Method, device and system for transferring a terminal attachment from a first access device to a second access device

Abstract

Method, device and system for transferring a terminal attachment from a first access device to a second access device. The invention relates to a method for transferring a terminal attachment (Term) from a first access device (STA) to a second access device (STB), the terminal (Term) having previously established a data session (Sess) via the first access device (STA), and said session data being routed between the terminal and the first access device (STA) using time and frequency resources (R1), the method being implemented in the second access device (STB) and comprising receiving from the first access device (STA) at least one transmission characteristic (Caract) of a first data file associated with a neural network (RN_STA), attaching the terminal to the second access device,an update of a second data file from at least one received feature, said second file associated with a neural network (RN_STB), comprising a plurality of session data transmission features specific to the session (Sess) and the second access device (STB), and routing of all subsequent session (Sess) data through the second access device (STB) alone, in accordance with the updated second data file, following the detachment (404) of the terminal with the first access device. Abstract figure: Figure 2,

Description

Title of the invention: Method, device and system for transferring a terminal attachment from a first access device to a second access device technical field

[0001] This disclosure relates to the field of communication networks and more particularly to techniques for transferring a terminal from a first access device to a second access device in a communication network. Its aim is more specifically to optimize data transmission following the terminal transfer by leveraging the terminal's attachment to the first access device. Prior art

[0002] Advances in the field of Artificial Intelligence (AI) have opened many doors and enabled the application of these techniques to numerous fields. Among these is, in particular, the field of digital signal processing for telecommunications.

[0003] A first approach to using artificial intelligence techniques in the field of telecommunications consists of implementing physical layer functions with AI techniques, such as neural networks. In this functional block approach (encoding, communication channel estimation, decoding, etc.), classical algorithms used in current telecommunications networks are replaced by an AI element. Thus, the same error correction and optimization algorithm can be implemented either by a standard algorithm or by means of a neural network. This makes it possible to benefit from the advantages of such an approach (performance, complexity, implementation flexibility) while remaining transparent from the point of view of the signal processing chain architecture, as well as the protocols used.In this approach, the usual functions for combating the deleterious effects of the propagation channel through equalization or error correction remain; only the way they are implemented changes, the new method being based on AI techniques.

[0004] A second, more disruptive approach abandons the objective of seamlessly integrating into a deterministic signal processing chain. It no longer involves preserving the blocks as described in the first approach, but rather considering a communication channel as a whole and acting on the communication without distinguishing between the different blocks. The degrees of freedom available to the AI ​​are then greater, and consequently, so is its optimization potential. In a bidirectional data exchange scheme between two learning systems, communicating at

[0005]

[0006]

[0007]

[0008]

[0009] Through a given propagation channel, this learning characteristic allows them to progressively learn the most efficient method for communication. By following common optimization metrics, the two systems learn to make the best use of the shared propagation channel and thus define an optimized communication system. From this perspective, it is not simply a matter of canceling out the harmful effects of the channel to get as close as possible to a perfect channel (Gaussian channel), but rather of finding the optimal way to use a given channel. If we take this approach to its logical conclusion, we arrive at what the state of the art refers to as communication between two autocoders that have developed their own "language." This second approach, although promising, faces two limitations: It can only be implemented between two systems with similar learning capabilities, and benefiting from a first "primary" bidirectional communication capability to allow the implementation of the feedback loop necessary for learning. The principle of channel-specific optimization has the direct consequence that this optimization is only relevant for that specific implementation. However, in certain contexts, such as mobile radio communications, the propagation channel is not stable but evolves regularly, which necessitates a form of continuous learning. In the context of mobile networks, these changes in the data propagation channel can take two forms: Continuous evolution: linked to natural channel phenomena, such as equipment movements or changes in the propagation environment. These evolutions are gradual and occur, for example, between the terminal and a base station. They are detected and monitored, generally through the use of reference signals that allow for updating channel knowledge. In the case of a communication system that has learned to communicate on the channel in question, two scenarios are possible: - Either the changes are very rapid compared to the time required for learning on a static channel. In this case, this variability will be integrated into the learning process, even if it limits the performance of the resulting configuration, because it is poorly adapted to the current channel. - Either the changes are slow, meaning the phenomenon in question can be considered static over the learning period. The occurrence of such variations will therefore necessitate an update of the training program to adapt the chosen model to the new channel configuration. Depending on the extent of this change, the revision of the existing training program will be more or less profound.

[0010] Discontinuous evolution: Here, the evolution of the radio channel is sudden and lacks continuity with the previous situation. It is no longer an evolution of the existing channel but rather a change to a new propagation channel. In the context of a telecommunications network, such evolutions are typically caused by a change of the access device during a communication (also called a handover).

[0011] It follows from such an evolution that the learning protocol is reset with a fallback to the primary communication mode during the handover from one access device to another access device.

[0012] In the case of a change of attachment access device, restarting the learning process from scratch is inevitable since the terminal <-> access device pair has changed.

[0013] Reverting to the primary communication mode will most often result in a significant degradation of the radio link's efficiency and therefore of the quality of service provided by the network. Furthermore, the learning process takes time, which does not guarantee good transmission quality during this period. Finally, this learning process involves the consumption of radio resources and therefore a temporary loss of capacity.

[0014] It is therefore apparent that discontinuous changes can be frequent and negatively impact network efficiency and the quality of the user experience. Summary of the invention

[0015] The purpose of this disclosure is to address all or part of the limitations of prior art solutions, in particular those described above, by proposing a solution that makes it possible to optimize data transmission between a terminal and a new access device using neural network techniques, by taking advantage of data transmission from the terminal with a previous access device, this transmission also using neural network techniques.

[0016] To this end, a method is proposed for transferring an attachment from a terminal from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the method being implemented in the second access device and comprising: - a reception from the first access device of at least one transmission characteristic of a first data file associated with a neural network, said file comprising a plurality of transmission characteristics of the session data specific to the session and the first access device, - a receipt of an attachment request from the terminal, - an update of a second data file from at least one received feature, said second file comprising a plurality of session data transmission features specific to the session and the second access device, said plurality being associated with the routing of session data through the second device using said time and frequency resources, - routing of all subsequent session data via the second access device only, in accordance with the second updated data file, following detachment of the terminal with the first access device.

[0017] The transfer method is implemented between two access devices, these two devices intervening in the routing of data from a session established by a terminal performing a handover between these two access devices. The session data is transmitted using the same time and frequency resources, regardless of which access device is routing the session data. The transfer method is advantageous because it allows the second access device to update its neural network more quickly, which is used to optimize the routing of data sent to or received from the terminal, during or after the handover.The transfer of terminal access between the two access devices includes a phase during which the terminal is simultaneously attached or connected to both access devices and communicates with both access devices using unique transmission means, namely time and frequency resources common to the terminal's communications with both access devices.By transmitting one or more transmission characteristics of a data file, specific to the session and the first device, to the second access device prior to the attachment of the terminal to the second access device, this second access device can update or initialize its file associated with its own neural network, specific to itself and to the current session, by reusing part of the transmission characteristics of the first file, thus sparing it a complete initialization of the neural network learning process, which could slow down on the one hand the increase in quality of data transmission via the second access device as well as the completeness of the handover when the terminal is detached from the first access device.When a neural network is indicated, it may be understood that the neural network may include a neural network and an associated file for sending data to the terminal as well as a neural network and a file. associated for receiving data from the terminal. The transfer process in this case involves transmitting a feature from a file via a neural network, for both sending and receiving, or a single file to both the sending and receiving neural networks. The second device then updates two neural networks using either two files or one file.

[0018] According to one aspect of the invention, the transfer method further includes prior to detachment of the terminal with the first access device, a routing of the session data received from the terminal, in place of the first access device, in the case where the processing of the data received by the second access device is greater than a reference value.

[0019] During the handover, the two communications between the terminal and the two respective access devices use the same communication resources, in terms of time and frequency, and the two devices therefore receive the same signals, in separate channels, from the terminal, which itself has a single transmitting neural network. In the absence of signal combination, each device takes the received signal and processes it, for example by demodulating it. It is therefore necessary that one of the two signals processed by each of the access devices be taken into account and that the data resulting from this processing be routed to the destination.The embodiment, based on a reference value, for example, data with zero errors or a transmission quality above a threshold, allows the selection of one of two access devices for the selection of the device whose data will be routed to the remote equipment with which the terminal established the data session. Given that the handover is implemented from a first access device to a second access device, this second access device should more likely be selected as the signal received by the terminal from the second device improves.

[0020] According to another aspect, the transfer method further includes a combination of the session data received from the terminal with the session data received by the first access device, prior to the detachment of the terminal with the first access device.

[0021] According to another embodiment, the second access device has the ability to combine session data received from the terminal with data received from the terminal by the first access device while the terminal is simultaneously connected to both access devices. Thus, the second device can reconstruct the session data by combining the data received by both devices from the terminal, the latter having a single neural network for transmitting session data to both access devices.

[0022] According to a particular embodiment, the transfer method further includes a modification of a transmission characteristic specific to the emission of data to the terminal, included in the second file, as a function of the evolution of a capacity of a propagation channel used for the routing of data between the terminal and the second access device.

[0023] In the downlink, that is, for the transmission of session data to the terminal, the terminal receives data on two propagation channels, respectively between the terminal and the first access device on the one hand, and between the terminal and the second access device on the other. The second access device, to which the terminal is transferred during the handover, updates its transmission characteristics in the file associated with the neural network or the transmission neural network, so that the weight of the signal, and therefore of the data transmitted by the second device, has a preponderance over the data transmitted by the first device, thus indicating to the terminal, which recombines the received signals, that the data from the second device should be taken into account with increasing priority in the signal recombination for the data received from the two access devices.

[0024] According to another particular embodiment, the transfer process is characterized by the updating of the second file, the second file comprising the creation of a second data file, the second file comprising session data transmission characteristics specific to the session and to the second access device, said characteristics being derived from a complete learning of a neural network to which the new file is associated, in the case where at least one transmission characteristic from the first device is not usable.

[0025] In the unfavorable case where the transmission of the feature between the two access devices is not possible or the received feature is unusable by the second access device due to a transmission problem, a version problem, or a file problem, then the second access device performs a complete reset of its file associated with its neural network (or neural networks if it has a transmitting neural network and a receiving neural network), requiring a learning of all the transmission features of the file.

[0026] The different aspects of the transfer process that have just been described can be implemented independently of each other or in combination with each other.

[0027] The invention also relates to a method for transferring a terminal attachment from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the process being implemented in the terminal and comprising: - the issuance of a terminal attachment request to the second access device, - the transmission of session data via the first access device and the second access device, using common time and frequency resources for communications with both access devices, based on at least one transmission characteristic of a data file associated with a terminal neural network, common for communications with both access devices, - a detachment of the terminal with the first access device and then the transmission of subsequent session data through the second access device only, depending on at least one transmission characteristic of the data file updated according to the detachment.

[0028] The terminal, equipped with a single neural network (this neural network may include a neural network for transmitting data and a neural network for receiving data), uses the same time and frequency resources to communicate with both access devices. When the handover occurs and the terminal is subsequently attached to the second device and then solely to that device, it must progressively adapt its data file associated with its neural network, for example by varying the scalar parameters, such as the weights of each access device, as the handover occurs until the weights associated with the first device become null, the data session then being of the unicast type, i.e., between the terminal and the second device.

[0029] According to one aspect, the mutation process further comprises a combination of the session data received from the first access device and the second access device, based on at least one transmission characteristic specific to the reception of the session data, at least one characteristic being included in the data file prior to the detachment of the terminal with the first access device.

[0030] Prior to the completion of the handover, corresponding to the situation where the terminal is attached only to the second access device, the terminal is multi-attached to both devices and receives the same data from both access devices, possibly with different transmission qualities. The terminal can advantageously modify the file associated with its neural network to increase the weights of the second access device in the neural network, as the quality of the signal between the terminal and the second access device, and as a corollary, to decrease the weight of the data of the first device in its file, thus giving an increasing priority to the data received from the second device, in the combination of data, as the handover progresses.

[0031] According to another aspect, the mutation process is characterized by the fact that the terminal includes two data files associated with two common neural networks for the two access devices in the terminal, one for receiving session data from the access devices and the other for sending data to the access devices.

[0032] The terminal may advantageously include two neural networks, respectively for the transmission and reception of session data, so as to optimize the neural network for each data transmission channel, and thus improve the quality of data transmission, respectively of data reception, for the terminal each neural network being specifically adapted to the constraints of each direction of transmission.

[0033] The different aspects of the mutation process that have just been described can be implemented independently of each other or in combination with each other.

[0034] The invention also relates to a device for transferring an attachment from a terminal from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the device comprising a transmitter, a receiver, a processor and memory coupled to the processor with instructions intended to be executed by the processor for:

[0035] - receive from the first access device at least one characteristic of transmission of a first data file associated with a neural network, said file comprising a plurality of session data transmission characteristics specific to the session and the first access device,

[0036] - receive an attachment request from the terminal,

[0037] - update a second data file from at least one character received information, the said second file comprising a plurality of session data transmission features specific to the session and the second access device, said plurality being associated with the routing of session data through the second device using said resources of time and frequency, - route all subsequent session data through the second access device only, in accordance with the second data file, following detachment of the terminal with the first access device.

[0038] This transfer device is capable of implementing in all its embodiments the transfer process which has just been described.

[0039] The invention also relates to a device for transferring a terminal attachment from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the transfer device comprising a transmitter, a receiver, a processor, and memory coupled to the processor with instructions intended to be executed by the processor for: - to send a terminal attachment request to the second access device, - transmit session data via the first access device and the second access device, using common time and frequency resources for communications with both access devices, based on at least one transmission characteristic of a data file associated with a terminal neural network, common for communications with both access devices,

[0040] - to transmit the following session data via the second only access device, following the detachment of the terminal with the first access device, depending on at least one data file transmission characteristic, updated depending on the detachment of the terminal with the first access device.

[0041] This mutation device is capable of implementing in all its embodiments the mutation process which has just been described.

[0042] The invention also relates to a system for transferring an attachment from a terminal from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the system comprising: - a transfer device as described above, - a mutation device as described above, - a change device comprising a transmitter, a receiver, a processor and a memory coupled to the processor with instructions intended to be executed by the processor to send to the second access device at least one transmission characteristic, and to ensure the detachment of the terminal with the first access device.

[0043] The invention also relates to a terminal comprising a mutation device as described above.

[0044] The terminal can be a smartphone, a PC or a local network access device such as a home gateway (box).

[0045] The invention also relates to computer program products comprising a set of program code instructions which, when executed by at least one processor, configure said at least one processor to implement the respective transfer and mutation processes according to any one of the implementation modes of this disclosure.

[0046] The invention also relates to a computer-readable recording medium on which is recorded a set of program code instructions which, when executed by at least one processor, configure said at least one processor to implement a transfer process or a mutation process according to any of the embodiments of this disclosure. Brief description of the drawings

[0047] The invention will be better understood upon reading the following description, given by way of non-limiting example, and made with reference to the figures which represent: - [Fig. 1][Fig. 1]: a schematic representation of a communication network comprising two access devices in which the methods for transferring an attachment of a terminal from a first access device to a second access device and for switching are implemented, according to an embodiment, - [Fig.2][Fig.2]: a schematic representation of a communication network comprising two access devices in which are implemented the processes for transferring an attachment of a terminal from a first access device to a second access device and for switching, according to an embodiment, - [Fig.3][Fig.3]: a representation of a neural network according to a mode of realization - [Fig.4][Fig.4]: a diagram illustrating the main steps of a process of transfer of a terminal attachment from a first access device to a second access device, according to one embodiment, - [Fig.5][Fig.5]: a representation of a device for transferring an at- Transfer of a terminal from a first access device to a second access device, for example, - [Fig.6][Fig.6]: a representation of a mutation device of an at transfer of a terminal from a first access device to a second access device, according to an example.

[0048] In these figures, identical reference numerals from one figure to another designate identical or analogous elements. For clarity, the elements shown are not to scale unless otherwise stated. Description of the implementation methods

[0049] More generally, it should be noted that the implementation and realization methods considered above have been described as non-limiting examples, and that other variants are therefore conceivable.

[0050] In the following description, a communication network is presented comprising access devices (cellular network access stations, Wi-Fi access stations, for example of the Box type, or any other access station providing access to the communication network, including a satellite access station, for example of the Internet type). The stations and network equipment can be instantiated as specific equipment or as virtualized functions.

[0051] We refer first of all to [Fig.1] which presents a schematic representation of a communication network comprising two access devices STA and STB in which a method of transferring an attachment of a terminal from a first access device to a second access device is implemented, according to an embodiment.

[0052] This [Fig.1] presents a communications network comprising two access devices, STA and STB, giving access to a cellular type communication network, to a terminal Term.

[0053] A data Sess session is established between the terminal Term and a device Disp via the access device STA of the Res communication network, the session data being routed via the Comm_A communication between the terminal Term and the access device STA. This may be the initialization of a session or the continuation of a session initiated via another access device of the Res network.

[0054] The Term terminal is attached to the STA cellular access device and exchanges session data via a Comm_A communication. The Comm_A communication enables data transmission between the Term terminal and the STA access device using time and frequency RI resources. Time slot and frequency block resources are allocated. by the Res network operator for each communication between two pieces of equipment and, without modification compared to the techniques of the state of the art, the terminal Term and the device STA transmit data using transmission resources allocated to them by the Res communication network operator.

[0055] The terminal Term (mobile terminal, laptop, local area network access equipment such as a router, etc.) has a neural network RN_Term that optimizes the transmission, including the sending and receiving of data from a Sess session with a remote device Disp. The terminal Term includes a file representing the data relating to the neural network RN_Term. This file includes data relating to the neurons and their respective weights. The different layers of the neural network thus represent hardware descriptions of the terminal (processor, interfaces, etc.), signal processing functions related to the data propagation channel of the Sess session, encoding and decoding functions, etc. The different neurons in each layer also include weights indicating their importance in the neural network.All this information is transcribed into a file representing the RN_Term neural network. This data file can be referred to interchangeably as a standardized file format or a standard representation of a neural network. The RN_Term neural network consists of a series of layers representing, in a more or less abstract way, signal processing functions related to the session data propagation channel, encoding and decoding functions, hardware imperfection compensation functions, and so on. Each layer consists of a set of neurons to which learnable scalar parameters (weights and biases) are associated. The learning process allows, in particular, the modification of these weights and biases to optimize the overall function performed by the neural network.

[0056] The Term terminal stores a file containing the data relating to the neural network RN_Term. This file describes the architecture and parameters (learnable weights and biases) of the neural network, so that the content of a file makes it possible to reproduce the neural network in question identically.

[0057] Correspondingly, the STA access device has a neural network RN_STA whose role is to optimize the data session by the STA station, both with regard to the transmission of session data to the Term terminal and the reception of session data from the Term terminal. This neural network is also transcribed into a data file whose data, such as transmission characteristics, vary as the propagation channel between the STA access device and the Term terminal evolves and as the data session is increasingly optimized, improving thus the transmission of session data, both sending and receiving.

[0058] The respective neural networks of the terminal Term, RN_Term, and the access device STA, RN_STA, conduct a joint learning process with respect to this session, enabling the transmission and reception of data by the Terminal Term and the STA device. Thus, neurons representing a dynamic transmission characteristic specific to the session, the propagation channel, or a hardware interface of a device (Term or access device STA) are assigned initial weights (and biases) which are modified as learning progresses until an optimal value is reached, allowing for the routing of session data with a better quality of service.These neural networks RN_Term and RN_STA are therefore potentially different and are respectively specific to the Terminal Term and the STA access device, and include data relating to the transmission and reception of data, and are also specific to the established session. In fact, they are not directly transposable or adapted to communication established, for example, between the Terminal Term and the STB access device, for the same session or a separate session.

[0059] Reference is then made to [Fig.2] which presents a schematic representation of a communication network comprising two access devices in which the processes of transferring an attachment of a terminal from a first access device to a second access device and of switching are implemented, according to an embodiment.

[0060] When a transfer, also called handover, HDVR of the current session occurs from the access device STA to the access device STB, a Comm_B communication is established between the terminal Term and the STB device for the routing of the Sess session data with the Disp device via the STB device.

[0061] The STB access device has a neural network (RN_STB) whose role is to optimize the transmission of data, sending and receiving, of the session of the terminal Term with the remote device Disp by the STB device.

[0062] The Term terminal is thus attached to the STB cellular device and exchanges session data via a Comm_B communication. The Comm_B communication allows data transmission between the Term terminal and the STB access device using the same time and frequency RI resources as those used for data transmission in the Comm_A communication.

[0063] This HDVR handover is implemented while the Term terminal can be simultaneously attached to the STA and STB devices for a period of time, thus allowing the handover to be prepared, communication with an access device is never interrupted, and at any given moment, the Term terminal is multi-attached to both access devices, STA and STB. During this period, the Term terminal is suspended Capable of receiving Sess session data transmitted by both access devices STA and STB. Access devices STA and STB receive the same signals from the terminal, since they are transmitted over the same RI resources, except for the propagation channel specific to access devices STA and STB. These signals originate from a single neural network RN_Term located in the terminal Term.

[0064] The method for transferring a terminal attachment from a first access device STA to a second access device STB allows the STA device to transmit to the STB device, either before or after the attachment of the terminal Term to the STB device, one or more session transmission characteristics contained in a file associated with the neural network RN_STA. The STA device can thus send to the STB device the representative file of its neural network RN_STA or a part thereof, such as, for example, one or more transmission characteristics of the file. Therefore, the access device STB will have a set of reusable characteristics for its own data file associated with its neural network RN_STB, after or at the time of the attachment of the terminal Term, and will be able to avoid a complete retraining of its neural network for the established communication Comm_B.Indeed, certain file transmission characteristics related to the session, the STA device, and routing conditions can be reused for the RN_STB neural network. This will reduce the optimization time of the RN_STB neural network, and the session-specific transmission characteristics via the STB station will adapt more quickly to this Comm_B communication than if a complete learning process had to be conducted. For example, the STA device can decide to transmit the entire file representing the RN_STA neural network or only a portion of the file, such as certain transmission characteristics that will require little or no modification for optimization.The transmitted transmission characteristics can advantageously represent a scalar parameter such as a weight or a bias, or even information representing a neural network, such as a neuron or a layer of neurons.

[0065] The transmission of the Caract feature allows, for example, the transmission of the types and configuration of neural networks used to perform the various functions of the signal processing chain for the Comm_A communication, thus providing a possible starting point for new learning (transfer learning and fine-tuning). To accelerate the learning of the STB device, the STA access device can indicate all the layers of the neural network or those requiring optimization for the Comm_B communication. Based on this model, the STB access device can start optimizing the upstream path for Sess session data received from the Term terminal.

[0066] Once it has received the Caract file or feature from the STA device, the STB access device updates or creates a second file, representing its neural network RN_STB for the Sess session, and modifies the neurons and / or the weights of the neurons to adapt it to the Comm_B communication. This update of the file received from the STA device is performed according to a parameter of the Sess data session established via the second STB access device. Thus, the features specific to the STB access device or to the data routing conditions between the terminal and the STB device can be updated because this type of feature, specific to the STB device or to the propagation channel between the terminal and the STB device, for example, is not present in the received data file or Caract features.The modification of the data transmission parameters to the terminal may therefore evolve according to the propagation channel between the STB device and the terminal and require the updating of the data file associated with the STB device's neural network.

[0067] According to an alternative, the STA and STB access devices do not recombine the data received from the Terminal Term. Each STA and STB access device performs local demodulation, and if at least one of the two devices obtains, for example, an error-free packet corresponding to a reference value, then that device is selected by the network. Uplink optimization (data transmission to the Terminal Term) must be performed progressively with the STB device (Term's neural network and STB device's neural network). In this situation, even if the terminal transmits its data to both STA and STB devices, using the same transmission RI resources, only one of the two devices, and most likely the STB device to which the HDVR handover occurs, routes the data received from the Terminal Term to the remote Disp device.

[0068] According to another alternative, the STA and STB access devices constructively recombine the Sess session data received from the Term terminal. This recombination can occur in one of the two STA or STB access devices, or in other equipment of the Res network, connected directly or indirectly to the STA and STB access devices, which is responsible for this recombination. For example, a BBU (BaseBand Unit) type device responsible for the STA and STB devices can perform this recombination within a cellular network.

[0069] According to an example, if the transfer process fails and the creation of the second file based on the first updated file cannot be carried out, then a process A complete training process for the STB device's neural network for the session must be initiated. This complete training process does not allow for optimized learning and faster implementation of high-quality Comm_B communication, but it offers a fallback solution in case the Caract feature or the file cannot be correctly transmitted or cannot be used by the STB device.

[0070] According to an alternative, in the downlink, when the Terminal Term is multi-attached to the two access devices STA and STB, the data from the access devices STA and STB originating from the Disp device and destined for the Terminal Term are constructively recombined to facilitate their demodulation by the Terminal Term. The Terminal Term then has a single neural network RN_Term in reception which it optimizes to demodulate the common signal received from the two devices STA and STB. The devices STA and STB optimize their respective neural networks RN_STA and RN_STB for the downlink (transmission of data to the Terminal Term) by taking into account the signal recombination at the Terminal Term, thus forming a jointly optimized distributed system.As the propagation channel between the Term terminal and the STB device improves, the weight of the STB device's transmission becomes increasingly significant in the recombined signal, while the contribution of the STA device decreases. The neural networks within the terminal and base station B, respectively RN_TERM and RN_STB, are progressively optimized to ensure improved communication for the transmission of Sess session data between the Term terminal and the STB access device. The contribution of the STA device thus becomes progressively minor, until the link with the STA device is severed and the HDVR handover is completed.

[0071] Indeed, when the HDVR handover is complete, and the Term terminal no longer receives a signal from the STA device, or if for some reason the attachment of the Term terminal to the STA device is broken, all the data of the Sess session with the Disp device are routed via the STB device, in accordance with the transmission characteristics of the second file associated with the neural network RN_STB. This file associated with the neural network RN_STB was trained more quickly, thanks to the acquisition of the characteristics of the first file, which were improved more rapidly.This improvement thus allows session data to be routed with quality of service, latency, and transport delay characteristics adapted to the propagation environment and corrected more quickly, depending on the intrinsic characteristics of the Comm_B communication, to allow good quality of service for the transmission of session data.

[0072] Reference is then made to [Fig. 3] which describes a representation of a neural network according to a particular embodiment.

[0073] The neural network is, for example, the neural network (RN_STA) of the STA access device shown in [Fig. 1]. Binary elements (eb) 15 emitted by an output interface of the STA device to the Term terminal are converted into a signal (sig) adapted to the propagation conditions of a channel established between the STA device and the Term terminal. This signal is optimized by progressively modifying dynamic transmission characteristics associated with the neural network RN_STA and contained in a data file associated with this neural network RN_STA. The neural network RN_STA is thus composed of several layers C1, C2...."C7 represents each of the layers involved in the transmission or reception of data via the optimized signal, that is, adapted to the propagation channel between the STA device and the terminal so that the data transmitted between the STA device and the terminal guarantees good quality of service for the session and consequently for the service associated with the data. Each layer is composed of neurons, as represented for layer C1, composed of neurons n1, n2, n3. At the output of a neuron, the generated data can be represented by the value y, which here is equal to a weighted sum of the neuron's inputs plus a bias b_i. The weighting is done using a set of weights w_i, with each input being associated with a weight." Each neuron n1, n2, n3 is therefore assigned a different set of weights w_i, which will evolve during the learning process, just like the biases b_i. This information w_i and b_i can be called scalar parameters. For example, the data y is calculated according to the following formula: y = phi(sum w_i x_i + b_i), where x_i are input values ​​of the neuron. In the subsequent layers, C2 to C7, these inputs are the outputs of the neurons in the preceding layers. Other equations are possible to represent the calculation performed by a neuron. All the layers of the RN_STA neural network are thus optimized for the transmission and reception of data to and from the terminal, guaranteeing good quality of service for this transmission.Furthermore, regarding data transmission from the STA device to a terminal, the neural network RN_STA, or more precisely a neural network for data transmission, is trained jointly with the terminal's receiving neural network RN_Term, or more precisely with a neural network for data reception, to ensure good transmission quality. The terminal can, in turn, accelerate its learning process by leveraging, for example, a receiving neural network used to receive data from another device. In one embodiment, the different layers C1, C2, ..., C7 and / or the scalar parameters independently represent dynamic data processing characteristics. In another embodiment, the correspondence... The correlation between dynamic processing characteristics and layers C1,...,C7 is not as straightforward, and several layers of neurons, or even multiple neurons, are involved for a single characteristic. The adaptation process as described allows weights and / or biases, or even one or more layers of a neural network—this information representing, according to specific embodiments, dynamic transmission characteristics associated with a neural network of one device—to be transmitted and reused by another device, thus reducing the learning process for a certain number of weights and biases, or even layers of neurons, in the neural network of that other device.

[0074] Reference is then made to [Fig.4] which presents a diagram illustrating the main steps of a process for transferring an attachment of a terminal from a first access device to a second access device, according to one embodiment.

[0075] During step 400, a data session is established between a terminal and a remote device. This remote device may be a terminal, a server, a machine adapted to communicate with the terminal, or any type of equipment suitable for establishing a data session with the terminal. The data of this session is routed within a communication network via a first access device, such as an eNodeB, a cellular network gateway, or satellite network access equipment. Both the terminal and the first access device include a neural network whose information, corresponding to transmission characteristics (neurons, weights, biases) of the session data, is transcribed into a data file.The terminal's neural network includes transmission characteristics related to the terminal (interface, processing capabilities, communication protocols), the session (protocols, latency, quality of service, encoding, decoding, etc.), and the first access device with which communication is established for routing session data. The neural network of the first access device also includes the types of characteristics indicated above, but these characteristics are specific to the first access device. The values ​​of the transmission characteristics of these neural networks evolved as they learned, based on the Sess session data being transported, the data transport characteristics of the Sess session, the signal propagation characteristics between the terminal and the first device, and the evolution of the communication channel between the terminal and the first device.Once the learning process is complete, the terminal and the first device each have neural networks enabling the routing of session data with the best possible quality of service, given the session establishment conditions (interfaces, propagation, session establishment context, etc.). The data from... Sess sessions are routed using time and frequency resources allocated by the Res network operator.

[0076] During a 401 step, the terminal performs a handover to a second access device. Communication between the terminal and the second device uses the same or a different technology as the communication between the terminal and the second access device. The second access device is managed by the same operator as the first access device or by a different operator. This handover may be triggered by movement of the terminal, by poorer reception of the signal emitted by the first access device, or by detection of the second access device. The terminal transmits an attachment request to the second access device and, during an Etab procedure, establishes a session with the remote Disp device via the second access device while maintaining the session established via the first access device.The objective is to maintain the Sess session established during the handover at all times. The time and frequency resources used for data exchange between the terminal and the second access device are the same as those used for session data exchange between the terminal and the first access device. At this point, the session data between the terminal and the remote device is routed along two separate paths, one via the first access device and the other via the second access device, while using the same time and frequency resources for both terminal-first device and terminal-second device communications.

[0077] During step 402, the second access device receives, via a Recept operation from the first access device, a transmission characteristic of the data file associated with the neural network of the first device, or the complete file. This transmission characteristic is specific to the first device and the session, but can thus be exploited by the second device so that communication between the terminal and the second access device for the transport of the Sess session data is optimized more quickly and efficiently.Indeed, certain transmission characteristics, related to the session, the signal propagation context, and the terminal, are identical or similar for both communications: between the terminal and the first device, and between the terminal and the second device. The transfer of one (or more) transmission characteristics can facilitate the learning of the neural network in the second access device. Communication between the terminal and the second device can thus be optimized more quickly, and the Sess session data routed between the terminal and the second device can be transmitted more rapidly with good quality of service. The neural network of the second device is trained more quickly thanks to the transmitted features. This also has the advantage of improving handover time by allowing session data to be switched over more rapidly via the second access device alone. The first device can select from the transmission features present in its data file those it transfers to the second access device in order to limit the size of the transmitted information or file, and also to restrict itself to features that the second device can use as is, or that the second device will need to modify in the optimized learning process it will implement for communication with the terminal for routing session data.In the case where the access devices are satellite access devices, the characteristics, particularly transmission characteristics, may include satellite navigation data (speed vector, position, etc.). This data can be used to determine radio parameters (Dopler, elevation angle, MIMO configuration, etc.). These satellite characteristics and radio parameters can be used to update the second file associated with the terminal's neural network for communication with the second access device.

[0078] During step 403, the second access device updates its neural network file using an update procedure based on the characteristics received from the first device. This constitutes the learning phase of its own neural network for routing session data, proposing the best routing quality given the signal propagation conditions. The data session parameters are taken into account for the update.Given that some transmission characteristics transmitted by the first access device can be reused without modification, the update only concerns characteristics that differ from the received characteristics or that were not transmitted, such as characteristics specifically related to the second access device, like the interface type, the capabilities of that interface, the available protocols or protocol versions, and the processing capabilities of the second device. The propagation conditions of the communication channel between the terminal and the second device may also vary from the corresponding characteristics of the first device, although these variations are likely limited since the handover occurs in a space that probably offers equivalent data routing conditions from one access device to the other.

[0079] During a 404 step, the terminal detaches during a Detach procedure from the first access device. This detachment can be sudden, for example if the terminal does not receive The radio signal emitted by the first access device, or a deliberate action by the terminal or the first access device, is also a factor. The terminal can decide to detach once the update step is complete and communicated by the second access device, or once joint learning is finished. This detachment can then be faster because the neural network of the second device will have reached a stable state more quickly thanks to the accelerated learning enabled by receiving the transmission characteristics.The first access device can also initiate the detachment of the terminal once it has transmitted one or more transmission characteristics, or even its data file, or after a period of time following the sending of the file to allow time for the second device to carry out the accelerated learning process of its neural network, for example jointly with the learning of the terminal's neural network.

[0080] During a step 405, once the terminal is detached from the first access device, the second access device routes all the Sess session data in an Achem process, always using the same time and frequency resources, also previously used for communication between the terminal and the first access device, and exploiting its optimized neural network, including modified transmission characteristic values ​​adapted to the propagation channel between the terminal and the second device, thus allowing a good quality transfer of session data to or from the terminal.

[0081] In the method of transferring an attachment from a terminal from a first access device to a second access device, and as described in [Fig. 2], given that, on the one hand, the terminal uses the same time and frequency resources for both paths when it is multi-attached to the two access devices, and that, on the other hand, the terminal comprises only one neural network, the terminal is adapted to demodulate the common data received from the two access devices. Similarly, in this method, the access devices are able to recombine the data received from the terminal in a coordinated manner, or, according to another example, the two devices individually process the received data by demodulating it, and obtaining better demodulation by one of the two devices qualifies it as the device selected for transmitting the demodulated data to the remote device.

[0082] According to an alternative, during a step 406, the first access device deletes its own data file associated with its neural network for the transmission of session data between the terminal and the remote device, in order to free up resources in the first access device.

[0083] In another embodiment, the terminal and / or one or both devices Access networks include a neural network associated with transmitting session data and a neural network associated with receiving session data. The neural network specific to the session and to a piece of equipment (terminal, access device), as described above, is then structured into two neural networks, one for transmitting data and the other for receiving it. According to this method, the first device transmits features present in the files associated with the two transmitting and receiving neural networks, or contained in a single file that includes the transmission features specific to both transmitting and receiving session data.The second access device then updates two data files, associated respectively with its transmitting and receiving neural networks, according to the transmitting and receiving transmission characteristics transmitted by the first access device, or a single file if the characteristics of the transmitting and receiving neural networks are contained in a single file.

[0084] Reference is then made to [Fig.5] which presents a device for transferring an attachment of a terminal from a first access device to a second access device, implementing the transfer method, according to one aspect of the invention.

[0085] The transfer device 100 can be implemented in an access station of a cellular network, a Wi-Fi network or a satellite network. It can, for example, be, without limitation, a NodeB, eNodeB, NR type device or even a Wi-Fi gateway or a local network access device, for example of the residential type (Box).

[0086] For example, the transfer device 100 comprises a transmitter 101, a receiver 102, a processing unit 130, equipped, for example, with a microprocessor qP, and controlled by a computer program 110, stored in a memory 120 and implementing the transfer method according to the invention. At initialization, the code instructions of the computer program 110 are, for example, loaded into a RAM memory before being executed by the processor of the processing unit 130.

[0087] Such a transmitter (101), such a receiver (102), such a processor (130) and such a memory (120) are configured to:

[0088] - receive from the first access device (STA) at least one character a transmission characteristic (Character) of a first data file associated with a neural network, said file comprising a plurality of session data transmission characteristics specific to the session (Sess) and the first access device (STA),

[0089] - receive an attachment request from the terminal,

[0090] - update a second data file from at least one character received ristique, the said second file comprising a plurality of session data transmission features specific to the session and the second access device (STB), said plurality being associated with the routing of session data through the second device (STB) using time and frequency (RI) resources, - route all subsequent session data through the second access device only, in accordance with the second updated data file, following the detachment of the terminal (Term) with the first access device (STA).

[0091] Reference is then made to [Fig.6] which presents a device for changing the attachment of a terminal from a first access device (STA) to a second access device (STB).

[0092] The 200 mutation device can be implemented in a terminal, which can be more specifically a 3G, 4G, 5G...xG compatible smartphone, a PC, a loT (Internet of Things) device, a box or a residential network access gateway.

[0093] For example, the mutation device 200 comprises a transmitter 201, a receiver 202, a processing unit 230, equipped, for example, with a qP microprocessor, and controlled by a computer program 210, stored in a memory 220 and implementing the mutation process according to the invention. At initialization, the code instructions of the computer program 210 are, for example, loaded into a RAM memory, before being executed by the processor of the processing unit 230. A processing unit 130, equipped, for example, with a qP microprocessor, and controlled by a computer program 110, stored in a memory 120 and implementing the method for determining a programmable device according to the invention. At initialization, the code instructions of computer program 110 are, for example, loaded into RAM memory, before being executed by the processor of the processing unit 130.

[0094] Such a transmitter (101), such a receiver (102), such a processor (130) and such a memory (120) are configured to:

[0095] - to send a request to the second access device (STB) terminal attachment, - to transmit session data via the first access device and the second access device, using the time and frequency resources common to both access devices, based on at least one transmission characteristic of a data file associated with a terminal neural network, common to both access devices,

[0096] - to transmit the following session data via the second only access device, following the detachment of the terminal with the first device access, depending on at least one transmission characteristic of the updated data file depending on the detachment.

[0097] The entities described and included in the devices described in relation to Figures 5 and 6 may be hardware or software. Figures 5 and 6 illustrate only one particular way, among several possible ways, of carrying out the methods detailed above, in relation to the preceding figures. Indeed, the technique of the invention can be carried out equally well on a reprogrammable computing machine (a PC, a DSP processor, or a microcontroller) executing a program comprising a sequence of instructions, or on a dedicated computing machine (for example, a set of logic gates such as an FPGA or an ASIC, or any other hardware module).

[0098] In the case where the invention is implemented on a reprogrammable computing machine, the corresponding program (i.e. the sequence of instructions) may be stored in a removable storage medium (such as, for example, a USB key, a floppy disk, a CD-ROM or a DVD-ROM) or not, this storage medium being readable partially or totally by a computer or a processor.

Claims

Claims

1. Method for transferring an attachment of a terminal (Terni) from a first access device (STA) to a second access device (STB), the terminal (Term) having previously established a data session (Sess) via the first access device (STA) and said session data being routed between the terminal and the first access device (STA) using time and frequency resources (RI), the method being implemented in the second access device (STB) and comprising: - a reception (402) from the first access device (STA) of at least one transmission characteristic (Caract) of a first data file associated with a neural network (RN_STA), said file comprising a plurality of transmission characteristics of the session data specific to the session (Sess) and to the first access device (STA),- a reception (401) of an attachment request from the terminal (Term), - an update (403) of a second data file from T at least one received characteristic, said second file associated with a neural network (RN_STB), comprising a plurality of characteristics for transmitting the session data specific to the session (Sess) and to the second access device (STB), said plurality being associated with the routing of the session data (Sess) via the second device using said time and frequency resources (RI), - a routing (405) of all the following data of the session (Sess) via the second access device (STB) only in accordance with the updated second data file, following the detachment (404) of the terminal with the first access device.,

2. Transfer method, according to claim 1, further comprising, prior to detachment of the terminal with the first access device, a routing of the session data received from the terminal, in substitution of the first access device, in the case where the processing of the data received by the second access device is greater than a reference value.

3. A transfer method, according to claim 1, further comprising a combining the session data received from the terminal with the session data received by the first access device, prior to detaching the terminal from the first access device.

4. Transfer method, according to one of claims 1 to 3, comprising a modification of a transmission characteristic specific to the transmission of data to the terminal, included in the second file, as a function of the evolution of a capacity of a propagation channel used for routing data between the terminal and the second access device.

5. Transfer method, according to one of claims 1 to 4, according to which the updating of the second file comprises a creation of a second data file, the second file comprising characteristics of transmission of the session data specific to the session (Sess) and to the second access device (STB), said characteristics being derived from a complete learning of a neural network (RN_STB) with which the new file is associated, in the case where the at least one transmission characteristic from the first device is not exploitable.

6. Method for mutating an attachment of a terminal (Term) from a first access device (STA) to a second access device (STB), the terminal having previously established a data session (Sess) via the first access device (STA) and said session data (Sess) being routed between the terminal (Term) and the first access device (STA) using time and frequency resources (RI), the method being implemented in the terminal (Term) and comprising: - a transmission of an attachment request from the terminal to the second access device (STB), - a transmission of the session data via the first access device (STA) and the second access device (STB), using the time and frequency resources (RI) common for communications with the two access devices (STA, STB),depending on at least one characteristic (Caract) of transmission of a data file associated with a neural network (RN_Term) of the terminal (Term), common for communications with the two access devices (STA, STB), - a detachment of the terminal with the first access device (STA), then the transmission of subsequent data of the session (Sess) via the second access device (STB) only, depending on the at least one characteristic (Caract) of transmission of the data file updated depending on the detachment.

7. A mutation method, according to claim 6, comprising a combination of the session data received from the first access device and the second access device, as a function of at least one transmission characteristic, specific to the reception of the session data, the at least one characteristic being included in the data file, prior to the detachment of the terminal with the first access device.

8. A mutation method, according to claim 6 or claim 7, wherein the terminal comprises two data files associated with two common neural networks for the two access devices in the terminal, one for receiving session data from the access devices and the other for transmitting data to the access devices.

9. A device (100) for transferring an attachment of a terminal from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the device comprising a transmitter (101), a receiver (102), a processor (130) and a memory (120) coupled to the processor with instructions intended to be executed by the processor for: - receiving from the first access device at least one transmission characteristic of a first data file associated with a neural network, said file comprising a plurality of transmission characteristics of the session data specific to the session and to the first access device,- receive an attachment request from the terminal, - update a second data file from the at least one received characteristic, said second file associated with a neural network (RN_STB), comprising a plurality of session data transmission characteristics specific to the session and to the second access device, said plurality being associated with the routing of the session data via the, second device using said time and frequency resources, - route all subsequent session data via the second access device alone in accordance with the updated second data file, following detachment of the terminal with the first access device.

10. Device (200) for mutating an attachment of a terminal from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the mutation device comprising a transmitter (201), a receiver (202), a processor (230) and a memory (220) coupled to the processor with instructions intended to be executed by the processor to: - transmit to the second access device a request for attachment of the terminal, - transmit session data via the first access device and the second access device, using the time and frequency resources common to the two access devices,based on at least one transmission characteristic of a data file associated with a neural network of the terminal, common for both access devices, - transmitting subsequent data of the session via the second access device only, following the detachment of the terminal with the first access device, based on the at least one transmission characteristic of the data file, updated based on the detachment of the terminal with the first access device.,

11. System for transferring an attachment of a terminal from a first access device to a second access device, the terminal having previously established a data session via the first access device and said session data being routed between the terminal and the first access device using time and frequency resources, the system comprising: - a transfer device according to claim 9, - a mutation device according to claim 10, - a change device, included in the first access device (STA), comprising a transmitter, a receiver, a processor and a memory coupled to the processor with instructions intended to be executed by the processor to transmit to the second access device the at least one transmission characteristic, and to ensure the detachment of the terminal with the first access device.

12. Terminal comprising a mutation device according to claim 10

13. IV. Program comprising instructions which, when the program is implemented by a processor, lead to implementing the transfer method according to one of claims 1 to 5.

14. Program comprising instructions which, when the program is implemented by a processor, lead to implementing the transfer method according to one of claims 6 to 8.

15. Information medium readable by an access station (STA) and comprising instructions of a computer program according to claim 13.

16. Information medium readable by a terminal (Term) and comprising instructions of a computer program according to claim 14.

Images