Method for establishing communication between at least two apparatuses in a communication network

Abstract

The invention relates to a method for establishing communication between at least two apparatuses in a communication network. Such a method comprises, in an intermediate device: - receiving (11), from one of said two apparatuses, referred to as first apparatus, a first message (M1) which is formatted in a first language associated with said first apparatus; - generating (12), from said first message (M1), a second message (M2) which is formatted in a second language associated with the other one of said two apparatuses, referred to as second apparatus, said second message (M2) corresponding to a translation of said first message (M1) into said second language, the generation being implemented by means of at least one artificial neural network; and - transmitting (13) said second message (M2) to said second apparatus.

Description

Method for establishing communication between at least two devices in a communication network.

[0001] The invention relates to the field of communication networks. More particularly, the invention relates to the administration and supervision of equipment used for the implementation of such networks. Prior art

[0002] A communications network is generally based on an infrastructure comprising numerous devices of various origins and types, which the network operator must be able to administer and supervise, for example, in order to quickly detect potential malfunctions or optimization options and be able to intervene accordingly to ensure optimal operation of the network. To this end, an operator can notably collect and monitor numerous metrics reported by this equipment, for example in the form of predefined key performance indicators (also called KPIs). If necessary, an operator can also send instructions to a device in order to temporarily or permanently modify its configuration.

[0003] In addition to the presence of different equipment to ensure various functions, it is common for equipment of the same type but from different equipment manufacturers to be implemented within the same communication network, for example for reasons of cost, hardware redundancy intended to make the network more robust, network deployment history, etc. This hardware diversity is not without raising certain problems for the operator: not only is it likely to constitute an obstacle to the interoperability of these different pieces of equipment, but it also significantly complicates the supervision, administration and configuration of the communication network. Indeed, each equipment manufacturer tends to implement its own system of metrics and commands, when it comes to providing a user (typically an operator) with the tools to manage the equipment it sells.Thus, metrics (i.e. indicators) of the same nature for equipment of the same nature but coming from different equipment manufacturers are often named differently (the same indicator is for example named "VS.DLPRBUsedPerTypeService.VoIPGBR.Cum" for one equipment manufacturer and "DLPRBUSEDPTYPESERV_VOIPGBR_CUM" for another equipment manufacturer), or even associated with different value formats (the same indicator is for example returned in the form of an integer for one equipment manufacturer, and a relative number for another equipment manufacturer). The same applies to the commands made available to modify the configuration of these equipments, which, from one equipment to another, are likely to have not only different names for similar functions, but also to accept parameters of different formats.Added to this already significant heterogeneity is the fact that the operator generally has its own nomenclature and format system, different from those of its equipment manufacturers, with regard to these indicators or orders, which further complicates network administration and supervision operations.

[0004] To address these issues, standardization work has been undertaken, particularly by organizations such as 3GPP ("3rd Generation Partnership Project") and ETSI ("European Telecommunications Standards Institute") in the field of telecommunications networks. Despite these standardization attempts, operators and equipment manufacturers have not managed to converge towards the use of a standard for nomenclature and format of data related to network configuration and administration. Furthermore, the proposals and additional recommendations formulated by these organizations in this field remain little adopted and little implemented by the various stakeholders involved.

[0005] As a result, an operator is generally forced to develop and maintain mediation interfaces, based on software code, in order to be able to consolidate in its own information system the indicators sent back from the various devices in its communication network, or to send configuration messages to this equipment. Given the frequent changes to a communication network (deployment of the network with more recent hardware and / or software, replacement of obsolete equipment, upgrade of certain equipment, etc.), this software code must be constantly reviewed and updated, and its complexity increases over time.For example, the integration of new equipment into the operator's network requires the operator to develop and integrate the software code necessary to, on the one hand, translate the indicators reported in the telemetry messages sent by the equipment from a proprietary language specific to the equipment manufacturer to the proprietary language specific to the operator, and on the other hand, translate the commands transmitted in the configuration messages sent by the operator from the proprietary language specific to the operator to the proprietary language specific to the equipment manufacturer. Such operations are generally not limited to a simple renaming of the names of the indicators and commands, but often require complex aggregation and adaptation manipulations (an indicator on the operator side may, for example, correspond to the sum of a plurality of indicators on the equipment manufacturer side, with different data formats).

[0006] The development and maintenance of the software code implemented at the level of these mediation interfaces is therefore proving increasingly tedious and costly, with a growing risk of errors, given the high number and variety of equipment integrated into current communication networks.

[0007] There is therefore a need for a solution to simplify the administration and supervision of the numerous heterogeneous devices in a communications network, and more generally to facilitate overall interoperability between these different devices.

[0008] The present technique makes it possible to propose a solution aimed at remedying certain drawbacks of the prior art. According to one aspect, the present technique relates to a method for establishing communication between two devices of a communication network. Such a method comprises, at an intermediate device, at least one iteration of the following steps for implementing said communication:

[0009] - the reception, from one of said two devices, called first device, of a first message formatted in a first language associated with said first device;

[0010] - the generation, from said first message, of a second message formatted in a second language associated with the other of said two devices, called second device, said second message corresponding to a translation of said first message into said second language, said generation being implemented by means of at least one artificial neural network;

[0011] - the transmission of said second message to said second equipment.

[0012] In this way, it is no longer necessary to resort to the tedious and complex operations of developing and maintaining a conversion code between different communication languages ​​at the level of mediation interfaces to enable the implementation of communication between equipment associated with different communication languages.

[0013] In a particular embodiment, said first message is a message associated with a telemetry task, said first message comprising at least one name and one value associated with at least one indicator sent by said first equipment, said at least one indicator being associated with an operating state of said first equipment and / or said communication network.

[0014] In this way, the present technique allows in particular easy management of the operations of collecting and monitoring metrics reported by the first equipment, and in particular key performance indicators linked to the first equipment and / or the communication network.

[0015] According to a particular characteristic of this embodiment, said second message comprises at least a translation of said name into said second language and / or a conversion of said value into a corresponding indicator value format of said second language.

[0016] In this way, the present technique allows automatic conversion of the metrics reported by the first equipment (typically equipment from an equipment manufacturer) into a format that can be directly used by the second equipment (typically equipment from an operator).

[0017] In a particular embodiment, said first message is a message associated with a configuration task, said first message comprising at least one configuration modification instruction sent by said first equipment to said second equipment.

[0018] In this way, the present technique allows in particular easy management of configuration operations, for example by an operator, of the equipment of a communication network.

[0019] According to a particular characteristic of this embodiment, said second message comprises at least one translation of said instruction into said second language and / or a conversion of at least one parameter associated with said instructions into a corresponding configuration parameter format of said second language.

[0020] In this way, the present technique allows an automatic conversion of the configuration instructions issued by the first equipment (typically an operator's equipment) into a format directly understandable and executable by the second equipment (typically an equipment manufacturer's equipment).

[0021] In a particular embodiment, said at least one artificial neural network is a transformer-based network.

[0022] In this way, the prospects for obtaining optimal performance for the translation from the first language to the second language are maximized, since transformer-based networks, and in particular autoregressive networks, have already proven themselves in contexts of automatic translations from one language to another for languages ​​used by human speakers.

[0023] In a particular embodiment, said at least one artificial neural network is trained by learning, by means of at least one learning base comprising a plurality of samples associating in this order input data formatted in said first language with target data formatted in said second language, said target data corresponding to a translation of said input data into said second language.

[0024] In this way, with the proposed technique, the business logic is managed at the level of one or more learning bases rather than at the level of complex and difficult to maintain conversion software code, which offers numerous advantages in terms of simplicity and flexibility, particularly for taking into account developments in the communication network.

[0025] In a particular embodiment, for each sample of said plurality of samples, said at least one learning base comprises a sample called a mirror sample associating in this order said target data formatted in said second language with said input data formatted in said first language.

[0026] In this way, a learning base for training artificial neural networks to support bidirectional or multidirectional translations is easily built, by simply duplicating samples with inversion of the input data and the target data.

[0027] In a particular embodiment, said at least one learning base further comprises a plurality of samples associating data formatted in said first language and / or said second language with translated data formatted in at least one other language different from said first language and said second language.

[0028] In this way, the present technique makes it possible to manage a “multilingual” context, with translations from at least one language to several other languages ​​being able to be implemented by the same intermediate device.

[0029] In a particular embodiment, said samples comprise at least one association between:

[0030] - at least one indicator name and one indicator value format in said first language with at least one corresponding indicator name and one indicator value format in said second language; and / or

[0031] - at least one configuration command name and configuration parameter format in said first language with at least one corresponding configuration command name and configuration parameter format in said second language.

[0032] In this way, a learning base for training a neural network to handle telemetry and / or configuration tasks is easily built.

[0033] In a particular embodiment, a specific indicator and / or parameter value in said input data is respectively representative of an absence of a corresponding indicator and / or parameter in said target data.

[0034] This way, the user has a way to indicate that an indicator or parameter has no equivalent in a target language, or that it should not be translated.

[0035] In a particular embodiment, said samples further comprise, in at least one of said input data and said target data, information belonging to the group comprising:

[0036] - an actor identifier associated with a piece of equipment;

[0037] - an equipment identifier;

[0038] - an equipment version;

[0039] - a software identifier associated with a piece of equipment;

[0040] - a version of software associated with equipment;

[0041] - a timestamp;

[0042] - a type of task.

[0043] In this way, various complementary data are present in the samples of the training base, in order to complement or facilitate the training of the neural network.

[0044] In a particular embodiment, said information is preceded by a prefix identifying the associated type of information, said prefix being, for a given type of information, constant throughout said learning base.

[0045] In this way, the detection of this additional information by the neural network is facilitated, and the learning task is further simplified.

[0046] According to another aspect, the present technique also relates to a device for establishing communication between two devices of a communication network. Such a device comprises:

[0047] - means for receiving, from one of said two devices, called first device, a first message formatted in a first language associated with said first device;

[0048] - means for generating, from said first message, a second message formatted in a second language associated with the other of said two devices, called second device, said second message corresponding to a translation of said first message into said second language, said generation being implemented by means of at least one artificial neural network;

[0049] - means of transmitting said second message to said second equipment.

[0050] According to another aspect, the proposed technique also relates to a computer program product downloadable from a communication network and / or stored on a computer-readable medium and / or executable by a microprocessor, comprising program code instructions for executing a method of establishing communication between two devices of a communication network as described above, when executed on a computer.

[0051] The proposed technique also relates to a computer-readable recording medium on which is recorded a computer program comprising program code instructions for executing the steps of the method as described above, in any of its embodiments.

[0052] Such a recording medium may be any entity or device capable of storing the program. For example, the medium may include a storage medium, such as a ROM, for example a CD-ROM or a microelectronic circuit ROM, or a magnetic recording medium, for example a USB flash drive or a hard disk.

[0053] On the other hand, such a recording medium may be a transmissible medium such as an electrical or optical signal, which may be conveyed via an electrical or optical cable, by radio or by other means, so that the computer program contained therein is remotely executable. The program according to the invention may in particular be downloaded over a network, for example the Internet.

[0054] The various embodiments mentioned above can be combined with each other to implement the invention. Figures

[0055] Other characteristics and advantages of the invention will appear more clearly on reading the following description of a preferred embodiment, given as a simple illustrative and non-limiting example, and the appended drawings, among which:

[0056] illustrates the general principle of a method for establishing communication between two devices of a communication network, in a particular embodiment of the proposed technique;

[0057] presents some samples of a learning base capable of being used to train at least one artificial neural network to translate a message from one language to another, in a particular embodiment of the proposed technique;

[0058] describes a simplified architecture of an intermediate device for implementing the proposed technique, in a particular embodiment. Detailed description of the invention

[0059] This application makes it possible to remedy some of the aforementioned drawbacks.

[0060] The proposed technique aims in particular to provide a simpler, less expensive and more flexible solution than the development and maintenance of mediation software interfaces according to the prior art – which generally rely on “raw” (i.e. “hard”) coding of translation rules – for establishing communication between potentially heterogeneous equipment (for example because they come from different equipment manufacturers) within a communication network.

[0061] In this document, the proposed technique is mainly presented in the context of exchanges of telemetry and configuration messages between network equipment forming at least part of the infrastructure of a telecommunications network (e.g. a 3G, 4G or 5G network). It is understood that this example is purely illustrative and non-limiting, and representative of a particular embodiment of the proposed technique. In particular, the present technique can be implemented in other contexts, including exchanges of messages relating to other types of tasks than telemetry or configuration tasks.

[0062] The term "equipment-associated language" (or, by extension, "equipment-specific language") is hereinafter understood to mean a set of syntax rules, nomenclature (of data such as indicators, functions, etc.) and format expected and / or used by a network device in its communications with third-party devices. By analogy with human speakers, this is the "language" spoken and understood by the network device, i.e. the communication language in which it delivers information or commands to other devices and in which it is able to understand information or commands received from other devices. The present technique thus relates to translation solutions making it possible to establish communication between network devices that do not necessarily share the same language.

[0063] In all figures of this document, identical elements and steps are designated by the same reference numeral. Furthermore, in the following description, the terms "first" and "second" (used to describe equipment, a message, a language, etc.) are intended only to allow a distinction to be made between two elements, and in no way imply the existence of any ordering relationship between these elements.

[0064] According to a first aspect, the present technique relates to a method for establishing communication between two devices of a communication network: a first device associated with a first communication language and a second device associated with a second communication language (generally different from the first communication language). The first language and the second language may differ in that the messages and / or the attributes and / or the values ​​of the respective languages ​​are different. The general principle of such a method is illustrated in relation to the, in a particular embodiment of the proposed technique. This method is implemented at the level of an intermediate device, i.e. at the level of a device capable of relaying any communication or any message relating to the communication from one of the two devices to the other of the two devices (and vice versa), where appropriate by adapting them.Such an intermediate device may be included in third-party equipment separate from the two equipments between which communication is to be established. Alternatively, the intermediate device may be embedded within one or other of these two equipments, for example within a communication interface of the equipment concerned.

[0065] In a step 11, the intermediate device receives a message M1 from the first device of the communication network. Such a message comprises data formatted in the language associated with said first device, i.e. in the first communication language.

[0066] In a step 12, the message M1 received in step 11, called the first message, is provided as input to at least one artificial neural network previously trained to translate data from at least one language, and more particularly from the first language associated with the first device, to at least one other language, and more particularly to the second language associated with the second device. This neural network processes the first message M1, and generates as output a second message M2 corresponding to a translation of the first message M1 into the second language associated with the second device.

[0067] In a particular embodiment, the neural network used is a transformer-based neural network (better known as "Transformers"). According to a particular characteristic, the neural network model is more particularly of the "pure decoder" type (e.g. GPT model, from the English "GenerativePre-Training"): only the decoder part of the transformer-based neural network is retained. Such a model, called autoregressive, is interesting in that it has already proven itself for the implementation of automatic translations from one language to another (e.g. from French to German), with regard to languages ​​spoken by human speakers. The proposed technique is however not limited to the "decoder" type model, and other transformer-based neural network models, for example of the "encoder-decoder" type (e.g. T5 or mT5 models), or of the "pure encoder" type (e.g.BERT model, from the English "BidirectionalEncoderRepresentationsfromTransformers") can also be used within the framework of this technique. It should be noted that it is not simply a question of using a technique or a tool (such as for example the GPT model) for a different context (network supervision) than the initial context (language translation). Indeed, the new context of use of this technique requires in particular more complex conversions, formatting or even aggregations, implying a significant adaptation of the technique as described in the.

[0068] According to the present technique, the neural network is trained by learning, for example by supervised learning, using a learning base constructed in a particular manner, as detailed later in relation to various particular embodiments of the proposed technique. More particularly, such a learning base comprises a large number of examples (typically thousands or hundreds of thousands), called samples, of translation from at least one source communication language to at least one target communication language.

[0069] In a step 13, the second message M2 is transmitted to the second device. This second message M2 being formatted in the second language associated with this second device, it is perfectly understandable by this second device, and communication is thus established between the first device and the second device.

[0070] Of course, several iterations of steps 11 to 13 can be implemented successively, in particular for the implementation of a two-way communication (the first device of an iteration becoming the second device of another iteration, and vice versa). According to a particular characteristic, a batch translation (batch processing in English) of a plurality of messages can be implemented during steps 11 to 13 (for example via parallel processing techniques implemented by means of an intermediate device based on a multi-core or multi-processor architecture).

[0071] Thus, the proposed technique makes it possible to avoid having to develop and maintain complex code for converting between different communication languages, thanks to the use of at least one neural network previously trained to deduce and generalize correspondences between these communication languages ​​from correspondence examples provided in one or more learning bases (also sometimes referred to as "training data sets"). In other words, with the present technique, the business logic is no longer managed algorithmically at the level of software code, but is moved to the level of one or more learning bases, which offers much more simplicity, flexibility and adaptability to modifications of one or other of the communication languages ​​to the user (the code of the neural networks notably remaining agnostic to the business logic).

[0072] The present technique is particularly suitable for implementation in the field of supervision and administration, by an operator, of the equipment of a telecommunications network. Indeed, as presented in relation to the prior art, such equipment (for example radio access network equipment of the “RAN” type) often uses a proprietary language specific to the equipment manufacturer that markets it.

[0073] Thus, in a particular embodiment of the proposed technique, in at least one iteration of the method for establishing a communication previously described, the message received by the intermediate device is a telemetry message from a piece of equipment implemented within the infrastructure of a communication network. Such a telemetry message comprises at least one value associated with at least one indicator sent by the equipment to the network operator, this indicator being for example associated with an operating state of said equipment and / or said communication network.This telemetry message received at the intermediate device in the language specific to the equipment that emitted it is then translated by the intermediate device, by means of one or more neural networks as previously described, into a language compatible with the operator's system, then relayed to this operator (for example to a specific server) so that the latter can use the information it contains.

[0074] In a complementary or alternative manner, in a particular embodiment of the proposed technique, in at least one iteration of the method for establishing a communication previously described, the message received by the intermediate device is a configuration message sent by the operator of the communication network (for example via a specific server) and intended for a particular piece of equipment implemented within the infrastructure of this network. Such a configuration message comprises at least one configuration modification instruction, and possibly one or more associated parameters.This configuration message received at the intermediate device in the language specific to the operator who sent it is then translated by the intermediate device, by means of one or more neural networks as previously described, into the language specific to the equipment targeted by the configuration modification request, then relayed to this equipment so that the latter can implement the required configuration modification operations.

[0075] We now describe, in relation to the, an extract of an example of a learning base capable of being used to train at least one neural network, so that an operator (here named O) is able to administer the equipment of two equipment manufacturers (here respectively named A and B), in a particular embodiment of the proposed technique. In this example, eight samples E1 to E8 are presented.

[0076] To facilitate reading, the parts of a sample containing data formatted according to the language of OEM A are underlined with a solid line, the parts of a sample containing data formatted according to the language of OEM B are underlined with a dotted line, and the parts of a sample containing data formatted according to the language of operator O are not underlined.

[0077] As can be seen in the, each sample associates input data formatted in one language with target data formatted in another language, the target data corresponding to a translation of the input data into this other language. A sample is therefore mainly composed of two parts – a left part corresponding to the input data and a right part corresponding to the input data translated into another language – possibly separated by a separator (the character string “->” in the example in the) to facilitate the identification of these two parts by the neural network.

[0078] More particularly, in a particular embodiment, the training base comprises samples corresponding to examples of translation of telemetry messages, and samples corresponding to examples of translation of configuration messages.

[0079] So, if we first look at the four samples E1, E2, E3 and E4:

[0080] - samples E1 and E3 relate to the translation of telemetry messages used to send indicators from equipment manufacturers A and B respectively to operator O;

[0081] - samples E2 and E4 relate to the translation of configuration messages used to send configuration instructions from operator O to equipment manufacturers A and B respectively.

[0082] The samples corresponding to examples of telemetry message translation associate at least one indicator name and one indicator value format in a first language with at least one corresponding indicator name and indicator value format in a second language. Thus, if we consider for example sample E1, we see that the indicator with the name "kpi-1" in the system of equipment manufacturer A corresponds to the indicator with a different name "kpi1" in the system of operator O, and that equipment manufacturer A values ​​this indicator in the form of a real number (value "3.1") while operator O associates it with an integer (value "3") in its own system.

[0083] The samples corresponding to examples of translation of configuration messages associate at least one configuration command name and one configuration parameter format in a first language with a configuration command name and one configuration parameter format in a second language. Thus, if we consider for example sample E2, we see that the command with the name "set-foo-threshold" in the system of operator O corresponds to the command with the different name "foo" in the system of equipment manufacturer A, and that while operator O passes as a parameter of this command an integer (parameter "param1" with value "10") the corresponding command of equipment manufacturer A expects such a parameter or an equivalent parameter with a different name and in the form of a real number (parameter "param-1" with value "10.0") in order to be able to execute it.

[0084] According to a particular characteristic, a specific value (for example the value "9999") may be assigned to an indicator (in the case of telemetry message translation) or to a parameter of a configuration instruction (in the case of configuration message translation) in the input data formatted in a first language, to indicate that the indicator or parameter in question has no equivalent in the second language and / or that it must be ignored when translating from the first language to the second language. For example, in sample E3, the value "9999" is assigned to the name indicator "kpi-III" in the input data, to signify an absence of a corresponding indicator in the target data (for example because such an indicator has no equivalent in the second language, or because for various reasons the operator voluntarily wishes to ignore it).

[0085] The preceding examples of samples E1, E2, E3 and E4 are purely illustrative and non-limiting, and other types of nomenclature and / or format correspondence may appear in the learning base within the framework of the present technique, for example associations between a single indicator for an actor and a plurality of indicators for another actor (e.g. when an indicator on the operator side corresponds to the aggregation of several indicators on the equipment manufacturer side), associations in which a configuration command for an actor is broken down into several configuration commands for another actor, associations between distinct formats (e.g. between integers “0” and “1” on the one hand with respectively character strings “false” and “true” on the other hand), etc.

[0086] In a particular embodiment, to supplement or facilitate the learning of the neural network, various additional data are present in the samples of the learning base, in addition to the data relating to the indicators and their values ​​or to the commands and their parameters. Thus, the samples comprise, for example, in their left part and / or in their right part, additional information in addition to the purely telemetric or configuration data, comprising (by way of illustration and not limitation) an actor identifier (for example the name of an equipment manufacturer or an operator), an equipment identifier (for example an equipment model name), an equipment version, a software identifier associated with an equipment, a software version associated with an equipment, a timestamp, a type of task (e.g. telemetry, configuration, other type of task), etc.According to a particular characteristic, to facilitate the detection of this additional information by the neural network, a prefix identifying the associated type of information is used within the samples of the training base. In this case, such a prefix, which can also be called a “tag”, is constant throughout the training base. For example, in the example of the, the same prefix “actor-id:” is used throughout the training base to specify that the information immediately following this prefix is ​​an actor identifier (identifier “O” for the operator, “A” for the equipment manufacturer A, or “B” for the equipment manufacturer B).

[0087] In a particular embodiment, for at least one sample of the learning base associating in this order input data formatted in a first language with target data formatted in a second language (corresponding to the input data translated into the second language), the learning base contains a so-called "mirror" sample associating in this order said target data formatted in said second language with said input data formatted in said first language. According to a particular characteristic, each sample present in the learning base corresponds to a mirror sample also present in the learning base. For example, the samples E5, E6, E7 and E8 present in the illustrated learning base correspond respectively to the mirror samples of the samples E1, E2, E3 and E4 also present in the learning base.

[0088] Such an implementation is particularly interesting when it comes to training autoregressive neural networks, which are particularly efficient in the context of the present technique, so that these causal type networks do not remain in monodirectional use after training (i.e. only able to translate in one direction, from a first language to another, but not in the other direction, from the second language to the first), but that they are on the contrary capable of bidirectional or multidirectional translations in the case where the translation is valid for a number greater than two actors.

[0089] It is also interesting to note that the present technique makes it possible to manage a context which can be described as "multilingual", in the sense that translations from at least one language to several other languages ​​(potentially up to several hundred other languages) can be implemented by the same intermediate device.

[0090] For example, according to a first implementation, a single neural network can be implemented at the intermediate device level, for the translation of many languages ​​(more than two), if the learning base which was used to train it contains examples of messages translated from at least one language to and from a plurality of other languages ​​(i.e. from at least one language to at least two other languages). This is the case in particular for the example of the learning base illustrated in relation to the, which is not limited to samples comprising examples of translation between only two languages, but which on the contrary comprises examples of translation of messages in a language specific to the operator O to or from several other languages, i.e. the language associated with the equipment manufacturer A and the language associated with the equipment manufacturer B.Such a neural network, and the learning base used to train it, can then be described as “multilingual”.

[0091] Alternatively or in a complementary manner, in a second implementation, several neural networks can be implemented at the intermediate device level, and more particularly one neural network per pair of languages ​​to be managed (e.g. a first neural network for translation between operator O and equipment manufacturer A, a second neural network for translation between operator O and equipment manufacturer B, possibly a third neural network for translation between equipment manufacturer A and equipment manufacturer B, etc.). In this case, each neural network is trained independently of the other neural networks, by means of a learning base of its own and which contains only associations between the two predefined languages ​​to be processed by the neural network in question, and which can therefore be described as “bilingual”.It may be interesting to note that a multilingual learning base for training a single neural network, as presented in relation to the first implementation previously described, can for example be obtained by concatenating several bilingual learning bases.

[0092] According to another aspect, the proposed technique also relates to an intermediate device capable of carrying out the method previously described in any of its embodiments, for establishing communication between two devices of a communication network. More particularly, such a device according to the present technique comprises:

[0093] - means for receiving, from one of said two devices, called first device, a first message formatted in a first language associated with said first device;

[0094] - means for generating, from said first message, a second message formatted in a second language associated with the other of said two devices, called second device, said second message corresponding to a translation of said first message into said second language, said generation being implemented by means of at least one neural network;

[0095] - means of transmitting said second message to said second equipment.

[0096] La represents, in a schematic and simplified manner, the structure of such a device, in a particular embodiment. The intermediate device according to the proposed technique comprises for example a memory 31 consisting of a buffer memory M, a processing unit 32, equipped for example with a microprocessor μP, and controlled by the computer program Pg 33, implementing steps of the method for establishing communication between two devices of a communication network according to at least one embodiment of the invention. To this end, the intermediate device also comprises at least one communication interface (for example an Ethernet communication interface), allowing it to receive and transmit messages from and to other devices present in the communication network, and at least one message translation neural network.

[0097] Upon initialization, the code instructions of the computer program 33 are loaded into the buffer memory before being executed by the processor of the processing unit 32. The processing unit 32 receives as input E, for example, a first message from a first device of the communication network, this first message being formatted in a first language associated with said first device.

[0098] The microprocessor of the processing unit 32 then carries out the steps of the method for establishing a communication, according to the instructions of the computer program 33. More particularly, the first message received at input E is provided as input to at least one neural network implemented by the processing unit 32 and previously trained to translate data formatted in at least one language into data formatted in at least one other language. From the first message formatted in the first language, the neural network more particularly generates a second message corresponding to a translation of the first message into a second language associated with a second device of the communication network. This second message is then transmitted by the processing unit 32 at output S to the second device, for exploitation.

Claims

Method for establishing communication between two pieces of equipment in a communication network, said method being characterized in that it comprises, at the level of an intermediate device, at least one iteration of the following steps for the implementation of said communication:- reception (11), from one of said two pieces of equipment, said first piece of equipment, of a first message (M1) formatted in a first language associated with said first piece of equipment;- generation (12), from said first message (M1), of a second message (M2) formatted in a second language associated with the other of said two pieces of equipment, said second piece of equipment, said second message (M2) corresponding to a translation of said first message (M1) into said second language, said generation being implemented by means of at least one artificial neural network;- transmission (13) of said second message (M2) to said second piece of equipment. Method according to claim 1 characterized in that said first message is a message associated with a telemetry task, said first message comprising at least one name and a value associated with at least one indicator reported by said first equipment, said at least one indicator being associated with an operating state of said first equipment and / or said communication network. The method according to claim 2 characterized in that said second message includes at least one translation of said name into said second language and / or a conversion of said value into a corresponding indicator value format of said second language. Method according to claim 1 characterized in that said first message is a message associated with a configuration task, said first message comprising at least one configuration modification instruction for said second equipment issued by said first equipment to said second equipment. Method according to claim 4 characterized in that said second message includes at least one translation of said instruction into said second language and / or a conversion of at least one parameter associated with said instruction into a corresponding configuration parameter format of said second language. Method according to claim 1, characterized in that said at least one artificial neural network is a transformer-based network. Method according to claim 1, characterized in that said at least one artificial neural network is trained by learning, by means of at least one training set comprising a plurality of samples associating in this order input data formatted in said first language with target data formatted in said second language, said target data corresponding to a translation of said input data into said second language. Method according to claim 7, characterized in that for each sample of said plurality of samples, said at least one training base comprises a sample called a mirror sample associating in this order said target data formatted in said second language with said input data formatted in said first language. Method according to claim 7, characterized in that said at least one training base further comprises a plurality of samples associating data formatted in said first language and / or said second language with translated data formatted in at least one other language different from said first language and said second language. A method according to claim 7, characterized in that said samples comprise at least one association belonging to the group comprising: - a telemetry type association, associating at least one indicator name and an indicator value format in said first language with at least one corresponding indicator name and indicator value format in said second language; - a configuration type association, associating at least one configuration command name and a configuration parameter format in said first language with at least one corresponding configuration command name and configuration parameter format in said second language. Method according to claim 10, characterized in that a specific value of indicator and / or parameter in said input data is respectively representative of an absence of corresponding indicator and / or parameter in said target data. A method according to claim 10, characterized in that said samples further comprise, in at least one of said input data and said target data, information belonging to the group comprising: - an actor identifier associated with a piece of equipment; - an equipment identifier; - an equipment version; - a software identifier associated with a piece of equipment; - a software version associated with a piece of equipment; - a timestamp; - a task type. Method according to claim 12, characterized in that said information is preceded by a prefix identifying an associated type of information, said prefix being, for a given type of information, constant throughout said training database. Device for establishing communication between two pieces of equipment in a communication network, said device being characterized in that it comprises: - means for receiving, from one of said two pieces of equipment, said first piece of equipment, a first message formatted in a first language associated with said first piece of equipment; - means for generating, from said first message, a second message formatted in a second language associated with the other of said two pieces of equipment, said second piece of equipment, said second message corresponding to a translation of said first message into said second language, said generation being implemented by means of at least one artificial neural network; - means for transmitting said second message to said second piece of equipment. Product computer program downloadable from a communication network and / or stored on a computer-readable medium and / or executable by a microprocessor, characterized in that it includes program code instructions for the execution of a process according to any one of claims 1 to 13, when executed by a computer.

Images