
Amongst the major problems encountered in dealing with the issue of automatic classification may be mentioned:
• the determination of the number of classes underlying the population in question,
• the performance in terms of processing times depending on the volume sizes to be processed and in terms of quality of the homogeneity of the classes obtained,
• the capability of interpretation of the results obtained: definition of statistical indicators for the measurement of the homogeneity of the classes together with the discriminating power of the descriptors participating in the formation of these classes.
The idea of the present invention rests notably on the theory of relational analysis. As a reminder, this theory, such as described in one of the following references: 1) P. Michaud and JF Marcotorchino, "Optimization models in rational data analysis", Mathematiques et Sciences Humaines n°67, 1979, p7-38: 2: JF Marcotorchino and P Michaud, "Aggregation of the similarities in automatic classification", Revue def statistique appliquee, Vol 30, n°2, 1981, provides a solution to the problems associated with the fixing of the number of classes and of the

interpretation of the result obtained. However, the underlying theoretical model is extremely costly in terms of machine resources whenever the number of objects exceeds 100. The invention uses a heuristic approach of this theory which allows the theoretical result on large databases to be very closely approximated.
The invention relates to a method of linear unsupervised classification allowing a database composed of objects and of descriptors to be structured, which is stable on the order of the objects, comprising an initial step for transformation of the qualitative, quantitative or textual data into presence-absence binary data, characterized in that it comprises at least the following steps:
a) determine a structural threshold as function of the n2 agreements between
the objects to be classified, the structural threshold defining an optimization criterion adapted to the data,
b) use the descriptors as structuring and construction generators of a partition P or set of classes,
c) progressively merge a class generated by a descriptor and a partition (40, 41,42),
d) for an optimization criterion involving a function f (Cii,CiT,) = Min(Cii,Cii),
linearize sums of Minimum functions.
The method can comprise a step where the classes of the partition are regrouped amongst themselves.
The merge step c) comprises, for example, a step where, based on two intersecting classes, the best operation (in terms of the optimization of the criterion) is determined from amongst the following 4:
• "Breaking" of the first class and formation of two classes;
• "Breaking" of the second class and formation of two classes;
• "Breaking" of the two classes in order to form three classes:
• Joining of the two intersecting classes in order to form one single class.
The regrouping of the classes of a partition is for example carried out over several hierarchical levels and comprises the following steps:
• decrease at each level the value of the structural threshold (70) in such a manner that the weakly negative contributions can become positive,
• maximize links between the classes formed where the links are determined by using the contribution from a pair of objects

Lienk

(Formula Removed)

with or'the new value of a
• combine (71) two classes whose link is positive, and reiterate this process
over all the levels.
The invention also relates to a device for linear unsupervised classification allowing a database composed of objects and of descriptors to be structured, which is stable on the order of the objects, comprising an initial step for transformation of the qualitative, quantitative or textual data into presence-absence binary data, characterized in that it comprises at least the following elements: a computer comprising a memory, a database and a processor designed to implement the steps of the method exhibiting one of the aforementioned features.
The invention notably has the following advantages:
• the possibility of automatically detecting the number of classes during the classification,
• the possibility of processing large quantities of data in reasonable amounts of time,
• its independence with regard to the order of the objects in the database. It is naturally stable with regard to the order of processing of the objects,
• the method allows indicators measuring the quality of the results obtained to be defined and calculated very rapidly (linear complexity),
• the method is stable with regard to the duplication of the objects. In other words, if the database is replicated several times, the same initial solution is recovered with the objects duplicated within the same class.
Other features and advantages of the present invention will become more apparent upon reading the description hereinbelow to which are appended the figures that show:
• Figure 1, a block diagram corresponding to a generic system of a system supporting the method according to the invention,
• Figure 2, a block flow diagram describing the general operation of the processing chain in the field of data mining applied to a corpus of documents or to a numerical database,
• Figure 3, a block flow diagram that shows the steps in the pre-processing

phase which is carried out upstream of the automatic classification process,
• Figure 4, a block flow diagram that shows the ordering of the steps forming the method of this invention,
• Figure 5, a block flow diagram that details the various operations carried out during the processing 41 in figure 4,
• Figure 6, the basic operation that consists in determining the optimum local partition (into one, two or three^ classes) coming from two intersecting classes,
• Figure 7, the quantities evaluated during the basic operation described in figure 6,
• Figure 8, a block flow diagram that shows the steps in the process of hierarchical organization of the classes.
Figure 1 presents a non-limiting illustration of an example of application of the method according to the invention, allowing various actions, which are to be implemented based on the classification results, to be generated automatically.
The system on which the method operates comprises, for example, a computer 1 comprising a memory 2 and a processor 3 associated with the process of classification 5. The computer 1 is in communication with a database 4. The result of classification, for example, takes the form of a set of classes stored in a suitable device 6. The device 6 is, for example, in communication with an email exchange server 7 for example. The server is equipped with suitable processing means known to those skilled in the art for processing the class information received and Dotentially triggering mechanisms for sending messages to the people in the classes ,n question.
Any device enabling actions to be undertaken and/or controlled as a function of the results of the classification may be used.
The description that follows is presented by way of illustration within a general context of executable instructions in a computer program, such as program modules run on a computer or any other calculation device. The invention may be implemented on any kind of computer, PDA, etc.
In figure 2, the starting point can be either any given database (set of individuals described by a set of numerical variables), or any given corpus of documents. These two types of data are respectively represented by the rounded

blocks 20 and 25.
In the case of numerical data, there may be an optional pre-processing phase 21 which consists of conventional statistical processing operations such as the centering or the reduction of the data or else transformations, etc. These pre¬processing operations lead to the data table 22. It is this table that constitutes the source for the information analysis processes 23.
With regard to a corpus of documents, in the course of a pre-processing phase 26, each text is transformed into a vector whose dimensions correspond to descriptors obtained by a linguistic process which can be a morpho-syntactic analysis, an extraction of concepts, an extraction of co-occurrences, linguistic and semantic processing operations, etc. A presence-absence (binary) or frequency matrix 27 is obtained which constitutes the source for the processing operations represented by the block 23.
The block 23 notably corresponds to the data processing and analysis phase. These processing operations can be of several types (supervised classification, unsupervised classification, statistical 'scoring', regression, etc.). The scope of the invention relates to unsupervised classification of data, also known as automatic classification or 'clustering'. The invention notably relates to an unsupervised classification process whose result is, for example, a hierarchy of partitions of the objects 24 or of the documents 28 depending on the initial type of data.
The input data in figure 3 takes the form of a table T, 22 or 27, respectively denoting the cases of numerical data and the case of a corpus of
documents, crossing the set / , composed of n objects Ov02,...,On (individuals or documents), and the set V composed of m variables (or descriptors),
measu-ed on = (Formula Removed)

The table T has as its general term tik which represents the value taken by the variable Vk on the object 0. and takes the following form:
(Formula Removed)

The general term tik, of the input data, represents:
• the modality of the variable k taken by the object i in the case of a qualitative variable,
• the value of the variable k taken by the object i in the case of a quantitative variable,
• the presence or the absence of the lexical unit k in the document i, in the case of textual data.
In the case of qualitative and quantitative data, the method applies re-boding operations 30, described hereinafter, to this table, for example the discretization of the quantitative variables or the re-coding of the qualitative /ariables into presence/absence descriptors. The qualitative and quantitative /ariables are transformed into binary variables that will form a presence-absence
able K.
In the case of the qualitative variables, the transformation consists, for example, in re-coding of the modalities into presence-absence descriptor vectors.
For quantitative variables, the discretizations consist in transforming the quantitative variables into qualitative variables where each modality corresponds to an interval. For example, let the quantitative variable "size" be expressed in cm and measured on a set of individuals. Assuming that, in the population in question, the size of the individuals composing it is in the range between 140 cm and 210 cm, one ossible discretization would be to divide up the variable into the three following ntervals [140,160[: [160,180[: [180,210]. These three intervals then respectively ;orrespond to the three following modalities: small, medium and large. Consequently, an individual who has the size 175 cm for example, after iiscretization, will have the modality medium.
The table K, 31, with general term ktj obtained after these ransformations will take the following form:
(Formula Removed)
Its general term ktJ can have two meanings depending on whether the variables are initially qualitative variables or quantitative variables:
In the case of a qualitative variable, ktj has the following definition:
, _ [ 1 if the object i has the modality j V [0 otherwise
In the case of a quantitative variable, ktj has the following definition:

l if the object i belongs to the segment j 0 otherwise
In the case of the textual data, there is no re-coding step since, after the pre-processing step, 26, a presence-absence binary table is already obtained K whose general term kij has the meaning:
[ 1 if the document i has the lexical unit j kij [0 otherwise
Each variable of the table T, whether it be qualitative or quantitative, will
generate several presence-absence descriptor vectors. Indeed, the tables T and K have different dimensions.
The variable "SPC" (Socio-Professional Category) is considered and it is assumed that there are four individuals . (11, 12, 13, 14) with four possible modalities of the variable SPC being: management, manual worker, professionals. It is furthermore assumed that these four individuals have the following modalities:
(Formula Removed)
After re-coding of the modalities of the qualitative variable SPC, the following result is obtained:

(Table Removed)
Each modality of the variable in question therefore becomes a presence-absence descriptor. Consequently, the table of the transformed data K will have dimensions (nx p) with p> m where m is the variable number in the set V.
Starting from the table K, 31, statistics calculations, 32 (means, standard deviations, discrimination coefficients , etc.), are carried out that notably allow, on the one hand, the filtering parameters of the descriptors, 33 (elimination of the poorly discriminating descriptors), to be set and, on the other hand, an indicator referred to as structural threshold, 34, to be calculated that removes the necessity for setting parameters for the classification process (neither the number of classes nor the maximum number of classes are fixed). The indicator is described in detail hereinbelow.
The filtering allows the descriptors that are poorly discriminating to be eliminated. The elimination of the descriptors will be different depending on their type. In the case of numerical data, a relevance indicator of the descriptor is used as the basis. i
In the case of the documents, the frequency of occurrence of a descriptor within the set of the corpus or any other discrimination measurement indicator such as the entropy, etc., and those that appear not to be very discriminating are eliminated. The filtering step results in a new, reduced binary table, 35, that contains a limited number of columns. It is this new table that is used as input data for the automatic classification process described by the block 36 and detailed in figures 4 and 5.
Structural threshold and criterion adapted to the data
The method according to the invention uses a structural threshold or indicator whose function is notably to define an optimization criterion adapted to the data.
In order to better understand its role, rational analysis theory is recalled which is based on the maximization of the simplified Condorcet criterion as follows:

(Formula Removed)
where C , represents the degree of similarity between the two objects i and i . For example:
and Ot represents the profile of the object 0, given by the ith row of the table K:
and where f(Cii,CiT is a function of the maximum specific agreements of the
individuals i and i.
For example:
etc...
Xii is furthermore given by:
(Formula Removed)
Y _ J1 if the objects i and i are in the same class
ii [0 otherwise
The method according to the invention is of linear complexity given that the formulae of the XS' and type may be calculated linearly.
The functions aforementioned as examples are all linearizable. Indeed, the measure of similarity Cii used is a scalar product having known linearity properties, the

function f(Cii, Cii) = — (Cii + CiT) is linear, whereas the function
f(Cii,Cri,) = Min(Cii,Crr) is not linear. However, calculations of the y^YJMin{Cii,dr) tvPe may be linearized.
By way of illustration, the invention describes the particular case f(Cit,Cn,) = Min(Cij,Crr) especially adapted to databases containing a large number of missing data and the procedures that allow calculations of the Min(Cij, Cir) type to be calculated with a linear complexity.
The method according to the invention implements for example the following criterion:
(Formula Removed)
the unitary contribution of the two
objects i and V to the criterion Cα (X).
According to the invention, the structural threshold parameter as is
calculated automatically. This is an indicator that is a function of the 1 agreements between the objects to be classified:
(Formula Removed)
As an example, its formulation when it represents the ratio of the arithmetical mean of the agreements between all the objects over the arithmetical mean of their maximum agreements:
(Formula Removed)
This formula is linearizable under the same conditions as those previously mentioned.
The criterion Cαs (X) used in the invention consists, for example, in comparing the agreements between any two objects with the product of the threshold as and their maximum agreement (which represents a percentage of the
maximum agreement).
Thus, two objects will automatically be in the same class whenever their similarity is higher than or equal to the calculated percentage of maximum agreement (positive contribution).
Automatic classification process of the invention
The classification process 36 is described in detail in figure 4. The starting point is the table of binary data 35 whose descriptors have been filtered.
The first step of the classification process which consists in sorting the descriptors, 40, relies on a measurement of the contribution of each descriptor to the criterion (quality of a descriptor). For example, the descriptors are used as structuring "generators" for the population of the objects to be classified. A descriptor is represented by a column vector of 1s and 0s (presence-absence). A class is associated with this descriptor that is composed of the objects that take the value of 1. For each class of objects Cq , its level of contribution Contrib(Cq) to the global criterion can then be calculated:
(Formula Removed)
The evaluation of the contribution of a class is of polynomial complexity. Indeed, if it
is assumed that all the objects form a single class, n2 unitary contributions would then need to be calculated in order to determine the value of the criterion.
In the case where Cw is a scalar product, the first part of the formula on
the right, may be simplified in the following manner.
where is called representative of the class C whose terms are
given by the column sum of each modality of the table K for the objects of the class: (Formula Removed)

Each value rf , j=\,...,p, represents the number of objects of the class C that
possess the modality /.
In the case where f(Cii, CiT,) = Min(f(Cii, CiT,), the second part of the formula on the
right of the equation [1] is equal to Minf(Cii, CiT,) The procedure allowing this

quantity to be calculated with a linear complexity is given hereinbelow.
Procedure MinCC (Class C)
Requires: CardC > 0
Requires: Sorted list of individuals for the class C Integer: result = 0 Integer: j - next element of C Integer: i = 0 While the class C has not ended, Do
(Formula Removed)
For each descriptor q, the value of the contribution of the class generated by the latter or else a measurement of the quality of the descriptor with respect to the criterion is thus obtained. These contributions are then sorted, for example by decreasing order, so as to obtain an order for the descriptors to be taken into account. The choice of this order has very little influence on the quality of the result (there may be a few minimal local differences). However, taking the classes generated by the descriptors of best contributions first, allows a stable solution to be obtained more quickly and hence the process of calculation of the best partition 41, coming from the intersection between the current partition and that generated by a
descriptor, to be accelerated.
This process 41 notably consists in progressively "merging" 42, a class generated by a descriptor 40, and a current partition (composed of several classes). This "merging" operation consists in determining, starting from two intersecting classes, the best operation (in terms of the criterion) from amongst the following 4:
• "Breaking" of the first class and formation of two classes;
• "Breaking" of the second class and formation of two classes;
• "Breaking" of the two classes in order to form three classes:
• Joining of the two intersecting classes in order to form one single class.
These operations are illustrated in figure 6 and the calculations allowing the best operation to be decided in figure 7.
This process amounts to constructing step by step a partition that locally and progressively optimizes the global criterion.
Once all the descriptors have been used, the partition obtained P0 is considered as being a first finalized partition of the objects 43. During the "merging" phase (40, 41, 42) of the classes, it is only attempted to "merge" the classes that possess intersections. The object of the processing operation 44 is to merge, in other words to combine, classes that do not have any intersection if this operation allows the criterion to be optimized (test for merging together of the classes of the partition obtained). This leads to a modified partition 45, a partition of level 1, which constitutes the final partition of the classification process.
This partition 45 forms the input for the process of aggregation of the classes, 46, which is described in figure 8.
Figure 5 shows an exemplary block flow diagram of the. processing operation 41. This notably consists in "merging" a new class generated by a
descriptor X denoted Cx, 50, with the current partition P composed of K classes
51. The process is as follows:
• Calculate of the intersections between the classes of the partition P and the class Cx, 52,
• Sort the set A of the classes Cy of the partition P intersecting with the class Cx into decreasing order of the cardinal of their intersection, 53, for
example, • For each class C , 55, of the set A , merge the two classes Cy and Cx, 54.
All the intersections between Cx and P are processed and once all the classes Cy of A have been merged with Cx , 55, a new partition of the objects is obtained
which improves the global criterion and which then becomes the new current partition 51. The next step consists in going to a new descriptor, 42, and this process is repeated until all the descriptors have been processed.
The cardinal of the elements of the set of the intersections of a class Cx
with the classes of a partition P, 52, can be obtained linearly in the manner described hereinafter.
The class Cx is considered as the class whose intersection with a
partition P it is desired to evaluate. With this class is associated a list sorted, for example, by increasing order of the indices of the objects that it contains. For this purpose, each object is identified by a single integer which is its index. In order to sort the objects, a linear sorting process is for example used (for example, sorting by base for which one reference is the following: Cormen et al (2002), Introduction to algorithmics, Dunod) since the upper bound of the values to be sorted is known.
The operation for calculating the cardinal of the intersections uses a
vector A of dimension n for which each dimension i represents the index of the class where the individual Oi .is stored.
Example of calculation of intersection cardinals:
If a population of 6 objects Ol,02,---,06 and a current partition of these
objects P, 51, composed of three classes
C1 = {O1, 03}, C2 = {02,04,06}, C3 = {O5} is taken
The vector A is equal to:

(Table Removed)
Thus, if the existing partition is "merged" with a class Cx = {02,03,04,06} 50, the cardinal can be quickly determined of the set intersection of the class Cx with the classes of the existing partition, in the present case Card{Inter(ClCx))=l, Card(lnter(C2Cx)=3 and Card(lnter(C3Cx)) = 0 .
The number of operations carried out during the calculation of the intersections 52 is equal to the number of objects in the class Cx to be merged with
the partition P. Indeed, for each object of the new class, it is verified whether it belongs to a class of the partition P; if it does, the intersection counter for this class is incremented.
If there are several intersections between a class Cx and a partition P, as indicated hereinbelow, the cardinal of the various intersections between Cx and the various classes Cy of the partition P are calculated in order to obtain an order for them to be taken into account.
Based on the intersection of Cx and of one class C of the partition P,
it is assessed which is the best configuration from amongst those present in figure 6. For this purpose, the quantities identified in figure 7 are evaluated. Figures 6 and 7 therefore explain an example of basic operations of the invention which are represented by the processing step 54.
The process of "merging" of two classes is for example as follows.
Let Rx and Ry be the representative vectors of the classes Cx and
C , the vectors R" , Rb and Rc are constructed that are defined by:
(Formula Removed)
where Cc =CZ n Cy is the class defined by the intersection of Cx and Cy (the
objects in both the classes Cx and Cy ) and Rc its representative.
Hence, Ra represents the objects which are only in C and Rb those which are only in CardA, CardB and CardC will be respectively defined as the cardinals of the classes represented by Ra , Rb and Rc . The two lists of objects contained in the classes Cy and Cz are sorted by
increasing order of their index. The following conventional procedure can therefore be applied in order to quickly calculate the three vectors:
*********************************************
Procedure for Vector calculation (Class Cx, Class Cy)
R° =Ry
Rb = Rx
Rc =0
CardA = CardB = CardC = 0
ij = list of the objects of Cy
e = head of the list £,
L, = list of the objects of Cx
f - head of the list L2
While the list L, has not ended, Do
While the list L2 has not ended, Do
If e (Formula Removed)

Based on these three vectors, it is possible to choose the best solution from amongst the following four, these being shown in an example in figure 6:
• - "break" the class Cy in order to deliver the two following classes: Cy - Cx
and Cx
• "break" the class Cx in order to deliver the two following classes: Cx - Cy and Cy
• "break" the class Cr and "break" the class C„ in order to deliver the three following classes: Cx - Cy , Cy- Cx and Cy n Cx
• merge the two classes in order to deliver a single class: Cy U Cx .
The choice of the best of the four solutions is, for example, based on the evaluation of the "links" between the 3 different sub-classes presented hereinabove. The general calculation of the "link" between two classes C and C , is given by the following formula:
(Formula Removed)
When the measure of similarity is a scalar product, and when f(Cij*,CiY) = Min(Cii,Cn,), as previously, the calculation of the link between two
different classes can be .linearized. The method uses, for this purpose, the linearity properties of the scalar product, which yields the following simplification:
(Formula Removed)
The following procedure may also be used which allows the quantity ^ ^Min(Cii9Cvr) to be evaluated with a linear complexity:
Procedure MinCC (Class C, Class C)
Requires: CardC > 0 Requires: CardC >0
Requires: Sorted list of individuals for the classes C and C Integer: resultat = 0 Integer: nb_rows - CardC Integer: nb_cols - CardC Integer: j = next element of C Integer: f = next element of C While the class C has not ended and the class C has not ended, Do If j 0
Requires: K > 0
Requires: Sorted list of individuals for the classes C
Integer: result = 0
Integer: nb _ rows - CardC
Integer: nb_cols = n
Integer: j = next element of C
(Formula Removed)
Procedure MiniC (Class C)
(Formula Removed)

CLAIMS
1 - A method of linear unsupervised classification allowing a database composed of
objects and of descriptors to be structured, which is stable on the order of the
objects, comprising an initial step for transformation of the qualitative, quantitative or
textual data into presence-absence binary data, characterized in that it comprises at
least the following steps:
• determine a structural threshold αs function of the n2 agreements between
the objects to be classified, the structural threshold defining an optimization criterion adapted to the data,
• use the descriptors as structuring and construction generators of a partition or set of classes,
• progressively merge a class generated by a descriptor and a partition (40, 41,42),
• for an optimization criterion involving a function f(Cu,Cir) = Min(Cu,Crr), linearize sums of Minimum functions.

2 - The method as claimed in claim 1, characterized in that it comprises a step where the classes of the partition are regrouped amongst themselves.
3 - The method as claimed in claim 1, characterized in that the merge step comprises a step where, based on two intersecting classes, the best operation (in terms of the optimization of the criterion) is determined from amongst the following 4:

• "Breaking" of the first class and formation of two classes;
• "Breaking" of the second class and formation of two classes;
• "Breaking" of the two classes in order to form three classes:
• Joining of the two intersecting classes in order to form one single class.
4 - The method of classification as claimed in claim 2, characterized in that the
regrouping of the classes of a partition is carried out over several hierarchical levels
and comprises the following steps:
• decrease at each level the value of the structural threshold (70) in such a
manner that the weakly negative contributions can become positive,

• maximize links between the classes formed where the links are determined
by using the contribution from a pair of objects
(Formula Removed)
with or'the new value of a
• combine (71) two classes whose link is positive, and reiterate this process
over all the levels.
5 - A device allowing linear unsupervised classification that allows a database composed of objects and of descriptors to be structured, which is stable on the order of the objects, comprising an initial step for transformation of the qualitative, quantitative or textual data into presence-absence binary data, characterized in that it comprises at least the following elements: a computer (1) comprising a memory (2), a database (4) and a processor (3) designed to implement the steps of the method as claimed in one of claims 1 to 4.
6 - The device as claimed in claim 2, characterized in that it comprises a means (7) for undertaking actions depending on the results of the classification.