Information processing device, real-time quality index calculation method, and program

Abstract

The present invention is an information processing device, the device comprising: an acquisition unit that acquires real-time information pertaining to the quality of communication; and a calculation unit that calculates, on the basis of the real-time information, a real-time quality index obtained by quantifying a real-time event.

Description

Information processing device, real-time quality index calculation method, and program

[0001] This invention relates to a technology for performing control based on communication quality.

[0002] Conventional techniques for estimating communication quality include creating a history of quality information based on the device's past use of the network (NW), storing this history in a database (DB), and estimating quality by referring to the quality history in the DB in response to requests from external functions.

[0003] Furthermore, Non-Patent Document 1 discloses a technique for reducing the amount of quality information managed in a database by characterizing quality information and using it as a statistical indicator.

[0004] By utilizing the quality information stored in the database, it becomes possible, for example, to predict the future communication quality of a controlled object and perform proactive control over that object.

[0005] Non-patent document 1. Ono et al., Study on a quality information management method for network quality estimation, 2024 IEICE General Conference, B-6-16

[0006] However, techniques that estimate quality based solely on statistical indicators in the spatiotemporal domain, such as the technique disclosed in Non-Patent Document 1, have the problem of being unable to detect sudden quality degradation that is not reproducible or deviates from the trend.

[0007] This invention has been made in view of the above points, and aims to provide a technology that enables the estimation of not only steady-state quality deterioration but also the occurrence of sudden quality deterioration.

[0008] According to the disclosed technology, an information processing device is provided that includes an acquisition unit for acquiring real-time information related to the quality of communication, and a calculation unit for calculating a real-time quality index that quantifies real-time events based on the real-time information.

[0009] The disclosed technology provides a method that enables the estimation of not only steady-state quality deterioration but also the occurrence of sudden quality deterioration.

[0010] This figure shows a method for managing quality indicators by domain in a space having a spatial axis and a temporal axis. This figure explains the problem. This figure explains the problem. This figure explains the outline of the technology related to the embodiment. This figure shows an example of real-time information acquired from the perspective of the device (D) state. This figure shows an example of real-time information acquired from the perspective of the spatiotemporal domain (R). This figure shows an example of the configuration of a communication system. This is a sequence diagram for explaining the operation of the communication system. This figure shows an example of the configuration of the information processing device 400. This figure shows an example of the hardware configuration of the device.

[0011] Hereinafter, embodiments of the present invention (this embodiment) will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the embodiments described below.

[0012] The following will first describe the problem in more detail, and then explain the system configuration and operation of this embodiment. In the following explanation, unless it is clear from the context that it has a different meaning, " / " means "or" or "and". For example, "A / B" means A, B, or A and B.

[0013] (Regarding the problem) As mentioned above, by utilizing the communication quality information (which may also be called network quality) stored in the database, it is possible to predict the future communication quality of the device to be controlled (e.g., a connected car). Furthermore, based on this prediction, it is possible to implement proactive control on the device. Note that prediction can also be rephrased as estimation.

[0014] More specifically, in the prior art disclosed in Non-Patent Document 1, as shown in Figure 1, quality-related information (quality information) is managed for each region in a space having a spatial axis and a time axis. Quality indicators are statistical information such as the mean value and standard deviation of the quality information. These quality indicators may also be called statistical indicators. Non-Patent Document 1 refers to this method as QIM (Quality Index Map). By using quality indicators managed in this way, for example, it is possible to calculate quality estimates from predetermined percentile values ​​in a normal distribution with specified mean and standard deviation values.

[0015] However, as mentioned above, quality estimation based solely on statistical indicators in the spatiotemporal domain cannot detect sudden quality degradation that is difficult to reproduce or deviates from the trend. Figure 2 illustrates this problem. In Figure 2, the region indicated by (2) corresponds to the region of sudden quality degradation.

[0016] Now, referring to Figure 3, we will explain the causes of missed detections of quality degradation. Figure 3 is a diagram illustrating the scope of degradation detection based on quality estimation using statistical indicators and the problems associated with it.

[0017] Figure 3 shows that the vertical axis represents the magnitude of differences / variations within the spatiotemporal domain, and the horizontal axis represents the frequency of quality degradation. As shown in Figure 3, regions where differences / variations within the spatiotemporal domain are large and the frequency of quality degradation is low are regions with a high risk of missed quality degradation detection. More specifically, missed quality degradation detection is likely to occur in "spatiotemporal domains where quality degradation has not occurred in the past," "environments where regularity / steadiness is not observed or is of low degree," and "regions where quality differences / variations within the spatiotemporal domain are large."

[0018] (Outline of Embodiment) Referring to Figure 4, an overview of the technology according to this embodiment for solving the above problems will be described. Figure 4 shows the RQI calculation unit 110 and the quality estimation unit 130, which are part of the system configuration described later. RQI is an abbreviation for Real-time Quality Index.

[0019] In this embodiment, in addition to statistical indicators in the spatiotemporal domain, real-time information (device state information and spatiotemporal domain information) and RQI are used as input information to the quality estimation unit 130, and the quality estimation unit 130 estimates quality using at least one of the statistical indicators, real-time information, and RQI.

[0020] The RQI calculation unit 110 uses the above real-time information to calculate an RQI that takes into account sudden / different quality fluctuations that cannot be expressed by statistical indicators. This RQI calculation is performed as a preprocessing step for quality estimation.

[0021] In this embodiment, the quality estimation algorithm in the quality estimation unit 130 (including the weighting and order of consideration of each piece of information) is optimized based on feedback loop control in response to fluctuations in the device state and spatiotemporal domain.

[0022] The quality estimation unit 130 uses an estimation method that utilizes general statistical processing, for example, based on a comparison between the "quality estimation result" and the actual "quality information" obtained after estimation (similar to QIM disclosed in Non-Patent Document 1). Alternatively, the quality estimation unit 130 may be implemented as a quality estimation model that utilizes machine learning / AI such as a random forest or a neural network, and the quality estimation model (or algorithm) is optimized by the above-mentioned feedback loop control.

[0023] In the example shown in Figure 4, the RQI calculation unit 110 receives device status information and spatiotemporal domain information as real-time information. Device status information includes, for example, the device's (terminal's) position / velocity / acceleration, device quality information, device wireless information, and device capability. Spatiotemporal domain information includes quality information and wireless information for each domain. Note that device information is obtained for each device, and spatiotemporal domain information is obtained for each spatiotemporal domain.

[0024] The wireless information in the device state is information regarding the radio wave propagation environment from the device's perspective, such as RSSI / RSRP / RSRQ / SINR. Further, the wireless information in the device state may include information regarding the connection path / transmission configuration, including the connected base station (Cell ID, etc.), the band / channel in use, the handover schedule, etc.

[0025] Capability is information regarding device functions / performance, such as "frequency / band / channel" supported by the device, for example.

[0026] The statistical indicators (average value, standard deviation, stability, etc.) are input to each of the RQI calculation unit 110 and the quality estimation unit 130. Note that the statistical indicators may not be input to the RQI calculation unit 110 in some cases. Also, stability may be calculated as one of the RQIs.

[0027] The quality estimation unit 130 calculates and outputs a quality estimation value based on, for example, the RQI and the statistical indicators. The quality estimation unit 130 can estimate, for example, the probability of occurrence of quality degradation at a certain future time.

[0028] (Regarding RQI: Real-time Quality Index) Subsequently, the RQI will be described in more detail. The RQI is an index that quantifies real-time quality fluctuations and the suddenness / continuity of events. For each numerical value such as quality information, only the latest one may be separately included in the RQI as reference information.

[0029] In the present embodiment, as an example, the RQI calculation unit 110 is assumed to calculate the following three types of numerical values as the RQI.

[0030] (1) Real-time fluctuations (e.g., fluctuation rate F) leading to the state indicated by the latest quality information (real-time information): This value is calculated based on the real-time information.

[0031] (2) Stationarity / tendency following of the above state (e.g., outlier coefficient O): This value is calculated based on the real-time information.

[0032] (3) Possibility of continuity of the state (e.g., stability S): This value is calculated using a statistical index based on real-time information.

[0033] FIG. 5 shows an example of real-time information obtained from the perspective of the device (D) state. In the example of FIG. 5, "position, quality information, wireless information" are obtained for each time. The quality information is, for example, throughput, and the wireless information is, for example, RSSI. In FIG. 5, the RQI calculation unit 110 uses this real-time information to calculate F , , ,

[0038] , １ , , Ｑ , Ｗ（Ｒ） , , Ｗ（Ｒ） ,

[0035] ,

[0039] , , , ｔ＿ｎ , Ｑ ,

[0037] , Ｗ（Ｒ） ,

[0036] , O Ｑ（Ｄ） , S Ｑ（Ｄ） , F Ｗ（Ｄ） , O Ｗ（Ｄ） , S Ｗ（Ｄ） , and calculates them.

[0034] FIG. 6 shows an example of real-time information obtained from the perspective of the spatio-temporal region (R). In the example of FIG. 6, for example, "quality information, wireless information" for each time at a specific spatial position are obtained. The quality information is, for example, throughput, and the wireless information is, for example, RSSI. In FIG. 6, the RQI calculation unit 110 uses this real-time information to calculate F Ｑ（Ｒ） , O Ｑ（Ｒ） , S Ｑ（Ｒ） , F Ｗ（Ｒ） , O Ｗ（Ｒ） , S Ｗ（Ｒ） , and calculates them.

[0035] Taking Q (quality information) as an example, an example of the RQI calculation formula will be described. The same applies to W (wireless information).

[0036] The RQI calculation unit 110 calculates the fluctuation rate F Ｑ using the following formula "Equation 1" or "Equation 2".

[0037]

[0038] The RQI calculation unit 110 calculates the outlier coefficient O​​​​​​​​= {(First Quartile) - 1.724 × (Interquartile Range)} - Q ｔ＿ｎ (2) "Q ｔ＿ｎ If the value is greater than or equal to the mean, then f １ = Q ｔ＿ｎ -{(Third Quartile) + 1.724 × (Interquartile Range)} In the case of (1) above, "{(First Quartile) - 1.724 × (Interquartile Range)}" represents the lower limit of the outlier test, and in the case of a normal distribution, it corresponds to "Mean - 3 × Standard Deviation".

[0040] In the case of (2) above, "{(third quartile) + 1.724 × (interquartile range)}" corresponds to the upper limit of the outlier test.

[0041] The RQI calculation unit 110 calculates the stability S Ｑ This is calculated using one of the following methods (1) to (4). In all of the following examples, the calculated value is based on the "variability of quality information (real-time information)".

[0042] (1) S Ｑ = f １ (CV) f １ (CV) = 1 / CV CV is the coefficient of variation, and "Coefficient of Variation CV = Standard Deviation / Mean". In the examples in Figures 5 and 6, both the standard deviation and the mean are values ​​for n quality information items.

[0043] (2) S Ｑ = f ２ (N,CV) f ２ (N, CV) = ln N / CV, that is, f ２ (N, CV) is the value obtained by dividing "ln N" (the natural logarithm of N) by CV. N is the number of quality information items (sample size).

[0044] (3) S Ｑ = f ３ (N, V) f ３ (N, V) = ln N / V, that is, f ３ (N, V) is the value obtained by dividing "ln N" (the natural logarithm of N) by V, where V is the variance.

[0045] (4) S Ｑ = f ４ (x) f ４(x) = mean / x% confidence interval, that is, f ４ (x) is the value obtained by dividing the mean value of the quality information in question by the x% confidence interval for that quality information.

[0046] One method for estimating quality values ​​using RQI is to calculate them from the latest quality information (quality value) and the rate of change F. For example, the quality value can be estimated as the quality value at the next time point, assuming that the latest quality value fluctuates by the rate of change F. However, this calculation method is just one example, and the way RQI is used and weighted in the quality estimation algorithm can be optimized based on self-learning. Furthermore, the outlier coefficient can be used to determine whether the latest quality value is in line with the quality fluctuation trend. In addition, the stability can be used to determine the continuity of events.

[0047] Furthermore, quality estimation algorithms, including the use of RQI, can be optimized based on feedback loop control (e.g., self-generation / automatic tuning of machine learning models).

[0048] (Example of System Configuration) Figure 7 shows an example of the configuration of the communication system in this embodiment. As shown in Figure 7, the communication system in this embodiment has an RQI calculation unit 110, a storage unit 120, a quality estimation unit 130, a quality indicator management unit 140, a cooperative control unit 200, and a quality information distribution unit 210. Here, the configuration having the RQI calculation unit 110, the storage unit 120, the quality estimation unit 130, and the quality indicator management unit 140 is referred to as the information processing device 100. The storage unit 120 may also be called a DB (database).

[0049] Furthermore, the RQI calculation unit 110, the storage unit 120, the quality estimation unit 130, the quality indicator management unit 140, the cooperative control unit 200, and the quality information distribution unit 210 may each be referred to as an information processing device. An information processing device is, for example, a computer. This computer may be a physical machine or a computing resource on the cloud.

[0050] Figure 7 also shows the controlled object 300, which is controlled by the cooperative control unit 200. The controlled object 300 is, for example, a device (e.g., a connected car), a network, an edge cloud server, etc.

[0051] The memory unit 210 stores quality information continuously acquired from the controlled object 300, etc., via the quality information distribution unit 210 and the quality indicator management unit 140, as well as quality indicators (feature quantities, statistical indicators) calculated from the quality information by the quality indicator management unit 140. This quality information is the real-time information described above and includes device status information and spatiotemporal information.

[0052] For example, if the device is a connected car, quality information (throughput, packet loss rate, delay, jitter, etc.) in the information transmission between the connected car and the remote monitoring and control system is continuously stored in the storage unit 120.

[0053] The RQI calculation unit 110 refers to the quality indicators / quality information stored in the storage unit 120, calculates the RQI for the quality information, and stores the calculated RQI in the storage unit 120. The RQI calculation unit 110 also updates the RQI periodically, for example.

[0054] The quality estimation unit 130 performs quality estimation by referring to quality indicators / RQI / real-time information stored in the memory unit 120 and notifies the cooperative control unit 200 of the quality estimation result. As described above, the quality estimation unit 130 can estimate, for example, the probability of quality degradation occurring in the communication of a certain device. Furthermore, the quality estimation unit 130 can optimize the derivation algorithm through feedback loop control.

[0055] Furthermore, the quality estimation unit 130 may perform quality estimation based on either a statistical indicator or RQI, or on both a statistical indicator and RQI.

[0056] The quality estimation results may include the estimated quality value and stability. The quality estimation method used by the quality estimation unit 130 when estimating quality values ​​is not limited to a specific method, but for example, percentile values ​​may be calculated from N pieces of quality information (measured values), and these values ​​may be used as the estimated NW quality. Alternatively, as described in Non-Patent Literature 1, percentile values ​​may be calculated from one quality index (mean value, standard deviation, etc.) per region, and these may be used as the estimated NW quality. Each of the above percentile values ​​may be determined based on stability.

[0057] Furthermore, for example, if the absolute value of the rate of variation is large (e.g., above a threshold), the estimated quality value for the next time period may be calculated from the latest quality information and the rate of variation.

[0058] Alternatively, the final estimated value may be obtained by multiplying the above estimated value by a coefficient based on stability.

[0059] The cooperative control unit 200 issues control instructions to the controlled object 300 based on the quality estimation results received from the quality estimation unit 130. Examples of control instructions include changing the connection network, changing the monitoring system, changing the information transmission method, changing the route, changing the speed, and other alert notifications.

[0060] In the above example, the data is routed through the storage unit 120 (i.e., database), but this is just one example of an embodiment. The quality indicators / quality information / RQI may also be input directly to the quality estimation unit 130 without going through the storage unit 120 (i.e., database).

[0061] (Processing Sequence) Referring to Figure 8, the processing sequence of the communication system according to this embodiment shown in Figure 7 will be described.

[0062] In S1, quality information (real-time information) measured by the controlled object 300 is transmitted to the quality information distribution unit 210. In S2, the quality information distribution unit 210 transmits the quality information to the quality indicator management unit 140. The quality indicator management unit 140 calculates the quality indicator.

[0063] In S3, the quality information distribution unit 210 transmits quality indicators / quality information to the storage unit 120. The quality indicators / quality information is stored in the storage unit 120.

[0064] In S4, the RQI calculation unit 110 requests quality indicators / quality information from the storage unit 120, and in S5, it obtains the quality indicators / quality information. In S6, the RQI calculation unit 110 calculates the RQI based on the quality indicators / quality information obtained in S5. In S7, the RQI calculation unit 110 stores the calculated RQI in the storage unit 120. If an RQI already exists, this is updated. The processes from S1 to S7 are performed continuously.

[0065] In S8, the quality estimation unit 130 requests quality indicators / quality information / RQI from the storage unit 120. In S9, the quality estimation unit 130 obtains quality indicators / quality information / RQI from the storage unit 120.

[0066] In S10, the quality estimation unit 130 performs quality estimation based on the quality indicators / quality information / RQI acquired in S9.

[0067] In S11, the quality estimation unit 130 transmits the quality estimation result (for example, the probability of quality degradation occurring) to the cooperative control unit 200. In S12, the cooperative control unit 200 issues a control instruction to the controlled object 300 based on the quality estimation result. For example, if the probability of quality degradation occurring is above a threshold, it issues a control instruction such as switching the connection frequency or the connection base station.

[0068] (Other examples) Quality information may include not only network quality information such as throughput, packet loss rate, communication delay, and jitter, but also application layer quality information such as image / video quality information such as SSIM and VMAF, and subjective quality evaluation information such as MOS values.

[0069] The calculation process of the rate of change F includes time t ｘ ,t ｙ It is also acceptable to adopt a form that does not limit the calculation formula, such as using only the information (1 ≤ x, y ≤ n), or a form that optimizes the calculation formula as well.

[0070] The calculation formula for the outlier coefficient O may not be limited to specific methods, such as using the difference between the outlier coefficient O and statistics used in various tests, such as the Smirnov-Grubbs test, or the significance level. Alternatively, the calculation formula may be optimized.

[0071] When calculating stability S, it is acceptable to take a form that does not limit the calculation formula, such as considering information about the surrounding environment, including surrounding objects and base station status, and macro-level information such as human flow / logistics, or to optimize the calculation formula itself.

[0072] As a quality estimation model / algorithm, it is also acceptable to use models / algorithms other than the "current QIM (estimation based on the inverse function of the cumulative distribution function of the probability distribution), random forests, and neural networks such as CNN," such as utilizing Gaussian processes or applying Bayesian models or STRIMA (spatiotemporal autoregressive integrated moving average model).

[0073] (Example of Information Processing Device Configuration) As mentioned above, a configuration having an RQI calculation unit 110, a storage unit 120, a quality estimation unit 130, and a quality indicator management unit 140 is called an information processing device 100. The storage unit 120 may also be called a DB (database). As mentioned above, the storage unit 120 may be omitted. In addition, the RQI calculation unit 110, the storage unit 120, the quality estimation unit 130, the quality indicator management unit 140, the cooperative control unit 200, and the quality information distribution unit 210 may each be called an information processing device. An information processing device is, for example, a computer. This computer may be a physical machine or a computing resource on the cloud.

[0074] Figure 9 shows an example configuration of an information processing device 400 having the functions of an RQI calculation unit 110 and a quality estimation unit 130. As shown in Figure 9, the information processing device 400 includes an acquisition unit 410 that acquires real-time information related to communication quality, a calculation unit 420 that calculates a real-time quality index that quantifies real-time events based on the real-time information, and a quality estimation unit 430 that estimates the quality based on the real-time quality index and a statistical index. Note that the information processing device 400 may be configured without the quality estimation unit 430.

[0075] (Example Hardware Configuration) Any of the information processing devices described in this embodiment can be realized, for example, by having a computer execute a program. This computer may be a physical computer or a virtual machine on the cloud.

[0076] In other words, the device can be realized by using hardware resources such as the CPU and memory built into a computer to execute a program corresponding to the processing performed by the device. The program can be recorded on a computer-readable recording medium (such as portable memory), saved, and distributed. It can also be provided via a network, such as the Internet or email.

[0077] Figure 10 shows an example of the hardware configuration of the computer described above. The computer in Figure 10 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., all of which are interconnected by bus B. The computer may also be equipped with a GPU.

[0078] The program that enables processing on the computer is provided on a recording medium 1001, such as a CD-ROM or memory card. When the recording medium 1001 containing the program is set in the drive device 1000, the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000. However, the program does not necessarily have to be installed from the recording medium 1001; it may also be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program as well as necessary files and data.

[0079] The memory device 1003 reads and stores a program from the auxiliary storage device 1002 when a program startup command is received. The CPU 1004 implements the functions related to the memory device 1003 according to the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network, etc. The display device 1006 displays a GUI (Graphical User Interface) etc., based on a program. The input device 1007 consists of a keyboard and mouse, buttons, or a touch panel, etc., and is used to input various operation commands. The output device 1008 outputs the calculation results.

[0080] (Summary of the embodiment, effects, etc.) The key points of the technology according to this embodiment are, for example, the following (1) to (3).

[0081] (1) In this embodiment, statistical indicators based on past / present information in the spatiotemporal domain and real-time information including the state of the device that is the subject of quality estimation are identified, and the suddenness / continuity of real-time fluctuations and events are quantified.

[0082] (2) In this embodiment, information that affects / correlated with quality in E2E is characterized and used for quality estimation.

[0083] (3) The estimation model itself, including the rules and neural networks related to the estimation, is updated and optimized as needed based on feedback loop control.

[0084] The technology according to this embodiment can respond to events caused by sudden fluctuations that cannot be detected by estimation based solely on statistical indicators, thereby improving estimation / detection accuracy.

[0085] Furthermore, quantifying and preprocessing real-time events makes it possible to improve the efficiency of the learning process (avoiding overfitting) and simplify the estimation model (avoiding complexity).

[0086] Furthermore, by applying an optimized estimation model that takes into account the requirements for quality estimation, such as prioritizing degradation detection and improving the accuracy of quality estimation, it becomes possible to provide an estimation system that can handle a variety of use cases, considering the extent to which past / present statistics, recent facts, the abruptness / continuity of events, and the level of fluctuation of each are taken into account.

[0087] The following additional information is disclosed regarding the embodiments described above.

[0088] <Notes> (Note 1) An information processing device comprising: an acquisition unit for acquiring real-time information related to the quality of communication; and a calculation unit for calculating a real-time quality index that quantifies real-time events based on the real-time information. (Note 2) The information processing device according to Note 1, wherein the acquisition unit acquires device state information and spatiotemporal information as the real-time information. (Note 3) The information processing device according to Note 1, wherein the calculation unit calculates the most recent rate of change of the real-time information, the outlier coefficient of the most recent value of the real-time information, and the stability of the real-time information as the real-time quality index. (Note 4) The information processing device according to Note 1, wherein the calculation unit performs the calculation of the real-time quality index as a preprocessing step before processing the quality estimation. (Note 5) The information processing device according to Note 1, further comprising a quality estimation unit for estimating the quality based on the real-time quality index and statistical index. (Note 6) The information processing device according to Note 5, wherein the quality estimation unit optimizes the quality estimation algorithm based on feedback loop control. (Appendix 7) A real-time quality index calculation method executed by an information processing device, comprising: an acquisition step of acquiring real-time information related to the quality of communication; and a calculation step of calculating a real-time quality index that quantifies real-time events based on the real-time information. (Appendix 8) A non-temporary storage medium storing a program for causing a computer to function as a part of the information processing device described in any one of Appendix 1 to 6.

[0089] Although this embodiment has been described above, the present invention is not limited to this specific embodiment, and various modifications and changes are possible within the scope of the gist of the invention as described in the claims.

[0090] 100 Information Processing Unit 110 RQI Calculation Unit 120 Storage Unit 130 Quality Estimation Unit 140 Quality Indicator Management Unit 200 Cooperative Control Unit 210 Quality Information Distribution Unit 400 Information Processing Unit 410 Acquisition Unit 420 Calculation Unit 430 Quality Estimation Unit 1000 Drive Unit 1001 Recording Medium 1002 Auxiliary Storage Device 1003 Memory Device 1004 CPU 1005 Interface Device 1006 Display Device 1007 Input Device 1008 Output Device

Claims

1. An information processing device comprising: an acquisition unit that acquires real-time information related to the quality of communication; and a calculation unit that calculates a real-time quality index that quantifies real-time events based on the real-time information.

2. The information processing apparatus according to claim 1, wherein the acquisition unit acquires device status information and spatiotemporal information as real-time information.

3. The information processing apparatus according to claim 1, wherein the calculation unit calculates the most recent rate of change of the real-time information, the outlier coefficient of the most recent value of the real-time information, and the stability of the real-time information as the real-time quality indicators.

4. The information processing apparatus according to claim 1, wherein the calculation unit performs the calculation of the real-time quality index as a preprocessing step before the quality estimation process.

5. The information processing apparatus according to claim 1, further comprising a quality estimation unit that estimates the quality based on the real-time quality indicator and statistical indicator.

6. The information processing apparatus according to claim 5, wherein the quality estimation unit optimizes the quality estimation algorithm based on feedback loop control.

7. A real-time quality index calculation method executed by an information processing device, comprising: an acquisition step of acquiring real-time information related to the quality of communication; and a calculation step of calculating a real-time quality index that quantifies real-time events based on the real-time information.

8. A program for causing a computer to function as a component of the information processing device described in any one of claims 1 to 6.

Images