Information processing device and information processing method

Abstract

An information processing device (100) according to the present application is a RAN intelligent controller (RIC) and an information processing device that estimates various types of information on the basis of a RAN and a prescribed calculation resource such as AI. Specifically, the information processing device (100) comprises an estimation unit (134), a calculation unit (135), and a transmission unit (136). The estimation unit (134) estimates a movement speed of a second mobile device on the basis of a relationship between a movement speed of a first mobile device, which moves on an expressway or an arterial road, and a time period in which the first mobile device moves on the expressway or the arterial road. The calculation unit (135) calculates a second weight of a beam to be transmitted to the second mobile device on the basis of the movement speed of the second mobile device and a first weight based on a prescribed signal received from the second mobile device. The transmission unit (136) transmits a signal to the second mobile device by using a beam formed on the basis of the second weight calculated by the calculation unit (135).

Description

Information Processing Apparatus and Information Processing Method

[0001] The present invention relates to an information processing apparatus and an information processing method.

[0002] Conventionally, there has been known a technique in which a base station allocates a common downlink reference signal to a plurality of beams and transmits the common downlink reference signal in the plurality of beams based on a Doppler shift estimated using an uplink reference signal (see Patent Document 1 below).

[0003] Japanese Unexamined Patent Publication No. 2020-182155

[0004] An information processing apparatus according to the present application comprises: an estimation unit that estimates a moving speed of a second mobile device based on a relationship between a moving speed of a first mobile device moving on an expressway or a main road and a time zone in which the first mobile device moves on the expressway or the main road; a calculation unit that calculates a second weight for a beam to be transmitted to the second mobile device based on the moving speed of the second mobile device and a first weight based on a predetermined signal received from the second mobile device; and a transmission unit that transmits a signal to the second mobile device using a beam formed based on the second weight calculated by the calculation unit.

[0005] FIG. 1 is a diagram illustrating an example of an information processing system according to an embodiment. FIG. 2 is a diagram illustrating an example of a conventional beamforming method. FIG. 3 is a diagram illustrating an example of a beamforming method using Range Doppler space. FIG. 4 is a diagram illustrating an example of transmission processing executed by the information processing apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of a beamforming method according to the embodiment. FIG. 6 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 7 is a diagram illustrating an example of a learning data storage unit according to the embodiment. FIG. 8 is a diagram illustrating an example of a beam information storage unit according to the embodiment. FIG. 9 is a flowchart illustrating an example of a generation processing flow executed by the information processing apparatus according to the embodiment. FIG. 10 is a flowchart illustrating an example of a transmission processing flow executed by the information processing apparatus according to the embodiment. FIG. 11 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus.

[0006] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing apparatus and information processing method according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing apparatus and information processing method according to the present application. Furthermore, each embodiment can be appropriately combined as long as the processing content is not inconsistent. Also, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0007] [1. Introduction] [1-1. Information Processing System] First, the information processing system 1 targeted in this embodiment will be described using Figure 1. Figure 1 is a diagram showing an example of the information processing system 1 according to this embodiment. As shown in Figure 1, the information processing system 1 includes an automobile (an example of a mobile device) 10, a base station 20, and an information processing device 100. The automobile 10, the base station 20, and the information processing device 100 are connected wirelessly via a network N such as the Internet. Note that the information processing system 1 shown in Figure 1 may include multiple automobiles 10, multiple base stations 20, and multiple information processing devices 100.

[0008] Automobile 10 is a connected vehicle that communicates with various other devices via wireless communication. Automobile 10 also has in-vehicle equipment. For example, the in-vehicle equipment includes a communication module, which communicates with the base station 20 and the information processing device 100. Examples of in-vehicle equipment include a car navigation system and a drive recorder. In the example shown in Figure 1, automobile 10 communicates with various other devices via network N. Also, in the example shown in Figure 1, automobile 10 is traveling on highway RO1.

[0009] Base station 20 is an information processing device that operates a predetermined cell based on a wireless communication method such as LTE (Long Term Evolution), LTE-Advanced, NR (New Radio), or 6G. In this case, base station 20 provides wireless communication to automobiles 10 located within the predetermined cell.

[0010] The information processing device 100 can be implemented, for example, by a server device such as MEC (Multi-access Edge Computing) or a cloud system. Furthermore, the information processing device 100 is a RIC (RAN (Radio Access Network) Intelligent Controller). A RIC is an information processing device that performs estimation of various types of information based on a RAN and predetermined computing resources such as AI (Artificial Intelligence). The information processing device 100 may also be an information processing device located within the core network.

[0011] For example, the information processing device 100 estimates the speed of a second vehicle 10 (an example of a second mobile device), which is different from the first vehicle 10, based on the relationship between the speed of the first vehicle 10 (an example of a first mobile device) moving on the highway RO1 and the time period during which the first vehicle 10 is moving on the highway RO1. Subsequently, the information processing device 100 calculates a second weight of the beam to be transmitted to the second vehicle 10 based on the speed of the second vehicle 10 and a first weight based on a predetermined signal received from the second vehicle 10. Then, the information processing device 100 transmits a signal to the second vehicle 10 using the beam formed based on the calculated second weight.

[0012] [1-2. Challenges] Next, we will explain the challenges. In conventional beamforming technology, the base station 20 receives uplink signals with multiple antennas and calculates the beam weight by calculating the direction of arrival of the uplink signals from the time difference of reception. For example, there is a known technology in which the base station assigns a unique downlink reference signal to multiple beams based on the direction of arrival of each uplink signal estimated using uplink reference signals transmitted from multiple mobile devices, and transmits a unique downlink data signal for each beam.

[0013] Here, using Figure 2, the procedure for communication processing performed by the automobile 10 and the base station 20 will be explained. Figure 2 is a diagram showing an example of a conventional beamforming method. As shown in Figure 2, the base station 20 receives an SRS (Sounding Reference Signal) from the automobile 10 (step S1). Subsequently, the base station 20 calculates a weight for each antenna (step S2). For example, the base station 20 calculates a weight for all antennas.

[0014] Then, the base station 20 transmits a signal to the automobile 10 using a beam formed based on the weight of each antenna (step S3). Here, the signal transmitted by the base station 20 can be any signal.

[0015] The weight calculation method described above had a problem: for example, the computational load for the beam increased as the number of antennas increased. For instance, if base station 20 is a Massive MIMO (Multiple-Input Multiple-Output) base station, the large number of antennas can sometimes consume a large amount of computational resources and require a long computation time to calculate the weights.

[0016] Furthermore, there was a problem in that the accuracy of tracking the beam with the rapidly moving vehicle 10 decreased. To explain using the example in Figure 2, when the vehicle 10 is moving at high speed, the vehicle 10 moves between steps S1 and S3. As a result, the base station 20 may not be able to track the beam with the vehicle 10 because the vehicle 10 moves while it is calculating the weight for each antenna. Thus, calculating the weights can consume a large amount of computational resources and requires a long computation time, making it difficult to track the beam with the movement of the vehicle 10.

[0017] Another example is a calculation method using Range Doppler space. In this technique, the received signal is converted to Range Doppler space by calculating iSFFT (Inverse Symplectic Fast Fourier Transform), and information about the propagation space is estimated from the information of the Doppler frequency and delay. This makes it possible to form a beam that takes into account the Doppler frequency and delay. Therefore, it is possible to track the beam with respect to the vehicle 10 even when the vehicle 10 is moving at high speed.

[0018] Here, using Figure 3, the procedure for communication processing performed by the automobile 10 and the base station 20 will be explained. Figure 3 is a diagram showing an example of a beamforming method using Range Doppler space. As shown in Figure 3, the base station 20 receives an uplink signal from the automobile 10 (step S11). Next, the base station 20 performs calculations using iSFFT for each antenna (step S12). For example, the base station 20 calculates the Doppler component and the delay component to estimate spatial channel information. Then, the base station 20 transmits a signal to the automobile 10 using the beam formed based on the iSFFT calculation results (step S13).

[0019] Thus, while techniques using Range Doppler space estimate spatial channel information based on information about Doppler frequency and delay, it was necessary to modify the RU (Radio Unit) circuitry because it was required to extract Range Doppler information. For this reason, it was sometimes difficult to easily introduce such techniques into existing automobiles 10.

[0020] The above-mentioned problems are merely examples, and the problems that this application seeks to solve are not necessarily limited to those mentioned above; other problems may also be addressed.

[0021] [1-3. Solution] In this application, the above problem is solved by estimating the speed of the vehicle 10 and using the estimated speed in the beam calculation. As a result, this application can reduce the amount of beam calculation required. For example, this application estimates the speed of the vehicle 10 using a learning model that has been trained on past traffic volume etc. using machine learning, etc. Then, this application calculates weights based on the speed of the vehicle 10. As a result, this application makes it possible to track the beam with high accuracy while suppressing the amount of beam calculation required. Furthermore, since the processing performed in this application is performed on the baseband side, modification of the RU is unnecessary. For this reason, it is easy to introduce to existing vehicles 10, etc.

[0022] [2. An Example of Transmission Processing Executed by the Information Processing Device] Next, an example of transmission processing executed by the information processing device 100 will be described using Figure 4. Figure 4 is a diagram showing an example of transmission processing executed by the information processing device 100 according to the embodiment.

[0023] Let's explain the premise here. The vehicle 10 in Figure 4 is assumed to be moving on highway RO1. For example, highway RO1 is an environment where line of sight is usually easy to maintain. Therefore, changes in the propagation channel, where direct waves due to the movement of vehicle 10 are dominant, are more influential than spatial channel information including reflections. Also, on highway RO1, the range and direction of movement of vehicle 10 are almost constant, making it easy to predict the direction of movement of vehicle 10. For these reasons, we will focus on vehicle 10 moving on highway RO1.

[0024] First, as shown in Figure 4, the information processing device 100 estimates the speed of the automobile 10 using a learning model (step S21). For example, the information processing device 100 estimates the speed of the automobile 10 using a pre-generated learning model.

[0025] For example, the learning model may be one that outputs the speed of car 10 based on the relationship between the speed of another car 10 (different from the car 10 whose speed was estimated) and the time of day when the other car 10 travels along highway RO1, by inputting the time of day when car 10 travels along highway RO1. In this case, the information processing device 100 estimates the speed of car 10 by inputting the time of day when car 10 travels along highway RO1 into the learning model.

[0026] Next, the information processing device 100 receives the SRS from the automobile 10 (step S22). For example, if the base station 20 receives the SRS from the automobile 10, it transmits the SRS to the information processing device 100. The information processing device 100 then receives the SRS from the base station 20. In this way, the information processing device 100 receives the SRS via the base station 20.

[0027] Then, the information processing device 100 calculates the weights for several antennas as an example of the first weights (step S23). For example, the information processing device 100 calculates the first weights for a predetermined number of antennas out of the total number of antennas, based on the SRS received from the automobile 10. For example, a predetermined number of antennas out of the total number of antennas are designated as an antenna group. In this case, the information processing device 100 calculates the first weight for each antenna belonging to the antenna group. To give a more specific example, suppose the total number of antennas is 128. In this case, the information processing device 100 calculates the first weight for each of the 16 antennas. Note that the predetermined number can be any number as long as it is less than the total number of antennas.

[0028] Next, the information processing device 100 calculates a weight based on the speed of movement as an example of a second weight (step S24). For example, the information processing device 100 calculates a second weight based on the speed of movement of the automobile 10 and a first weight based on the SRS received from the automobile 10.

[0029] Here, a specific example of a beamforming method will be explained using Figure 5. Figure 5 is a diagram showing an example of a beamforming method according to the embodiment. Figure 5 shows a conceptual diagram of beamforming using a phased array antenna. In the example in Figure 5, a transmitter TX1, a number of antenna elements AE1, and a phase shifter PS1 that controls the phase Φ of each antenna are shown. Figure 5 shows an example with eight antenna elements. Also, Figure 5 shows an example with eight phase shifters. Note that the phase shifter PS1 may be implemented in software by calculations in the information processing device 100.

[0030] For example, when forming a beam based on a first weight, the information processing device 100 forms beam BF1. The orientation of beam BF1 is angle θ1. On the other hand, suppose the car 10 is moving away from the antenna. In this case, the time for outputting the beam from the leftmost antenna element among the antenna elements shown in Figure 5 is made earlier, and the time for outputting the beam from the antenna elements on the right is made later. As a result, the information processing device 100 can form beam BF2 with an orientation of angle θ2. In such a case, the information processing device 100 calculates a second weight based on the speed of the car 10 and the first weight. Then, the information processing device 100 forms beam BF2 based on the second weight. The orientation of beam BF2 is angle θ2.

[0031] In this way, by using weights based on the speed of movement, the beam direction changes from beam BF1, which has an angle θ1, to beam BF2, which has an angle θ2. That is, the information processing device 100 calculates a second weight that forms a beam having a different direction (for example, angle θ2) than the beam direction (for example, angle θ1) formed based on the first weight. As a result, the information processing device 100 can form a beam that can follow the automobile 10 even when the automobile 10 moves away from the antenna.

[0032] Then, as shown in Figure 4, the information processing device 100 transmits a signal to the automobile 10 using a beam formed based on a weight derived from the moving speed (step S25). For example, the information processing device 100 transmits the signal to the automobile 10 via the base station 20.

[0033] In this way, the information processing device 100 can reduce the computational load related to weight calculation. As a result, the information processing device 100 can reduce the beam calculation processing, making it possible to miniaturize the device. Furthermore, the information processing device 100 can improve the accuracy of beam tracking relative to the vehicle 10, even when the vehicle 10 is moving at high speed, such as on highway RO1. This enables the information processing device 100 to maintain a high communication speed.

[0034] Furthermore, the information processing device 100 can integrate AI and RAN processing by using a technology that performs AI and machine learning processing, which are not directly related to RAN, and RAN processing on the same computing infrastructure. As a result, the information processing device 100 can improve the efficiency of infrastructure utilization.

[0035] [3. Configuration of the Information Processing Device] Next, the configuration of the information processing device 100 according to the embodiment will be described using Figure 6. Figure 6 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 6, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0036] (Regarding the communication unit 110) The communication unit 110 is implemented by, for example, a NIC (Network Interface Card). The communication unit 110 transmits and receives information with various devices via the network N.

[0037] (Regarding the memory unit 120) The memory unit 120 is implemented by semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. For example, the memory unit 120 has a learning data storage unit 121, a learning model 122, and a beam information storage unit 123.

[0038] (Regarding the learning data storage unit 121) The learning data storage unit 121 stores various information about the learning data used to generate the learning model 122. Here, Figure 7 shows an example of the learning data storage unit 121 according to the embodiment. Figure 7 is a diagram showing an example of the learning data storage unit 121 according to the embodiment.

[0039] In the example shown in Figure 7, the learning data storage unit 121 has items such as "Learning Data Set ID (Identifier)", "Mobile Device ID", "Time", and "Movement Speed".

[0040] "Mobile Device ID" is an identifier that identifies the mobile device. "Time" is information about the time the mobile device associated with the "Mobile Device ID" traveled on the highway. "Travel Speed" is information about the travel speed of the mobile device associated with the "Mobile Device ID".

[0041] For example, in Figure 7, "M1," identified by the mobile device ID, has a time of "DA1" and a travel speed of "MV1." Note that in the example shown in Figure 7, time and other parameters are represented by abstract codes, but time and other parameters may also be represented by specific numerical values ​​or strings, or by a specific file format containing time and other parameters.

[0042] (Regarding the beam information storage unit 123) The beam information storage unit 123 stores various information related to beam information. Here, Figure 8 shows an example of the beam information storage unit 123 according to the embodiment. Figure 8 is a diagram showing an example of the beam information storage unit 123 according to the embodiment.

[0043] In the example shown in Figure 8, the beam information storage unit 123 has items such as "beam information ID," "mobile device ID," "movement speed," and "weight."

[0044] "Beam information ID" is an identifier that identifies beam information. "Mobile device ID" is an identifier that identifies a mobile device that is a target to which a beam associated with the "beam information ID" is to be transmitted. "Movement speed" is information related to the movement speed of the mobile device associated with the "mobile device ID". "Weight" is information related to the weight corresponding to the beam associated with the "beam information ID". For example, the weight includes a plurality of weights. For example, the weight includes a weight corresponding to each antenna. Note that the weight shown in FIG. 8 corresponds to a second weight.

[0045] For example, in FIG. 8, "B1" identified by the beam information ID has a mobile device ID of "M11", a movement speed of "MV11", and a weight of "W1". In the example shown in FIG. 8, the movement speed and the like are represented by abstract codes, but the movement speed and the like may be specific numerical values or character strings indicating the movement speed and the like, or a specific file format including the movement speed and the like.

[0046] (Regarding Control Unit 130) The control unit 130 is a controller, and is realized, for example, by executing various programs stored in a storage device inside the information processing apparatus 100 with a RAM as a work area by a CPU, an MPU (Micro Processing Unit), or the like. The control unit 130 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0047] As shown in FIG. 6, the control unit 130 includes an acquisition unit 131, a generation unit 132, a reception unit 133, an estimation unit 134, a calculation unit 135, and a transmission unit 136, and realizes or executes the functions and operations of information processing described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 6, and any other configuration may be used as long as it can perform the information processing described later. Further, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship shown in FIG. 6, and other connection relationships may be adopted.

[0048] (Regarding Acquisition Unit 131) Acquisition unit 131 acquires various types of information. Specifically, acquisition unit 131 acquires the moving speed of a first automobile 10 moving on an expressway RO1 and the time zone in which the first automobile 10 moves on the expressway RO1 in association with each other. For example, it is assumed that there is an external server that provides statistical data of the moving speed of the first automobile 10 moving on the expressway RO1 and the time zone in which the first automobile 10 moves on the expressway RO1. In this case, acquisition unit 131 acquires the moving speed and the time zone of the first automobile 10 from said external server. Then, acquisition unit 131 stores the moving speed and the time zone of the first automobile 10 in a learning data storage unit 121.

[0049] As another example, it is assumed that cameras for acquiring traffic information and cracking down on violating vehicles are installed on the expressway RO1. In this case, acquisition unit 131 acquires a moving image including the first automobile 10 from the camera. Subsequently, acquisition unit 131 acquires the moving speed of the first automobile 10 and the corresponding time zone by analyzing the moving image based on conventional technology such as image analysis technology. Then, acquisition unit 131 stores the moving speed and the time zone of the first automobile 10 in the learning data storage unit 121.

[0050] (Regarding Generation Unit 132) Generation unit 132 generates a learning model 122 that outputs the moving speed of a second automobile 10 by inputting the time zone in which the second automobile 10 moves on the expressway RO1, based on the relationship between the moving speed of the first automobile 10 stored in the learning data storage unit 121 and the time zone. Then, generation unit 132 stores the generated learning model 122 in a storage unit 120.

[0051] For example, the generation unit 132 performs learning processing using methods such as backpropagation. For example, the generation unit 132 adjusts the weight values ​​that are considered when values ​​are transmitted between nodes through the learning process. In this way, the generation unit 132 learns the learning model 122 by processing such as backpropagation to correct the parameters so that the error between the output of the learning model and the correct answer corresponding to the input is reduced. For example, the generation unit 132 generates the learning model 122 by processing such as backpropagation to minimize a predetermined loss function. In this way, the generation unit 132 performs learning processing to learn the parameters of the learning model 122.

[0052] The learning model 122 can be any learning model as long as it outputs the speed of the automobile 10. In this case, any input information can be input to the learning model as long as it outputs the speed of the automobile 10.

[0053] (Regarding the receiving unit 133) The receiving unit 133 receives various signals. Specifically, the receiving unit 133 receives SRS via the base station 20.

[0054] (Regarding the estimation unit 134) The estimation unit 134 estimates the speed of the second vehicle 10 based on the relationship between the speed of the first vehicle 10 traveling on highway RO1 and the time period during which the first vehicle 10 travels on highway RO1. For example, the estimation unit 134 estimates the speed of the vehicle 10 by inputting the time period during which the vehicle 10 travels on highway RO1 into the learning model 122.

[0055] (Regarding the calculation unit 135) The calculation unit 135 calculates a second weight of the beam to be transmitted to the second vehicle 10 based on the moving speed of the second vehicle 10 and a first weight based on the SRS received from the second vehicle 10. In this case, the calculation unit 135 calculates the second weight as the weight for each antenna to form the beam to be transmitted to the second vehicle 10. The calculation unit 135 then stores this second weight in the beam information storage unit 123.

[0056] For example, the calculation unit 135 calculates first weights for a predetermined number of antennas out of the total number of antennas, based on the SRS received from the automobile 10. For example, a predetermined number of antennas out of the total number of antennas are designated as antenna groups. In this case, the calculation unit 135 calculates the first weight for each antenna belonging to the antenna group. To give a more specific example, suppose the total number of antennas is 128. In this case, the calculation unit 135 calculates the first weight for each of the 16 antennas. Next, the calculation unit 135 calculates second weights based on the moving speed of the automobile 10 estimated by the estimation unit 134 and the calculated first weights. Then, the calculation unit 135 stores the calculated second weights in the beam information storage unit 123.

[0057] (Regarding the transmitting unit 136) The transmitting unit 136 transmits various signals. Specifically, the transmitting unit 136 transmits signals to the second automobile 10 using a beam formed based on a second weight calculated by the calculation unit 135. In this case, the transmitting unit 136 transmits signals to the second automobile 10 via the base station 20.

[0058] [4. Processing Procedure (1)] Next, the procedure for the generation process executed by the information processing device 100 according to the embodiment will be explained using Figure 9. Figure 9 is a flowchart showing an example of the flow of the generation process executed by the information processing device 100 according to the embodiment.

[0059] As shown in Figure 9, the acquisition unit 131 acquires training data (step S101). Subsequently, the generation unit 132 generates a learning model 122 based on the training data acquired by the acquisition unit 131.

[0060] [5. Processing Procedure (2)] Next, the procedure for the transmission process performed by the information processing device 100 according to the embodiment will be described using Figure 10. Figure 10 is a flowchart showing an example of the flow of the transmission process performed by the information processing device 100 according to the embodiment.

[0061] As shown in Figure 10, the receiving unit 133 receives the SRS (step S201). For example, if the receiving unit 133 has not received the SRS (step S201; No), it waits until it receives the SRS.

[0062] Meanwhile, if the receiving unit 133 receives an SRS signal (step S201; Yes), the calculation unit 135 calculates the weights for several antennas (step S202). Subsequently, the calculation unit 135 calculates the weights based on the moving speed (step S203).

[0063] Then, the transmitting unit 136 transmits a signal using a beam formed with a weight based on the moving speed calculated by the calculation unit 135 (step S204).

[0064] [6. Modifications] The information processing device 100 described above may be implemented in various other forms besides those described above. Therefore, other embodiments of the information processing device 100 will be described below.

[0065] [6-1. Expressways] In the above embodiment, expressways were used as an example of the road on which the automobile 10 travels, but the vehicle is not limited to expressways. For example, the road in question may be a main road, or any other type of road where visibility during driving is easily ensured.

[0066] [6-2. Mobile Devices] Although automobiles have been used as an example of mobile devices in this explanation, other mobile devices may be used instead of automobiles. Other mobile devices here include, for example, motorcycles, automobiles provided through car-sharing services, and autonomous vehicles. Other mobile devices may also include automobiles, etc., that have become connected vehicles by being equipped with aftermarket communication devices, information processing devices, etc.

[0067] [6-3. In-vehicle devices] Although we have used in-vehicle devices as an example, this can also be applied to other terminal devices. Specifically, terminal devices may be devices used by users to access content such as web pages displayed in a browser or content for applications. For example, terminal devices may be desktop PCs (Personal Computers), notebook PCs, tablet devices, mobile phones, PDAs (Personal Digital Assistants), wearable devices, etc.

[0068] [6-4. Application Examples] The processing performed by the receiving unit 133, estimation unit 134, calculation unit 135, and transmitting unit 136 may also be performed by an ETC (Electronic Toll Collection System) installed on expressways, etc. For example, the processing performed by the receiving unit 133, estimation unit 134, calculation unit 135, and transmitting unit 136 may be performed using the antenna of the ETC. This makes it possible for the ETC to improve the speed of passing through ETC gates by controlling the beam. In addition, it is possible for the ETC to alleviate congestion near toll booths on expressways, etc.

[0069] [6-5. Learning Model] The learning model 122 may also be a learning model that has been trained to output the moving speed of other vehicles 10 by inputting location information of other vehicles 10, based on the relationship between the location information of vehicle 10 and its moving speed. Here, the location information may be obtained from vehicle 10, or from an external server that provides the location information of vehicle 10. The moving speed may also be obtained from vehicle 10. The moving speed may also be calculated based on the location information of vehicle 10 and the time when the location information was obtained.

[0070] Furthermore, the memory unit 120 may store other learning models besides the learning model 122. For example, the other learning model may be a learning model that outputs weights for each antenna. For example, a predetermined number of antennas out of the total number of antennas may be designated as antenna groups. In this case, the other learning model may be a learning model that has been trained to output weights for each antenna by taking the weights for each antenna belonging to the antenna group as input, based on the relationship between the weights for each antenna belonging to the antenna group and the weights for each individual antenna.

[0071] [7. Hardware Configuration] The automobile 10, base station 20, and information processing device 100 according to the above-described embodiment are realized by a computer 1000 having a configuration as shown in Figure 11. The following explanation will use the information processing device 100 as an example. Figure 11 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, RAM 1200, ROM (Read Only Memory) 1300, HDD (Hard Disk Drive) 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0072] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, and controls various parts. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0073] The HDD 1400 stores programs executed by the CPU 1100, as well as data used by such programs. The communication interface 1500 receives data from other devices via the network N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 via the network N to other devices.

[0074] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the data it has generated to output devices via the input / output interface 1600.

[0075] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0076] For example, when the computer 1000 functions as an information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded on the RAM 1200. The HDD 1400 stores the data in the storage unit 120. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a network N.

[0077] [8. Others] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0078] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0079] Furthermore, the base station 20 may have the components of the information processing device 100. In this case, the base station 20 may perform various information processing operations that the information processing device 100 performs. For example, the receiving unit 133 receives the SRS from the automobile 10. The transmitting unit 136 transmits a signal to the second automobile 10 using a beam formed based on a first weight calculated by the calculation unit 135.

[0080] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0081] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuits." For example, a calculation unit can be replaced with a calculation means or a calculation circuit.

[0082] [9. Effects] As described above, the information processing device 100 according to the embodiment includes an estimation unit 134, a calculation unit 135, and a transmission unit 136. The estimation unit 134 estimates the speed of the second mobile device based on the relationship between the speed of the first mobile device moving on the expressway or main road and the time period during which the first mobile device is moving on the expressway or main road. The calculation unit 135 calculates a second weight of the beam to be transmitted to the second mobile device based on the speed of the second mobile device and a first weight based on a predetermined signal received from the second mobile device. The transmission unit 136 transmits a signal to the second mobile device using a beam formed based on the second weight calculated by the calculation unit 135.

[0083] Thus, the information processing device 100 according to this embodiment can reduce the computational complexity related to the calculation of the second weight. For example, the information processing device 100 learns the traffic conditions near where the base station 20 is installed and estimates the speed of the second mobile device in advance from information such as the time. As a result, the information processing device 100 can reduce the computational complexity required to calculate the second weight of the beam from the reception of the SRS and predict the destination of the second mobile device. As a result, the information processing device 100 can accurately perform beam formation and thus improve signal quality and / or communication quality.

[0084] Furthermore, in the information processing device 100 according to the embodiment, the estimation unit 134 estimates the movement speed of the second mobile device using a learning model 122 that has been trained to output the movement speed of the second mobile device by inputting the time period during which the second mobile device is moving on an expressway or main road, based on the relationship between the movement speed of the first mobile device and the time period.

[0085] As a result, the information processing device 100 according to the embodiment can suitably estimate the moving speed of the second mobile device.

[0086] Furthermore, in the information processing device 100 according to the embodiment, the calculation unit 135 calculates a second weight as the weight for each antenna for forming a beam to be transmitted to the second mobile device.

[0087] As a result, the information processing device 100 according to this embodiment can reduce the amount of computation required for calculating the second weight.

[0088] Furthermore, in the information processing device 100 according to the embodiment, the calculation unit 135 calculates a second weight based on a first weight corresponding to a predetermined number of antennas among all antennas for forming a beam to be transmitted to the second mobile device, and the moving speed of the second mobile device.

[0089] As a result, the information processing device 100 according to this embodiment can reduce the amount of computation required for calculating the second weight.

[0090] Furthermore, in the information processing device 100 according to the embodiment, the calculation unit 135 calculates a second weight that forms a beam having a different orientation from the beam formed based on the first weight.

[0091] As a result, the information processing device 100 according to this embodiment can reduce the amount of computation required for calculating the second weight.

[0092] Furthermore, the information processing device 100 according to the embodiment further includes a generation unit 132 that generates a learning model 122 that outputs the movement speed of the second mobile device by inputting the time period during which the second mobile device is traveling on a highway or main road, based on the relationship between the movement speed of the first mobile device and the time period. The estimation unit 134 estimates the movement speed of the second mobile device by inputting the time period during which the second mobile device is traveling on a highway or main road to the learning model 122 using the learning model 122.

[0093] As a result, the information processing device 100 according to the embodiment can suitably estimate the moving speed of the second mobile device.

[0094] Furthermore, in the information processing device 100 according to the embodiment, the estimation unit 134 estimates the speed of a second vehicle 10, which is different from the first vehicle 10, as a second mobile device, based on the relationship between the speed of the first vehicle 10 as a first mobile device and the time of day when the first vehicle 10 is traveling on an expressway or main road.

[0095] As a result, the information processing device 100 according to the embodiment can suitably estimate the moving speed of the second automobile 10.

[0096] Furthermore, in the information processing device 100 according to the embodiment, the calculation unit 135 calculates a second weight of the beam to be transmitted to the second mobile device based on a first weight based on SRS and the moving speed of the second mobile device as predetermined signals.

[0097] As a result, the information processing device 100 according to this embodiment can reduce the amount of computation required for calculating the second weight.

[0098] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0099] This invention aims to improve communication quality and operational efficiency by utilizing AI, thereby becoming an innovative technological foundation in the telecommunications business and contributing to the achievement of Sustainable Development Goal (SDG) 9, "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0100] N Network 1 Information Processing System 10 Automobile 20 Base Station 100 Information Processing Device 110 Communication Unit 120 Storage Unit 121 Learning Data Storage Unit 122 Learning Model 123 Beam Information Storage Unit 130 Control Unit 131 Acquisition Unit 132 Generation Unit 133 Receiving Unit 134 Estimation Unit 135 Calculation Unit 136 Transmission Unit

Claims

1. An information processing device comprising: an estimation unit that estimates the speed of a second mobile device based on the relationship between the speed of a first mobile device moving on an expressway or main road and the time period during which the first mobile device is moving on the expressway or main road; a calculation unit that calculates a second weight of a beam to be transmitted to the second mobile device based on the speed of the second mobile device and a first weight based on a predetermined signal received from the second mobile device; and a transmission unit that transmits a signal to the second mobile device using a beam formed based on the second weight calculated by the calculation unit.

2. The information processing apparatus according to claim 1, wherein the estimation unit estimates the moving speed of the second mobile device by inputting the time period during which the second mobile device moves on the expressway or the main road, based on the relationship between the moving speed of the first mobile device and the time period, using a learning model that has been trained to output the moving speed of the second mobile device.

3. The information processing apparatus according to claim 1, wherein the calculation unit calculates the second weight as the weight for each antenna for forming a beam to be transmitted to the second mobile device.

4. The information processing apparatus according to claim 1, wherein the calculation unit calculates the second weight based on the first weight corresponding to a predetermined number of antennas among all antennas for forming a beam to be transmitted to the second mobile device, and the moving speed of the second mobile device.

5. The information processing apparatus according to claim 4, wherein the calculation unit calculates a second weight that forms a beam having a different orientation from the orientation of the beam formed based on the first weight.

6. The information processing apparatus according to claim 1, further comprising a generation unit that generates a learning model for outputting the movement speed of the second mobile device by inputting the time period during which the second mobile device moves on the expressway or the main road, based on the relationship between the movement speed of the first mobile device and the time period, wherein the estimation unit estimates the movement speed of the second mobile device by inputting the time period during which the second mobile device moves on the expressway or the main road to the learning model using the learning model.

7. The information processing apparatus according to claim 1, wherein the estimation unit estimates the speed of a second vehicle, which is different from the first vehicle, as the second vehicle, based on the relationship between the speed of the first vehicle as the first vehicle and the time period during which the first vehicle is traveling on the expressway or the main road.

8. The information processing apparatus according to claim 1, wherein the calculation unit calculates a second weight of the beam to be transmitted to the second mobile device based on the first weight based on the Sounding Reference Signal (SRS) as the predetermined signal and the moving speed of the second mobile device.

9. An information processing method performed by an information processing device, comprising: an estimation step of estimating the speed of a second mobile device based on the relationship between the speed of a first mobile device moving on an expressway or main road and the time period during which the first mobile device is moving on the expressway or main road; a calculation step of calculating a second weight of a beam to be transmitted to the second mobile device based on the speed of the second mobile device and a first weight based on a predetermined signal received from the second mobile device; and a transmission step of transmitting a signal to the second mobile device using a beam formed based on the second weight calculated in the calculation step.

Images