Information processing device, information processing method, and recording medium

Abstract

The information processing device has an acquisition unit that acquires first terminal data regarding a first terminal and first base station data regarding a first base station that is a communication partner of the first terminal, handover performance data based on each terminal data regarding each of a plurality of terminals and each base station data regarding each base station that is a communication partner of each of the plurality of terminals, a modification unit that changes the handover conditions of the first terminal using the first terminal data and the first base station data acquired by the acquisition unit, and a notification unit that notifies the first terminal of the handover conditions of the first terminal changed by the modification unit.

Description

Technology Field

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. Background Technology

[0002] Handover is known as an operation of switching the base station that is the communication partner of a terminal. Regarding handover, techniques are known for determining whether communication is taking place in an environment where unnecessary handovers occur frequently, and for allowing connection to another wireless communication service based on learned behavioral patterns of terminal users. Prior art literature

[0003] Japanese Patent Publication No. 2006-186797, Japanese Patent Publication No. 2014-217023 The problem to be solved

[0004] However, in conventional technology, handover conditions, such as radio wave conditions for handover, are statically set within the base station. Consequently, in conventional technology, a "ping-pong" phenomenon occurs between base stations within the communication range of a terminal, causing the user to frequently perform handovers; this can lead to communication quality degradation due to unnecessary signaling. Furthermore, users are highly likely to perceive communication quality degradation, such as interruptions in communication or voice, due to the ping-pong phenomenon.

[0005] The present invention is made in consideration of the above and aims to suppress the deterioration of communication quality caused by handover. means of solving the problem

[0006] An information processing device according to one embodiment of the present invention comprises: an acquisition unit for acquiring first terminal data regarding a first terminal and first base station data regarding a first base station that is a communication partner of the first terminal; actual handover data based on each terminal data regarding each of a plurality of terminals and each base station data regarding a communication partner of each of the plurality of terminals; a modification unit for changing the handover conditions of the first terminal using the first terminal data and the first base station data acquired by the acquisition unit; and a notification unit for notifying the first terminal of the handover conditions of the first terminal changed by the modification unit. Effects of the invention

[0007] According to one embodiment of the present invention, the deterioration of communication quality caused by handover can be suppressed. Brief explanation of the drawing

[0008] FIG. 1 is a diagram illustrating an information processing system according to embodiment 1. FIG. 2 is a diagram illustrating the change of the handover conditions of the first terminal. FIG. 3 is a block diagram showing the configuration of an information processing device according to embodiment 1. FIG. 4 is a diagram illustrating the learning process according to embodiment 1. FIG. 5 is a flowchart showing the flow of information processing according to Embodiment 1. FIG. 6 is a diagram illustrating the learning process according to embodiment 2. FIG. 7 is a diagram illustrating the learning process according to embodiment 3. Figure 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of an information processing device. Specific details for implementing the invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings, but the present invention is not limited to the following embodiments. Furthermore, in the drawings, the same reference numerals are assigned to identical parts, redundant descriptions are omitted, and descriptions of components having the same function and the same processing are also omitted.

[0010] [1. Embodiment 1]

[0011] [1-1. Introduction]

[0012] Using FIG. 1, an overview of an information processing system according to an embodiment is described. FIG. 1 is a diagram for explaining an information processing system according to embodiment 1. In FIG. 1, the information processing system is composed of an information processing device (100), a first terminal (200), and a first base station (300).

[0013] The information processing device (100) is a device that performs information processing between the first terminal (200) and the first base station (300), and is an RIC (RAN (Radio Access Network) Intelligent Controller) or a server, etc. An RIC is an information processing device that performs the estimation of various information based on a RAN and a predetermined computing resource such as AI (Artificial Intelligence).

[0014] The first terminal (200) is a terminal that communicates with an information processing device (100) and a first base station (300), and is a smartphone, etc. The first base station (300) is a communication partner of the first terminal (200) and is a Radio Unit (RU), etc. managed by a Distributed Unit (DU).

[0015] Conventionally, regarding handover, techniques for determining whether communication is taking place in an environment where unnecessary handovers occur frequently, and techniques for allowing connection to other wireless communication services based on learned behavioral patterns of terminal users are known.

[0016] However, in conventional technology, handover conditions are statically set within the base station. Consequently, in conventional technology, a ping-pong phenomenon occurs between base stations within the communication range of a terminal, which can lead to communication quality degradation due to unnecessary signaling. Furthermore, users are highly likely to perceive this deterioration in communication quality, such as interruptions in communication or voice, due to the ping-pong phenomenon.

[0017] The present invention is made in consideration of the above and aims to suppress the deterioration of communication quality caused by handover. Below, an example is described in which an information processing device (100) changes the handover conditions of the first terminal (200) using handover performance data, first terminal data, and first base station data.

[0018] Handover performance data is based on each terminal data regarding each of the multiple terminals and each base station data regarding each base station that is the communication partner of each of the multiple terminals, and is data regarding the performance of each of the multiple terminals performing a handover to their communication partner. Handover performance data is, for example, a database such as a trained model that outputs handover conditions based on the input of each terminal data and each base station data, or a table in which each terminal data and each base station data are linked.

[0019] The first terminal data is terminal data regarding the first terminal (200). The first terminal data is cell ID (Identification), GPS (Global Positioning System), or RSRP (Reference Signal Received Power), etc. The first base station data is base station data regarding the first base station (300). The first base station data is adjacent base station data regarding a base station that is a candidate communication partner of the first terminal (200), or UL (Uplink) SINR (Signal-to-Interference-plus-Noise Ratio), etc.

[0020] First, the information processing device (100) acquires first terminal data and first base station data. For example, the information processing device (100) acquires cell ID, GPS, or RSRP as first terminal data. In addition, the information processing device (100) acquires adjacent base station data or UL SINR as first base station data.

[0021] Next, the information processing device (100) changes the handover conditions of the first terminal (200) using the handover performance data, the first terminal data, and the first base station data. For example, the information processing device (100) changes these conditions by inputting the first terminal data and the first base station data into a model that has completed learning and outputs handover conditions according to the input of each terminal data and each base station data.

[0022] This point is explained in detail using the example of FIG. 2. FIG. 2 is a diagram for explaining the change of the handover condition of the first terminal. The information processing device (100) inputs the first terminal data and the first base station data into a model that has completed learning and outputs a threshold value of the difference in RSRP between each base station as a handover condition of the first terminal (200), and changes the threshold value of the difference in RSRP between the first base station (300) and the communication partner candidate of the first terminal (200) from “X” to “XX”.

[0023] Additionally, the information processing device (100) inputs the first terminal data and the first base station data into a model that has completed learning and outputs a threshold value of the difference between two parameters between each base station for the conditional handover condition of the first terminal (200) for which additional conditions are imposed on the handover condition of the first terminal (200), and changes the threshold value of the difference between two parameters between the first base station (300) and the communication partner candidate of the first terminal (200).

[0024] Specifically, the information processing device (100) inputs the first terminal data and the first base station data into the model that has completed this learning, and changes the threshold value of the difference in RSRP between the first base station (300) and the communication partner candidate from “Y” to “YY”. In addition, the information processing device (100) changes the threshold value of the difference in RTT (Round-Trip Time) between the first base station (300) and the communication partner candidate from “Z” to “ZZ”.

[0025] In FIG. 2, the information processing device (100) raises the threshold value to make the handover condition of the first terminal (200) strict. However, in a predetermined environment, such as when changing this condition using each terminal data and each base station data in the entire area where the radio waves of each base station reach, as in Embodiment 3 described later, the information processing device (100) may lower the threshold value to relax this condition.

[0026] Returning to the description of FIG. 1. The information processing device (100) notifies the first terminal (200) of the handover conditions of the changed first terminal (200) and the conditions of the conditional handover of the changed first terminal (200).

[0027] For example, the information processing device (100) indirectly notifies the first terminal (200) of the conditions, such as the handover conditions of the first terminal (200), by having the first base station (300) notify the first terminal (200) of the conditions. In this case, the first base station (300) notifies the first terminal (200), for example, together with the transmission of a Radio Resource Control (RRC) reconfiguration message or a System Information Block (SIB). After that, a known process as described in 3GPP (registered trademark) TS 38.300, etc., is performed.

[0028] In this way, the information processing device (100) dynamically changes the handover conditions of the first terminal (200) according to the first terminal data and the first base station data while referring to the handover performance data. Because of this, the information processing device (100) can suppress the deterioration of communication quality caused by handover. In addition, the information processing device (100) can reduce the occurrence of ping-pong phenomena or unnecessary signaling, thereby realizing the construction of a communication environment with excellent user experience.

[0029] [1-2. Configuration of Information Processing Devices]

[0030] The configuration of an information processing device (100) is explained using FIG. 3. FIG. 3 is a block diagram showing the configuration of an information processing device according to embodiment 1. In FIG. 3, the information processing device (100) has a communication unit (110), a memory unit (120), and a control unit (130).

[0031] (Communications Department)

[0032] The communication unit (110) is a processing unit that communicates with other devices and is a communication interface, etc. For example, the communication unit (110) receives first terminal data from the first terminal (200) and receives first base station data from the first base station (300). In addition, the communication unit (110) transmits the handover conditions of the changed first terminal (200), etc., to the first base station (300), etc.

[0033] (Memory Department)

[0034] The memory unit (120) is a processing unit that stores various data or programs executed by the control unit (130), and is a memory device or semiconductor memory. The memory unit (120) stores, for example, various data such as the above-described model, handover performance data, first terminal data, first base station data, handover conditions of the first terminal (200), OS (Operating System) executed by the information processing device (100), and various programs.

[0035] (Control unit)

[0036] The control unit (130) is a processing unit responsible for the entire information processing device (100) and is a processor, etc. This control unit (130) has a learning unit (131), an acquisition unit (132), a modification unit (133), and a notification unit (134). In addition, the learning unit (131), the acquisition unit (132), the modification unit (133), and the notification unit (134) can also be realized as electronic circuits of a processor or as processes executed by a processor.

[0037] (Learning Department)

[0038] The learning unit (131) takes a data set consisting of each terminal data and each base station data as an input variable and a handover condition as an output variable to train the model. Below, the learning process will be explained in detail using the example of FIG. 4. FIG. 4 is a diagram for explaining the learning process.

[0039] Each terminal data includes, for example, terminal data associated with each base station data and terminal data that can be referenced when changing handover conditions. As an example, each terminal data associated with each base station data includes TimeStamp, RAT (Radio Access Technology), TDD (Time Division Duplex), FDD (Frequency Division Duplex), PCI (Physical Cell Identification), TAC (Type Allocation Code), CI (Call Indicator), BAND, BANDWIDTH, ARFCN (Absolute Radio-Frequency Channel Number), etc.

[0040] For example, each terminal data that can be referenced when changing handover conditions includes RSRP, RSRQ (Reference Signal Received Quality), SNR (Signal Noise Rate), SINR, RSSI (Received Signal Strength Indicator), LATTITUDE, LONGITUDE, GPSSPEED, DL (Downlink) THP (Throughput), UL THP, RTT, etc. Each terminal data that can be referenced when changing handover conditions may not include DL THP, UL THP, RTT for reasons such as the load on commercial use.

[0041] Each base station data includes, for example, base station data regarding a specific base station that is the communication partner of a specific terminal, and the adjacent base station data described above. As an example, the base station data includes Date Time, RAT, TDD, FDD, gNB (next generation Node B), eNB (evolved Node B) ID, ARFCN, PCI, TAC, CI, BAND, BANDWIDTH, SINR, RSSI, etc.

[0042] For example, adjacent base station data includes CI, PCI, ARFCN, TAC, Q(Quadrature)-OFFSET, RACH(Random-Access Channel) INFORMATION, TYPE of NEIBOR RELATION, BLACKLISTED CELLS, MEASUREMENT REPORT THRESHOLDS, etc.

[0043] In addition, each base station data of FIG. 4 is data that is updated every 15 minutes, and the learning unit (131) generates the data set of FIG. 4 by linearly interpolating each terminal data and each base station data in seconds and linking them.

[0044] Next, the learning unit (131) trains the model by using a data set consisting of each terminal data and each base station data as an input variable, and evaluation data consisting of handover conditions and conditional handover conditions as an output variable.

[0045] The learning unit (131) trains the model with one parameter, such as RSRP, as the output variable when the evaluation data is a handover condition. Additionally, the learning unit (131) trains the model with two parameters, such as RSRP and RSRQ, as the output variable when the evaluation data is a conditional handover condition. In this case, the learning unit (131) trains the model in the case where the evaluation data is a handover condition and in the case where the evaluation data is a conditional handover condition, respectively.

[0046] (Acquisition Department)

[0047] Returning to the description of FIG. 3. The acquisition unit (132) acquires the first terminal data and the first base station data.

[0048] (Change section)

[0049] The changing unit (133) changes the handover conditions of the first terminal (200) using the handover performance data and the first terminal data and first base station data acquired by the acquisition unit (132).

[0050] As an example, the change unit (133) changes the handover conditions of the first terminal (200) by referring to a table in which each terminal data and each base station data are linked, instead of a model that has been trained as handover performance data.

[0051] As another example, the change unit (133) changes the handover conditions of the first terminal (200) by inputting the first terminal data and the first base station data into a model that has completed learning and outputs handover conditions according to the input of each terminal data and each base station data.

[0052] In the above-described change processing, the change unit (133) may change the threshold value of the difference of any one parameter between the first base station (300) and the communication partner candidate of the first terminal (200) by inputting the first terminal data and the first base station data into a model that has completed learning and outputs the threshold value of the difference of one parameter between each base station as a handover condition of the first terminal (200). For example, the change unit (133) changes the threshold value of the difference of the RSRP between the first base station (300) and the communication partner candidate by inputting the first terminal data and the first base station data into the model that has completed learning.

[0053] In the above-described change processing, the change unit (133) may change the threshold value of the difference between two parameters between the first base station (300) and the first terminal (200) by inputting the first terminal data and the first base station data into a model that has completed learning and outputs the threshold value of the difference between two parameters between each base station for the conditional handover condition of the first terminal (200).

[0054] For example, the modification unit (133) inputs the first terminal data and the first base station data into the model that has completed this learning, and changes the threshold values ​​of two differences among the RSRP, RSRQ, RTT, DL THP, and UL THP between the first base station (300) and the communication partner candidate.

[0055] The change unit (133) may change the handover conditions of the first terminal (200) by additionally using network data regarding the network as a change to the handover conditions of the first terminal (200).

[0056] In this case, the changing unit (133) changes the threshold value of the difference between the first base station (300) and the first terminal (200) communication partner candidate to a different value according to network data regarding the design of the network by the vendor or carrier. By doing so, the changing unit (133) can further suppress the deterioration of communication quality caused by handover.

[0057] (Notification Department)

[0058] The notification unit (134) notifies the first terminal (200) of the handover conditions of the first terminal (200) that have been changed by the change unit (133). The notification unit (134) may additionally notify the first base station (300) of the conditions of the conditional handover of the first terminal (200) that have been changed.

[0059] For example, the notification unit (134) indirectly notifies the first terminal (200) of the conditions, etc. by having the first base station (300) notify the first terminal (200) of the conditions, etc. In this case, the first base station (300) notifies the first terminal (200) of the conditions, etc. together with the transmission of an RRC reconstruction message or a SIB. The notification unit (134) may also notify the first terminal (200) of the conditions, etc. by interposing another device, such as a web server, or another path instead of the first base station (300).

[0060] [1-3. Processing Flow]

[0061] FIG. 5 is a flowchart illustrating the flow of information processing according to Embodiment 1. The learning unit (131) trains a model using each terminal data and each base station data as input variables and a handover condition as an output variable (S1). Subsequently, the acquisition unit (132) acquires the first terminal data and the first base station data (S2).

[0062] Next, the changing unit (133) changes the handover conditions of the first terminal (200) using the handover performance data and the first terminal data and first base station data acquired by the acquisition unit (132) (S3). Next, the notification unit (134) notifies the first terminal (200) of the handover conditions of the first terminal (200) changed by the changing unit (133) (S4).

[0063] [2. Embodiment 2]

[0064] When the information processing device (100) changes the handover condition of the first terminal (200) in Embodiment 1, it may change this condition to a condition that makes it easier to avoid the ping-pong phenomenon. Therefore, in Embodiment 2, an example of changing this condition to a condition that makes it easier to avoid the ping-pong phenomenon is explained.

[0065] [2-1. Configuration of Information Processing Devices]

[0066] The information processing device (100) has the same components as in embodiment 1. However, in embodiment 2, the functions of the learning unit (131) and the changing unit (133) are different.

[0067] (Learning Department)

[0068] The learning unit (131) trains the model by using terminal data as input variables, specifically terminal data regarding terminals among a plurality of terminals where a ping-pong phenomenon occurs more than a predetermined number of times within a predetermined period.

[0069] The learning unit (131) trains a model using each terminal data, including terminal data regarding a terminal where a ping-pong phenomenon occurs, as an input variable. For example, the learning unit (131) trains a model using each terminal data, including terminal data regarding at least one of the location of this terminal and the number of handovers by this terminal, as an input variable.

[0070] Hereinafter, an example of learning processing by the learning unit (131) is described in detail using FIG. 6. FIG. 6 is a diagram for explaining learning processing according to embodiment 2. The learning unit (131) determines that a ping-pong phenomenon has occurred if, based on the PCI and TimeStamp in each terminal data, the number of times the PCI in each terminal data is switched is 4 or more times within 10 seconds, or if it is more than a predetermined number of times within a predetermined period.

[0071] Next, the learning unit (131) visually identifies the location of the terminal by comparing at least one location data among LATTITUDE, LONGITUDE, and GPSSPEED with map data in the terminal data of the terminal where the ping-pong phenomenon occurs. In FIG. 6, the learning unit (131) identifies the location of the first terminal (201), the location of the second terminal (202), and the location of the third terminal (203) as the locations of the terminal where the ping-pong phenomenon occurs. Then, the learning unit (131) trains a model using each terminal data including these terminal locations as input variables.

[0072] In addition, the first terminal corresponding to the location (201) of the first terminal in FIG. 6 may be the same as or different from the first terminal (200) in FIG. 1.

[0073] (Change section)

[0074] The changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning based on the input of terminal data regarding the terminal that has a ping-pong phenomenon as each terminal data, thereby changing the handover conditions of the first terminal (200). For example, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning based on the number of handovers of the terminal that has a ping-pong phenomenon as an input variable, thereby changing the threshold value of the difference in RSRP between the first base station (300) and the communication partner candidate of the first terminal (200).

[0075] Additionally, the modification unit (133) may change the handover conditions of the first terminal (200) by inputting the first terminal data and the first base station data into a model that has completed learning based on the input of location data regarding the location of the terminal that has a ping-pong phenomenon as terminal data. For example, the modification unit (133) changes the threshold value of the difference between the first base station (300) and the communication partner candidate of the first terminal (200) by inputting the first terminal data and the first base station data into a model that has completed learning using at least one of LATTITUDE, LONGITUDE, and GPSSPEED of the terminal that has a ping-pong phenomenon as input variables.

[0076] [3. Embodiment 3]

[0077] When the information processing device (100) changes the handover condition of the first terminal (200) in Embodiment 1, it can change this condition based on the entire area where the radio waves of each base station reach. Therefore, in Embodiment 3, an example of changing this condition based on the entire area is explained.

[0078] [3-1. Configuration of Information Processing Devices]

[0079] The information processing device (100) has the same components as in embodiment 1. However, in embodiment 3, the functions of the learning unit (131) and the changing unit (133) are different.

[0080] (Learning Department)

[0081] The learning unit (131) trains a model using a data set consisting of each terminal data and each base station data in the entire area as input variables. This point is explained in detail using the example of FIG. 7. FIG. 7 is a diagram for explaining the learning process according to embodiment 3. In FIG. 7, each base station that is the communication partner of each of the plurality of terminals, namely the first terminal (200X) and the second terminal (200Y), is represented as the first base station (300X), the second base station (300Y), and the third base station (300Z).

[0082] In FIG. 7, the learning unit (131) trains a model using a data set in the entire area covered by radio waves from the first base station (300X), the second base station (300Y), and the third base station (300Z), which are managed by a management device (400) such as a DU, as an input variable. That is, the learning unit (131) trains a model using a data set in the entire area covered by radio waves from the first base station (300X) as an input variable, the second area (500Y) covered by radio waves from the second base station (300Y) as an input variable, and the third area (500Z) covered by radio waves from the third base station (300Z) as an input variable.

[0083] Additionally, the first terminal (200X) of FIG. 7 may be the same as or different from the first terminal (200) in FIG. 1, etc. or the terminal corresponding to the location (201) of the first terminal in FIG. 6. The second terminal (200Y) of FIG. 7 may be the same as or different from the terminal corresponding to the location (202) of the second terminal in FIG. 6. Additionally, the first base station (300X) of FIG. 7 may be the same as or different from the first base station (300) in FIG. 1, etc.

[0084] (Change section)

[0085] The changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning based on the input of each terminal data and each base station data in the entire area, and changes the handover conditions of the first terminal (200).

[0086] This point will be explained in detail using the example of FIG. 7. In FIG. 7, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning, which has the entire data set of the first area (500X), the second area (500Y), and the third area (500Z) as input variables, and changes the handover conditions of the first terminal (200). Here, the first terminal (200) is assumed to be located at the first handover occurrence point (600X) where the first area (500X) and the second area (500Y) overlap.

[0087] In FIG. 7, if optimization is performed only at the first handover point (600X), there is a possibility that a ping-pong phenomenon may occur at the second handover point (600Y) where the second area (500Y) and the third area (500Z) overlap. Furthermore, optimization here refers to making the handover conditions of the first terminal (200) located at the first handover point (600X) stricter by raising the threshold value of the difference in RSRP between the first base station (300) and the communication partner candidate of the first terminal (200).

[0088] Therefore, the modification unit (133) inputs the first terminal data and the first base station data into a model that has completed learning, considering both the first handover occurrence point (600X) and the second handover occurrence point (600Y). Then, the modification unit (133) changes the threshold value of the difference in parameters, such as RSRP, between the first base station (300) and the first terminal (200) communication partner candidate.

[0089] In this case, the changing unit (133) lowers the threshold value of the difference between the first base station (300) and the communication partner candidate RSRP, thereby relaxing the handover conditions of the first terminal (200) located at the first handover occurrence point (600X). By doing so, the changing unit (133) can reduce the total number of ping-pong phenomena at the second handover occurrence point (600Y).

[0090] [4. Effects]

[0091] As described above, the information processing device (100) according to the embodiment has an acquisition unit (132), a modification unit (133), and a notification unit (134). The acquisition unit (132) acquires first terminal data regarding the first terminal (200) and first base station data regarding the first base station (300) which is the communication partner of the first terminal (200). The modification unit (133) changes the handover conditions of the first terminal (200) using the handover performance data based on each terminal data regarding each of the plurality of terminals and each base station data regarding each base station which is the communication partner of each of the plurality of terminals, and the first terminal data and first base station data acquired by the acquisition unit (132). The notification unit (134) notifies the first terminal (200) of the handover conditions of the first terminal (200) that have been changed by the modification unit (133).

[0092] In this way, the information processing device (100) dynamically changes the handover conditions of the first terminal (200) according to the first terminal data and the first base station data while referring to the handover performance data. Because of this, the information processing device (100) can suppress the deterioration of communication quality caused by handover. In addition, the information processing device (100) can reduce the occurrence of ping-pong phenomena or unnecessary signaling, thereby realizing the construction of a communication environment with excellent user experience.

[0093] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning and outputs handover conditions according to the input of each terminal data and each base station data, and changes the handover conditions of the first terminal (200).

[0094] In this way, the information processing device (100) can further suppress the deterioration of communication quality caused by handover by using a model that has been learned.

[0095] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning and outputs a threshold value of the difference in RSRP between each base station as a handover condition for the first terminal (200), and changes the threshold value of the difference in RSRP between the first base station (300) and the communication partner candidate of the first terminal (200).

[0096] In this way, the information processing device (100) can further suppress the deterioration of communication quality caused by handover by changing the threshold value of the difference of parameters that have a large influence on handover.

[0097] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning and outputs the threshold value of the difference between two parameters between each base station, and changes the threshold value of the difference between two parameters between the first base station (300) and the first terminal (200) communication partner candidate.

[0098] In this way, the information processing device (100) can further suppress the deterioration of communication quality caused by handover by changing the handover condition, such as the condition of conditional handover, which has two output variables.

[0099] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning and outputs the threshold value of the difference between two parameters between each base station, and changes the threshold value of the difference between two of the RSRP, RSRQ, RTT, DL THP, and UL THP between the first base station (300) and the first terminal (200) communication partner candidate.

[0100] In this way, the information processing device (100) can further suppress the deterioration of communication quality caused by handover by changing the threshold value of the difference between two parameters that have a large influence on handover.

[0101] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning based on the input of terminal data regarding a terminal among a plurality of terminals in which a handover has occurred more than a predetermined number of times within a predetermined period as each terminal data, and changes the handover condition of the first terminal (200).

[0102] Accordingly, the information processing device (100) can change the handover condition of the first terminal (200) to a threshold value, such as one where it is difficult for the handover to occur more than a predetermined number of times. Because of this, the information processing device (100) can change the handover condition to one that makes it easy to avoid the ping-pong phenomenon.

[0103] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning based on the input of location data regarding the location of a terminal in which a handover has occurred more than a predetermined number of times within a predetermined period as terminal data, and changes the handover conditions of the first terminal (200).

[0104] In this way, the information processing device (100) changes the handover conditions of the first terminal (200) using a learned model, etc., which has the point where the ping-pong phenomenon occurs as an input variable. By doing so, the information processing device (100) can change the handover conditions, etc., to make it easier to avoid the ping-pong phenomenon of the first terminal (200) at the point where the ping-pong phenomenon occurs.

[0105] In addition, in the information processing device (100) according to the embodiment, the changing unit (133) inputs the first terminal data and the first base station data into a model that has completed learning based on the input of each terminal data and each base station data in the entire area where the radio waves of each base station reach, and changes the handover conditions of the first terminal (200).

[0106] In this way, the information processing device (100) changes the handover conditions of the first terminal (200) using a model that has completed learning, taking into account handover occurrence points in the entire area. By doing so, the information processing device (100) can reduce the total number of ping-pong phenomena in the entire area and make the signaling of the entire area more efficient.

[0107] [5. Hardware Configuration]

[0108] In addition, the information processing device (100) according to the above-described embodiment is realized by a computer (1000) with a configuration such as that shown in FIG. 8. FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of an information processing device. The computer (1000) is equipped with a CPU (1100), RAM (1200), ROM (1300), HDD (1400), a communication interface (I / F) (1500), an input / output interface (I / F) (1600), and a media interface (I / F) (1700).

[0109] The CPU (1100) operates based on a program stored in the ROM (1300) or HDD (1400) and controls each part. The ROM (1300) stores a boot program executed by the CPU (1100) when the computer (1000) starts up, or a program that depends on the hardware of the computer (1000).

[0110] The HDD (1400) stores programs executed by the CPU (1100) and data used by such programs. The communication interface (1500) receives data from another device via a predetermined communication network and sends it to the CPU (1100), and transmits data generated by the CPU (1100) to another device via a predetermined communication network.

[0111] The CPU (1100) controls output devices such as a display or printer and input devices such as a keyboard or mouse via an input / output interface (1600). The CPU (1100) acquires data from an input device via an input / output interface (1600). Additionally, the CPU (1100) outputs generated data to an output device via the input / output interface (1600).

[0112] The media interface (1700) reads a program or data stored in a recording medium (1800) and provides it to the CPU (1100) via 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), an optical magneto-optical recording medium such as a MO (Magneto-Optical Disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0113] 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 function of the control unit (130) by executing a program loaded on the RAM (1200). The CPU (1100) of the computer (1000) reads and executes such a program from a recording medium (1800), but as another example, such a program may be obtained from another device via a predetermined communication network.

[0114] Although several embodiments of the present invention have been described in detail with reference to the drawings, these are examples, and it is possible to implement the present invention in other forms by making various modifications and improvements based on the knowledge of those skilled in the art, including the embodiments described in the disclosure of the invention.

[0115] [6. Others]

[0116] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically may be performed manually, or all or part of the processes described as being performed manually may be performed automatically using known methods. In addition, information including the processing sequence, specific names, and various data or parameters shown in the above documents or drawings may be changed at will, except where specifically noted. For example, the various information shown in each drawing is not limited to the information illustrated.

[0117] Furthermore, each component of each device described is functionally conceptual and is not required to be physically configured as described. In other words, the specific form of distribution and integration of each device is not limited to what is described, and all or part thereof can be configured by functionally or physically distributing and integrating them into arbitrary units depending on various loads or usage situations.

[0118] In addition, the information processing device (100) described above may be implemented with multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform, etc. via API (Application Programming Interface) or network computing.

[0119] In addition, the above-described embodiments can be appropriately combined within a range that does not contradict the processing contents. Explanation of the symbols

[0120] 100 : Information processing unit 110 : Communications Department 120 : Memory section 130 : Control unit 131 : Learning Department 132 : Acquisition Department 133 : Change section 134 : Notification Department

Claims

Claim 1 An information processing device having: an acquisition unit for acquiring first terminal data regarding a first terminal and first base station data regarding a first base station that is a communication partner of the first terminal; handover performance data based on each terminal data regarding each of a plurality of terminals and each base station data regarding a communication partner of each of the plurality of terminals; a modification unit for changing the handover conditions of the first terminal using the first terminal data and the first base station data acquired by the acquisition unit; and a notification unit for notifying the first terminal of the handover conditions of the first terminal changed by the modification unit. Claim 2 In claim 1, the changing unit is an information processing device that changes the handover condition of the first terminal by inputting the first terminal data and the first base station data into a learned model that outputs the handover condition according to the input of each terminal data and each base station data. Claim 3 In claim 2, the changing unit is an information processing device that inputs the first terminal data and the first base station data into the learned model, which outputs a threshold value of the difference in RSRP (Reference Signal Received Power) between each base station as a handover condition of the first terminal, and changes the threshold value of the difference in RSRP between the first base station and the communication partner candidate of the first terminal. Claim 4 In claim 2, the changing unit inputs the first terminal data and the first base station data into the learned model that outputs a threshold value of the difference between two parameters between each base station, and changes the threshold value of the difference between two parameters between the first base station and the first terminal communication partner candidate. Claim 5 In claim 4, the changing unit inputs the first terminal data and the first base station data into the learned model that outputs a threshold value of the difference between two parameters between each base station, and changes the threshold value of the difference between two of the RSRP, RSRQ (Reference Signal Received Quality), RTT (Round-Trip Time), DL (Downlink) THP (Throughput), and UL (Uplink) THP between the first base station and the communication partner candidate. Claim 6 In claim 2, the changing unit is an information processing device that changes the handover conditions of the first terminal by inputting the first terminal data and the first base station data into a model that has completed learning based on the input of terminal data regarding a terminal among the plurality of terminals in which the handover has occurred more than a predetermined number of times within a predetermined period as each terminal data. Claim 7 In claim 6, the changing unit is an information processing device that changes the handover conditions of the first terminal by inputting the first terminal data and the first base station data into the model that has completed learning based on the input of location data regarding the location of a terminal in which the handover has occurred more than a predetermined number of times within a predetermined period as the terminal data. Claim 8 In claim 2, the changing unit is an information processing device that changes the handover conditions of the first terminal by inputting the first terminal data and the first base station data into the model that has completed learning based on the input of the each terminal data and each base station data in the entire area where the radio waves of each base station reach. Claim 9 An information processing method executed by an information processing device, comprising: an acquisition process for acquiring first terminal data regarding a first terminal and first base station data regarding a first base station that is a communication partner of the first terminal; actual handover data based on each terminal data regarding each of a plurality of terminals and each base station data regarding a communication partner of each of the plurality of terminals; a modification process for modifying the handover conditions of the first terminal using the first terminal data and the first base station data acquired by the acquisition process; and a notification process for notifying the first terminal of the handover conditions of the first terminal modified by the modification process. Claim 10 An information processing program characterized by executing on a computer: an acquisition step of acquiring first terminal data regarding a first terminal and first base station data regarding a first base station that is a communication partner of the first terminal; actual handover data based on each terminal data regarding each of a plurality of terminals and each base station data regarding a communication partner of each of the plurality of terminals; a modification step of modifying the handover conditions of the first terminal using the first terminal data and the first base station data acquired by the acquisition step; and a notification step of notifying the first terminal of the handover conditions of the first terminal modified by the modification step.

Images