Quality estimation system, quality estimation method, and program

Abstract

The present invention makes it possible to calculate an index with high accuracy, even for an area with limited data. This quality estimation system includes: a context data generation unit that generates a plurality of pieces of context data from measurement data; a first index calculation unit that generates first index data for each context and for each area, using the context data; an identification unit that identifies a second context similar to a first context; a second index calculation unit that defines an area for which the first index data is not generated, among a plurality of areas, as an unmeasured area, and generates second index data for the first context by using the context data of the first context for an area other than the unmeasured area, and using the context data of the second context for the unmeasured area; and an output unit that outputs the second index data.

Description

Quality estimation system, quality estimation method, and program

[0001] The present disclosure relates to a quality estimation system, a quality estimation method, and a program.

[0002] As a related technique, Patent Document 1 discloses a quality evaluation device that evaluates the quality of an application during execution. The quality evaluation device described in Patent Document 1 estimates a user's perceived waiting time from a user operation log. The quality evaluation device also calculates, from the user operation log, a status index that indicates the network status and terminal status during the perceived waiting time. The quality evaluation device visualizes the quality by displaying the estimated perceived waiting time and the calculated status index on a map.

[0003] JP 2014-203371 A

[0004] When displaying measured or calculated indicators on a map and analyzing the geographical characteristics of the measured or calculated indicators, the data required to calculate the indicators may not be available in all areas. If the required amount of data is not available in a certain area, the indicators cannot be calculated correctly.

[0005] An exemplary objective of the present disclosure is to provide a quality estimation system, a quality estimation method, and a program that can calculate an index with high accuracy even in an area with little data.

[0006] A quality estimation system according to a first aspect of the present disclosure includes: a context data generation unit that generates, from measurement data, a plurality of context data corresponding to each of a plurality of contexts; a first index calculation unit that generates, using the context data, first index data for each of the contexts and for each of the plurality of areas; an identification unit that identifies a second context similar to the first context based on a similarity between the first index data of the first context and first index data of a context included in the plurality of contexts and different from the first context; a second index calculation unit that determines, among the plurality of areas, an area for which the first index data is not generated as an unmeasured area, and uses the context data of the first context for areas other than the unmeasured areas, and uses the context data of the second context for the unmeasured areas, to generate second index data for the first context for each of the plurality of areas; and an output unit that outputs the second index data.

[0007] A quality estimation method according to a second aspect of the present disclosure includes generating, from measurement data, a plurality of context data corresponding to each of a plurality of contexts; generating first index data using the context data for each of the contexts and for each of the plurality of areas; identifying a second context similar to the first context based on a similarity between the first index data of the first context and first index data of a context included in the plurality of contexts and different from the first context; determining, among the plurality of areas, an area for which the first index data is not generated as an unmeasured area; using the context data of the first context for areas other than the unmeasured areas; and using the context data of the second context for the unmeasured areas to generate second index data for the first context for each of the plurality of areas; and outputting the second index data.

[0008] A program according to a third aspect of the present disclosure causes a computer to execute a process including: generating, from measurement data, a plurality of pieces of context data corresponding to each of a plurality of contexts; generating first index data using the context data for each of the contexts and for each of the plurality of areas; identifying a second context similar to the first context based on the similarity between the first index data of the first context and first index data of a context included in the plurality of contexts and different from the first context; determining, among the plurality of areas, an area for which the first index data is not generated as an unmeasured area; using the context data of the first context for areas other than the unmeasured areas; using the context data of the second context for the unmeasured areas to generate second index data for the first context for each of the plurality of areas; and outputting the second index data.

[0009] The quality estimation system, quality estimation method, and program according to the present disclosure can calculate indices with high accuracy even in areas with little data.

[0010] It is a block diagram showing an example of the configuration of a quality estimation system according to the present disclosure. It is a diagram showing a specific example of a measured / unmeasured map. It is a diagram showing a schematic diagram of calculation of similarity. It is a flowchart showing an operation procedure in the quality estimation system. It is a block diagram showing an example of the configuration of a computer device.

[0011] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the following description and drawings have been omitted and simplified as appropriate for clarity of explanation. In addition, in the following drawings, the same or similar elements are designated by the same reference numerals, and duplicate explanations are omitted as necessary.

[0012] An embodiment will be described. FIG. 1 is a block diagram showing an example configuration of a quality estimation system according to the present disclosure. The quality estimation system 100 shown in FIG. 1 includes a context data generation unit 101, a first QoE calculation unit 102, an identification unit 103, a second QoE calculation unit 104, and an output unit 105. The quality estimation system 100 may be configured using, for example, one or more devices, each having one or more processors and one or more memories. In the quality estimation system 100, the one or more processors may execute processing in accordance with instructions read from one or more memories, thereby realizing at least a portion of the functions of each unit in the quality estimation system 100.

[0013] In one embodiment, an example is described in which the index generated from the measurement data is the user's quality of experience. However, the present disclosure is not limited to this. The index generated from the measurement data may be radio wave quality or communication quality. The first QoE calculation unit 102 is also referred to as a first index calculation unit. The second QoE calculation unit 104 is also referred to as a second index calculation unit.

[0014] The context data generator 101 generates multiple pieces of context data corresponding to multiple contexts from the measurement data. Here, context means, for example, a specific situation or condition. Context data means, for example, a specified context, i.e., data that satisfies a specific situation or condition. The measurement data is data used to calculate QoE. The measurement data includes, for example, information such as time, location information such as latitude and longitude, data size, and communication session length. For example, in an application including video distribution, the measurement data may include video quality information and communication quality information. The video quality information may include, for example, information such as video size, video bit rate, and frame rate. The delay quality information may include, for example, information such as round trip time (RTT) and network throughput.

[0015] The context data generator 101 generates context data for each context, for example, by filtering the measurement data using a plurality of mutually different filtering conditions. The filtering conditions include, for example, communication conditions, environmental conditions, and movement conditions. The communication conditions include, for example, a communication carrier and a communication standard generation (such as 3rd generation (3G), 4th generation (4G), or 5th generation (5G)). The environmental conditions include, for example, day of the week, time, and weather. The movement conditions include speed, acceleration, and angular velocity.

[0016] The first QoE calculation unit 102 generates first QoE data for each context and for each area included in the plurality of areas using the context data. In one embodiment, the calculated QoE is not limited to a particular QoE. For example, the first QoE calculation unit 102 may calculate "Quality of Experience in Tele-operated Driving (ToD QoE)" as described in "Quality of experience (QoE) requirements for real-time multimedia services over 5G networks" of the International Telecommunication Union Telecommunication Standardization Sector (ITU-T) GSTR-5GQoE.

[0017] The first QoE calculation unit 102 may be unable to calculate the first QoE data in some areas, for example, due to a lack of context data. Such areas are also referred to as unmeasured areas. On the other hand, areas in which the first QoE data can be successfully calculated are also referred to as measured areas. The first QoE calculation unit 102 may interpolate the first QoE data by performing probabilistic spatial interpolation on the first QoE data calculated for each area. For example, the first QoE calculation unit 102 may interpolate the QoE of areas with a lack of context data by spatial interpolation using Kriging. The first QoE data calculated for each area is also referred to as a first QoE map.

[0018] The identification unit 103 identifies a second context similar to the first context based on the similarity between the first QoE data of the first context and the first QoE data of a context different from the first context. The identification unit 103 may, for example, calculate the similarity between statistics of the first QoE data of the first context and statistics of the first QoE data of a context different from the first context. The identification unit 103 may identify the second context based on the similarity of the calculated statistics.

[0019] More specifically, each area includes multiple subareas, and the first QoE calculation unit 102 calculates the QoE for each subarea for each area. The first QoE calculation unit 102 calculates the average value and variance of the QoE calculated for each subarea as statistics of the first QoE data for the area. The identification unit 103 calculates the similarity of statistics for the first context and the second context in a surrounding area, which is an area surrounding the unmeasured area. Here, the surrounding area may mean, for example, an area adjacent to the unmeasured area. The surrounding area may also be an area that borders the unmeasured area at a side or a vertex.

[0020] The identification unit 103 may calculate the similarity of the statistics for each of the multiple areas. The similarity of the statistics calculated for each area is also called a similarity map. The identification unit 103 identifies a second context similar to the first context based on the similarity of the statistics in the surrounding areas. For example, the identification unit 103 identifies, among contexts different from the first context, a context having the largest total or average similarity of the statistics in the surrounding areas as the second context similar to the first context. For each context in which an unmeasured area is included in the first QoE data, the identification unit 103 identifies a context in the unmeasured area that is similar to the context.

[0021] The second QoE calculation unit 104 adds context data of the second context for an unmeasured area of ​​the first context to generate second QoE data for the first context. That is, the second QoE calculation unit 104 calculates the second QoE data by using the context data of the first context for areas other than the unmeasured area and the context data of the second context for the unmeasured area. Note that the calculation of the second QoE data does not necessarily require the use of all of the context data of the second context for the area corresponding to the unmeasured area. For example, if the number of data points is larger than that of other areas, the second QoE calculation unit 104 may generate the second QoE data by using part of the context data of the second context for the area corresponding to the unmeasured area.

[0022] For each context in which an unmeasured area is included in the first QoE data, the second QoE calculation unit 104 calculates second QoE data using context data of a context similar to the unmeasured area. The second QoE calculation unit 104 may interpolate the second QoE data by performing probabilistic spatial interpolation on the second QoE data calculated for each area. For example, the second QoE calculation unit 104 may interpolate the QoE of an area with little context data by spatial interpolation using Kriging. The second QoE data is also referred to as a second QoE map.

[0023] The output unit 105 outputs the second QoE data. The output unit 105 displays the second QoE data of the context specified by the user on, for example, the screen of a display device. The output unit 105 may display the second QoE data overlaid on a map. The second QoE data overlaid on the map, i.e., the QoE map, can be used for consulting work or network control. For example, in consulting work, the QoE map may be provided to a telecommunications carrier. The telecommunications carrier can use the QoE map for network design, such as base station design. Furthermore, in network control, the QoE map can be used for control, such as switching a user equipment to a telecommunications carrier with better communication quality in real time while the user equipment is moving.

[0024] A specific example will be described below. Here, consider three contexts: context A, context B, and context C. The context data generation unit 101 generates, from the measurement data, context data A for context A, context data B for context B, and context data C for context C, which are subsets of the measurement data.

[0025] The first QoE calculation unit 102 generates first QoE data for context A using context data A. The first QoE calculation unit 102 generates first QoE data for context B using context data B. The first QoE calculation unit 102 generates first QoE data for context C using context data C. In generating the first QoE data, the first QoE calculation unit 102 may store, in a storage unit (not shown), information indicating whether each area had sufficient data for generating QoE data. The information indicating whether each area had sufficient data for generating QoE data is also called a measured / unmeasured map.

[0026] FIG. 2 is a diagram showing a specific example of a measured / unmeasured map. Nine areas, area 1 to area 9, are shown in FIG. 2. In FIG. 2, "measured" indicates that the QoE was able to be calculated. "unmeasured" indicates that the QoE could not be calculated due to reasons such as a lack of context data. In other words, "unmeasured" indicates that there is no context data at all or that the context data is insufficient. It is assumed that the measured / unmeasured map shown in FIG. 2 is a map for context C. In the example of FIG. 2, area 5 is an unmeasured area in context C.

[0027] The first QoE calculation unit 102 calculates statistics of the first QoE data for each area. For example, the first QoE calculation unit 102 calculates the QoE for each sub-area of ​​each area, and calculates the average value and variance of the calculated QoE for each area. The first QoE calculation unit 102 may probabilistically interpolate the first QoE data using Kriging or the like. In this case, the first QoE data and its statistics can be obtained even for unmeasured areas.

[0028] The identification unit 103 calculates the similarity between contexts for each area. In calculating the similarity, the identification unit 103 sets surrounding areas around unmeasured areas. For example, in the example of FIG. 2 , areas 1 to 4 and areas 6 to 9, which are adjacent to area 5 at vertices or edges, are set as surrounding areas. The identification unit 103 calculates the similarity of the statistics of the first QoE data between contexts for each area included in the surrounding areas. The identification unit 103 calculates, for example, cosine similarity. For example, the cosine similarity between context C and context A in a certain area can be expressed by the following formula. Here, x Ｃ is a vector indicating the statistics of context C, and x Ａ is a vector indicating the statistics of context A.

[0029] 3 is a diagram illustrating a schematic diagram of similarity calculation. The identification unit 103 calculates the similarity between context C and context A in the surrounding areas, and the similarity between context C and context B. The identification unit 103 calculates the similarity between the statistics of areas 1 to 4 and 6 to 9 of context C and the statistics of areas 1 to 4 and 6 to 9 of context A. The identification unit 103 also calculates the similarity between the statistics of areas 1 to 4 and 6 to 9 of context C and the statistics of areas 1 to 4 and 6 to 9 of context B. The identification unit 103 may calculate the similarity for areas in the surrounding areas where "measurement" is stored in both contexts.

[0030] The identification unit 103 calculates the sum of similarities in the surrounding areas for each context. The identification unit 103 compares the sum of similarities between context C and context A with the sum of similarities between context C and context B. Here, it is assumed that the sum of similarities between context C and context A is greater than the sum of similarities between context C and context B. In this case, the identification unit 103 identifies context A as a context similar to context C in the unmeasured area. If similarities have not been calculated in some of the surrounding areas, the identification unit 103 may calculate an average of the calculated similarities.

[0031] The second QoE calculation unit 104 calculates second QoE data for context C. In calculating the second QoE data, the second QoE calculation unit 104 adds context data of an area corresponding to an unmeasured area of ​​a similar context to context data C of context C. For example, if the similar context is context A, the second QoE calculation unit 104 adds data of area 5, which is an unmeasured area in context C, from context data A of context data A to context data C. In other words, the second QoE calculation unit 104 regards context data A of similar context A as context data C of context C in the unmeasured area of ​​context C, and generates the second QoE data.

[0032] The second QoE calculation unit 104 probabilistically interpolates the second QoE data using Kriging or the like. The output unit 105 displays the second QoE data calculated by the second QoE calculation unit 104 for context C as a map on a display screen or the like. If contexts A and B also have unmeasured areas, the same processing as above is performed on contexts A and B, and second QoE data for contexts A and B is calculated.

[0033] Next, the operation procedure will be described. Fig. 4 is a flowchart showing the operation procedure in the quality estimation system 100. The operation procedure in the quality estimation system 100 corresponds to a quality estimation method. The context data generation unit 101 generates context data for each context from measurement data (step A1). The first QoE calculation unit 102 generates first QoE data for each context and for each area using the context data (step A2).

[0034] The identification unit 103 identifies a second context similar to the first context based on the similarity between the first QoE data of the first context and the first QoE data of another context different from the first context (step A3). The second QoE calculation unit 104 generates second QoE data for each unmeasured area for the first context using the context data of the similar second context (step A4). In step A4, the second QoE calculation unit 104 generates second QoE data for areas other than the unmeasured area using the context data of the first context. The output unit 105 outputs the second QoE data (step A5).

[0035] In one embodiment, the first QoE calculation unit 102 generates first QoE data for each area based on the context data generated for each context. The first QoE calculation unit 102 also calculates statistics of the first QoE data for each area. The identification unit 103 calculates similarity between contexts for each area. If the first context has an unmeasured area, the identification unit 103 identifies a second context that has a high similarity in a surrounding area of ​​the unmeasured area. The second QoE calculation unit 104 generates second QoE data for the first context using context data of the similar second context for the unmeasured area.

[0036] In one embodiment, the second QoE calculation unit 104 utilizes similarity between contexts to generate QoE data for areas where sufficient context data is unavailable using context data from other similar contexts. The QoE data generated using context data from other similar contexts is considered to be more accurate than QoE data interpolated probabilistically. Therefore, the quality estimation system according to one embodiment can generate a QoE map with high accuracy and geographical coverage from a small amount of filtered context data.

[0037] Next, a description will be given of the physical configuration of the quality estimation system 100. Fig. 5 is a block diagram showing an example configuration of a computer device that can be used as the quality estimation system 100. The computer device 500 has a processor 510 such as a CPU (Central Processing Unit), a storage unit 520, a ROM (Read Only Memory) 530, a RAM (Random Access Memory) 540, a communication interface (IF) 550, and a user interface 560.

[0038] The communication interface 550 is an interface for connecting the computer device 500 to a communication network via wired communication means, wireless communication means, etc. The user interface 560 includes a display unit such as a display, and an input unit such as a keyboard, a mouse, and a touch panel.

[0039] The storage unit 520 is an auxiliary storage device that can store various types of data. The storage unit 520 does not necessarily have to be a part of the computer device 500, but may be an external storage device or cloud storage connected to the computer device 500 via a network.

[0040] The ROM 530 is a non-volatile storage device. For example, a semiconductor storage device with a relatively small capacity, such as a flash memory, is used for the ROM 530. The programs executed by the CPU 510 can be stored in the storage unit 520 or the ROM 530. The storage unit 520 or the ROM 530 stores various programs that realize the functions of each unit of the quality estimation system 100.

[0041] The program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include RAM, ROM, flash memory, solid-state drive (SSD) or other memory technologies, compact discs (CDs), digital versatile discs (DVDs), Blu-ray discs or other optical disc storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. The program may also be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0042] The RAM 540 is a volatile storage device. Various semiconductor memory devices such as DRAM (Dynamic Random Access Memory) or SRAM (Static Random Access Memory) are used for the RAM 540. The RAM 540 can be used as an internal buffer for temporarily storing data, etc. The CPU 510 loads a program stored in the storage unit 520 or the ROM 530 into the RAM 540 and executes the program. The CPU 510 executes the program, thereby realizing the functions of each unit in the quality estimation system 100. The CPU 510 may have an internal buffer for temporarily storing data, etc.

[0043] In the present disclosure, the quality estimation system 100 does not necessarily have to be configured as a single computer device. The quality estimation system 100 may be configured using multiple physically separated devices. The quality estimation system 100 may be configured as an application server, a Mobile / Multi-access Edge Computing (MEC) server, or an in-vehicle device.

[0044] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0045] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0046] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0047] [Supplementary Note 1] A quality estimation system comprising: a context data generation unit that generates a plurality of context data corresponding to each of a plurality of contexts from measurement data; a first index calculation unit that generates first index data using the context data for each of the contexts and for each area included in the plurality of areas; an identification unit that identifies a second context that is similar to the first context based on a similarity between first index data of the first context and first index data of a context that is included in the plurality of contexts and is different from the first context; a second index calculation unit that determines, as unmeasured areas, areas among the plurality of areas for which the first index data is not generated, and uses the context data of the first context for areas other than the unmeasured areas, and uses the context data of the second context for the unmeasured areas, to generate second index data for the first context for each of the plurality of areas; and an output unit that outputs the second index data.

[0048] [Supplementary Note 2] The quality estimation system according to Supplementary Note 1, wherein the identification unit calculates a similarity between a statistic of the first index data of the first context and a statistic of the first index data of a context different from the first context, and identifies the second context based on the calculated similarity of the statistic.

[0049] [Supplementary Note 3] The quality estimation system according to Supplementary Note 2, wherein the identification unit identifies the second context based on a similarity of the statistics in a surrounding area that is an area surrounding the unmeasured area.

[0050] [Supplementary Note 4] The quality estimation system according to Supplementary Note 3, wherein the identification unit calculates the similarity of the statistics for each area included in the surrounding area, and identifies, as the second context, a context different from the first context that has the largest sum or average similarity of the statistics in the surrounding area.

[0051] [Supplementary Note 5] The quality estimation system according to any one of Supplementary Notes 1 to 4, wherein the area includes a plurality of subareas, and the first index calculation unit calculates an index for each of the subareas for the area, and calculates the average value and variance of the index calculated for each of the subareas as statistics of the first index data for the area.

[0052] [Supplementary Note 6] The quality estimation system according to any one of Supplementary Notes 1 to 5, wherein the second index calculation unit interpolates the second index data calculated for each of the areas by performing probabilistic spatial interpolation on the second index data.

[0053] [Supplementary Note 7] The quality estimation system according to any one of Supplementary Notes 1 to 6, wherein the first index calculation unit interpolates the first index data by performing probabilistic spatial interpolation on the first index data calculated for each of the areas.

[0054] [Supplementary Note 8] The quality estimation system according to any one of Supplementary Notes 1 to 7, wherein the output unit displays the second index data by superimposing it on a map.

[0055] [Supplementary Note 9] The quality estimation system according to any one of Supplementary Notes 1 to 8, wherein the context data generation unit generates the context data for the plurality of contexts by filtering the measurement data under a plurality of filtering conditions that are different from each other.

[0056] [Supplementary Note 10] The quality estimation system according to any one of Supplementary Notes 1 to 9, wherein the first index calculation unit generates a first Quality of experience (QoE) as the first index data, and the second index calculation unit generates second QoE data as the second index data.

[0057] [Supplementary Note 11] A quality estimation method comprising: generating a plurality of context data corresponding to a plurality of contexts from measurement data; generating first index data for each of the contexts and for each area included in the plurality of areas using the context data; identifying a second context similar to the first context based on a similarity between the first index data of the first context and first index data of a context different from the first context included in the plurality of contexts; determining, among the plurality of areas, an area for which the first index data is not generated as an unmeasured area, and using the context data of the first context for areas other than the unmeasured areas; and generating second index data for the first context for each of the plurality of areas using the context data of the second context for the unmeasured areas; and outputting the second index data.

[0058] [Supplementary Note 12] The quality estimation method according to Supplementary Note 11, further comprising: calculating a similarity between a statistic of the first index data of the first context and a statistic of the first index data of a context different from the first context; and identifying the second context based on the calculated similarity of the statistic.

[0059] [Supplementary Note 13] The quality estimation method according to Supplementary Note 12, wherein the second context is identified based on a similarity of the statistics in a surrounding area that is an area surrounding the unmeasured area.

[0060] [Supplementary Note 14] The quality estimation method according to Supplementary Note 13, further comprising: calculating a similarity of the statistics for each area included in the surrounding area; and identifying, as the second context, a context different from the first context that has the largest sum or average similarity of the statistics in the surrounding area.

[0061] [Supplementary Note 15] The quality estimation method according to any one of Supplementary Notes 11 to 14, wherein the area includes a plurality of subareas, and an index is calculated for each of the subareas for the area, and an average value and variance of the index calculated for each of the subareas are calculated as statistics of the first index data for the area.

[0062] [Supplementary Note 16] The quality estimation method according to any one of Supplementary Notes 11 to 15, wherein the second index data calculated for each area is interpolated by performing probabilistic spatial interpolation on the second index data.

[0063] [Supplementary Note 17] The quality estimation method according to any one of Supplementary Notes 11 to 16, wherein the first index data calculated for each area is interpolated by performing probabilistic spatial interpolation on the first index data.

[0064] [Supplementary Note 18] The quality estimation method according to any one of Supplementary Notes 11 to 17, wherein the second index data is displayed superimposed on a map.

[0065] [Supplementary Note 19] The quality estimation method according to any one of Supplementary Notes 11 to 18, wherein the context data of the plurality of contexts is generated by filtering the measurement data under a plurality of filtering conditions that are different from each other.

[0066] [Supplementary Note 20] The quality estimation method according to any one of Supplementary Notes 11 to 19, wherein the first indicator data is a first Quality of experience (QoE), and the second indicator data is a second QoE data.

[0067] [Supplementary Note 21] A program for causing a computer to execute a process including: generating a plurality of context data corresponding to each of a plurality of contexts from measurement data; generating first index data using the context data for each of the contexts and for each area included in the plurality of areas; identifying a second context similar to the first context based on a similarity between first index data of the first context and first index data of a context different from the first context included in the plurality of contexts; determining, among the plurality of areas, an area for which the first index data is not generated as an unmeasured area, and using the context data of the first context for areas other than the unmeasured areas; and generating second index data for the first context for each of the plurality of areas; and outputting the second index data.

[0068] [Supplementary Note 22] The program according to Supplementary Note 21, wherein the processing includes calculating a similarity between a statistic of the first index data of the first context and a statistic of the first index data of a context different from the first context, and identifying the second context based on the calculated similarity of the statistic.

[0069] [Supplementary Note 23] The program according to Supplementary Note 22, wherein the processing includes identifying the second context based on a similarity of the statistics in a surrounding area that is an area surrounding the unmeasured area.

[0070] [Supplementary Note 24] The program according to Supplementary Note 23, wherein the processing includes: calculating the similarity of the statistics for each area included in the surrounding area; and identifying, as the second context, a context different from the first context that has the largest sum or average similarity of the statistics in the surrounding area.

[0071] [Supplementary Note 25] The program according to any one of Supplementary Notes 21 to 24, wherein the area includes a plurality of subareas, and the processing includes calculating an index for each of the subareas for the area, and calculating an average value and a variance of the index calculated for each of the subareas as statistics of the first index data for the area.

[0072] [Supplementary Note 26] The program according to any one of Supplementary Notes 21 to 25, wherein the processing includes interpolating the second index data calculated for the area by performing probabilistic spatial interpolation on the second index data.

[0073] [Supplementary Note 27] The program according to any one of Supplementary Notes 21 to 26, wherein the processing includes interpolating the first index data by performing probabilistic spatial interpolation on the first index data calculated for each of the areas.

[0074] [Supplementary Note 28] The program according to any one of Supplementary Notes 21 to 27, wherein the processing includes displaying the second index data by overlaying it on a map.

[0075] [Supplementary Note 29] The program according to any one of Supplementary Notes 21 to 28, wherein the processing includes generating the context data of the plurality of contexts by filtering the measurement data using a plurality of filtering conditions that are different from each other.

[0076] [Supplementary Note 30] The program according to any one of Supplementary Notes 21 to 29, wherein the first index data is a first Quality of experience (QoE), and the second index data is second QoE data.

[0077] Some or all of the elements described in any appendix may be applied to a variety of hardware, software, recording means for recording software, systems, and methods.

[0078] This application claims priority based on Japanese Patent Application No. 2024-092754, filed on June 7, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0079] 100: Quality estimation system 101: Context data generation unit 102: First QoE calculation unit 103: Identification unit 104: Second QoE calculation unit 105: Output unit 500: Computer device 510: Processor 520: Storage unit 530: ROM 540: RAM 550: Communication IF 560: User IF

Claims

1. A quality estimation system comprising: a context data generation unit that generates multiple pieces of context data corresponding to multiple contexts from measurement data; a first index calculation unit that generates first index data using the context data for each of the contexts and for each area included in the multiple areas; an identification unit that identifies a second context that is similar to the first context based on the similarity between the first index data of the first context and first index data of a context different from the first context included in the multiple contexts; a second index calculation unit that determines, among the multiple areas, those areas for which the first index data is not generated as unmeasured areas, and uses the context data of the first context for areas other than the unmeasured areas, and uses the context data of the second context for the unmeasured areas, to generate second index data for the first context for each of the multiple areas; and an output unit that outputs the second index data.

2. The quality estimation system according to claim 1, wherein the identification unit calculates a similarity between a statistic of the first index data of the first context and a statistic of the first index data of a context different from the first context, and identifies the second context based on the calculated similarity of the statistic.

3. The quality estimation system according to claim 2, wherein the identification unit identifies the second context based on the similarity of the statistics in a surrounding area that is an area surrounding the unmeasured area.

4. The quality estimation system described in claim 3, wherein the identification unit calculates the similarity of the statistics for each area included in the surrounding area, and identifies as the second context the context different from the first context that has the largest sum or average similarity of the statistics in the surrounding area.

5. A quality estimation system as claimed in any one of claims 1 to 4, wherein the area includes a plurality of subareas, and the first index calculation unit calculates an index for each subarea of ​​the area, and calculates the average value and variance of the index calculated for each subarea as statistics of the first index data in the area.

6. A quality estimation system as claimed in any one of claims 1 to 5, wherein the second index calculation unit interpolates the second index data by performing probabilistic spatial interpolation on the second index data calculated for each area.

7. A quality estimation system as claimed in any one of claims 1 to 6, wherein the first index calculation unit interpolates the first index data by performing probabilistic spatial interpolation on the first index data calculated for each area.

8. A quality estimation system according to any one of claims 1 to 7, wherein the output unit displays the second index data superimposed on a map.

9. A quality estimation system according to any one of claims 1 to 8, wherein the context data generation unit generates the context data for the plurality of contexts by filtering the measurement data using a plurality of mutually different filtering conditions.

10. A quality estimation system as claimed in any one of claims 1 to 9, wherein the first index calculation unit generates a first Quality of experience (QoE) as the first index data, and the second index calculation unit generates second QoE data as the second index data.

11. A quality estimation method comprising: generating a plurality of context data corresponding to a plurality of contexts from measurement data; generating first index data for each of the contexts and for each area included in the plurality of areas using the context data; identifying a second context similar to the first context based on the similarity between the first index data of the first context and first index data of a context included in the plurality of contexts and different from the first context; determining, among the plurality of areas, areas for which the first index data is not generated as unmeasured areas, and using the context data of the first context for areas other than the unmeasured areas; and generating second index data for the first context for each of the plurality of areas using the context data of the second context for the unmeasured areas; and outputting the second index data.

12. The quality estimation method according to claim 11, further comprising calculating a similarity between a statistic of the first index data of the first context and a statistic of the first index data of a context different from the first context, and identifying the second context based on the calculated similarity of the statistic.

13. The quality estimation method according to claim 12, wherein the second context is identified based on a similarity of the statistics in a surrounding area that is an area surrounding the unmeasured area.

14. The quality estimation method according to claim 13, further comprising: calculating the similarity of the statistical quantities for each area included in the surrounding area; and identifying, as the second context, a context different from the first context that has the largest sum or average similarity of the statistical quantities in the surrounding area.

15. A quality estimation method according to any one of claims 11 to 14, wherein the area includes a plurality of subareas, and an index is calculated for each of the subareas for the area, and the average value and variance of the index calculated for each of the subareas are calculated as statistics of the first index data in the area.

16. A quality estimation method according to any one of claims 11 to 15, wherein the second index data is interpolated by performing probabilistic spatial interpolation on the second index data calculated for each area.

17. A quality estimation method according to any one of claims 11 to 16, wherein the first index data is interpolated by performing probabilistic spatial interpolation on the first index data calculated for each area.

18. A quality estimation method according to any one of claims 11 to 17, wherein the second index data is displayed superimposed on a map.

19. A quality estimation method according to any one of claims 11 to 18, wherein the context data for the plurality of contexts is generated by filtering the measurement data using a plurality of filtering conditions that are different from each other.

20. A program for causing a computer to execute a process including: generating, from measurement data, a plurality of context data corresponding to each of a plurality of contexts; generating first index data using the context data for each of the contexts and for each of the plurality of areas; identifying a second context similar to the first context based on the similarity between the first index data of the first context and first index data of a context different from the first context included in the plurality of contexts; determining, among the plurality of areas, areas for which the first index data is not generated as unmeasured areas, and using the context data of the first context for areas other than the unmeasured areas; generating second index data for the first context for each of the plurality of areas; and outputting the second index data.

Images