Transmitting device, receiving device and methods thereof in wireless communication network

Abstract

The invention discloses a transmitting device, a receiving device and a method thereof in a wireless communication network. The data sending method provided by the invention comprises the steps of coding to-be-sent data for first user equipment based on a first neural network model to obtain a first coding sequence; on the basis of a second neural network model, encoding scrambling code information corresponding to the first user equipment to obtain a first scrambling code sequence; a product-related operation is performed on the first coding sequence and the first scrambling sequence to obtain a first sequence to be sent, and the first neural network model is the same as a neural network model used for coding data to be sent of second user equipment in the wireless communication network to obtain a second coding sequence; and sending according to the first to-be-sent sequence. According to the data sending method provided by the invention, the to-be-sent data of the user equipment can be identified by introducing the scrambling code information, so that the data corresponding to the user equipment can be accurately decoded subsequently, and the data sending method provided by the invention is relatively good in effect during transmission of multiple user equipment. In addition, according to the data sending method provided by the invention, the same neural network model is adopted for different user equipment, so that the size of the model adopted in the data sending method provided by the invention is not increased along with the increase of the number of the user equipment.

Description

Technical Field

[0001] The present disclosure relates to the field of wireless communications, and more particularly to a transmitting device, a receiving device and a method thereof in a wireless communication network. Background Art

[0002] In the Universal Mobile Telecommunications System (UMTS) network, Long Term Evolution (LTE) has been standardized for the purpose of further high-speed data rates, low latency, etc. In addition, with the purpose of further broadbandization and high speed of LTE, successor systems of LTE are also being studied. Among the successor systems of LTE, for example, there are systems called Long Term Evolution Technology Upgrade (LTE-Advanced (LTE-A)), Future Radio Access (FRA)), 5th Generation Mobile Communication System (5G), 5G+ (5G plus), Radio Access Technology (Radio Access Technology (New-RAT)), New Radio (NR), etc.

[0003] In the universal mobile communications system network, various generations of mobile communication technologies are adopted, including different multiple access technologies, such as 1G frequency division multiple access technology (FDMA), 2G time division multiple access technology (TDMA), 3G code division multiple access technology (CDMA), 4G orthogonal frequency division multiple access technology (OFDMA), etc.

[0004] With the development of 6G and subsequent generation-based communications, more advanced multiple access technologies are needed. Summary of the Invention

[0005] In response to the above problems, according to one aspect of the present disclosure, a sending device in a wireless communication network is provided, including: a processing unit, configured to encode data to be sent for a first user equipment based on a first neural network model to obtain a first coding sequence; encode scrambling code information corresponding to the first user equipment based on a second neural network model to obtain a first scrambling code sequence; perform a product-related operation on the first coding sequence and the first scrambling code sequence to obtain a first sequence to be sent, wherein the first neural network model is the same as the neural network model used to encode data to be sent for a second user equipment in the wireless communication network to obtain a second coding sequence; and a sending unit, configured to send according to the first sequence to be sent.

[0006] According to one aspect of the present disclosure, a receiving device in a wireless communication network is provided, comprising: a receiving unit configured to obtain a signal sequence, wherein the signal sequence includes a first signal sequence corresponding to a first user equipment and a second signal sequence corresponding to a second user equipment in the wireless communication network; a processing unit configured to encode first scrambling code information corresponding to the first user equipment based on a first neural network model to obtain a first scrambling code sequence; perform a product-related operation on the signal sequence and the first scrambling code sequence to obtain a first sequence to be decoded; and decode the first sequence to be decoded to obtain transmit data corresponding to the first user equipment.

[0007] According to one aspect of the present disclosure, a data sending method is provided, including: encoding data to be sent for a first user equipment based on a first neural network model to obtain a first coding sequence; encoding scrambling code information corresponding to the first user equipment based on a second neural network model to obtain a first scrambling code sequence; performing a product-related operation on the first coding sequence and the first scrambling code sequence to obtain a first sequence to be sent, wherein the first neural network model is the same as the neural network model used to encode data to be sent for a second user equipment in the wireless communication network to obtain a second coding sequence; and sending according to the first sequence to be sent.

[0008] According to one aspect of the present disclosure, a data receiving method is provided, comprising: obtaining a signal sequence, wherein the signal sequence includes a first signal sequence corresponding to a first user equipment and a second signal sequence corresponding to a second user equipment in the wireless communication network; encoding first scrambling code information corresponding to the first user equipment based on a first neural network model to obtain a first scrambling code sequence; performing a product-related operation on the signal sequence and the first scrambling code sequence to obtain a first sequence to be decoded; and decoding the first sequence to be decoded to obtain transmit data corresponding to the first user equipment.

[0009] According to the device and method of the above-mentioned aspect of the present disclosure, the data transmission method provided by the present disclosure can identify the data to be transmitted by the user equipment by introducing scrambling code information, thereby facilitating the subsequent accurate decoding of the data corresponding to the user equipment, thereby making the data transmission method provided by the present disclosure more effective when transmitting to multiple user equipment. In addition, the data transmission method provided by the present disclosure uses the same neural network model for different user equipment, thereby ensuring that the model size used in the data transmission method provided by the present disclosure does not increase as the number of user equipment increases. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other purposes, features, and advantages of the present disclosure will become more apparent through a more detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and are not intended to limit the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0011] Figure 1 A schematic diagram of a network architecture based on modular division multiple access according to an embodiment of the present disclosure is shown.

[0012] Figure 2 A flow chart of a data sending method 200 according to an embodiment of the present disclosure is shown.

[0013] Figure 3 Shown with Figure 2 Schematic diagram of the corresponding network architecture.

[0014] Figure 4 A schematic diagram of a network architecture after adding a spread spectrum operation according to an embodiment of the present disclosure is shown.

[0015] Figure 5 A schematic diagram of a network architecture after adding signal-to-noise ratio information according to an embodiment of the present disclosure is shown.

[0016] Figure 6 A flow chart of a data receiving method 600 according to an embodiment of the present disclosure is shown.

[0017] Figure 7 Shown with Figure 6 Schematic diagram of the corresponding network architecture.

[0018] Figure 8 A block diagram of a transmitting device 800 in a wireless communication network according to an embodiment of the present disclosure is shown.

[0019] Figure 9 A block diagram of a receiving device 900 in a wireless communication network according to an embodiment of the present disclosure is shown.

[0020] Figure 10 A schematic diagram of a detailed network architecture including a sending side and a receiving side according to an embodiment of the present disclosure is shown.

[0021] Figure 11 A schematic diagram shows the result of simultaneous transmission by two users based on an existing solution according to an embodiment of the present disclosure.

[0022] Figure 12 A schematic diagram shows the result of simultaneous transmission for four users based on an existing solution according to an embodiment of the present disclosure.

[0023] Figure 13 Schematic diagrams are shown showing the results of performing simultaneous transmission by two users, four users, eight users, and sixteen users, respectively, based on the solution proposed in the present disclosure according to an embodiment of the present disclosure.

[0024] Figure 14-16 A schematic diagram showing test results according to an embodiment of the present disclosure is shown.

[0025] Figure 17 This is a diagram showing an example of the hardware configuration of a network-side device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions, and advantages of the present disclosure more apparent, exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. In the accompanying drawings, like reference numerals represent like elements throughout. It should be understood that the embodiments described in the present disclosure are merely illustrative and should not be construed as limiting the scope of the present disclosure.

[0027] Multiple access technologies are required in universal mobile communication system networks to enable simultaneous communication among multiple users. However, the current multiple access technologies for 1G, 2G, and 3G networks cannot meet the requirements of 6G and subsequent generation-based communications, so more advanced multiple access technologies are needed.

[0028] In recent years, with the development of artificial intelligence technology, the new concept of "modular division multiple access" has been proposed. Modular division multiple access technology relies on a deep learning model for each user to extract semantic information from the information provided by the user, and then directly superimposes the semantic information of multiple users together for transmission, and finally restores the original information by using their respective models at the receiving end. Figure 1 To understand the network architecture based on "Modem Division Multiple Access".

[0029] Figure 1 A schematic diagram of a network architecture based on modular division multiple access according to an embodiment of the present disclosure is shown.

[0030] exist Figure 1 In the figure, the left side is the sending side and the right side is the receiving side.

[0031] On the transmitting side, the transmitting device encodes information 1 to be sent from user device 1 using deep learning-based model 1. It also encodes information 2 to be sent from user device 2 using deep learning-based model 2. It also encodes information 3 to be sent from user device 3 using deep learning-based model 3. It also encodes information 4 to be sent from user device 4 using deep learning-based model 4. Finally, the transmitting device superimposes these four encoded information signals and transmits them.

[0032] On the receiving side, the receiving device receives the superimposed signal. The receiving device can decode the received signal using deep learning-based model 1' corresponding to model 1 to obtain information transmitted by user device 1. The receiving device can also decode the received signal using deep learning-based model 2' corresponding to model 2 to obtain information transmitted by user device 2. The receiving device can also decode the received signal using deep learning-based model 3' corresponding to model 3 to obtain information transmitted by user device 3. The receiving device can also decode the received signal using deep learning-based model 4' corresponding to model 4 to obtain information transmitted by user device 4.

[0033] However, during testing, it was found that Figure 1 The network architecture based on mode division multiple access shown in the figure has a significantly degraded transmission effect as the number of user devices increases. In addition, each user device has a model corresponding to the user device and the models of different user devices are different. For example, Figure 1 In the example shown, Model 1 is a model trained only for user device 1, Model 2 is a model trained only for user device 2, Model 3 is a model trained only for user device 3, and Model 4 is a model trained only for user device 4. Therefore, as the number of user devices increases, the model size also increases accordingly.

[0034] therefore, Figure 1 The described network architecture based on modem multiple access is not suitable for the development requirements of 6G and subsequent generation-based communications.

[0035] In order to solve the above problems, the present disclosure provides a data transmission method. The data transmission method provided by the present disclosure can make the neural network model used to encode the data to be transmitted for the first user equipment the same as the neural network model used to encode the data to be transmitted for the second user equipment in the wireless communication network. The method provided by the present disclosure also introduces different scrambling code information for different user equipments, so that it can achieve better results when transmitting on multiple user equipments and the model size will not increase as the number of user equipments increases. A data transmission method provided by one aspect of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0036] Figure 2 A flow chart of a data sending method 200 according to an embodiment of the present disclosure is shown. Figure 2Steps S210 to S240 in the data sending method 200 shown can be performed by a user device or a network side device. As an example, the network side device can be a base station, such as a next generation Node B (gNB). Alternatively, the network side device can be an operation administration and maintenance (OAM) module or a service management and orchestration (SMO) module that interacts with the base station outside the base station. In the case where the network side device is the above-mentioned OAM or SMO module, the OAM or SMO module needs to transmit the sequence to be sent determined by executing the data sending method provided by the present disclosure to, for example, a base station, so that the base station can perform subsequent operations. Alternatively, the network side device can also be an upper node of the base station.

[0037] Reference Figure 2 In step S210, the user equipment or the network side device may encode the data to be sent to the first user equipment based on the first neural network model to obtain a first coding sequence.

[0038] As an example, the first neural network model can be any neural network model based on deep learning, such as a convolutional neural network model (CNN), a recurrent neural network (RNN), a deep neural network (DNN), etc.

[0039] As an example, the data to be sent by the first user equipment may be any data to be sent determined by the first user equipment based on actual conditions, such as text, pictures, videos, audio and other data.

[0040] In step S220, the user equipment or the network side device may encode the scrambling code information corresponding to the first user equipment based on the second neural network model to obtain a first scrambling code sequence.

[0041] As an example, the scrambling code information corresponding to the first user equipment may be of various types and may include any information suitable for use as a scrambling code, such as a random code, an orthogonal code, a non-orthogonal code, a user identifier, etc. corresponding to the first user equipment. The data transmission method provided in the present disclosure can identify the data to be transmitted by the user equipment by introducing a scrambling code, thereby facilitating subsequent accurate decoding of the data corresponding to the user equipment.

[0042] As an example, the second neural network model can be any neural network model based on deep learning, such as CNN, RNN, DNN, etc.

[0043] As an example, the first neural network model and the second neural network model can be the same neural network model or different neural network models. Preferably, the first neural network model and the second neural network model are the same neural network model, so that the neural network model used in the data transmission method provided by the present disclosure can be unified, and a single neural network model can be used to implement encoding of the data to be transmitted and the scrambling code information, thereby further reducing the model size.

[0044] In step S230, the user equipment or the network-side device may perform a product-related operation on the first coding sequence and the first scrambling sequence to obtain a first sequence to be transmitted, wherein the first neural network model is the same as the neural network model used to encode data to be transmitted by a second user equipment in the wireless communication network to obtain a second coding sequence. The data transmission method provided in the present disclosure effectively decodes user equipment data in a subsequent decoding process by performing a product-related operation on the coding sequence and the scrambling sequence.

[0045] As an example, the data to be sent by the second user equipment may be any data to be sent determined based on actual conditions, such as text, pictures, videos, audios and other data.

[0046] As an example, the product-related operation performed on the first coding sequence and the first scrambling sequence can be any suitable product-based operation. For example, the first coding sequence and the first scrambling sequence can be directly multiplied. For another example, the product of the first coding sequence and the first scrambling sequence can be added to one of the first coding sequence and the first scrambling sequence, or another suitable parameter.

[0047] Continue to refer to Figure 2 In step S240, the user equipment or the network side equipment may send according to the first sequence to be sent.

[0048] As an example, the user equipment or the network-side equipment may obtain an analog signal corresponding to the first sequence to be sent, and then send the analog signal through a transmission channel in the wireless communication network.

[0049] According to an embodiment of the present disclosure, the first neural network model used to encode the data to be transmitted of the first user equipment in the wireless communication network to obtain a first coding sequence can be the same as the neural network model used to encode the data to be transmitted of the second user equipment in the wireless communication network to obtain a second coding sequence, so that the data transmission method provided by the present disclosure can adopt the same neural network model for different user equipment, thereby making the model size adopted in the data transmission method provided by the present disclosure not increase with the increase in the number of user equipment. In fact, the data transmission method provided by the present disclosure can adopt a single neural network model to process different user equipment, so as to limit the model size to the greatest extent.

[0050] According to the embodiment of the present disclosure, Figure 2 When the method shown is performed by a network-side device (e.g., a base station), the network-side device may need to send data to multiple user devices at the same time, and perform operations similar to the above-mentioned first user device for each of the multiple user devices. In this case, first, the network-side device may encode the data to be sent for the second user device based on the first neural network model to obtain a second coding sequence. Then, the network-side device may encode the scrambling code information corresponding to the second user device based on the second neural network model to obtain a second scrambling code sequence. Then, the network-side device may perform operations related to the product on the second coding sequence and the second scrambling code sequence to obtain a second sequence to be sent. Finally, the network-side device may send according to the second sequence to be sent and the first sequence to be sent.

[0051] As an example, the scrambling code information corresponding to the second user equipment may be of various types and may include any information suitable for use as a scrambling code, such as a random code, an orthogonal code, a non-orthogonal code, a user identifier, etc. corresponding to the second user equipment. The data transmission method provided in the present disclosure can identify the data to be transmitted by the user equipment by introducing a scrambling code, thereby facilitating subsequent accurate decoding of the data corresponding to the user equipment.

[0052] As an example, performing a product-related operation on the second coding sequence and the second scrambling sequence may be any suitable product-based operation. For example, the second coding sequence and the second scrambling sequence may be directly multiplied. For another example, the product of the second coding sequence and the second scrambling sequence may be added to one of the second coding sequence and the second scrambling sequence, or another suitable parameter.

[0053] As an example, transmitting according to the second sequence to be transmitted and the first sequence to be transmitted may include superimposing a signal corresponding to the second sequence to be transmitted and a signal corresponding to the first sequence to be transmitted and then transmitting the superimposed signals.

[0054] It can be seen that the base station can use the same neural network model (i.e., the first neural network model) to encode the data to be sent for the first user equipment and the data to be sent for the second user equipment. The base station can use the same neural network model (i.e., the second neural network model) to encode the scrambling code information corresponding to the first user equipment and the scrambling code information corresponding to the second user equipment.

[0055] In this case, when there are more than two user equipments, the base station can also use the same neural network model (i.e., the first neural network model) to encode the data to be transmitted for the first user equipment to the Nth (N is a positive integer) user equipment. The base station can also use the same neural network model (i.e., the second neural network model) to encode the scrambling code information corresponding to the first user equipment to the Nth (N is a positive integer) user equipment. It can be seen that the model size used in the data transmission method provided by the present disclosure does not increase as the number of user equipments increases.

[0056] The above has been combined Figure 2 The data transmission method provided by the present disclosure is described in detail. The data transmission method provided by the present disclosure can identify the data to be transmitted by a user device by introducing scrambling code information, thereby facilitating the subsequent accurate decoding of the data corresponding to the user device, thereby making the data transmission method provided by the present disclosure more effective when transmitting to multiple user devices. In addition, the data transmission method provided by the present disclosure uses the same neural network model for different user devices, thereby ensuring that the model size used in the data transmission method provided by the present disclosure does not increase as the number of user devices increases.

[0057] Figure 3 Shown with Figure 2 Schematic diagram of the corresponding network architecture.

[0058] exist Figure 3 FIG shows a scenario in which data to be sent to four user equipments is sent. It should be noted that Figure 3 This is just an example. The data sending method provided in the present disclosure can be applied to a scenario where data to be sent to any number of user equipments is sent.

[0059] Reference Figure 3, based on the neural network model 1, the data to be sent 1 for the first user equipment is encoded to obtain a first coding sequence; based on the neural network model 2, the scrambling code information including the random code 1 corresponding to the first user equipment is encoded to obtain a first scrambling code sequence; the first coding sequence and the first scrambling code sequence are subjected to a product-related operation (as shown in the symbol As shown), to obtain the first sequence to be sent.

[0060] Based on the neural network model 1, the data 2 to be sent for the second user equipment is encoded to obtain a second coded sequence; based on the neural network model 2, the scrambling code information corresponding to the second user equipment and including the random code 2 is encoded to obtain a second scrambling code sequence; an operation related to the product is performed on the second coded sequence and the second scrambling sequence (as shown by the symbol As shown), to obtain the second sequence to be sent.

[0061] Based on the neural network model 1, the data 3 to be sent to the third user equipment is encoded to obtain a third coding sequence; based on the neural network model 2, the scrambling code information including the random code 3 corresponding to the third user equipment is encoded to obtain a third scrambling code sequence; an operation related to the product is performed on the third coding sequence and the third scrambling sequence (as shown by the symbol As shown), to obtain the third sequence to be sent.

[0062] Based on the neural network model 1, the data 4 to be sent for the fourth user equipment is encoded to obtain a fourth coded sequence; based on the neural network model 2, the scrambling code information including the random code 4 corresponding to the fourth user equipment is encoded to obtain a fourth scrambling code sequence; an operation related to the product is performed on the fourth coded sequence and the fourth scrambling sequence (as shown by the symbol As shown), to obtain the fourth sequence to be sent.

[0063] The first sequence to be sent, the second sequence to be sent, the third sequence to be sent and the fourth sequence to be sent are sent after signal superposition (as indicated by the symbol ∑ in the figure).

[0064] According to the embodiment of the present disclosure, the user equipment or the network side device can directly perform the operations related to the product on the coding sequence and the scrambling sequence. Alternatively, the user equipment or the network side device can also first perform the spread spectrum operation on the coding sequence, and then perform the operations related to the product on the spread spectrum coding sequence and the scrambling sequence. In this case, Figure 2 The performing a product-related operation on the first coding sequence and the first scrambling sequence to obtain the first sequence to be transmitted as described in may include: performing a spreading operation on the first coding sequence; and performing a product-related operation on the first coding sequence and the first scrambling sequence after the spreading to obtain the first sequence to be transmitted.

[0065] As an example, the spreading operation may be any suitable operation for spreading the data sequence, such as spreading the first coding sequence from a dimension (Dim) of 128 to a dimension of 512. Figure 4 shown. Figure 4 FIG. 1 shows a schematic diagram of a network architecture after adding a spread spectrum operation according to an embodiment of the present disclosure. Figure 4 FIG shows a scenario in which data to be sent to four user equipments is sent. It should be noted that Figure 4 This is just an example. The data sending method provided in the present disclosure can be applied to a scenario where data to be sent to any number of user equipments is sent.

[0066] Reference Figure 4 Based on the neural network model 1, the data 1 to be sent to the first user equipment is encoded to obtain a first coding sequence, and then the first coding sequence is spread from a dimension of 128 to a dimension of 512. Based on the neural network model 2, the scrambling code information containing the random code 1 corresponding to the first user equipment is encoded to obtain a first scrambling code sequence. The product-related operation is performed on the first coding sequence after the spread (as shown by the symbol in the figure) and the first scrambling code sequence. As shown), to obtain the first sequence to be sent.

[0067] In addition, if Figure 4 As shown, similar operations as those for the first user equipment's data 1 to be sent can be performed on the data 2 to be sent for the second user equipment, the data 3 to be sent for the third user equipment, and the data 4 to be sent for the fourth user equipment to be sent, thereby obtaining a second sequence to be sent, a third sequence to be sent, and a fourth sequence to be sent, respectively. The first sequence to be sent, the second sequence to be sent, the third sequence to be sent, and the fourth sequence to be sent are then superimposed (as indicated by the symbol ∑ in the figure) and sent.

[0068] The data transmission method provided in the present disclosure can increase the dimension of the obtained sequence to be transmitted by introducing the above-mentioned spread spectrum operation, thereby enabling the data corresponding to the user equipment to be decoded more accurately in the subsequent decoding process.

[0069] Taking into account the interference conditions existing in an actual wireless communication network environment, in order to better improve the accuracy of data corresponding to the user equipment decoded in a subsequent decoding process, the data transmission method provided in the present disclosure may further include the user equipment or the network-side device obtaining the first coding sequence or the first scrambling code sequence based on the signal-to-noise ratio information of the transmission channel of the first user equipment.

[0070] As an example, the signal-to-noise ratio information of the transmission channel of the first user equipment may be any suitable signal-to-noise ratio information, such as a signal-to-noise ratio (SNR), a signal-to-interference plus noise ratio (SINR), and the like. Furthermore, the signal-to-noise ratio information of the transmission channel of the first user equipment may be signal-to-noise ratio information of the transmission channel when data to be transmitted for the first user equipment is to be transmitted. According to an example of the present disclosure, the signal-to-noise ratio information of the transmission channel may be determined in advance. For example, it may be determined in advance through statistical analysis based on historical communication information.

[0071] By introducing the above-mentioned signal-to-noise ratio information, the data sending method provided by the present disclosure can better send data based on the actual network transmission environment, thereby further improving the accuracy of decoding data corresponding to the user equipment in the subsequent decoding process.

[0072] According to an embodiment of the present disclosure, obtaining the first coding sequence or the first scrambling code sequence based on the signal-to-noise ratio information of the transmission channel of the first user equipment may include: encoding the data to be transmitted for the first user equipment and the signal-to-noise ratio information of the transmission channel of the first user equipment based on the first neural network model to obtain the first coding sequence; or encoding the scrambling code information corresponding to the first user equipment and the signal-to-noise ratio information of the transmission channel of the first user equipment based on the second neural network model to obtain the first scrambling code sequence. As can be seen from the above content, the introduced signal-to-noise ratio information can be encoded together with the data to be transmitted for the first user equipment, or can be encoded together with the scrambling code information corresponding to the first user equipment, so that the signal-to-noise ratio information can be introduced in a more flexible manner in the method provided by the present disclosure.

[0073] like Figure 5 shown. Figure 5 A schematic diagram of a network architecture after adding signal-to-noise ratio information according to an embodiment of the present disclosure is shown.

[0074] exist Figure 5 FIG shows a scenario in which data to be sent to four user equipments is sent. It should be noted that Figure 5 This is just an example. The data transmission method provided by the present disclosure can be applied to the scenario of transmitting data to be transmitted for any number of user devices. In addition, it should be noted that Figure 5 Only the scenario in which the added signal-to-noise ratio information is encoded together with the scrambling code information corresponding to the user equipment is shown. Alternatively, the added signal-to-noise ratio information can also be encoded together with the data to be sent to the user equipment.

[0075] Reference Figure 5 Based on the neural network model 1, the data 1 to be sent for the first user equipment is encoded to obtain a first coding sequence. Based on the neural network model 2, the scrambling code information corresponding to the first user equipment including the random code 1 and the signal-to-noise ratio information of the transmission channel of the first user equipment (such as SNR1) are encoded to obtain a first scrambling code sequence; the first coding sequence and the first scrambling code sequence are subjected to a product-related operation (as shown by the symbol in the figure). As shown), to obtain the first sequence to be sent.

[0076] In addition, if Figure 5 As shown, similar operations as those for the first user equipment's data 1 to be sent can be performed on the data 2 to be sent for the second user equipment, the data 3 to be sent for the third user equipment, and the data 4 to be sent for the fourth user equipment to be sent, thereby obtaining a second sequence to be sent, a third sequence to be sent, and a fourth sequence to be sent, respectively. The first sequence to be sent, the second sequence to be sent, the third sequence to be sent, and the fourth sequence to be sent are then superimposed (as indicated by the symbol ∑ in the figure) and sent.

[0077] In addition to providing the above-mentioned data sending method, the present disclosure also provides a data receiving method. Figure 6 A data receiving method provided in one aspect of the present disclosure is described in detail.

[0078] Figure 6 A flow chart of a data receiving method 600 according to an embodiment of the present disclosure is shown. Figure 6 Steps S610 to S640 in the data reception method 600 shown can be performed by a network-side device or a user equipment. As an example, the network-side device can be a base station, such as the gNB described above. Alternatively, the network-side device can be the OAM module or SMO module described above. If the network-side device is the OAM or SMO module described above, the OAM or SMO module needs to transmit the transmit data corresponding to the user equipment obtained by executing the data reception method provided in this disclosure to, for example, the base station for subsequent operations. Alternatively, the network-side device can also be an upper-layer node of the base station.

[0079] Reference Figure 6 In step S610, the network side device or the user equipment may obtain a signal sequence.

[0080] According to an embodiment of the present disclosure, the signal sequence may include a first signal sequence corresponding to a first user equipment and a second signal sequence corresponding to a second user equipment in the wireless communication network.

[0081] As an example, the first signal sequence corresponding to the first user equipment may be a sequence of signals in combination with the above Figure 2 The second signal sequence corresponding to the second user equipment may be a sequence corresponding to the first sequence to be sent. Figure 2 The described sequence corresponds to the second sequence to be sent.

[0082] In step S620, the network side device or the user equipment may encode the first scrambling code information corresponding to the first user equipment based on the first neural network model to obtain a first scrambling code sequence.

[0083] As an example, the first neural network model can be any neural network model based on deep learning, such as CNN, RNN, DNN, etc. The first neural network model used in the data sending method 600 can be combined with the above Figure 2 The second neural network model described is the same.

[0084] As an example, the scrambling code information corresponding to the first user equipment may be of various types and may include any information suitable for use as a scrambling code, such as a random code, an orthogonal code, a non-orthogonal code, a user identifier, etc. corresponding to the first user equipment. The data receiving method provided in the present disclosure, by introducing a scrambling code, can identify the data of the user equipment, thereby facilitating subsequent accurate decoding of the data corresponding to the user equipment, thereby making the data receiving method provided in the present disclosure more effective when transmitting data to multiple user equipment.

[0085] The scrambling code information corresponding to the first user equipment used in the data transmission method 600 can be combined with the above Figure 2 The scrambling code information described is the same as the scrambling code information corresponding to the first user equipment. In order to make the above two scrambling code information the same, the sending side and the receiving side can exchange a message about the scrambling code information before formally communicating the information, or the sending side and the receiving side can obtain the scrambling code information according to a rule agreed in advance.

[0086] In step S630, the network-side device or the user equipment may perform a product-related operation on the signal sequence and the first scrambling code sequence to obtain a first sequence to be decoded.

[0087] As an example, the product-related operation performed on the signal sequence and the first scrambling code sequence can be any suitable product-based operation. For example, the signal sequence and the first scrambling code sequence can be directly multiplied. For another example, the product of the signal sequence and the first scrambling code sequence can be multiplied and then added to one of the signal sequence and the first scrambling code sequence, or another suitable parameter.

[0088] In step S640, the network side device or the user equipment may decode the first sequence to be decoded to obtain the transmission data corresponding to the first user equipment.

[0089] As an example, the network side device or the user equipment can decode the first sequence to be decoded based on the second neural network model to obtain the transmission data corresponding to the first user equipment. The second neural network model can be any neural network model based on deep learning, such as CNN, RNN, DNN, etc. The second neural network model used in the data transmission method 600 can be combined with the above Figure 2 The first neural network model described corresponds to the first neural network model. By using the neural network model to decode the sequence, the method provided by the present disclosure can decode the data more accurately.

[0090] Alternatively, the network-side device or the user equipment may also decode the first sequence to be decoded in other ways (for example, filtering, etc.) to obtain the transmission data corresponding to the first user equipment.

[0091] According to an embodiment of the present disclosure, when the data receiving method 600 provided in the present disclosure is executed by a network-side device (for example, a base station), the data receiving method 600 may further include encoding second scrambling code information corresponding to the second user equipment based on the first neural network model to obtain a second scrambling code sequence; performing a product-related operation on the signal sequence and the second scrambling code sequence to obtain a second sequence to be decoded; and decoding the second sequence to be decoded based on the second neural network model to obtain transmitted data corresponding to the second user equipment.

[0092] As an example, the scrambling code information corresponding to the second user equipment may be of various types and may include any information suitable for use as a scrambling code, such as a random code, an orthogonal code, a non-orthogonal code, a user identifier, etc. corresponding to the second user equipment. The data receiving method provided in the present disclosure can identify the data of the user equipment by introducing a scrambling code, thereby facilitating subsequent accurate decoding of the data corresponding to the user equipment.

[0093] The scrambling code information corresponding to the second user equipment used in the data transmission method 600 can be combined with the above Figure 2 The scrambling code information described is the same as the scrambling code information corresponding to the second user equipment. In order to make the above two scrambling code information the same, the sending side and the receiving side can exchange a message about the scrambling code information before formally communicating the information, or the sending side and the receiving side can obtain the scrambling code information according to a rule agreed in advance.

[0094] As an example, the product-related operation performed on the signal sequence and the second scrambling sequence can be any suitable product-based operation. For example, the signal sequence and the second scrambling sequence can be directly multiplied. For another example, the product of the signal sequence and the second scrambling sequence can be added to one of the signal sequence and the second scrambling sequence or another suitable parameter after the product is multiplied.

[0095] It can be seen that the base station can use the same neural network model (i.e., the first neural network model) to encode the scrambling code information corresponding to the first user equipment and the scrambling code information corresponding to the second user equipment. The base station can use the same neural network model (i.e., the second neural network model) to decode the to-be-decoded sequences corresponding to the first user equipment and the second user equipment, respectively.

[0096] In this case, when there are more than two user equipments, the base station can also use the same neural network model (i.e., the first neural network model) to encode the scrambling code information corresponding to the first user equipment to the Mth (M is a positive integer) user equipment. The base station can also use the same neural network model (i.e., the second neural network model) to decode the sequences to be decoded corresponding to the first user equipment to the Mth (M is a positive integer) user equipment. It can be seen that the model size used in the data receiving method provided by the present disclosure does not increase as the number of user equipments increases.

[0097] Figure 7 Shown with Figure 6 Schematic diagram of the corresponding network architecture.

[0098] exist Figure 7 FIG shows a scenario of receiving and processing data from four user devices. It should be noted that Figure 7 This is just an example. The data receiving method provided by the present disclosure can be applied to scenarios where data from any number of user devices is received and processed. Figure 7 Also shown with Figure 3 Schematic diagram of the corresponding receiving-side network architecture.

[0099] Reference Figure 7 ,First, a superimposed signal from the transmitting side is received.

[0100] Next, a signal sequence is obtained based on the superimposed signal, wherein the signal sequence includes a first signal sequence corresponding to the first user equipment, a second signal sequence corresponding to the second user equipment in the wireless communication network, a third signal sequence corresponding to the third user equipment in the wireless communication network, and a fourth signal sequence corresponding to the fourth user equipment in the wireless communication network.

[0101] Finally, based on the neural network model 2, the first scrambling code information including the random code 1 corresponding to the first user equipment is encoded to obtain a first scrambling code sequence; an operation related to the product is performed on the signal sequence and the first scrambling code sequence (as shown by the symbol as shown), to obtain a first sequence to be decoded; based on a neural network model 1' corresponding to the neural network model 1, the first sequence to be decoded is decoded to obtain sending data 1 corresponding to the first user equipment.

[0102] Based on the neural network model 2, the second scrambling code information including the random code 2 corresponding to the second user equipment is encoded to obtain a second scrambling code sequence; an operation related to the product is performed on the signal sequence and the second scrambling sequence (as shown in the symbol as shown), to obtain a second sequence to be decoded; based on the neural network model 1' corresponding to the neural network model 1, the second sequence to be decoded is decoded to obtain the sending data 2 corresponding to the second user equipment.

[0103] Based on the neural network model 2, the third scrambling code information including the random code 3 corresponding to the third user equipment is encoded to obtain a third scrambling code sequence; an operation related to the product is performed on the signal sequence and the third scrambling code sequence (as shown in the symbol as shown), to obtain a third sequence to be decoded; based on the neural network model 1' corresponding to the neural network model 1, the third sequence to be decoded is decoded to obtain the sending data 3 corresponding to the third user equipment.

[0104] Based on the neural network model 2, the fourth scrambling code information including the random code 4 corresponding to the fourth user equipment is encoded to obtain a fourth scrambling code sequence; an operation related to the product is performed on the signal sequence and the fourth scrambling code sequence (as shown by the symbol as shown), to obtain a fourth sequence to be decoded; based on the neural network model 1' corresponding to the neural network model 1, the fourth sequence to be decoded is decoded to obtain the sending data 4 corresponding to the fourth user equipment.

[0105] The above has been combined Figure 6-7 The data reception method provided by the present disclosure is described in detail. The data reception method provided by the present disclosure can identify data from a user device by introducing scrambling code information, thereby facilitating subsequent accurate decoding of the data corresponding to the user device, thereby making the data reception method provided by the present disclosure more effective when transmitting data from multiple user devices. Furthermore, by using the same neural network model for different user devices, the size of the model used in the data reception method provided by the present disclosure does not increase as the number of user devices increases.

[0106] Combination of the above Figure 1-7 The present disclosure provides a data sending method and a data receiving method. Figure 8 and Figure 9 The transmitting device and receiving device in the wireless communication network provided by the present disclosure are described. Figure 8 The sending device 800 shown is combined with the above Figure 2 The data transmission method described corresponds to and Figure 9 The receiving device 900 shown is combined with the above Figure 6 The data receiving method described in the present invention corresponds to the data receiving method described in the present invention, so for the sake of simplicity, the detailed description of the same content is omitted here.

[0107] Figure 8 A block diagram of a transmitting device 800 in a wireless communication network according to an embodiment of the present disclosure is shown.

[0108] Reference Figure 8 The sending device 800 may include a processing unit 810 and a sending unit 820. Although in this example, the sending device 800 is shown to include the processing unit 810 and the sending unit 820, it should be understood that the sending device 800 may also include other components. However, since these components are not related to the content of the embodiment of the present disclosure, their illustration and description are omitted here.

[0109] As an example, transmitting device 800 may be user equipment or a network-side device. The network-side device may be a base station, such as a gNB. Alternatively, the network-side device may be an OAM module or a SMO module. If the network-side device is the aforementioned OAM or SMO module, the OAM or SMO module needs to transmit the determined sequence to be transmitted to, for example, the base station for subsequent operations. Alternatively, the network-side device may be an upper-layer node of the base station.

[0110] Reference Figure 8 , the processing unit 810 can be configured to encode the data to be sent for the first user equipment based on the first neural network model to obtain a first coding sequence; encode the scrambling code information corresponding to the first user equipment based on the second neural network model to obtain a first scrambling code sequence; perform a product-related operation on the first coding sequence and the first scrambling code sequence to obtain a first sequence to be sent, wherein the first neural network model is the same as the neural network model used to encode the data to be sent for the second user equipment in the wireless communication network to obtain a second coding sequence.

[0111] As an example, the first neural network model and the second neural network model can be any neural network model based on deep learning, such as CNN, RNN, DNN, etc. The first neural network model and the second neural network model can be the same or different neural network models. Preferably, the first neural network model and the second neural network model are the same neural network model, so that the neural network model used in the data transmission method provided by the present disclosure can be unified, and a single neural network model can be used to encode the data to be transmitted and the scrambling information, thereby further reducing the model size.

[0112] As an example, the data to be sent by the first user equipment and the data to be sent by the second user equipment can be any data to be sent determined based on actual conditions. The scrambling code information corresponding to the first user equipment can be of various types and can include any information suitable for use as a scrambling code.

[0113] As an example, performing the product-related operation on the first coding sequence and the first scrambling sequence may be performing any suitable product-based operation on the first coding sequence and the first scrambling sequence.

[0114] According to an embodiment of the present disclosure, performing a product-related operation on a first coding sequence and a first scrambling sequence to obtain a first sequence to be transmitted may include: performing a spreading operation on the first coding sequence; and performing a product-related operation on the spread first coding sequence and the first scrambling sequence to obtain the first sequence to be transmitted.

[0115] The transmitting device provided by the present disclosure can increase the dimension of the obtained sequence to be transmitted by introducing the above-mentioned spread spectrum operation, thereby enabling the data corresponding to the user equipment to be decoded more accurately in the subsequent decoding process.

[0116] According to an embodiment of the present disclosure, the first neural network model used to encode the data to be transmitted of the first user equipment in the wireless communication network to obtain a first coding sequence can be the same as the neural network model used to encode the data to be transmitted of the second user equipment in the wireless communication network to obtain a second coding sequence, so that the transmitting device provided by the present disclosure can adopt the same neural network model for different user equipment, thereby making the model size adopted in the transmitting device provided by the present disclosure not increase with the increase in the number of user equipment. In fact, the transmitting device provided by the present disclosure can adopt a single neural network model to process different user equipment, thereby limiting the model size to the greatest extent.

[0117] Continue to refer to Figure 8 , the sending unit 820 can be configured to send according to the first sequence to be sent.

[0118] As an example, the sending device may obtain an analog signal corresponding to the first sequence to be sent, and then send the analog signal through a transmission channel in a wireless communication network.

[0119] According to an embodiment of the present disclosure, the processing unit 810 may be further configured to obtain the first coding sequence or the first scrambling sequence according to signal-to-noise ratio information about a transmission channel of the first user equipment.

[0120] As an example, the signal-to-noise ratio information about the transmission channel of the first user equipment can be any suitable signal-to-noise ratio information, such as SNR, SINR, etc. Furthermore, the signal-to-noise ratio information about the transmission channel of the first user equipment can be signal-to-noise ratio information of the transmission channel when transmitting data to be transmitted for the first user equipment. According to one example of the present disclosure, the signal-to-noise ratio information of the transmission channel can be determined in advance. For example, it can be determined in advance through statistical analysis based on historical communication information.

[0121] By introducing the above-mentioned signal-to-noise ratio information, the sending device provided by the present disclosure can better send data based on the actual network transmission environment, thereby further improving the accuracy of decoding data corresponding to the user equipment in the subsequent decoding process.

[0122] According to an embodiment of the present disclosure, obtaining the first coding sequence or the first scrambling code sequence based on the signal-to-noise ratio information of the transmission channel of the first user equipment may include: encoding the data to be transmitted for the first user equipment and the signal-to-noise ratio information of the transmission channel of the first user equipment based on the first neural network model to obtain the first coding sequence; or encoding the scrambling code information corresponding to the first user equipment and the signal-to-noise ratio information of the transmission channel of the first user equipment based on the second neural network model to obtain the first scrambling code sequence. As can be seen from the above, the introduced signal-to-noise ratio information can be encoded together with the data to be transmitted for the first user equipment, or can be encoded together with the scrambling code information corresponding to the first user equipment, thereby enabling the introduction of signal-to-noise ratio information in a more flexible manner in the transmitting device provided by the present disclosure.

[0123] According to an embodiment of the present disclosure, when the transmitting device is a network-side device (e.g., a base station), the processing unit 810 may further be configured to encode the data to be transmitted for the second user equipment based on the first neural network model to obtain a second coded sequence; encode the scrambling code information corresponding to the second user equipment based on the second neural network model to obtain a second scrambling code sequence; and perform a product-related operation on the second coded sequence and the second scrambling code sequence to obtain a second sequence to be transmitted. The transmitting unit 820 may further be configured to transmit according to the second sequence to be transmitted and the first sequence to be transmitted.

[0124] As an example, the scrambling code information corresponding to the second user equipment may be of various types and may include any information suitable for use as a scrambling code. As an example, performing a product-related operation on the second coding sequence and the second scrambling sequence may be performing any suitable product-based operation on the second coding sequence and the second scrambling sequence.

[0125] As an example, transmitting according to the second sequence to be transmitted and the first sequence to be transmitted may include superimposing a signal corresponding to the second sequence to be transmitted and a signal corresponding to the first sequence to be transmitted and then transmitting the superimposed signals.

[0126] It can be seen that the base station can use the same neural network model (i.e., the first neural network model) to encode the data to be sent for the first user equipment and the data to be sent for the second user equipment. The base station can use the same neural network model (i.e., the second neural network model) to encode the scrambling code information corresponding to the first user equipment and the scrambling code information corresponding to the second user equipment.

[0127] In this case, when there are more than two user equipments, the base station can also use the same neural network model (i.e., the first neural network model) to encode the data to be transmitted for the first user equipment to the Nth (N is a positive integer) user equipment. The base station can also use the same neural network model (i.e., the second neural network model) to encode the scrambling code information corresponding to the first user equipment to the Nth (N is a positive integer) user equipment. It can be seen that the model size used in the transmitting device provided by the present disclosure does not increase as the number of user equipments increases.

[0128] Figure 9 A block diagram of a receiving device 900 in a wireless communication network according to an embodiment of the present disclosure is shown.

[0129] Reference Figure 9, the sending device 900 may include a receiving unit 910 and a processing unit 920. Although in this example, the receiving device 900 is shown to include the receiving unit 910 and the processing unit 920, it should be understood that the receiving device 900 may also include other components. However, since these components are not related to the content of the embodiments of the present disclosure, their illustration and description are omitted here.

[0130] The transmitting device can be a network device or a user equipment. For example, the network device can be a base station, such as the gNB described above. Alternatively, the network device can be the OAM module or SMO module described above. If the network device is the OAM or SMO module described above, the OAM or SMO module needs to transmit the obtained transmission data corresponding to the user equipment to, for example, the base station for subsequent operations. Alternatively, the network device can be an upper-layer node of the base station.

[0131] Reference Figure 9 , the receiving unit 910 can be configured to obtain a signal sequence.

[0132] According to an embodiment of the present disclosure, the signal sequence may include a first signal sequence corresponding to a first user equipment and a second signal sequence corresponding to a second user equipment in the wireless communication network.

[0133] As an example, the first signal sequence corresponding to the first user equipment may be a sequence of signals in combination with the above Figure 2 The second signal sequence corresponding to the second user equipment may be a sequence corresponding to the first sequence to be sent. Figure 2 The described sequence corresponds to the second sequence to be sent.

[0134] The processing unit 920 can be configured to encode the first scrambling code information corresponding to the first user equipment based on a first neural network model to obtain a first scrambling code sequence; perform a product-related operation on the signal sequence and the first scrambling code sequence to obtain a first sequence to be decoded; and decode the first sequence to be decoded to obtain the transmission data corresponding to the first user equipment. According to an embodiment of the present disclosure, decoding the first sequence to be decoded to obtain the transmission data corresponding to the first user equipment may include: decoding the first sequence to be decoded based on a second neural network model to obtain the transmission data corresponding to the first user equipment. Alternatively, decoding the first sequence to be decoded to obtain the transmission data corresponding to the first user equipment may also include: decoding the first sequence to be decoded based on other methods (for example, filtering, etc.) to obtain the transmission data corresponding to the first user equipment.

[0135] As an example, the first neural network model and the second neural network model can be any neural network model based on deep learning, such as CNN, RNN, DNN, etc. The first neural network model used in the receiving device 900 can be combined with the above Figure 2 The second neural network model used in the receiving device 900 can be combined with the above Figure 2 The first neural network model described corresponds to .

[0136] As an example, the scrambling code information corresponding to the first user equipment may be of various types and may include any information suitable for use as a scrambling code.

[0137] The scrambling code information corresponding to the first user equipment used in the receiving device 900 can be combined with the above Figure 2 The scrambling code information described is the same as the scrambling code information corresponding to the first user equipment. In order to make the above two scrambling code information the same, the sending side and the receiving side can exchange a message about the scrambling code information before formally communicating the information, or the sending side and the receiving side can obtain the scrambling code information according to a rule agreed in advance.

[0138] As an example, performing the product-related operation on the signal sequence and the first scrambling sequence may be performing any suitable product-based operation on the signal sequence and the first scrambling sequence.

[0139] According to an embodiment of the present disclosure, when the receiving device 900 is a network-side device (for example, a base station), the processing unit 910 can also be configured to encode the second scrambling code information corresponding to the second user equipment based on the first neural network model to obtain a second scrambling code sequence; perform product-related operations on the signal sequence and the second scrambling code sequence to obtain a second sequence to be decoded; and decode the second sequence to be decoded based on the second neural network model to obtain transmitted data corresponding to the second user equipment.

[0140] As an example, the scrambling code information corresponding to the second user equipment may be of various types and may include any information suitable for use as a scrambling code.

[0141] The scrambling code information corresponding to the second user equipment used in the receiving device 900 can be combined with the above Figure 2 The scrambling code information described is the same as the scrambling code information corresponding to the second user equipment. In order to make the above two scrambling code information the same, the sending side and the receiving side can exchange a message about the scrambling code information before formally communicating the information, or the sending side and the receiving side can obtain the scrambling code information according to a rule agreed in advance.

[0142] As an example, performing the product-related operation on the signal sequence and the second scrambling sequence may be any suitable product-based operation on the signal sequence and the second scrambling sequence.

[0143] It can be seen that the base station can use the same neural network model (i.e., the first neural network model) to encode the scrambling code information corresponding to the first user equipment and the scrambling code information corresponding to the second user equipment. The base station can use the same neural network model (i.e., the second neural network model) to decode the to-be-decoded sequences corresponding to the first user equipment and the second user equipment, respectively.

[0144] In this case, when there are more than two user equipments, the base station can also use the same neural network model (i.e., the first neural network model) to encode the scrambling code information corresponding to the first user equipment to the Mth (M is a positive integer) user equipment. The base station can also use the same neural network model (i.e., the second neural network model) to decode the sequences to be decoded corresponding to the first user equipment to the Mth (M is a positive integer) user equipment. It can be seen that the model size used in the receiving device provided by the present disclosure does not increase as the number of user equipment increases.

[0145] The above has been combined Figure 2-Figure 9 The method and corresponding device provided by the present disclosure are described in detail. The method and device provided by the present disclosure can identify the data to be transmitted by the user device by introducing scrambling code information, thereby facilitating the subsequent accurate decoding of the data corresponding to the user device, thereby making the method and device provided by the present disclosure more effective when transmitting to multiple user devices. In addition, the method and device provided by the present disclosure adopt the same neural network model for different user devices, thereby ensuring that the size of the model used in the method and device provided by the present disclosure does not increase as the number of user devices increases.

[0146] In order to make the data sending method, data receiving method and corresponding devices provided by the present disclosure clearer, the data sending method, data receiving method and corresponding devices will be further explained in the form of several examples.

[0147] Figure 10 A schematic diagram of a detailed network architecture including a sending side and a receiving side according to an embodiment of the present disclosure is shown. Figure 10 In this example, the MNIST dataset of handwritten digits is used as test data. Here, the data to be sent 1 to the first user device is the handwritten digit 0, and the random code corresponding to the first user device is 42. The data to be sent 2 to the second user device is the handwritten digit 3, and the random code corresponding to the second user device is 53.

[0148] At this time, the hidden layer features are shown in Figure 2. Figure 1 Corresponding to the first sequence to be sent. Hidden layer feature diagram Figure 2 Corresponding to the second sequence to be sent. At this time, the schematic diagram corresponding to the superimposed signal received by the receiving side is the hidden layer feature schematic diagram Figure 3 The hidden layer features are shown as follows: Figure 3 The effect of multiplying the scrambling sequence corresponding to the random code 42 is as shown in the hidden layer feature diagram Figure 4 The schematic diagram shown. The hidden layer features are shown Figure 3 The effect of multiplying the scrambling sequence corresponding to the random code 53 is as shown in the hidden layer feature diagram Figure 5 Finally, after being decoded by the corresponding neural network models, the transmission data corresponding to the first user device (ie, the handwritten number 0) and the transmission data corresponding to the second user device (ie, the handwritten number 3) can be obtained respectively.

[0149] Next, we will use the MNIST dataset of handwritten digits as test data to compare the proposed solution with the existing solution (such as Figure 1 It should be noted that although the present disclosure is based on the MNIST data set of handwritten digits, the above combination Figure 2-Figure 9 It can be seen from the described method and corresponding device that the method and corresponding device provided by the present disclosure are suitable for any data to be sent, including various data such as text, pictures, audio, video, etc.

[0150]

[0151]

[0152] Table 1: Test results

[0153] Figure 11 A schematic diagram shows the result of simultaneous transmission by two users based on an existing solution according to an embodiment of the present disclosure. Figure 12 A schematic diagram shows the result of simultaneous transmission for four users based on an existing solution according to an embodiment of the present disclosure. Figure 13 Schematic diagrams are shown showing the results of performing simultaneous transmission by two users, four users, eight users, and sixteen users, respectively, based on the solution proposed in the present disclosure according to an embodiment of the present disclosure.

[0154] From the above Table 1 and Figure 11-13 As can be seen from the content shown, the existing solution is already unable to decode the data of all users in the scenario where four users transmit simultaneously (e.g. Figure 12As shown in the figure, the data of user 1 and user 4 cannot be decoded). Existing solutions are unable to decode the data of any user in scenarios where more than four users are transmitting simultaneously. However, the solution proposed in this disclosure can decode the corresponding user data regardless of the number of user devices transmitting data simultaneously, and the MSE of the solution proposed in this disclosure is significantly smaller than that of existing solutions. In addition, the model size of the solution proposed in this disclosure is always maintained at the level of a neural network model (X1), and unlike existing solutions, the model size does not increase as the number of user devices increases.

[0155] Next, additive white Gaussian noise (AWGN) will be introduced to further test the performance of the solution proposed in this disclosure.

[0156] The test data is still the MNIST dataset of handwritten digits. The number of users transmitting data simultaneously in the test is 4. The following Table 2-4 and the attached data are obtained. Figure 14-16 .

[0157] Table 2 shows that no white noise data was added when training the neural network model, but the table was obtained when the test was conducted under white noise conditions during the actual test. Figure 14 is the corresponding result diagram.

[0158] Table 3 shows a table obtained by adding white noise data when training the neural network model and also testing under white noise conditions during actual testing. Figure 15 is the corresponding result diagram.

[0159] Table 4 shows that white noise data is added when training the neural network model and the white noise data is encoded together during encoding (as shown in the above combination Figure 2 The SNR described in the table is also obtained by testing under white noise conditions in actual testing. Figure 16 is the corresponding result diagram.

[0160]

[0161]

[0162] Table 2: Test results

[0163] Mode Multiple Access + SNR Channel MSE Noiseless 0.0201 SNR=50 0.0201 SNR=40 0.0201 SNR=30 0.0201 SNR=20 0.0201 SNR=10 0.0201 SNR=0 0.0201 SNR = -10 0.0203 SNR = -20 0.0225

[0164] Table 3: Test results

[0165]

[0166] Table 4: Test results

[0167] The above is Table 2-4 and the attached Figure 14-16 As can be seen from the above content, adding white noise data during training can reduce the MSE (especially when the SNR is relatively low). In addition, encoding the white noise data during encoding can further reduce the MSE.

[0168] <Hardware Structure>

[0169] In addition, the block diagrams used for the description of the above-mentioned embodiments represent blocks of functional units. These functional blocks (structural units) are implemented by any combination of at least one of hardware and software. In addition, the implementation method of each functional block is not particularly limited. That is, each functional block can be implemented using a device that is physically or logically combined, or two or more devices that are physically or logically separated can be directly or indirectly (for example, using wired, wireless, etc.) connected and implemented using these multiple devices. The functional block can also be implemented by combining software in the above-mentioned one device or the above-mentioned multiple devices.

[0170] Functionally, there are judgment, determination, judgment, calculation, calculation, processing, deriving, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, expectation, consideration, broadcasting, notification, communication, forwarding, configuration, reconstruction (reconfiguring), allocation (allocating, mapping), assignment, etc., but it is not limited to these. For example, the functional block (structural unit) that enables the transmission function is called a transmitting unit or a transmitter. As mentioned above, the implementation method is not particularly limited.

[0171] For example, a base station, a user terminal, etc. in one embodiment of the present disclosure may also function as a computer that performs the processing of the method of the present disclosure. Figure 17 This figure shows an example of the hardware structure of a network-side device according to one embodiment of the present disclosure. The network-side device described above can also be physically configured as a computer device including a processor 1701, memory 1702, storage 1703, a communication device 1704, an input device 1705, an output device 1706, a bus 1707, and the like.

[0172] In the following description, the term "device" can be replaced with circuit, equipment, unit, etc. The hardware configuration of the network-side device may include one or more of the devices shown in the figures, or may exclude some of the devices.

[0173] Regarding the various functions in the network side device, this is achieved by reading specific software (program) into hardware such as the processor 1701 and the memory 1702, so that the processor 1701 performs calculations and controls communication based on the communication device 1704, or controls at least one of the reading and writing of data in the memory 1702 and the storage 1703.

[0174] Processor 1701 controls the entire computer by, for example, operating an operating system. Processor 1701 can also be implemented as a central processing unit (CPU) that includes interfaces with peripheral devices, a control device, a computing device, registers, and the like. For example, the transmission unit and processing unit of the aforementioned network-side devices can also be implemented by processor 1701.

[0175] In addition, the processor 1701 reads programs (program codes), software modules, data, etc. from at least one of the storage 1703 and the communication device 1704 to the memory 1702, and performs various processes according to them. As a program, a program that enables a computer to perform at least a part of the operations described in the above-mentioned embodiment is used. For example, the processing unit or control unit of the network side device can also be implemented by a control program that is stored in the memory 1702 and operates in the processor 1701, and the same can be achieved for other functional blocks. It is explained that the various processes mentioned above are performed by one processor 1701, but they can also be performed simultaneously or sequentially by more than two processors 1701. The processor 1701 can also be implemented by one or more chips. In addition, the program can also be sent from the network via an electrical communication line.

[0176] The memory 1702 may also be a computer-readable recording medium, for example, comprised of at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1702 may also be referred to as a register, a cache, a main memory (main storage device), etc. The memory 1702 may store executable programs (program code), software modules, etc., for implementing the wireless communication method according to an embodiment of the present disclosure.

[0177] Storage 1703 may also be a computer-readable recording medium, for example, composed of at least one of an optical disc such as a CD-ROM (Compact Disc Read-Only Memory), a hard disk drive, a flexible disk, an optical magnetic disc (for example, a compact disc, a digital versatile disc, a Blu-ray (registered trademark) disc), a smart card, a flash memory (for example, a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic stripe, etc. Storage 1703 may also be referred to as an auxiliary storage device. The above-mentioned recording medium may also be, for example, a database, a server, or other appropriate medium that includes at least one of memory 1702 and storage 1703.

[0178] Communication device 1704 is hardware (a transmitting and receiving device) used to communicate between computers via at least one of a wired network and a wireless network. It is also referred to as a network device, network controller, network card, or communication module. Communication device 1704 may include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, and the like to implement at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0179] The input device 1705 is an input device that receives input from the outside (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1706 is an output device that outputs to the outside (e.g., a display, speaker, LED light, etc.). Alternatively, the input device 1705 and the output device 1706 may be integrated (e.g., a touch panel).

[0180] Furthermore, the processor 1701, memory 1702, and other devices are connected via a bus 1707 for communicating information. The bus 1707 may be configured using a single bus or different buses between the devices.

[0181] Furthermore, the network-side device may also include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array), and the like, and implement a portion or all of each functional block using this hardware. For example, the processor 1701 may also be implemented using at least one of these hardware components.

[0182] <Modification>

[0183] In addition, in the present disclosure, the notification of information is not limited to the manner / implementation method described in the present disclosure, and other methods may also be used. For example, the notification of information may also be implemented through physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), high-layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals or a combination thereof. In addition, RRC signaling may also be referred to as an RRC message, such as an RRC Connection Setup message, an RRC Connection Reconfiguration message, etc.

[0184] The various modes and embodiments described in the present disclosure may also be applied to LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (x is, for example, an integer or a decimal)), FRA (Future Radio Access), NR (New Radio), New Radio Access (NX), Future Generation Radio Access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE At least one of IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth (registered trademark), systems utilizing other appropriate systems, and next-generation systems expanded, modified, created, or specified based on these. Furthermore, multiple systems may be combined (for example, a combination of at least one of LTE and LTE-A with 5G).

[0185] The processing procedures, timings, flow charts, etc. of each method / implementation described in this disclosure may be rearranged in order as long as there is no contradiction. For example, the methods described in this disclosure use an illustrative order to present various step elements, and are not limited to the specific order presented.

[0186] In this disclosure, specific operations are performed by a base station, but depending on the circumstances, they may also be performed by its upper node. In a network consisting of one or more network nodes including a base station, various operations performed for communication with a terminal can obviously be performed by at least one of the base station and other network nodes other than the base station (for example, but not limited to, the MME or S-GW). The above example illustrates a single other network node other than the base station, but a combination of multiple other network nodes (for example, an MME and an S-GW) is also possible.

[0187] Information (see "Information, Signals") can be transmitted from a higher layer (or lower layer) to a lower layer (or higher layer), and can also be input and output via multiple network nodes.

[0188] Input and output information can be stored in a specific location (e.g., memory) or managed using a management table. Input and output information can be overwritten, updated, or appended. Output information can also be deleted. Input information can also be sent to other devices.

[0189] The determination can be made using a value represented by 1 bit (0 or 1), a true or false value (Boolean value: true or false), or a comparison of numerical values (for example, comparison with a specific value).

[0190] Each method / implementation method described in this disclosure may be used alone or in combination, or may be switched during execution. Furthermore, notification of specific information (e.g., notification of "it is X") is not limited to being performed explicitly, but may also be performed implicitly (e.g., not notifying the specific information).

[0191] While the present disclosure has been described in detail above, it will be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description of the present disclosure is for illustrative purposes only and is not intended to limit the present disclosure in any way.

[0192] In this disclosure, whether software is referred to as software, firmware, middleware, microcode, hardware description language, or otherwise, it should be interpreted broadly to mean instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, execution threads, procedures, functions, etc.

[0193] Furthermore, software, instructions, information, and the like may also be transmitted and received via a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using at least one of a wired technology (coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.) and a wireless technology (infrared, microwave, etc.), at least one of these wired and wireless technologies is included within the definition of a transmission medium.

[0194] Information, signals, and the like described in this disclosure may also be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, and the like referred to throughout the foregoing description may also be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or photons, or any combination thereof.

[0195] In addition, the terms described in this disclosure and the terms required for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may also be referred to as a carrier frequency, a cell, a frequency carrier, etc.

[0196] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0197] Furthermore, information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values relative to a specific value, or other corresponding information. For example, wireless resources may also be indicated by indexes.

[0198] The names used for the parameters described above are not intended to be limiting in any respect. Furthermore, the mathematical formulas for these parameters may differ from those explicitly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable names, and therefore the names assigned to these channels and information elements are not intended to be limiting in any respect.

[0199] In this disclosure, terms such as "base station (BS)," "wireless base station," "fixed station," "NodeB," "eNodeB (eNB)," "gNodeB (gNB)," "access point," "transmission point," "reception point," "transmission / reception point," "cell," "sector," "cell group," "carrier," and "component carrier" are used interchangeably. Base stations are also sometimes referred to as macrocells, small cells, femtocells, and picocells.

[0200] A base station can accommodate one or more (for example, three) cells. When a base station accommodates multiple cells, the overall coverage area of the base station can be divided into multiple smaller areas, and each smaller area can also provide communication services through a base station subsystem (for example, a small base station for indoor use (remote radio head (RRH))). Terms such as "cell" or "sector" refer to a part or the entire coverage area of at least one of the base station and the base station subsystem that provides communication services within the coverage area.

[0201] In the present disclosure, terms such as “mobile station (MS)”, “user terminal”, “user device (UE)”, and “terminal” can be used interchangeably.

[0202] A mobile station is also sometimes referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or several other appropriate terms.

[0203] At least one of the base station and the mobile station may also be referred to as a transmitting device, a receiving device, a communication device, etc. In addition, at least one of the base station and the mobile station may also be a device mounted on a mobile body, a mobile body, etc. The mobile body is an object that can move, and the moving speed is arbitrary. In addition, of course, it also includes the situation where the mobile body is stopped. The mobile body includes, for example, vehicles, transport vehicles, cars, two-wheeled motorcycles, bicycles, connected cars, forklifts, bulldozers, wheel loaders, dump trucks, forklifts, trains, buses, trailers, rickshaws, ships (ships and other watercraft), airplanes, rockets, artificial satellites, drones (registered trademark), multicopters, quadcopters (vertical take-off and landing) helicopters (quadcopters), balloons, and objects carried thereon, or not limited thereto. In addition, the mobile body may also be a mobile body that moves autonomously based on an operating instruction. It can be a vehicle (e.g., a car, airplane, etc.), a mobile object that moves unmanned (e.g., a drone, an autonomous vehicle, etc.), or a robot (manned or unmanned). Furthermore, at least one of the base station and the mobile station also includes a device that does not necessarily move during communication operations. For example, at least one of the base station and the mobile station can be an IoT (Internet of Things) device such as a sensor.

[0204] In addition, the base station in the present disclosure can also be interpreted as a user terminal. For example, the various methods / implementations of the present disclosure can also be applied to a structure in which the communication between a base station and a user terminal is replaced by communication between multiple user terminals (for example, it can also be called D2D (Device-to-Device), V2X (Vehicle-to-Everything), etc.). In this case, it can also be set as a structure in which the user terminal has the functions of the above-mentioned base station. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channel, downlink channel, etc. can also be replaced by side channel.

[0205] Likewise, the user terminal in this disclosure can also be interpreted as a base station. In this case, the base station can also be configured to have the functions of the user terminal described above.

[0206] The term "determine" used in this disclosure sometimes includes a variety of operations. For example, "determine" may include judging, calculating, computing, processing, deriving, investigating, looking up (for example, searching in a table, database or other data structure), confirming (for example, ascertaining) as having performed "determination", etc. In addition, "determine" may include receiving (for example, receiving information), transmitting (for example, sending information), inputting, outputting, accessing (for example, accessing data in a memory) as having performed "judgment", "decision", etc. In addition, "judgment" and "decision" may include resolving, selecting, choosing, establishing, comparing, etc. as having performed "judgment", "decision". That is, "judgment" and "decision" may include certain operations as having performed "judgment" and "decision". In addition, “judgment (decision)” can also be replaced by “assuming (assuming)”, “expecting (expecting)”, “considering (considering)”, etc.

[0207] In the present disclosure, terms such as "connected", "coupled", or all variations thereof mean all direct or indirect connections or combinations between two or more elements, and may include the situation where one or more intermediate elements exist between the two elements that are "connected" or "coupled" to each other. The combination or connection between elements may also be physical, logical, or a combination thereof. For example, "connect" may also be replaced by "access". In the context of use in the present disclosure, it is contemplated to use at least one of one or more wires, cables, and printed electrical connections, and as some non-limiting and non-inclusive examples, wavelengths having wireless frequency domains, microwave domains, and optical (both visible and invisible) domains may be used.

[0208] The phrase “based on” used in this disclosure does not mean “based only on” unless otherwise explicitly stated. In other words, the phrase “based on” means both “based only on” and “based at least on.”

[0209] Any reference to an element using the designations "first," "second," etc., as used in this disclosure, does not necessarily define the quantity or order of these elements. These designations can be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, reference to a first and a second element does not imply that only two elements can be used, or that the first element must take precedence over the second element in some form.

[0210] In the present disclosure, the “unit” in the configuration of each of the above-mentioned devices may be replaced with a “circuit”, a “device”, or the like.

[0211] In this disclosure, when the terms "include," "including," and variations thereof are used, these terms, like the term "comprising," are inclusive. Furthermore, the term "or" used in this disclosure does not mean exclusive or.

[0212] While the present disclosure has been described in detail above, it will be apparent to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure may be implemented in various modifications and variations without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the descriptions in this specification are for illustrative purposes only and are not intended to be limiting of the present disclosure.

Claims

1. A transmitting device in a wireless communication network, comprising: a processing unit configured to encode the to-be-sent data for the first user equipment based on the first neural network model to obtain a first coding sequence; encoding scrambling code information corresponding to the first user equipment based on a second neural network model to obtain a first scrambling code sequence; performing a product-related operation on the first coding sequence and the first scrambling sequence to obtain a first sequence to be transmitted, wherein the first neural network model is the same as a neural network model used to encode data to be transmitted by a second user equipment in the wireless communication network to obtain a second coding sequence; A sending unit is configured to send according to the first sequence to be sent.

2. The transmitting device according to claim 1, wherein The processing unit is further configured to obtain the first coding sequence or the first scrambling code sequence according to signal-to-noise ratio information about a transmission channel of the first user equipment.

3. The transmitting device according to claim 2, wherein: The obtaining the first coding sequence or the first scrambling sequence according to signal-to-noise ratio information of a transmission channel of the first user equipment includes: encoding, based on the first neural network model, data to be sent for the first user equipment and signal-to-noise ratio information of a transmission channel of the first user equipment to obtain the first coding sequence; or Based on the second neural network model, scrambling code information corresponding to the first user equipment and signal-to-noise ratio information of a transmission channel of the first user equipment are encoded to obtain the first scrambling code sequence.

4. The transmitting device according to any one of claims 1 to 3, wherein: The first neural network model and the second neural network model are the same neural network model.

5. The sending device according to any one of claims 1 to 3, wherein: The sending device is a base station, The processing unit is further configured to encode the to-be-sent data for the second user equipment based on the first neural network model to obtain a second coded sequence; encoding scrambling code information corresponding to the second user equipment based on the second neural network model to obtain a second scrambling code sequence; performing a product-related operation on the second coding sequence and the second scrambling sequence to obtain a second sequence to be transmitted; The sending unit is further configured to send according to the second sequence to be sent and the first sequence to be sent.

6. A receiving device in a wireless communication network, comprising: a receiving unit configured to obtain a signal sequence, wherein the signal sequence includes a first signal sequence corresponding to a first user equipment and a second signal sequence corresponding to a second user equipment in the wireless communication network; a processing unit configured to, based on a first neural network model, encode first scrambling code information corresponding to the first user equipment to obtain a first scrambling code sequence; and perform a product-related operation on the signal sequence and the first scrambling code sequence to obtain a first sequence to be decoded; The first sequence to be decoded is decoded to obtain transmission data corresponding to the first user equipment.

7. The receiving device according to claim 6, wherein The decoding the first sequence to be decoded to obtain transmission data corresponding to the first user equipment includes: Based on the second neural network, the first sequence to be decoded is decoded to obtain transmission data corresponding to the first user equipment.

8. The receiving device according to claim 6 or 7, wherein: The receiving device is a base station, The processing unit is further configured to encode second scrambling code information corresponding to the second user equipment based on the first neural network model to obtain a second scrambling code sequence; and perform a product-related operation on the signal sequence and the second scrambling code sequence to obtain a second sequence to be decoded; Based on the second neural network model, the second sequence to be decoded is decoded to obtain transmission data corresponding to the second user equipment.

9. A data transmission method, comprising: Encoding data to be sent to the first user equipment based on the first neural network model to obtain a first coding sequence; encoding scrambling code information corresponding to the first user equipment based on a second neural network model to obtain a first scrambling code sequence; performing a product-related operation on the first coding sequence and the first scrambling sequence to obtain a first sequence to be transmitted, wherein the first neural network model is the same as a neural network model used to encode data to be transmitted by a second user equipment in the wireless communication network to obtain a second coding sequence; Sending is performed according to the first sequence to be sent.

10. A data receiving method, comprising: Obtaining a signal sequence, wherein the signal sequence includes a first signal sequence corresponding to a first user equipment and a second signal sequence corresponding to a second user equipment in the wireless communication network; encoding first scrambling code information corresponding to the first user equipment based on a first neural network model to obtain a first scrambling code sequence; performing a product-related operation on the signal sequence and the first scrambling code sequence to obtain a first sequence to be decoded; The first sequence to be decoded is decoded to obtain transmission data corresponding to the first user equipment.

Images