A data processing method and related device

Abstract

The application relates to a data processing method and related equipment for improving the calculation speed of determining the throughput rate of a communication system by learning a neural network model, avoiding complex theoretical modeling and the process of calculating a spectrum efficiency mapping table, and optimizing the determination process of the throughput rate in the communication system. In the method, first information between a transmitter and a receiver in the communication system is determined (S101), and the first information comprises characteristic information of data transmission between the transmitter and the receiver; thereafter, the data processing device takes the first information as input of a prediction model, outputs second information after processing by the prediction model (S102), and the second information is used for determining the throughput rate of the communication system.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of wireless communication, and in particular, to a data processing method and related equipment. BACKGROUND

[0002] In the planning and optimization phase of a wireless network, the performance of a newly built network or a stock network is simulated, and the key performance indicator (KPI) compliance rate of the network is evaluated, and the number of additional stations and the expansion ratio are output to provide suggestions for network phased construction, which can improve the investment return ratio. Among the KPI indicators, the throughput rate is one of the key indicators.

[0003] Currently, in the determination process of the throughput rate, the network device calculates the performance parameters of the terminal device, determines the spectrum efficiency (SE) corresponding to the performance parameters in the preset spectrum efficiency mapping table, and further determines the throughput rate of the communication system in which the network device is located. The performance parameters of the terminal device can include, for example, reference signal receiving power (RSRP), signal to interference plus noise ratio (SINR), and channel quality indicator (CQI).

[0004] However, in the above manner, the existing spectrum efficiency mapping table is generally obtained based on theoretical simulation under certain channel conditions, and compared with the actual communication process of the channel, the accuracy is greatly deviated. Therefore, how to optimize the determination process of the throughput rate is a technical problem to be solved. SUMMARY

[0005] Embodiments of the present application provide a data processing method and related equipment for learning through a neural network model, which improves the calculation speed of determining the throughput rate of a communication system, avoids the complex theoretical modeling and the process of determining the spectrum efficiency mapping table, and optimizes the determination process of the throughput rate in the communication system.

[0006] The first aspect of the embodiment of the present application provides a data processing method, which is applied to a data processing device. The data processing device can be a server, for example, a network management server arranged in a network device (for example, a base station), a network management server externally connected to a network device (for example, a base station), or a component (for example, a processor, a chip or a chip system) of a network device (for example, a base station). In the method, the data processing device first determines first information between a transmitter and a receiver in a communication system, and the first information includes characteristic information of data transmission between the transmitter and the receiver. Then, the data processing device takes the first information as an input of a prediction model, and outputs second information after processing by the prediction model. The second information is used to determine a throughput rate of the communication system. The first information input to the prediction model includes characteristic information of data transmission between the transmitter and the receiver in the communication system, and the characteristic information of the data transmission is used to indicate the data transmission characteristics between the transmitter and the receiver, that is, the characteristic information of the data transmission is associated with the throughput rate of the communication system. Then, the prediction model outputs the second information used to determine the throughput rate of the communication system according to the first information. Thus, the method of learning by the neural network model improves the calculation speed of determining the throughput rate of the communication system, avoids the process of complex theoretical modeling and calculation of determining the spectrum efficiency mapping table, and optimizes the determination process of the throughput rate in the communication system.

[0007] In a possible implementation manner of the first aspect of the embodiment of the present application, the characteristic information of the data transmission includes at least one of the following:

[0008] Reference signal received power (RSRP), distance information, relative direction angle information or relative down tilt angle information.

[0009] In the embodiment, the first information input to the prediction model, that is, the characteristic information of the data transmission can include at least one of reference signal received power (RSRP), distance information, relative direction angle information or relative down tilt angle information between the transmitter and the receiver in the communication system, that is, the data transmission characteristics between the transmitter and the receiver can be embodied by the at least one. Thus, the multiple specific implementation manners of the characteristic information of the data transmission are provided, and the realizability of the scheme is improved.

[0010] In a possible implementation manner of the first aspect of the embodiment of the present application, the characteristic information of the data transmission further includes at least one of the following:

[0011] Frequency band information, antenna type information, rank (RANK) or block error rate (BLER).

[0012] In the embodiment, the first information input to the prediction model can also be implemented in other manners, that is, the characteristic information of the data transmission can also include at least one of frequency band information of data transmission between the transmitter and the receiver in the communication system, antenna type information (of the transmitter or the receiver), rank RANK or block error rate BLER. Thus, while providing other specific implementation manners of the characteristic information of the data transmission, the implementability of the scheme is improved.

[0013] In a possible implementation manner of the first aspect of the embodiment, the first information further includes characteristic information of a geographical environment between the transmitter and the receiver.

[0014] In the embodiment, the first information input to the prediction model can also include characteristic information of a geographical environment between the transmitter and the receiver, that is, the characteristic information of the geographical environment is associated with the throughput rate of the communication system. Therefore, the characteristic information of the geographical environment between the transmitter and the receiver is taken as part of the input of the prediction model, and the prediction model uses the characteristic information of the data transmission and the characteristic information of the geographical environment as the prediction basis, so that the accuracy of the throughput rate determined by the second information output by the prediction model is higher.

[0015] In a possible implementation manner of the first aspect of the embodiment, the characteristic information of the geographical environment includes at least one of the following:

[0016] building height information, ground object height information or altitude information.

[0017] In the embodiment, the characteristic information of the geographical environment included in the first information input to the prediction model can specifically include at least one of building height information, ground object height information or altitude information, that is, the geographical environment characteristics between the transmitter and the receiver can be embodied by at least one of the above. Thus, while providing various specific implementation manners of the characteristic information of the geographical environment, the implementability of the scheme is improved.

[0018] In a possible implementation manner of the first aspect of the embodiment, the method further includes: obtaining target map information between the transmitter and the receiver in the communication system, the target map information including at least one of digital map information and satellite map information; and processing the target map information to obtain the characteristic information of the geographical environment between the transmitter and the receiver.

[0019] In the embodiment, since the digital map and the satellite map can determine the geographical environment between the transmitter and the receiver, the characteristic information of the geographical environment can be determined by at least one of the digital map information and the satellite map information. Thus, while providing various specific implementation manners of generating the characteristic information of the geographical environment, the implementability of the scheme is improved.

[0020] In a possible implementation of the first aspect of the embodiment of the application, the second information comprises a spectral efficiency of data transmission between the transmitter and the receiver.

[0021] In the embodiment, the second information used for determining the throughput of the communication system can comprise a spectral efficiency of data transmission between the transmitter and the receiver, and the throughput of the communication system can be subsequently determined through the spectral efficiency, thereby providing a specific implementation of the second information.

[0022] In a possible implementation of the first aspect of the embodiment of the application, before the first information is input into the prediction model and the second information is output after processing of the prediction model, the method further comprises: obtaining sample data, the sample data comprising input data and label data, the input data comprising feature information of simulated data transmission, and the label data being used for determining a throughput corresponding to the input data; and inputting the sample data into a preset neural network to train the prediction model.

[0023] In the embodiment, before the second information is output by the prediction model according to the first information, the prediction model can be obtained through a training process of the neural network, that is, the prediction model is obtained through input of the sample data into the preset neural network and training, thereby providing a specific implementation of obtaining the prediction model through the training of the neural network.

[0024] In a possible implementation of the first aspect of the embodiment of the application, the feature information of the simulated data transmission comprises at least one of the following:

[0025] Reference signal received power (RSRP), distance information, relative direction angle information, relative down-tilt angle information, frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

[0026] In the embodiment, in the training process of the neural network, the feature information of the simulated data transmission input into the preset neural network can comprise at least one of the following: reference signal received power (RSRP), distance information, relative direction angle information, relative down-tilt angle information, frequency band information, antenna type information, rank (RANK), or block error rate (BLER). Since the at least one parameter is associated with the throughput of the communication system, the training data of the neural network can be enriched according to the at least one parameter subsequently, thereby improving the accuracy of the prediction model in the subsequent prediction process.

[0027] In a possible implementation of the first aspect of the embodiment of the application, the input data further comprises feature information of a simulated geographic environment.

[0028] In the embodiment, in the training process of the neural network, the input data input to the preset neural network can further include feature information of a simulated geographic environment, and the feature information of the simulated geographic environment is related to the throughput of the communication system. Therefore, the training data of the neural network can be enriched according to the feature information of the simulated geographic environment, and the accuracy of the prediction model in the subsequent prediction process can be improved.

[0029] In a possible implementation of the first aspect of the embodiment of the application, the feature information of the simulated geographic environment includes at least one of the following:

[0030] Building height information, ground feature height information or altitude information.

[0031] In the embodiment, in the training process of the neural network, the feature information of the simulated geographic environment input to the preset neural network can include at least one of the building height information, the ground feature height information or the altitude information. Thus, multiple specific implementation modes of the feature information of the simulated geographic environment are provided, and the realizability of the scheme is improved.

[0032] In a possible implementation of the first aspect of the embodiment of the application, the label data includes the spectral efficiency corresponding to the input data.

[0033] In the embodiment, in the training process of the neural network, the label data input to the preset neural network can include the spectral efficiency corresponding to the input data, that is, the label data used to determine the throughput corresponding to the input data can include the spectral efficiency of data transmission. The throughput of the communication system can be determined through the spectral efficiency, and a specific implementation mode of the label data is provided.

[0034] The second aspect of the embodiment of the application provides a data processing apparatus, including:

[0035] A determination unit configured to determine first information between a transmitter and a receiver in a communication system, the first information including feature information of data transmission between the transmitter and the receiver;

[0036] A first processing unit configured to input the first information to a prediction model, and output second information after processing by the prediction model, the second information being used to determine a throughput of the communication system.

[0037] In a possible implementation of the second aspect of the embodiment of the application, the feature information of the data transmission includes at least one of the following:

[0038] Reference signal received power (RSRP), distance information, relative direction angle information or relative down tilt angle information.

[0039] In a possible implementation manner of the second aspect of the embodiment of the present application, the feature information of the data transmission further includes at least one of the following:

[0040] The frequency band information, the antenna type information, the rank RANK, or the block error rate BLER.

[0041] In a possible implementation manner of the second aspect of the embodiment of the present application, the first information further includes feature information of a geographical environment between the transmitter and the receiver.

[0042] In a possible implementation manner of the second aspect of the embodiment of the present application, the feature information of the geographical environment includes at least one of the following:

[0043] The building height information, the ground feature height information, or the altitude information.

[0044] In a possible implementation manner of the second aspect of the embodiment of the present application, the apparatus further includes a first obtaining unit and a second processing unit:

[0045] The first obtaining unit is configured to obtain target map information between the transmitter and the receiver in the communication system, the target map information including at least one of digital map information and satellite map information;

[0046] The second processing unit is further configured to process the target map information to obtain the feature information of the geographical environment between the transmitter and the receiver.

[0047] In a possible implementation manner of the second aspect of the embodiment of the present application, the second information includes a spectral efficiency of data transmission between the transmitter and the receiver.

[0048] In a possible implementation manner of the second aspect of the embodiment of the present application, the apparatus further includes a second obtaining unit and a training unit:

[0049] The second obtaining unit is configured to obtain sample data, the sample data including input data and label data, the input data including feature information of simulated data transmission, and the label data being used to determine a throughput rate corresponding to the input data;

[0050] The training unit is configured to input the sample data to a preset neural network to train the prediction model.

[0051] In a possible implementation manner of the second aspect of the embodiment of the present application, the feature information of the simulated data transmission includes at least one of the following:

[0052] The reference signal received power RSRP, the distance information, the relative direction angle information, the relative down-tilt angle information, the frequency band information, the antenna type information, the rank RANK, or the block error rate BLER.

[0053] In a possible implementation manner of the second aspect of the embodiment of the present application, the input data further comprises feature information of a simulated geographic environment.

[0054] In a possible implementation manner of the second aspect of the embodiment of the present application, the feature information of the simulated geographic environment comprises at least one of the following:

[0055] building height information, ground feature height information or altitude information.

[0056] In a possible implementation manner of the second aspect of the embodiment of the present application, the label data comprises a spectrum efficiency corresponding to the input data.

[0057] The third aspect of the embodiment of the present application provides a data processing apparatus, which can be a network device or a component (for example, a processor, a chip or a chip system, etc.) of the network device, wherein the data processing apparatus comprises a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run computer programs or instructions, so that the method of the first aspect or any possible implementation manner of the first aspect is executed.

[0058] The fourth aspect of the embodiment of the present application provides a computer readable storage medium storing one or more computer execution instructions, when the computer execution instructions are executed by a processor, the processor executes the method of the first aspect or any possible implementation manner of the first aspect.

[0059] The fifth aspect of the embodiment of the present application provides a computer program product (or computer program) storing one or more computers, when the computer program product is run on a computer, so that the computer executes the first aspect or any possible implementation manner of the first aspect.

[0060] The sixth aspect of the embodiment of the present application provides a chip system, which comprises a processor, and is configured to support the access network device to implement the functions involved in the first aspect or any possible implementation manner of the first aspect. In a possible design, the chip system can further comprise a memory, and the memory is configured to store necessary program instructions and data of the access network device. The chip system can be composed of a chip, or can comprise a chip and other discrete devices.

[0061] The seventh aspect of the embodiment of the present application provides a communication system, which comprises the data processing apparatus of the second aspect or the data processing apparatus of the third aspect.

[0062] The technical effects brought by the third to seventh aspects or any possible implementation manner thereof can refer to the technical effects brought by the first aspect or different possible implementation manners of the first aspect, which will not be described herein.

[0063] From the above technical solutions, in some embodiments of the present application, the data processing apparatus first determines the first information between the transmitter and the receiver in the communication system, and the first information includes the characteristic information of data transmission between the transmitter and the receiver; thereafter, the data processing apparatus takes the first information as the input of the prediction model, and outputs the second information after processing by the prediction model, and the second information is used to determine the throughput rate of the communication system. Among them, the first information input to the prediction model includes the characteristic information of data transmission between the transmitter and the receiver in the communication system, that is, the characteristic information is used to indicate the data transmission characteristics between the transmitter and the receiver, and thereafter, the prediction model outputs the second information for determining the throughput rate of the communication system according to the first information. Therefore, by using the neural network model learning method, the calculation speed of determining the throughput rate of the communication system is improved, and the process of complex theoretical modeling and calculating the spectrum efficiency mapping table is avoided, and the determination process of the throughput rate in the communication system is optimized. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 A schematic diagram of a network system in an embodiment of the present application;

[0065] Figure 2 A flowchart for determining the throughput rate through the spectrum efficiency table;

[0066] Figure 3 A schematic diagram of a data processing method provided by an embodiment of the present application;

[0067] Figure 4-1 Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0068] Figure 4-2 Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0069] Figure 5 Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0070] Figure 6 Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0071] Figure 7 Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0072] Figure 8-1Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0073] Figure 8-2 Another schematic diagram of a data processing method provided by an embodiment of the present application;

[0074] Figure 9 A schematic diagram of a data processing device provided by an embodiment of the present application;

[0075] Figure 10 Another schematic diagram of a data processing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0076] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0077] First, some terms in the embodiments of the present application are explained to facilitate understanding by those of ordinary skill in the art.

[0078] 1. Terminal device: can be a wireless terminal device capable of receiving network device scheduling and indication information. The wireless terminal device can be a device providing voice and / or data connectivity to a user, or a handheld device with wireless connection function, or other processing devices connected to a wireless modem.

[0079] A terminal device can communicate with one or more core networks or the Internet via a radio access network (RAN), and the terminal device can be a mobile terminal device, such as a mobile phone (or called "cellular" phone, mobile phone), a computer, and a data card, for example, which can be a portable, pocket, hand-held, computer-embedded, or vehicle-mounted mobile device that exchanges voice and / or data with the radio access network. For example, a personal communication service (PCS) phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a Pad, a computer with wireless transceiver function, and the like. The wireless terminal device can also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station (MS), a remote station, an access point (AP), a remote terminal, an access terminal, a user terminal, a user agent, a subscriber station (SS), a customer premises equipment (CPE), a terminal, a user equipment (UE), a mobile terminal (MT), and the like. The terminal device can also be a wearable device and a terminal device in a next-generation communication system, such as a terminal device in a 5G communication system or a terminal device in a future evolved public land mobile network (PLMN), and the like.

[0080] 2、Network device: can be a device in a wireless network, for example, the network device can be a radio access network (RAN) node (or device) that connects the terminal device to the wireless network, which can also be referred to as a base station. Currently, some examples of RAN devices are: a new generation base station (gNodeB) in a 5G communication system, a transmission reception point (TRP), an evolved Node B (eNB), a radio network controller (RNC), a Node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home base station (e.g., home evolved Node B or home Node B, HNB), a baseband unit (BBU), or a wireless fidelity (Wi-Fi) access point (AP), etc. In addition, in one network structure, the network device can include a centralized unit (CU) node, or a distributed unit (DU) node, or a RAN device including a CU node and a DU node.

[0081] Among them, the network device can send configuration information (e.g., carried in a scheduling message and / or an indication message) to the terminal device, and the terminal device further performs network configuration according to the configuration information, so that the network configuration between the network device and the terminal device is aligned; or, through the preset network configuration of the network device and the preset network configuration of the terminal device, so that the network configuration between the network device and the terminal device is aligned. Specifically, "alignment" means that when there is an interactive message between the network device and the terminal device, the two are consistent in understanding the carrier frequency of the interactive message transmission and reception, the determination of the interactive message type, the meaning of the field information carried in the interactive message, or other configurations of the interactive message.

[0082] In addition, in other possible cases, the network device can be other apparatuses that provide wireless communication functions for the terminal device. Embodiments of the present application do not limit the specific technology and specific device form adopted by the network device. For the convenience of description, the network device can also include a core network device, for example, an access and mobility management function (AMF), a user plane function (UPF), or a session management function (SMF), and the like.

[0083] In the embodiments of the present application, the apparatus for implementing the function of the network device can be the network device, or an apparatus capable of supporting the network device to implement the function, such as a chip system, which can be installed in the network device. In the technical solutions provided in the embodiments of the present application, the apparatus for implementing the function of the network device is taken as an example to describe the technical solutions provided in the embodiments of the present application.

[0084] 3. Neural network: The neural network can be composed of neural units, and the neural unit can be an operation unit with xs and intercept 1 as inputs. The output of the operation unit can be:

[0085]

[0086] wherein s = 1, 2, … n, n is a natural number greater than 1, Ws is the weight of xs, b is the bias of the neural unit. f is an activation function of the neural unit, which is used to introduce a nonlinear characteristic into the neural network to convert the input signal in the neural unit into an output signal. The output signal of the activation function can be used as the input of the next convolution layer. The activation function can be a sigmoid function. The neural network is a network formed by connecting many single neural units together, that is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field, and the local receptive field can be a region composed of several neural units. The neural network can include a plurality of neural units to form a "layer", such as an input layer, a hidden layer, and an output layer. The input layer is responsible for receiving input data and distributing to the hidden layer. The hidden layer is responsible for the required calculation and output result to the output layer, and the output layer outputs the output result.

[0087] 4、The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "At least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the cases of A alone, A and B together, and B alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single item or multiple items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. In addition, unless otherwise specified, the ordinal numbers "first", "second" and the like mentioned in the embodiments of the present application are used to distinguish a plurality of objects, and are not used to limit the order, time sequence, priority or importance of the plurality of objects.

[0088] Figure 1 is a schematic diagram of a communication system in the present application. In Figure 1 the communication system shown, at least one network device and at least one terminal device are included, such as Figure 1 the network device 101, and the terminal device 102, the terminal device 103, the terminal device 104, the terminal device 105, the terminal device 106 and the terminal device 107, etc. In Figure 1 the example shown, the terminal device 102 is taken as a vehicle, the terminal device 103 is taken as a smart air conditioner, the terminal device 104 is taken as a smart refueling machine, the terminal device 105 is taken as a mobile phone, the terminal device 106 is taken as a smart tea cup, and the terminal device 107 is taken as a printer. In Figure 1 the communication process of the communication system shown, the signal transmitting end (transmitter) can be a network device or a terminal device, and the signal receiving end (receiver) can be a network device or a terminal device.

[0089] In the wireless network planning and optimization phase, simulation is one of the key steps. By simulating the performance of the newly built network or the existing network, the network KPI target rate is evaluated around the network building standard, the number of added stations and the expansion ratio are output, suggestions are provided for network phased construction, and the investment return ratio is improved. Among the KPI indicators, the uplink and downlink throughput rate is one of the key indicators. With the coming of 5G, the business is promoted from enhanced mobile broadband (eMBB) business to various new businesses, such as home broadband business and different service level requirement business. The accuracy of the throughput rate simulation for such businesses has been upgraded from statistical accuracy to deterministic requirement. Therefore, improving the accuracy of the throughput rate simulation (or throughput rate determination) is one of the core technologies of network planning and optimization. In Figure 1For example, the throughput of the communication system can indicate the information flow transmitted per unit time, i.e., the amount of effective data on the transmission bandwidth (resource block (RB), one RB is composed of a fixed number of resource elements (RE)) within 1 second.

[0090] At present, a conventional throughput simulation method is as follows: a channel model is specified, a physical layer model is established (a process of encoding, modulation, interleaving, etc. of data flow on different time and frequency domain resources needs to be established), a transceiver link reference signal receiving power (RSRP) is obtained, a RB scheduling situation of a user on different time of a wireless bandwidth is simulated, and thus a throughput performance under various channel environments and different transmission modes is obtained.

[0091] However, the method one has high theory degree, but has deviation from an actual channel environment, and actual accuracy is not good to measure, in addition, modeling complexity of the method is high, and the method cannot be directly used in a network planning optimization stage.

[0092] Compared with the above implementation method, a conventional throughput simulation method two is as follows: a channel model is not specified, network environment information, engineering parameters, a RB scheduling strategy, and an actual effective RE number are input, and performance indicators such as RSRP, a signal to interference plus noise ratio (SINR), or a channel quality indicator (CQI) of each user in the network are calculated. However, a physical layer model is not established in the throughput calculation, but a user peak throughput is calculated by looking up a spectral efficiency mapping table through the SINR or the CQI. The throughput calculation process is as shown in Figure 2 For a base station, the SINR is calculated according to a level of a primary service cell and a level of a neighbor cell and a load, and the rate (i.e., the throughput) is further determined through a data transmission RE, a downlink RANK, and a spectral efficiency mapping table. The spectral efficiency mapping table is a key step of the implementation method, and the spectral efficiency mapping table is closely related to product capability of a transceiver side in a wireless network link. There are three forms of the spectral efficiency table as follows:

[0093] 1) SINR\CQI->spectral efficiency: different SINR\CQI corresponds to different spectral efficiency;

[0094] 2) SINR\CQI+RANK->spectral efficiency: different SINR\CQI+RANK corresponds to different spectral efficiency, i.e., if the RANK is different, a demodulation performance table looked up for the same SINR\CQI can be different;

[0095] Wherein, RANK is used to indicate the number of spatial multiplexing streams, that is, the number of streams simultaneously transmitted in space on the same time-frequency resource. Generally, under the condition that the time-frequency resource is unchanged, the higher the RANK is, the higher the actual throughput rate is. In addition, RANK is the number of streams scheduled by the base station, and the rank indicator (RI) is the result measured by the terminal. For the base station, the RANK scheduled by the base station can first filter the RI reported by the terminal, and then calculate the final scheduled RANK according to the algorithm.

[0096] 3) SINR / CQI-> modulation and coding scheme (MCS), and then the existing MCS is used to look up the spectrum efficiency table: that is, different SINR / CQI corresponds to different MCS, and the relationship between different SINR / CQI and spectrum efficiency is obtained through the relationship between MCS and spectrum efficiency.

[0097] For the three spectrum efficiency tables, the output can be obtained according to the product theory simulation platform (that is, the aforementioned mode one), or can be obtained based on the relationship between the throughput rate and SINR in a measured data.

[0098] However, the acquisition of the spectrum efficiency mapping table in mode two is the core, but the scheme has the following problems:

[0099] 1) The spectrum efficiency mapping table (SINR or CQI->MCS, SINR or CQI->spectrum efficiency, SINR or CQI+RANK->spectrum efficiency) is a performance of the product, which is non-public data and is not easy to obtain;

[0100] 2) The performance of different products is different, and only one kind of product cannot represent the performance difference between products, and the scene adaptability is low;

[0101] 3) Most of the existing spectrum efficiency mapping tables are obtained based on theoretical simulation under certain channel conditions, and the accuracy is greatly deviated compared with the actual channel and performance.

[0102] In summary, mode one is complex in modeling and cannot be directly applied in the network planning optimization stage; in mode two, there are problems such as difficulty in obtaining the spectrum efficiency table, low accuracy, and low scene adaptability. The current throughput rate determination scheme cannot solve the related technical problems.

[0103] In order to solve the above problems, the embodiments of the present application provide a plurality of schemes through different embodiments of the present application, which can be respectively implemented from different angles of solving problems, which will be described in detail below.

[0104] Figure 3 An example of a data processing method provided by the embodiments of the present application is shown in the figure, and the data processing method includes the following steps.

[0105] S101, determining first information between a transmitter and a receiver in a communication system;

[0106] In the embodiment, the data processing apparatus determines the first information between the transmitter and the receiver in the communication system in step S101, wherein the first information comprises at least characteristic information of data transmission between the transmitter and the receiver.

[0107] It should be noted that the data processing apparatus mentioned in the embodiments of the present application can be a server, for example, can be a network management server arranged in a network device (such as a base station), or can be a network management server externally connected to a network device (such as a base station), or can be a component (such as a processor, a chip or a chip system, etc.) of a network device (such as a base station), which is not limited here. In addition, as shown in the system described above, the transmitter mentioned in the embodiments of the present application can be a network device or a terminal device, and the receiver mentioned in the embodiments of the present application can be a network device or a terminal device. The data processing apparatus can be any transmitter or any receiver, which is not limited here. Figure 1

[0108] In a possible implementation, the characteristic information of the data transmission can be used to indicate the data transmission characteristics between the transmitter and the receiver, that is, the characteristic information of the data transmission is associated with the throughput of the communication system. The characteristic information of the data transmission can include at least one of the following:

[0109] 1. SINR, which can be used to indicate the reference signal quality of the pilot channel at the location of the receiver in the communication system.

[0110] The characteristic can be output by an existing network simulation platform, or can be obtained from a measurement report reported by an actual receiver, or can be determined by other means, which is not limited here.

[0111] 2. Distance information, which can be used to indicate the distance between the transmitter and the receiver.

[0112] The characteristic can be calculated by the transmitter or by the receiver, which is not limited here.

[0113] For example, the horizontal line distance between the receiver and the transmitter can be calculated as the distance characteristic of the receiving point, and the distance information can be determined in the following way:

[0114]

[0115] wherein, ​For distance information, X Grid Y Grid For receiver coordinate information; X Cell Y Cell This refers to the transmitter's coordinates. Obviously, this distance information can also be determined by calculating other distance parameters between the receiver and transmitter, such as the distance between a straight line; however, this is not a limitation here.

[0116] 3. Relative direction angle information: This feature can be used to indicate the relative direction angle between the transmitter and the receiver.

[0117] Similarly, this feature can be calculated by either the transmitter or the receiver; no specific limitation is made here.

[0118] For example, the angle between the receiver and transmitter can be calculated as the relative azimuth angle feature of the receiving point based on the direction of the line connecting them and the direction of the transmitter's transmitting antenna. Specifically, it can be calculated as follows:

[0119] Azimuth Grid =degree(atan2(Y) Grid -Y Cell ,X Grid -X Cell ));

[0120] Azimuth Delta =Mod(Azimuth) Grid -Azimuth Cell +720,360);

[0121]

[0122] Among them, Azimuth Grid Azimuth defines the connection direction between the receiver and transmitter. Delta For the transmitter's transmitting antenna defense line, This refers to relative orientation angle information; X Grid Y Grid X represents the coordinates of the receiving point. Cell Y Cell π represents the transmitter coordinates; atan2 is the arctangent function; degree is the conversion from radians to degrees, i.e., degree = radian * 180 / pi; Azimuth Cell denoted as the transmitter's direction angle; Mod represents the modulo operation. Clearly, other implementations can be obtained through simple formula transformations, which are not limited here.

[0123] Specifically, such as Figure 4-1As shown, the non-bold dot is the location of the receiving point, the bold black dot is the location of the transmitter, and the illustrated rectangular frame is used to simulate the environment object where the transmitter and receiver are located. Taking the north direction as the reference (N = 0°), the arc solid line indicates the azimuth_cell, which is the direction angle of the transmitting antenna, and the arc dotted line indicates the azimuth_Grid, which is the direction angle of the line connecting the transceiver; the angle is the included angle between the two.

[0124] 4. Relative downtilt angle information, which can be used to indicate the relative downtilt angle between the transmitter and the receiver.

[0125] Similarly, this feature can be calculated by the transmitter or by the receiver, which is not limited here.

[0126] Exemplarily, the elevation angle can be calculated according to the line connecting the receiver and the transmitter, and the downtilt angle of the transmitting antenna in the transmitter is obtained, and the included angle between the two is calculated as the relative downtilt angle feature of the receiving point. Specifically, it can be calculated in the following way:

[0127]

[0128]

[0129] wherein DownTilt Grid is the elevation angle calculated according to the line connecting the receiver and the transmitter, is the downtilt angle of the transmitting antenna in the transmitter, Height Grid is the height of the receiving point, Height Cell is the height of the transmitter, DownTilt Mechanical , DownTilt Electrical are the mechanical downtilt angle and the electronic downtilt angle of the transmitter, respectively. Obviously, other implementation forms can be obtained by simple formula transformation of the above-mentioned way, which is not limited here.

[0130] As shown in Figure 4-2 , the non-bold dot is the location of the receiving point, and the bold black dot is the location of the transmitter. Taking the horizontal direction as the reference, the illustrated angle "1" indicates the downtilt_cell, which is the downtilt angle of the transmitting antenna, and the illustrated angle "2" indicates the downtilt_grid, which is the elevation angle of the line connecting the transceiver; the illustrated angle "3" indicates the angle between the two.

[0131] In addition, the characteristic information of the data transmission can further include one or more of the following: a relative height characteristic between the receiver and the transmitter, a characteristic of whether the location of the receiver is indoors or outdoors, frequency band information, antenna type information, rank RANK, or block error rate (BLER). The implementation process of the values of the above characteristics can refer to the implementation process described above, which will not be described here. In the following, several implementation processes will be described by way of example. For example, the frequency band information. Since frequency is a key factor affecting signal propagation, the network performance characteristics are quite different under different frequency bands. However, since the number of frequency bands used by wireless networks is small, the frequency can not be used as an input of the model, and the model can be constructed according to different frequency bands, i.e., the frequency band information. For another example, the antenna type information. For different types of antennas, especially different types of massive multiple input multiple output (Massive MIMO) antennas, there are large differences. Therefore, similar to the frequency band characteristics, the antenna type information can be used as an implementation of the characteristic information of the data transmission.

[0132] wherein RANK is used to indicate the number of spatial multiplexing streams, i.e., the number of streams simultaneously transmitted in space for the same time-frequency resource. Generally, under the condition that the time-frequency resource is unchanged, the higher the RANK, the higher the actual throughput. In addition, RANK is the number of streams scheduled by the base station, and the rank indicator (RI) is the result measured by the terminal. For the base station, the base station can first filter the RI reported by the terminal, and then calculate the final scheduled RANK according to the algorithm.

[0133] In a possible implementation, the first information determined by the data processing apparatus in step S101 further includes characteristic information of a geographical environment between the transmitter and the receiver, wherein the characteristic information of the geographical environment is associated with the throughput of the communication system. Therefore, the characteristic information of the geographical environment between the transmitter and the receiver is used as part of the input of the prediction model, and the subsequent prediction model uses the characteristic information of the data transmission and the characteristic information of the geographical environment as the basis for prediction, which can make the accuracy of the throughput determined by the second information output by the prediction model higher.

[0134] Specifically, the data processing apparatus can obtain the characteristic information of the geographical environment in a self-measuring manner, or can obtain the characteristic information of the geographical environment by receiving data sent by other devices (such as the transmitter or the receiver), which is not limited here. The characteristic information of the geographical environment included in the first information can include at least one of building height information, ground object height information, or altitude information, i.e., the characteristics of the geographical environment between the transmitter and the receiver can be embodied by at least one of the above.

[0135] The process of obtaining geographical environment feature information by the data processing device itself is described here. Before step S101, the method further includes: the data processing device acquiring target map information between the transmitter and the receiver in the communication system, the target map information including at least one of digital map information and satellite map information; processing the target map information to obtain feature information of the geographical environment between the transmitter and the receiver. Since digital maps and satellite maps can determine the geographical environment between the transmitter and the receiver, the feature information of the geographical environment can be determined by at least one of digital map information and satellite map information.

[0136] Taking the process achieved through data map information as an example, the data processing equipment can determine the characteristic information of the geographical environment between the transmitter and the receiver by acquiring the digital map information. Specifically, the characteristic information of the geographical environment between the transmitter and the receiver can indicate the characteristic information of the geographical environment within the range (rectangular, circular, or other regular or irregular shapes) between the transmitter and the receiver communicating with the transmitter, or it can indicate the characteristic information of the geographical environment within the range (rectangular, circular, or other regular or irregular shapes) between the receiver and the transmitter communicating with the receiver.

[0137] For example, with Figure 5 For example, the planned simulation area for the receiver and transmitter can first be divided into grids. The grid size uses the resolution of the digital map for that area. Each grid can be a square with dimensions of 5 meters (1 meter, 10 meters, or other values). Then, the grid containing the transmitter (or receiver) is used as the center... Figure 5 Define a square region (filled with a raster frame) that is an integer multiple of the resolution. Figure 5 The dashed box (in the middle) serves as the statistical range for geographic environmental feature information. That is, this square area can represent the communication range between the transmitter and the receiver communicating with it, or it can indicate the communication range between the receiver and the transmitter communicating with it. At this time, in Figure 5 In this context, the building height of each grid cell stored in the digital map within the statistical range can be used as building height information; the land feature type height of each grid cell stored in the digital map within the statistical range can be used as land feature height information; and the altitude of each grid cell stored in the digital map within the statistical range can be used as altitude information.

[0138] S102. The first information is used as the input to the prediction model, and the second information is output after being processed by the prediction model.

[0139] In this embodiment, the data processing device takes the first information obtained in step S101 as input of the prediction model, and obtains and outputs second information after processing by the prediction model, where the second information is used to determine the throughput rate of the communication system.

[0140] In a possible implementation, the second information can be specifically the spectral efficiency of data transmission between the transmitter and the receiver, and the throughput rate of the communication system can be determined through the spectral efficiency. For example, the throughput rate calculation formula is as follows (taking the following row throughput rate as an example), the second information (i.e., the spectral efficiency) is one of the inputs, and is a key input, and other parameters are fixed or inputs with little change in the channel:

[0141] Throughput rate = number of transmission bandwidth RE * effective data transmission ratio * (1-BLER) * spectral efficiency * RANK

[0142] Wherein, the calculation formula of the number of transmission bandwidth RE is: 12*14*number of scheduling times per second*number of RBs per time slot. Obviously, other implementation forms can be obtained by simple formula transformation of the above-mentioned manner, which is not limited here.

[0143] In addition, in the implementation process of the scheme, the second information output in step S102 can also be the throughput rate of the communication system, that is, the throughput rate of the communication system can be output without further calculation process.

[0144] In a possible implementation, in step S102, the data processing device can pre-store the prediction model, or receive model data sent by other devices to obtain the prediction model, or obtain the prediction model through training of a neural network, which is not limited here.

[0145] The process of obtaining the prediction model by training the neural network by the data processing device will be described below, and the training process of the neural network involved in the present application will be exemplarily described as follows.

[0146] Referring to Figure 6 The embodiment of the present application provides a system architecture 100. The data acquisition device 160 is used to acquire input data and store in the database 130, and the training device 120 generates the target model / rule 101 based on the input data maintained in the database 130. How the training device 120 obtains the target model / rule 101 based on the input data will be described in detail below.

[0147] The work of each layer in the deep neural network can be expressed by a mathematical expression To describe: the work of each layer in a deep neural network can be understood as a transformation from an input space (a set of input vectors) to an output space (a set of output vectors) through five kinds of operations on the input space, which include: 1, dimensionality increase / decrease; 2, magnification / reduction; 3, rotation; 4, translation; 5, "bending". Among them, the operations of 1, 2, and 3 are completed by , the operation of 4 is completed by +b, and the operation of 5 is realized by a(). The reason for using the word "space" here is that the objects being classified are not single things, but a class of things, and the space refers to the set of all individuals of this class. Among them, W is a weight vector, and each value in this vector represents the weight value of a neuron in the neural network of this layer. This vector W determines the spatial transformation from the input space to the output space described above, that is, the weight W of each layer controls how to transform the space. The purpose of training a deep neural network is to ultimately obtain the weight matrix of all layers of the trained neural network (the weight matrix formed by the vectors W of many layers). Therefore, the training process of a neural network is essentially learning the way to control the spatial transformation, more specifically, learning the weight matrix.

[0148] Because the output of the deep neural network is expected to be as close as possible to the value that is truly intended to be predicted, the weight vector of each layer of the neural network can be updated according to the difference between the predicted value of the current network and the target value that is truly intended to be predicted. (Of course, before the first update, there is usually an initialization process, that is, the parameters of each layer in the deep neural network are pre-configured). For example, if the predicted value of the network is too high, adjust the weight vector to make it predict lower, and keep adjusting until the neural network can predict the target value that is truly intended to be predicted. Therefore, it is necessary to define "how to compare the difference between the predicted value and the target value", which is the loss function or the objective function, which is an important equation for measuring the difference between the predicted value and the target value. Among them, taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference, and then the training of the deep neural network becomes a process of trying to minimize this loss.

[0149] The target model / rule obtained by the training device 120 can be applied in different systems or devices. In Figure 6 , the execution device 110 is configured with an I / O interface 112 to interact with external devices, and a "user" can input data to the I / O interface 112 through the client device 140.

[0150] The execution device 110 can invoke data, code, etc. in the data storage system 150, or store data, instructions, etc. in the data storage system 150. Among them, the signal detection apparatus in the embodiment of the application can include the execution device 110 to realize the processing process of the neural network, or be connected to the execution device 110 to realize the processing process of the neural network, which is not limited here.

[0151] The computing module 111 processes the input data using the target model / rule 101, for example, in step S102, the computing module 111 is used to process the input first information at least once to obtain second information.

[0152] Finally, the I / O interface 112 returns the processing result to the client device 140 and provides it to the user.

[0153] Optionally, the processing process of the execution device 110 can be further optimized through the association function module 113 and the association function module 114.

[0154] More deeply, the training device 120 can generate corresponding target models / rules 101 based on different data for different targets to provide better results for users.

[0155] It is worth noting that, Figure 6 The system architecture provided by the embodiment of the application is only a schematic diagram, and the positional relationship between the devices, devices, modules, etc. shown in the diagram does not constitute any limitation, for example, in Figure 6 In the embodiment, the data storage system 150 is an external memory relative to the execution device 110, and in other cases, the data storage system 150 can also be placed in the execution device 110.

[0156] In a possible implementation, before step S102, the first information is input into the prediction model, and the second information is output after the prediction model processing, the method further includes: the data processing device obtains sample data, the sample data includes input data and label data, the input data includes feature information simulating data transmission, and the label data is used to determine the throughput rate corresponding to the input data; then, the data processing device inputs the sample data into the preset neural network to train the prediction model. That is, before the prediction model is used to output the second information according to the first information, the prediction model can be obtained through the training process of the neural network, that is, the sample data is input into the preset neural network, and the prediction model is obtained through training.

[0157] Specifically, in the training process of the neural network, the feature information of the simulation data transmission input to the preset neural network can specifically include at least one of reference signal receiving power (RSRP), distance information, relative direction angle information, relative down tilt angle information, frequency band information, antenna type information, rank (RANK), or block error rate (BLER). Since the at least one parameter is associated with the throughput of the communication system, the training data of the neural network can be enriched based on the at least one parameter subsequently, and the accuracy of the prediction model in the subsequent prediction process can be improved.

[0158] In addition, in the training process of the neural network, the input data input to the preset neural network can also include feature information of a simulated geographic environment, since the feature information of the simulated geographic environment is associated with the throughput of the communication system. Therefore, the training data of the neural network can be enriched based on the feature information of the simulated geographic environment subsequently, and the accuracy of the prediction model in the subsequent prediction process can be improved. The feature information of the simulated geographic environment input to the preset neural network can specifically include at least one of building height information, ground object height information, or altitude information. As shown in FIG. 6, the feature information of the geographic environment can be rasterized and stored, and extracted according to the same range size, so that all original information can be directly overlapped and stored to form multi-channel image information, each channel corresponding to a type of original information. The converted data meets the data format of image processing. In addition, when using satellite image information, a satellite photo can be used as input, without image processing, and the values of the three layers of the image RGB are directly used as three channels for input. Figure 5

[0159] In a possible implementation, the label data includes the spectral efficiency corresponding to the input data. That is, in the training process of the neural network, the label data input to the preset neural network can specifically include the spectral efficiency corresponding to the input data, that is, the label data used to determine the throughput corresponding to the input data can include the spectral efficiency of the data transmission, and the throughput of the communication system can be determined subsequently by using the spectral efficiency. The process of determining the throughput by using the spectral efficiency is similar to the process of step S101, which will not be described herein again. Similarly to the implementation of the second information in step S101, the label data can also be the throughput corresponding to the input data.

[0160] As described above, using the feature information of the geographic environment and the feature information of the data transmission as input enables the deep neural network to "learn" the deep "knowledge" that is not considered or not fully considered in the traditional way of determining the throughput. Meanwhile, the model training speed can be accelerated by combining artificial experience features.

[0161] The model training process of the neural network will be described below by using an example of a specific implementation. As shown in FIG. 7, the model training process of the neural network can include the following steps. Figure 7 ​As shown, based on the foregoing input information, a spectrum efficiency prediction model is constructed, and after the feature information of the geographic environment (input1) is converted into a multi-channel image format, a convolutional neural network is used to extract features (feature extraction) from the feature information of the geographic environment. The output of the feature extraction is used as the input of a full connected neural network together with part of the feature information of the data transmission (input2), where the full connected neural network can be a regression network model. The output result includes another part of the feature information of the data transmission, i.e., the spectrum efficiency (output2) and the process indicator RANK (output1). The purpose of outputting the RANK indicator is that the RANK indicator can be collected in network testing and used together with the SE in the training data for training of the model.

[0162] The process of converting the feature information of the geographic environment (input1) into a multi-channel image format can be implemented as shown in the following process, and specifically includes the following steps. Figure 8-1

[0163] Step 1. Extract the shallow features (i.e., the feature information of the geographic environment) from the 3D electronic map and the work parameter information, and rasterize and image the features and the measured data. The original data obtained in this way is in a vector format, which needs to be converted into image-like input and output.

[0164] As an optional step, in step 1, the measured data can be filtered and cleaned to improve the reliability of the measured data.

[0165] Optionally, in the implementation process of step 1, the following steps can be included:

[0166] 1. Obtain the coordinates of the transmitter (or receiver), and use a certain distance (10 m or 20 m) as the length and width of a grid. Finally, obtain a rasterized image with the base station as the center and the size of 50*50 m or 100*100 m. The grid is analogous to a pixel point of an image.

[0167] 2. Rasterize the RSRP and each feature data, i.e., for each feature, we can obtain a graph, which is analogous to the red, green and blue color channels of an image. Each feature can be regarded as a channel of the graph. Finally, we can obtain a 9-channel graph, i.e., 9 feature inputs; and the output is a channel graph of the RSRP.

[0168] ​3, from the 3D electronic map building height, ground object type, elevation, distance and other features (directly from the map file), and the information characteristics such as the horizontal azimuth angle, the vertical azimuth angle, the station height, the frequency and the transmission power, as input X; from the manual report, extract rscp / rsrp as output Y, form a labeled data (X, Y) according to the base station / cell; according to the accuracy requirement, grid and image processing are performed on X and Y.

[0169] Step2: according to the data amount and the data feature dimension, establish a deep learning propagation model suitable for the planning area, realize the mapping prediction from graph to graph.

[0170] Step3: train the model with data, determine the weight coefficient of the deep learning propagation model, can predict the mapping from graph to graph between the transmitter and the receiver according to the model, obtain the grid propagation loss value, so as to realize the conversion of the feature information of the geographical environment into a multi-channel image format.

[0171] As shown in Figure 7 After the definition of the features and the model is completed, the next step is to collect the test data in the actual network for the training of the model parameters. The collected network test data contains various different scenes (such as different cities, different regions, etc.), which is the sample data mentioned in the foregoing, so that the model has better generalization ability.

[0172] Among them, for the input feature information of the geographical environment, data processing (standardization processing, normalization processing or other processing methods) is needed before inputting into the neural network. Here, taking the mean-standard deviation standardization processing method as an example, the feature value is transformed to a distribution with a mean of 0 and a standard deviation of 1, and the processing process includes the following methods:

[0173]

[0174]

[0175]

[0176] Among them, is the standardization processing result, n is the sample number for model training, j represents the sample position in n samples, i represents the feature position in the jth sample, is the original feature i of the jth sample. is the mean and standard deviation of the feature i, respectively.

[0177] Figure 7 ​As shown in the training process, the input data is input into the fully connected neural network together with the features extracted from the image by the convolutional neural network. This avoids the problem of forcibly converting a single value into a single-color layer to match the input data format when the image is input at the initial stage, which reduces the model training and prediction efficiency and destroys the spatial relationship between grids. In addition, the label data used for model training is increased to include other output results output1 in addition to the throughput rate output2. The multi-class labels of the test data are used for training at the same time, so that the expression ability and generalization ability of the trained model are better.

[0178] Further, in combination with the implementation process of Figure 3 to Figure 8-1 , the data processing method can be further comprehensively described, please refer to Figure 8-2 , which is another implementation schematic diagram of the data processing method in the embodiment of the present application.

[0179] In the process of training the prediction model, the implementation process shown in Figure 6 , Figure 7 , Figure 8-1 may be referred to. The parameters input into the preset neural network can include at least one of the following: feature information of the imaged geographical environment, RSRP, distance information, relative direction angle information or relative downtilt angle information, spectral efficiency, RANK, BLER, etc. After the training process of the preset neural network, the prediction model is obtained.

[0180] In the process of using the prediction model, the implementation process shown in Figure 3 to Figure 5 may be referred to. After the feature statistics of the first information and optionally the feature standardization, the spectral efficiency is predicted through the processing of the prediction model. Further, the throughput rate can be predicted according to the result of the spectral efficiency prediction, so as to determine the value of the throughput rate.

[0181] Through the above implementation process, the throughput rate prediction model considers a variety of important influencing factors, so that the accuracy of the model in predicting the throughput rate is higher. Through the method of learning by neural network model, complex theoretical modeling and calculation are avoided. The calculation speed of the model in predicting the throughput rate is faster. In multiple scenarios, the prediction accuracy (the proportion of samples with throughput rate error within 30%) of the embodiment of the present application is improved by 32% (43%->76%) compared with the implementation effect of the traditional mode two through SINR\CQI+RANK->spectral efficiency, and is improved by 12% (64%->76%) compared with the implementation effect of the traditional mode two through SINR\CQI->spectral efficiency.

[0182] In this embodiment, the data processing apparatus first determines first information between a transmitter and a receiver in a communication system, the first information including characteristic information of data transmission between the transmitter and the receiver; then, the data processing apparatus takes the first information as input of a prediction model, and outputs second information after processing by the prediction model, the second information being used to determine the throughput rate of the communication system. The first information input to the prediction model includes characteristic information of data transmission between the transmitter and the receiver in the communication system, the characteristic information of data transmission being used to indicate the data transmission characteristics between the transmitter and the receiver, i.e., the characteristic information of data transmission is associated with the throughput rate of the communication system, and then the prediction model outputs the second information used to determine the throughput rate of the communication system according to the first information. Thus, the method of learning by the neural network model improves the calculation speed of determining the throughput rate of the communication system, avoids the process of complex theoretical modeling and calculation of determining the spectrum efficiency mapping table, and optimizes the determination process of the throughput rate in the communication system.

[0183] The above describes the embodiments of the application from the perspective of methods, and the following introduces a signal detection device in the embodiments of the application from the perspective of specific device implementation.

[0184] Please refer to Figure 9 The embodiment of the application provides a data processing apparatus 900, which comprises:

[0185] A determination unit 901 is configured to determine first information between a transmitter and a receiver in a communication system, the first information including characteristic information of data transmission between the transmitter and the receiver.

[0186] A first processing unit 902 is configured to take the first information as input of a prediction model, and output second information after processing by the prediction model, the second information being used to determine the throughput rate of the communication system.

[0187] In a possible implementation manner, the characteristic information of data transmission includes at least one of the following:

[0188] Reference signal received power (RSRP), distance information, relative direction angle information, or relative down tilt angle information.

[0189] In a possible implementation manner, the characteristic information of data transmission further includes at least one of the following:

[0190] Frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

[0191] In a possible implementation manner, the first information further includes characteristic information of a geographical environment between the transmitter and the receiver.

[0192] In a possible implementation, the feature information of the geographic environment includes at least one of the following:

[0193] building height information, ground object height information, or altitude information.

[0194] In a possible implementation, the apparatus further includes a first obtaining unit 903 and a second processing unit 904.

[0195] The first obtaining unit 903 is configured to obtain target map information between the transmitter and the receiver in the communication system, the target map information including at least one of digital map information and satellite map information.

[0196] The second processing unit 904 is further configured to process the target map information to obtain feature information of a geographic environment between the transmitter and the receiver.

[0197] In a possible implementation, the second information includes a spectral efficiency of data transmission between the transmitter and the receiver.

[0198] In a possible implementation, the apparatus further includes a second obtaining unit 905 and a training unit 906.

[0199] The second obtaining unit 905 is configured to obtain sample data, the sample data including input data and label data, the input data including feature information of simulated data transmission, and the label data being used to determine a throughput rate corresponding to the input data.

[0200] The training unit 906 is configured to input the sample data to a preset neural network to train the prediction model.

[0201] In a possible implementation, the feature information of the simulated data transmission includes at least one of the following:

[0202] reference signal received power (RSRP), distance information, relative direction angle information, relative down tilt angle information, frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

[0203] In a possible implementation, the input data further includes feature information of a simulated geographic environment.

[0204] In a possible implementation, the feature information of the simulated geographic environment includes at least one of the following:

[0205] building height information, ground object height information, or altitude information.

[0206] In a possible implementation, the label data includes a spectral efficiency corresponding to the input data.

[0207] It should be noted that the information execution process and the like of the units of the data processing apparatus 900 described above can be specifically understood from the descriptions in the method embodiments described above, and will not be described here.

[0208] Please refer to Figure 10 The above-mentioned structural schematic diagram of the communication apparatus involved in the embodiments of the present application can be specifically the communication apparatus in the foregoing embodiments, and the structure of the communication apparatus can refer to the structure shown in Figure 10 .

[0209] The communication apparatus includes at least one processor 1011, at least one memory 1012, at least one transceiver 1013, at least one network interface 1014, and one or more antennas 1015. The processor 1011, the memory 1012, the transceiver 1013, and the network interface 1014 are connected, for example, through a bus, and in the embodiments of the present application, the connection can include various interfaces, transmission lines, or buses, etc., which are not limited in the embodiments. The antenna 1015 is connected to the transceiver 1013. The network interface 1014 is configured to enable the communication apparatus to be connected to other communication devices through a communication link, for example, the network interface 1014 can include a network interface between the communication apparatus and a core network device, for example, an S1 interface, and the network interface can include a network interface between the communication apparatus and other network devices (for example, other access network devices or core network devices), for example, an X2 or Xn interface.

[0210] The processor 1011 is mainly configured to process communication protocols and communication data, and control the entire communication apparatus, execute software programs, process data of the software programs, for example, to support the communication apparatus to perform the actions described in the embodiments. The communication apparatus can include a baseband processor and a central processor, the baseband processor is mainly configured to process communication protocols and communication data, and the central processor is mainly configured to control the entire network device, execute software programs, and process data of the software programs. Figure 10 The processor 1011 in the foregoing embodiments can integrate the functions of the baseband processor and the central processor, and those skilled in the art can understand that the baseband processor and the central processor can also be independent processors interconnected through a bus. Those skilled in the art can understand that the network device can include multiple baseband processors to adapt to different network standards, and the network device can include multiple central processors to enhance its processing capability, and various components of the network device can be connected through various buses. The baseband processor can also be referred to as a baseband processing circuit or a baseband processing chip. The central processor can also be referred to as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data can be built-in in the processor, or stored in the memory in the form of a software program, and the processor executes the software program to realize the baseband processing function.

[0211] The memory is mainly used for storing software programs and data. The memory 1012 can exist independently and be connected to the processor 1011. Alternatively, the memory 1012 can be integrated with the processor 1011, for example, integrated in a chip. The memory 1012 can store program codes for implementing the technical solutions of the embodiments of the present application and be controlled to execute by the processor 1011. Various computer programs executed can also be regarded as a driver of the processor 1011.

[0212] Figure 10 Only one memory and one processor are shown. In actual network devices, multiple processors and multiple memories can exist. The memory can also be referred to as a storage medium or a storage device. The memory can be a storage element on the same chip as the processor, that is, an on-chip storage element, or an independent storage element, and the embodiments of the present application do not limit this.

[0213] The transceiver 1013 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1013 can be connected to the antenna 1015. The transceiver 1013 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1015 can receive radio frequency signals, the receiver Rx of the transceiver 1013 is used to receive the radio frequency signals from the antenna and convert the radio frequency signals into digital baseband signals or digital intermediate frequency signals, and provide the digital baseband signals or digital intermediate frequency signals to the processor 1011, so that the processor 1011 further processes the digital baseband signals or digital intermediate frequency signals, such as demodulation processing and decoding processing. In addition, the transmitter Tx in the transceiver 1013 is also used to receive the modulated digital baseband signals or digital intermediate frequency signals from the processor 1011, and convert the modulated digital baseband signals or digital intermediate frequency signals into radio frequency signals, and transmit the radio frequency signals through one or more antennas 1015. Specifically, the receiver Rx can selectively perform one or more levels of down-mixing and analog-to-digital conversion to obtain digital baseband signals or digital intermediate frequency signals, and the order of the down-mixing and analog-to-digital conversion can be adjusted. The transmitter Tx can selectively perform one or more levels of up-mixing and digital-to-analog conversion on the modulated digital baseband signals or digital intermediate frequency signals to obtain radio frequency signals, and the order of the up-mixing and digital-to-analog conversion can be adjusted. The digital baseband signals and the digital intermediate frequency signals can be collectively referred to as digital signals.

[0214] The transceiver can also be referred to as a transceiving unit, a transceiver, a transceiving device, etc. Optionally, a device in the transceiving unit for implementing a receiving function can be regarded as a receiving unit, and a device in the transceiving unit for implementing a sending function can be regarded as a sending unit, that is, the transceiving unit includes the receiving unit and the sending unit, the receiving unit can also be referred to as a receiver, an input port, a receiving circuit, etc., and the sending unit can be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0215] It should be noted that, Figure 10 The communication device shown can be specifically used to implement Figure 3 to Figure 8-2 The steps implemented by the data processing device in the corresponding method embodiment will not be described here.

[0216] The embodiment of the present application also provides a computer readable storage medium storing one or more computer execution instructions, when the computer execution instructions are executed by a processor, the processor executes the method described in the possible implementation manner of the communication device as in the foregoing embodiment, wherein the communication device can be specifically the communication device in the foregoing embodiment.

[0217] The embodiment of the present application also provides a computer program product (or computer program) of one or more computers, when the computer program product is executed by the processor, the processor executes the method of the possible implementation manner of the communication device, wherein the communication device can be specifically the communication device in the foregoing embodiment.

[0218] The embodiment of the present application also provides a chip system, which includes a processor for supporting the communication device to implement the functions involved in the possible implementation manner of the communication device. In a possible design, the chip system can also include a memory, the memory is used to save the necessary program instructions and data of the communication device. The chip system can be composed of a chip, or can include a chip and other discrete devices, wherein the communication device can be specifically the signal detection device in the foregoing embodiment.

[0219] The embodiment of the present application also provides a network system architecture, which includes the communication device, and the communication device can be specifically the data processing device in the foregoing embodiment, or the data processing device in any one of the embodiments.

[0220] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. The division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0221] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0222] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0223] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or the part that makes contributions, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

Claims

1. A data processing method, characterized by, The method comprises: determining first information between a transmitter and a receiver in a communication system, the first information comprising characteristic information of data transmission between the transmitter and the receiver, and the first information further comprising characteristic information of a geographical environment between the transmitter and the receiver; inputting the first information into a prediction model, and outputting second information after processing by the prediction model, the second information being used to determine a throughput rate of the communication system.

2. The method of claim 1, wherein, The characteristic information of the data transmission comprises at least one of: reference signal received power (RSRP), distance information, relative direction angle information, or relative down tilt angle information.

3. The method of claim 2, wherein, The characteristic information of the data transmission further comprises at least one of: frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

4. The method according to any one of claims 1 to 3, characterized in that, The characteristic information of the geographical environment comprises at least one of: building height information, ground object height information, or altitude information.

5. The method of claim 4, wherein, The method further comprises: obtaining target map information between the transmitter and the receiver in the communication system, the target map information comprising at least one of digital map information and satellite map information; processing the target map information to obtain the characteristic information of the geographical environment between the transmitter and the receiver.

6. The method according to any one of claims 1 to 3, characterized in that, The second information comprises spectral efficiency of data transmission between the transmitter and the receiver.

7. The method according to any one of claims 1 to 3, characterized in that, Before the first information is inputted into the prediction model and the second information is outputted after processing by the prediction model, the method further comprises: obtaining sample data, the sample data comprising input data and label data, the input data comprising characteristic information of simulated data transmission, and the label data being used to determine a throughput rate corresponding to the input data; inputting the sample data into a preset neural network to train the prediction model.

8. The method of claim 7, wherein, The characteristic information of the simulated data transmission comprises at least one of: reference signal received power (RSRP), distance information, relative direction angle information, relative down tilt angle information, frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

9. The method of claim 7, wherein, The input data further comprises characteristic information of a simulated geographical environment.

10. The method of claim 9, wherein, The characteristic information of the simulated geographical environment comprises at least one of: building height information, ground object height information, or altitude information.

11. The method of claim 7, wherein, The label data comprises spectral efficiency corresponding to the input data.

12. A data processing apparatus, characterized by The method comprises: a determination unit configured to determine first information between a transmitter and a receiver in a communication system, the first information comprising characteristic information of data transmission between the transmitter and the receiver, and the first information further comprising characteristic information of a geographical environment between the transmitter and the receiver; a first processing unit configured to input the first information into a prediction model, and output second information after processing by the prediction model, the second information being used to determine a throughput rate of the communication system.

13. The apparatus of claim 12, wherein, The characteristic information of the data transmission comprises at least one of: reference signal received power (RSRP), distance information, relative direction angle information, or relative down tilt angle information.

14. The apparatus of claim 13, wherein, The characteristic information of the data transmission further comprises at least one of: frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

15. The apparatus of any one of claims 12 to 14, wherein, The feature information of the geographic environment includes at least one of the following: building height information, ground feature height information, or altitude information.

16. The apparatus of claim 15, wherein, The device further includes a first acquisition unit and a second processing unit: The first acquisition unit is configured to acquire target map information between the transmitter and the receiver in the communication system, the target map information including at least one of digital map information and satellite map information; The second processing unit is further configured to process the target map information to obtain feature information of a geographic environment between the transmitter and the receiver.

17. The apparatus of any one of claims 12 to 14, wherein, The second information includes a spectral efficiency of data transmission between the transmitter and the receiver.

18. The apparatus of any one of claims 12 to 14, wherein, The device further includes a second acquisition unit and a training unit: The second acquisition unit is configured to acquire sample data, the sample data including input data and label data, the input data including feature information of simulated data transmission, and the label data being used to determine a throughput rate corresponding to the input data; The training unit is configured to input the sample data into a preset neural network to train the prediction model.

19. The apparatus of claim 18, wherein, The feature information of the simulated data transmission includes at least one of the following: reference signal received power (RSRP), distance information, relative direction angle information, relative down-tilt angle information, frequency band information, antenna type information, rank (RANK), or block error rate (BLER).

20. The apparatus of claim 18, wherein, The input data further includes feature information of a simulated geographic environment.

21. The apparatus of claim 20, wherein, The feature information of the simulated geographic environment includes at least one of the following: building height information, ground feature height information, or altitude information.

22. The apparatus of claim 18, wherein, The label data includes a spectral efficiency corresponding to the input data.

23. A data processing apparatus, characterized by: It includes: a processor coupled with a memory, the memory being used to store computer programs or instructions, and the processor being used to execute the computer programs or instructions in the memory, so that the communication device executes the method in any one of claims 1 to 11.

24. A chip, characterized by The chip includes a processor and a communication interface; wherein the communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to realize the method in any one of claims 1 to 11.

25. A computer-readable storage medium, the storage medium being used to store computer programs or instructions, the computer programs or instructions being executed to make a computer execute the method in any one of claims 1 to 11.

26. A computer program product comprising a computer program or instructions, characterized in that, The computer program product, when running on a computer, makes the computer execute the method in any one of claims 1 to 11.

Images