Information processing device and information processing method

The information processing device addresses inconsistent sensor data issues by generating a whitelist based on missing value analysis, ensuring accurate service provision on mobile terminals with varying configurations, thus enhancing service reliability and reducing complaints.

JP7589735B2Active Publication Date: 2024-11-26SONY GROUP CORP
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
JP2022508031
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-03-17
Filing Date
2020-07-20
Publication Date
2024-11-26
Estimated Expiration
2040-07-20

AI Technical Summary

Technical Problem

Existing technologies face challenges in accurately determining whether a mobile terminal can provide services due to varying hardware configurations across different manufacturers, models, and OS types, leading to inconsistent and potentially missing sensor data detection results.

Method used

An information processing device and method that generates a missing histogram from sensor data, calculates a missing value, and compares it against a threshold to create a whitelist of compatible terminals, ensuring accurate service provision by identifying suitable devices based on manufacturer, model, sensor type, and OS version.

Benefits of technology

Enables low-cost, high-accuracy determination of a mobile terminal's capability to provide services, preventing improper service provision and reducing user complaints by ensuring reliable sensor data detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007589735000002
    Figure 0007589735000002
  • Figure 0007589735000003
    Figure 0007589735000003
  • Figure 0007589735000004
    Figure 0007589735000004
Patent Text Reader

Abstract

The present disclosure relates to an information processing device, an information processing method, and a program that enable, upon delivery of a service using a mobile terminal, highly precise and low-cost determination of whether or not the service can be provided to the mobile terminal being used. The information processing device calculates a loss value indicating a degree of loss of data detected in a communication terminal, and generates a white list associated with a query comprising a manufacturer, a model, OS version information, and the like of a communication terminal of which the loss value is smaller than a predetermined threshold and the degree of loss is small. When delivery of a service based on data detected in the communication terminal is requested by the communication terminal, the information processing device searches the white list for the query and determines whether the delivery of the service is possible or not. The present disclosure may be applied to a system providing a service based on a detection result from a sensor mounted on a smartphone.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to an information processing device and an information processing method, and more particularly to an information processing device and an information processing method that, when providing a service using a mobile terminal, are capable of determining at low cost and with high accuracy whether a mobile terminal to be used is capable of providing a service. [Background technology]

[0002] Technologies have been proposed that provide specific services by using the detection results of sensors mounted on portable communication terminals such as smartphones.

[0003] For example, one service offered by an automobile insurance company may be to detect the driver's driving state (driving condition) using various sensors built into the smartphone carried by the driver who is the insured person, and then provide a discount on insurance premiums according to the driving condition.

[0004] In other words, if the detection results of the sensor on the policyholder's smartphone indicate that the driver normally drives calmly, the insurance company may offer a service such as a discount on the insurance premium, since the accident occurrence rate is expected to be lower than usual.

[0005] As a technology for realizing the provision of such services, a technology has been proposed that classifies the behavioral patterns of users who own mobile devices such as smartphones based on the detection results of sensors built into the devices (see Patent Document 1). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] International Publication No. 2014 / 136466 Summary of the Invention [Problem to be solved by the invention]

[0007] However, there are countless manufacturers, models, and OS types of mobile devices such as smartphones, and each device has a different hardware configuration, such as sensors and processors, so it may not be possible to obtain appropriate detection results.

[0008] For example, in the case of a mobile terminal whose processor has a processing capacity higher than a specified capacity, a detection result can be obtained at a specified frequency, but in the case of a mobile terminal whose processor has a processing capacity lower than the specified capacity, a detection result cannot be obtained at the specified frequency, resulting in a missing state.

[0009] When this missing state occurs, the user's behavioral patterns cannot be properly recognized. For example, in the case of an insurance premium discount service, even if the policyholder's usual driving habits are actually calm, the policyholder may not be able to receive the insurance premium discount service because the policyholder's usual driving habits are not properly recognized.

[0010] In other words, depending on the manufacturer, model, and type of OS of the mobile device owned by the user, a missing state may occur, and detection results sufficient to recognize the behavior of the user who owns the mobile device may not be obtained, which may make it impossible to provide appropriate services.

[0011] The present disclosure has been made in consideration of such circumstances, and in particular, when providing a service using a mobile terminal, it is possible to determine at low cost and with a high degree of accuracy whether the mobile terminal being used is capable of providing the service. [Means for solving the problem]

[0012] An information processing device according to one aspect of the present disclosure is an information processing device that determines whether a predetermined service can be provided to a service receiving terminal, and includes: a loss histogram including the number of occurrences of loss times for sensor data detected by a plurality of communication terminals equipped with sensors, the sensor data being collected from the communication terminals; generating a loss value representing a degree of loss in the sensor data based on a continuous drive time related to the measurement of the loss histogram;Terminal information of the communication terminal associated with the defect histogram A comparison of the missing value with a predetermined threshold value required by the communication terminal to receive the predetermined service for each of the plurality of communication terminals. and a determination unit that, in response to a request for provision of the specified service and the terminal information of the service receiving terminal sent from the service receiving terminal requesting the provision of the specified service, determines whether or not the specified service can be provided to the service receiving terminal by referring to the list generated by the list generation unit.

[0013] An information processing method according to one aspect of the present disclosure is an information processing method of an information processing device that determines whether a predetermined service can be provided to a service receiving terminal, the information processing method including: a loss histogram including a number of occurrences of loss times for sensor data collected from a plurality of communication terminals equipped with sensors and detected by the communication terminals, the loss times being related to a time when the sensor data is lost; generating a loss value representing a degree of loss in the sensor data based on a continuous drive time related to the measurement of the loss histogram; Terminal information of the communication terminal associated with the defect histogram A comparison of the missing value with a predetermined threshold value required by the communication terminal to receive the predetermined service for each of the plurality of communication terminals. and performing a determination process for determining whether or not the specified service can be provided to the service receiving terminal by referring to the list generated in the list generation process in response to a request for the provision of the specified service and the terminal information of the service receiving terminal sent from the service receiving terminal requesting the provision of the specified service.

[0014] In one aspect of the present disclosure, a loss histogram is formed by counting the number of occurrences of each loss time regarding a time when sensor data is lost and the sensor data is detected by a plurality of communication terminals each having a sensor; generating a loss value representing a degree of loss in the sensor data based on a continuous drive time related to the measurement of the loss histogram; Terminal information of the communication terminal associated with the defect histogram A comparison of the missing value with a predetermined threshold value required by the communication terminal to receive the predetermined service for each of the plurality of communication terminals.Based on this, a list including terminal information for which the specified service can be provided is generated, and in response to a request for the provision of the specified service and the terminal information of the service receiving terminal sent from the service receiving terminal requesting the provision of the specified service, the generated list is referenced to determine whether or not the specified service can be provided to the service receiving terminal. [Brief description of the drawings]

[0015] [Figure 1] FIG. 1 is a diagram illustrating a discount service for automobile insurance premiums. [Diagram 2] 10A to 10C are diagrams illustrating an example of a detection result by an acceleration sensor. [Diagram 3] FIG. 13 is a diagram illustrating a Forbidden signal. [Figure 4] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to the present disclosure. [Diagram 5] FIG. 2 is a diagram illustrating an example of the configuration of a data collection terminal. [Figure 6] FIG. 2 is a diagram illustrating an example of the configuration of a server. [Figure 7] FIG. 2 is a diagram illustrating an example of the configuration of a service receiving terminal. [Figure 8] 5 is a diagram for explaining functions realized by the information processing system of FIG. 4. [Figure 9] 11A to 11C are diagrams illustrating an example of an interpolation process for a detection result by an acceleration sensor. [Figure 10] FIG. 13 is a diagram illustrating an allowable defect histogram. [Figure 11] FIG. 13 is a diagram illustrating a normalized defect tolerance histogram and weighting coefficients. [Figure 12] FIG. 13 is a diagram illustrating an allowable missing value. [Figure 13] FIG. 13 is a diagram illustrating an example of a whitelist. [Figure 14] 11 is a flowchart illustrating a whitelist generation process. [Figure 15] 11 is a flowchart illustrating a service providing process. [Figure 16]FIG. 1 is a diagram illustrating an example of the configuration of a general-purpose personal computer. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.

[0017] Hereinafter, an embodiment of the present technology will be described in the following order. 1. Overview of this Disclosure 2. Preferred Embodiments 3. Software implementation example

[0018] <<1. Overview of this Disclosure>> The present disclosure is directed to determining, at low cost and with high accuracy, whether or not a mobile terminal to be used is capable of providing a service when providing a service using the mobile terminal.

[0019] Here, as an example of a service provided using a mobile terminal, we will explain an insurance premium discount service provided by an automobile insurance company that is based on the driving pattern of a driver who is the policyholder, as recognized based on the detection results detected by various sensors on the driver's mobile terminal.

[0020] Standard automobile insurance premiums are set based on the general probability of an accident occurring.

[0021] However, the probability of an accident occurring is not necessarily the same depending on the driving pattern (driving habits) of the driver who is the policyholder.

[0022] In other words, if a driver's driving pattern shows that he or she normally follows traffic rules strictly, the probability of the driver having an accident is expected to be lower than the general probability of the driver having an accident.

[0023] In addition, if a driver's driving patterns show that he or she does not deviate from traffic rules in normal driving but frequently makes sudden starts or brakes, the probability of that driver having an accident is expected to be higher than the general probability of accidents.

[0024] Therefore, if a driver's usual driving pattern involves strictly following traffic rules, the probability of an accident occurring is expected to be lower than in general, so insurance premiums should be set lower than general insurance premiums.

[0025] The automobile insurance premium discount service was created in consideration of this situation. It detects the driver's driving pattern and, if the driver normally follows traffic rules strictly, it is predicted that the probability of an accident occurring is lower than normal, so the service discounts a specified amount from the regular insurance premium to make up for this.

[0026] In other words, as shown in Figure 1, driver H2, who is an insured person who owns vehicle C2 and whose normal driving does not deviate from traffic rules but who frequently makes sudden starts and brakes, will be charged the standard insurance premium F2.

[0027] In contrast, for driver H1, who is an insured who owns a vehicle C1 and fully observes traffic rules in his or her normal driving, a specified amount of cashback CB is made from the general insurance premium F2, making the premium F1 essentially a discount on the premium F2.

[0028] This is a discount service for insurance premiums provided by automobile insurance companies using the detection results of various sensors built into the driver's mobile terminal.

[0029] In order to realize a discount service for automobile insurance premiums, it is necessary to detect the driving patterns of the driver who is the policyholder.

[0030] A method of detecting the driver's driving pattern may involve providing a dedicated acceleration sensor, or determining the pattern from the displacement of the vehicle's own position in a car navigation system.

[0031] Here, if a dedicated acceleration sensor or car navigation system is used, the cost of the device will be high, and in the case of car navigation systems, there is a risk that the applicable vehicle models will be limited.

[0032] Therefore, in recent years, as communication terminals such as smartphones have become more widespread, it has been proposed to register the smartphones owned by each driver and use the detection results of various sensors such as acceleration sensors, gyro sensors, and GPS sensors installed on the registered smartphones.

[0033] However, smartphones may differ in hardware configuration (such as manufacturer, model, and type of sensor installed) and in type and version of OS (Operating System), and processing capabilities may differ depending on the respective conditions, so it may not be possible to obtain consistently appropriate detection results.

[0034] For example, if a smartphone is equipped with an acceleration sensor and configured to perform detection operations at 50 Hz, i.e., to detect acceleration at intervals of 0.02 sec, a detection result D1 such as that shown in the left part of Figure 2 may be obtained.

[0035] In the detection result D1, the detection times are shown from top to bottom on the left side, and the accelerations detected at the corresponding times are shown on the right side.

[0036] More specifically, in detection result D1, from the top, at time 4.997, an acceleration of 0.071 is detected, at time 5.014, an acceleration of 0.016 is detected, at time 5.034, an acceleration of 0.029 is detected, and at time 5.064, an acceleration of 0.048 is detected.

[0037] Furthermore, at time 5.074, an acceleration of 0.046 is detected, at time 3.508, an acceleration of 0.040 is detected, and at time 3.529, an acceleration of 0.041 is detected.

[0038] Furthermore, at time 3.566, accelerations of 0.046 and 0.042 are detected, at time 3.588, acceleration 0.036 is detected, at time 3.606, acceleration 0.044 is detected, and at time 3.641, acceleration 0.049 is detected.

[0039] In the data T1 enclosed by the dotted line, the next time after time 5.074 is time 3.508, which is not 0.02 seconds apart. This is a deviation caused by, for example, the GPS sensor reacquiring and correcting time information based on a signal from a satellite at the timing after time 5.074, or changing Japan time to the time of another country.

[0040] As a result, as shown by data T1, the time interval between time 5.074 and time 3.508 is not 0.02 sec but is 1.4 sec or more, and therefore cannot be treated as appropriate data.

[0041] In addition, in data T2 enclosed by a dotted line, two detection results of acceleration, 0.046 and 0.042, are obtained at the same time, 3.566.

[0042] This is caused, for example, by a high processing load on the processor, which causes a delay in reading out the acceleration detection results stored in the memory, resulting in two results being output at the same time.

[0043] As a result, data T2 cannot be treated as appropriate data either.

[0044] Therefore, the data output from the smartphone is subjected to data cleansing, for example, as shown in the detection result D2 in the center of FIG.

[0045] That is, in the detection result D2, the time interval in the data T1 is set to 0.02 sec and the subsequent times are corrected, thereby performing data cleansing.

[0046] That is, in data T11 surrounded by a dotted line and corresponding to data T1, the time following time 5.074 is from time 3.508 to time 5.094, which is an interval of 0.02 seconds, and thereafter the intervals are also 0.02 seconds.

[0047] However, even in the case of detection result D2, in data T12 which corresponds to data T2 of detection result D1, the time following time 5.135 is time 5.152, and the time interval is 0.017. Also, as shown in data T13, the time following time 5.152 is time 5.174, and the time interval is 0.022. Furthermore, the time following time 5.174 is time 5.192, and the time interval is 0.018, and the time interval is not corrected to 0.02 sec.

[0048] This is a deviation caused by jitter that occurs when obtaining time information via the OS.

[0049] Therefore, the detection result D2 is further corrected for time information to have intervals of 0.02 sec, starting from the time 5.000, and the corresponding acceleration is interpolated, so that the data is cleansed like the detection result D3.

[0050] In this way, the detection results obtained by the sensor installed in the smartphone may not always be accurate at appropriate time intervals, and various corrections may be required.

[0051] However, some services and algorithms required for certain services require real-time processing using the detection results of sensors. However, values ​​calculated by data cleansing are merely estimates based on previous and subsequent information, and especially when the missing period is long, the estimated values ​​calculated by data cleansing are unreliable. For this reason, it is necessary to avoid using the detection results of models that have frequent missing periods.

[0052] Therefore, for example, when an acceleration detection result D11 as shown in FIG. 3 is obtained, a Forbidden signal is generated for data F1 having a time interval that is out of sync, so that the data is not used in subsequent processing.

[0053] In the detection result D11 of Figure 3, from top to bottom, at time 48.582, an acceleration of 0.362846 is detected, at time 48.602, an acceleration of 0.254973 is detected, at time 48.622, an acceleration of 0.333426 is detected, at time 48.642, an acceleration of 0.1471 is detected, at time 48.663, an acceleration of 0.353039 is detected, and at time 48.684, an acceleration of 0.05884 is detected.

[0054] Furthermore, at time 48.705, an acceleration of 0.441299 was detected, at time 272.404, an acceleration of 0.460913 was detected, at time 272.421, an acceleration of 0.254973 was detected, at time 272.441, an acceleration of 0.009807 was detected, at time 272.461, an acceleration of 0.284393 was detected, and at time 272.481, an acceleration of 0.333426 was detected.

[0055] In data F1, the next time after time 48.705 is time 272.404, and the time interval is not 0.02 sec. In such a case, data cleansing is possible by interpolation, but since it is an interpolation result, the reliability of the data decreases if there is a loss of a certain amount of time or more.

[0056] For this reason, when the time period during which data loss occurred is longer than a predetermined time, as in the case of data F1, a Forbidden signal is given to the data so that it is not used in processing.

[0057] However, if data with a Forbidden signal is generated more frequently than a certain frequency, the application program will not be able to process it appropriately, and as a result, it will not be possible to provide services using the detection results of the sensor installed in the smartphone.

[0058] Therefore, when an application program is installed and a service is requested, it is necessary to determine whether the smartphone is capable of providing the service by the application program based on the frequency of occurrence of a Forbidden signal.

[0059] However, since the frequency of occurrence of the Forbidden signal needs to be measured during a predetermined drive time, it is not possible to know the frequency immediately at the time when the provision of the service is requested.

[0060] Therefore, in the present disclosure, for each query that is a combination of the smartphone manufacturer, type, model, and sensor model number, as well as the OS type and OS version, a list is registered along with information indicating in advance whether the service can be provided based on a missing state in which data longer than a specified period of time is lost, and when the service is requested, the corresponding query is searched from the list to determine whether the smartphone is capable of providing the service.

[0061] As a result, when a service is requested by a user, it is possible to immediately and accurately determine and notify whether the smartphone is capable of providing the service.

[0062] As a result, when a service is provided, it is possible to properly obtain the detection results of the sensor built into the user's smartphone, thereby enabling the provision of an appropriate service.

[0063] In addition, when a service is requested and an appropriate service cannot be provided depending on the smartphone model, etc., it is possible to notify the user that the appropriate service cannot be provided before the service is provided. This makes it possible to prevent situations in which the detection results from the smartphone's sensors cannot be obtained properly and the appropriate service cannot be provided.

[0064] Furthermore, it will be possible to reduce the occurrence of complaints from users due to the inability to properly obtain detection results from the smartphone sensor and therefore to provide services appropriately, thereby reducing the costs associated with responding to complaints about the provision of services.

[0065] <<2. Preferred embodiment>> <Example of information processing system configuration> Next, with reference to the block diagram of FIG. 4, a configuration example of an information processing system to which the technology of the present disclosure is applied will be described.

[0066] The information processing system 11 in Figure 4 will be described as providing a discount service for automobile insurance premiums, but the system may be configured to provide other services as long as the services are based on information detected by a sensor in a mobile terminal.

[0067] The information processing system 11 in FIG. 4 is composed of data collection terminals 31-1 to 31-n, a server 32, and service receiving terminals 33-1 to 33-m, and the data collection terminals 31-1 to 31-n, the server 32, and the service receiving terminals 33-1 to 33-m are electrically connected by a network 34 such as the Internet, and are configured to be able to communicate with each other.

[0068] Incidentally, the data collection terminals 31-1 to 31-n and the service receiving terminals 33-1 to 33-m will be simply referred to as the data collection terminal 31 and the service receiving terminal 33 when there is no particular need to distinguish between them.

[0069] In addition, the data collection terminals 31-1 to 31-n and the service receiving terminals 33-1 to 33-m are so-called smartphones or the like that have basically the same functions, and are portable communication terminals that include a variety of manufacturers, models, sensor types, OS types, and OS versions.

[0070] In this embodiment, the data collection terminal 31 is a communications terminal that is not used to provide the above-mentioned insurance premium discount service, and the service receiving terminal 33 is a communications terminal that is used to provide the above-mentioned insurance premium discount service.

[0071] The data collection terminal 31 has various built-in sensors and detects various information for recognizing the behavior of the user who owns it, in this example, the driving pattern (driving state) when the user who owns it drives a car.

[0072] The sensors built into the data collection terminal 31 include, for example, an acceleration sensor, a gyro sensor, a geomagnetic sensor, an air pressure sensor, a microphone, a light quantity sensor, a human presence sensor, and a position sensor (for example, a GPS sensor), but are not limited to these and also include other sensors.

[0073] In this embodiment, the explanation will be given on the assumption that the data collection terminal 31 is equipped with an acceleration sensor, a gyro sensor, and a position sensor to detect the driving state of the driver, but this is not limited to this.

[0074] The data collection terminal 31 uses various sensors to detect various detection results used to recognize the driving state when the user who owns the terminal is driving the car, at predetermined time intervals, and generates information indicating the degree of data loss that occurs when the above-mentioned Forbidden signal is detected.

[0075] More specifically, the data collection terminal 31 obtains an allowable loss histogram consisting of loss times, which are times when data is lost in the sensor detection results, and the number of occurrences of each loss time, as information indicating the degree of data loss.

[0076] Then, the data collection terminal 31 associates terminal information consisting of the name of the manufacturer that produced the terminal, the model name, the model name, the sensor model number, the OS type, and the OS version information with the allowable defect histogram, and outputs the result to the server 32 together with the continuous operating time for measuring the allowable defect histogram.

[0077] The server 32 is a server computer managed and operated by an automobile insurance company, and acquires the allowable loss histograms and continuous drive times supplied from the data collection terminals 31-1 to 31-n via a network 34.

[0078] In addition, the server 32 forms a query for each combination of the manufacturer name, model name, model number of the built-in sensor (hereinafter simply referred to as the sensor model number), OS type, and OS version that are associated with the allowable defect histogram and continuous operation time, and stores the queries in association with the allowable defect histogram and continuous operation time.

[0079] Furthermore, the server 32 generates an allowable missing value that scalarizes the degree of data missing based on the allowable missing value and the continuous driving time, and determines whether or not a discount service can be provided based on the allowable missing value, and generates a list of the determination results for each query as a whitelist.

[0080] The service receiving terminal 33 is a mobile terminal carried by the policyholder of the above-mentioned automobile insurance, and when requesting the provision of a discount service for the policyholder's insurance premium, the service receiving terminal 33 accesses the server 32 and requests the provision of the discount service for the insurance premium along with information on the policyholder's manufacturer name, model name, model name, and sensor model number, as well as the OS type and OS version.

[0081] When a request for an insurance premium discount service is received from the service receiving terminal 33, the server 32 searches the whitelist for a query corresponding to the combination of information supplied, such as the manufacturer name, model name, and sensor model number of the service receiving terminal 33, as well as the OS type and OS version, and determines whether or not it is possible to provide an insurance premium discount service based on the information on whether or not the service can be provided that is registered in correspondence with the searched query.

[0082] If a query corresponding to a combination of information such as the manufacturer name, model name, model name, and sensor model number of the service receiving terminal 33 requesting the provision of an insurance premium discount service, as well as the OS type and OS version, is registered in the whitelist and information indicating that the discount service can be provided is registered, the server 32 assumes that the insurance premium discount service can be provided, accepts the request for service provision, and notifies the service receiving terminal 33 that has requested the provision of the insurance premium discount service that the discount service can be provided.

[0083] When the provision of the service is accepted, the service receiving terminal 33 detects various detection results from its built-in acceleration sensor, gyro sensor, GPS sensor, etc., to recognize the driving state of the user who is the policyholder, at predetermined time intervals and supplies the results to the server 32.

[0084] Based on the detection results supplied from the service receiving terminal 33, the server 32 recognizes the driving state of the insurance policyholder who possesses the service receiving terminal 33, calculates the amount of discount on the insurance premium according to the recognition result, and provides an insurance premium discount service such as a cash back.

[0085] In such a case, the insurance policyholder who has the service receiving terminal 33 can receive a discount on the insurance premium according to the driving condition.

[0086] On the other hand, if a query corresponding to the combination of information such as the manufacturer name, model name, model name, and sensor model number of the service receiving terminal 33 requesting the provision of the insurance premium discount service, as well as the OS type and OS version, is not searched for in the whitelist (or is searched for in the whitelist but the service is registered as unavailable), the server 32 determines that it is unable to properly detect the driving condition of the owner of the service receiving terminal 33, who is the insurance policyholder, based on the detection results supplied by the service receiving terminal 33 requesting the provision of the insurance premium discount service, and does not accept the request for service provision and notifies the service receiving terminal 33 that it is unable to provide the insurance premium discount service.

[0087] In this case, the insurance policyholder who possesses the service receiving terminal 33 will be unable to receive the insurance premium discount service according to the driving condition.

[0088] That is, through a series of processes of the information processing system 11 in Figure 4, an allowable missing value is calculated for each query corresponding to a combination of manufacturer name, model name, model name, sensor model number, OS type, and OS version based on the detection results supplied from multiple data collection terminals 31-1 to 31-n, and a query that is lower than a predetermined allowable missing value, that is, a query that identifies a smartphone among the data collection terminals 31-1 to 31-n that can supply to the server 32 detection results that can properly detect the driving state when carried by the policyholder while driving, is registered in the whitelist.

[0089] As a result, when a discount service is requested, whether or not the discount service can be provided is immediately determined based on whether a query corresponding to the combination of the manufacturer name, model name, model name, and sensor model number of the smartphone requesting the discount service, as well as the OS type and OS version, is registered on the whitelist as a query for which a discount service can be provided.

[0090] As a result, in the information processing system 11 of Figure 4, each of the multiple data collection terminals 31 has various sensors built in, and generates an allowable loss histogram as information indicating the degree of data loss in the detection results, and transmits it to the server 32 together with terminal information consisting of its own manufacturer name, model name, and sensor model number, as well as OS type and OS version, and information on continuous operation time.

[0091] The server 32 statistically processes the allowable missing value histogram and continuous operating time supplied from the data collection terminal 31 for each query corresponding to the terminal information to determine an allowable missing value, and by comparing the allowable missing value with a threshold value, generates a whitelist that identifies queries corresponding to terminal information consisting of the manufacturer name, model name, sensor model number, OS type, and OS version, which can obtain the detection results necessary to realize the insurance premium discount service.

[0092] When a discount service is requested from the service receiving terminal 33, the server 32 searches the whitelist for a query corresponding to the terminal information consisting of the manufacturer name, model name, model name, and sensor model number of the service receiving terminal 33 for which the discount service is requested, as well as the OS type and OS version, and determines whether the service can be provided based on whether the query is searched for as a query for which the service can be provided, and notifies the service receiving terminal 33 of the determination result.

[0093] Here, if the query is found from the whitelist as one for which a discount service can be provided, the service receiving terminal 33 can receive the discount service for the insurance premium based on its own detection result.

[0094] That is, in the information processing system 11 of Figure 4, the server 32 generates in advance a whitelist indicating the determination result of whether or not an insurance premium discount service can be provided for each query corresponding to terminal information consisting of a combination of information such as manufacturer name, model name, sensor model number, OS type, and OS version, based on the information supplied from the data collection terminal 31.

[0095] In the server 32, when the provision of an insurance premium discount service is requested by the service receiving terminal 33, a query corresponding to the terminal information consisting of a combination of information such as the manufacturer name, model name, model name, sensor model number, OS type, and OS version is searched from a whitelist generated in advance, and based on the search result, it is determined whether or not the provision of an insurance premium discount service is possible.

[0096] As a result, when an insurance premium discount service is requested by a service receiving terminal 33 requesting the provision of the insurance premium discount service, the server 32 searches for the terminal information of the service receiving terminal 33 based on the whitelist, making it possible to immediately determine whether or not the insurance premium discount service can be provided.

[0097] <Example of data collection terminal configuration> Next, a configuration example of the data collection terminal 31 will be described with reference to FIG.

[0098] The data collection terminal 31 is composed of a control unit 51, an input unit 52, an output unit 53, a memory unit 54, a communication unit 55, a drive 56, a removable storage medium 57, and sensors 59-1 to 59-s, which are connected to each other via a bus 58 and can send and receive data and programs.

[0099] The control unit 51 is composed of a processor and a memory, and controls the overall operation of the data collection terminal 31. The control unit 51 also includes a data collection unit 71.

[0100] The data collection unit 71 acquires the detection results of the sensors 59-1 to 59-s in the data collection terminal 31 in association with the detection times, obtains an allowable defect histogram, and detects the continuous drive time.

[0101] Then, the data collection unit 71 transmits the allowable defect histogram and the continuous drive time to the server 32 together with terminal information including the manufacturer name, the machine type name, the model name, the sensor model number, the OS type, and the OS version, which are terminal information. The allowable defect histogram will be described in detail later.

[0102] The input unit 52 is made up of input devices such as a keyboard, buttons, and a mouse through which the user inputs operation commands, and supplies various input signals to the control unit 51.

[0103] The output unit 53 is controlled by the control unit 51, and outputs and displays the supplied operation screen and images of the processing results on a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

[0104] The storage unit 54 is composed of a hard disk drive (HDD), a solid state drive (SSD), a semiconductor memory, or the like, and is controlled by the control unit 51 to write or read various data including content data and programs.

[0105] The communication unit 55 is controlled by the control unit 51, and transmits and receives various data and programs to and from various devices via a communication network such as a LAN (Local Area Network) via a wired (or wireless (not shown)) connection.

[0106] The drive 56 reads and writes data from and to a removable storage medium 57 such as a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory) and a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor memory.

[0107] Sensors 59-1 to 59-s are a group of multiple built-in sensors, such as an acceleration sensor, a gyro sensor, a geomagnetic sensor, an air pressure sensor, a microphone, a light quantity sensor, a human presence sensor, and a position sensor (e.g., a GPS sensor), which detect various types of information and output it to the control unit 51.

[0108] <Server configuration example> Next, a configuration example of the server 32 will be described with reference to FIG.

[0109] The server 32 is composed of a control unit 91, an input unit 92, an output unit 93, a memory unit 94, a communication unit 95, a drive 96, and a removable storage medium 97, which are connected to each other via a bus 98 and can send and receive data and programs.

[0110] The control unit 91 is composed of a processor and a memory, and controls the overall operation of the server 32. The control unit 91 also includes a data collection unit 101 and a service provision unit .

[0111] The data collection unit 101 acquires information on the allowable loss histogram and the continuous drive time supplied from the data collection terminal 31 in association with the terminal information. The data collection unit 101 generates a normalized allowable loss histogram based on the allowable loss histogram and the continuous drive time, and outputs the normalized allowable loss histogram to the service provision unit 102 in association with a query according to the terminal information.

[0112] The service providing unit 102 calculates an allowable missing value based on the normalized allowable missing value histogram supplied from the data collecting unit 101, and determines whether or not to provide a discount service by comparing the allowable missing value with a threshold value. The service providing unit 102 generates and stores a whitelist 111 consisting of the determination result and a query corresponding to the terminal information.

[0113] In addition, when the service providing unit 102 receives a request for the provision of a discount service from the service receiving terminal 33 together with terminal information, it searches the whitelist for a query corresponding to the terminal information, determines whether or not the discount service can be provided based on whether or not the query is registered in the whitelist as a query for which the discount service can be provided, and notifies the service receiving terminal 33 of the determination result.

[0114] When it is possible to provide a discount service, the service providing unit 102 recognizes the driving state based on various detection results notified by the data collecting unit 101, and provides a discount service for the insurance premium according to the recognition result.

[0115] The input unit 92 is made up of input devices such as a keyboard and a mouse through which the user inputs operation commands, and supplies various input signals to the control unit 91.

[0116] The output unit 93 is controlled by the control unit 91, and outputs and displays the supplied operation screen and processing result images on a display device such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

[0117] The storage unit 94 is composed of a hard disk drive (HDD), a solid state drive (SSD), a semiconductor memory, or the like, and is controlled by the control unit 91 to write or read various data including content data and programs.

[0118] The communication unit 95 is controlled by the control unit 91, and transmits and receives various data and programs to and from various devices via a communication network such as a LAN (Local Area Network) via a wired (or wireless (not shown)) connection.

[0119] The drive 96 reads and writes data from and to a removable storage medium 97 such as a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory) and a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor memory.

[0120] <Example of the configuration of a service receiving terminal> Next, a configuration example of the service receiving terminal 33 will be described with reference to FIG.

[0121] The service receiving terminal 33 is composed of a control unit 121, an input unit 122, an output unit 123, a memory unit 124, a communication unit 125, a drive 126, a removable storage medium 127, and sensors 129-1 to 129-t, which are mutually connected via a bus 128 and can transmit and receive data and programs.

[0122] In addition, the configuration of the service receiving terminal 33 is basically the same as that of the data collecting terminal 31, and the control unit 121, input unit 122, output unit 123, memory unit 124, communication unit 125, drive 126, and removable storage medium 127, as well as the sensors 129-1 to 129-t correspond to the control unit 51, input unit 52, output unit 53, memory unit 54, communication unit 55, drive 56, and removable storage medium 57, as well as the sensors 59-1 to 59-s, respectively, and therefore detailed explanations are omitted.

[0123] However, the control unit 121 includes a service request unit 131 instead of the data collection unit 71 in the control unit 51 .

[0124] The service request unit 131 acquires the detection results of the sensors 129-1 to 129-t in the service receiving terminal 33 in association with the detection times, supplies them to the server 32, and receives discount services based on the detection results.

[0125] To receive this discount service, the service request unit 131 acquires the terminal information and requests the server 32 to provide the service. The server 32 determines whether the service can be provided based on the terminal information and notifies the server 32 of information on whether the service can be provided, so that the service request unit 131 can receive the insurance premium discount service when it is notified that the service can be provided.

[0126] <Functions realized by the information processing system> Next, functions realized by the information processing system 11 in FIG. 4 will be described with reference to FIG.

[0127] The data collection unit 71 in the data collection terminal 31 constituting the information processing system 11 includes a terminal information collection unit 141 and an allowable defect histogram generation unit 142 .

[0128] The terminal information collection unit 141 collects terminal information consisting of the manufacturer name, model name, sensor model number, OS type, and OS version of the data collection terminal 31, and supplies this to the allowable loss histogram generation unit 142.

[0129] The allowable loss histogram generation unit 142 acquires the detection results detected by the operation of various sensors 59 built into the data collection terminal 31, corresponding to the time information at the time of detection, and generates an allowable loss histogram consisting of the number of times data loss occurs for each sensor 59 per time period based on the acquired information.

[0130] Here, in explaining the tolerable defect histogram, for example, a case will be considered in which the detection result D51 shown in the left part of FIG. 9 is acquired from the sensor 59.

[0131] In the detection result D51, the time at which the sensor value of the sensor 59 is detected is shown on the left side, and the sensor value detected at the corresponding time is shown on the right side.

[0132] In the detection result D51 of Figure 9, it is shown that, from top to bottom, with the sensor 59 operating at 50 Hz, a sensor value of 0.071 is detected at time 4.997, a sensor value of 0.016 is detected at time 5.014, a sensor value of 0.029 is detected at time 5.034, a sensor value of 0.048 is detected at time 5.054, a sensor value of 0.040 is detected at time 5.074, a sensor value of 0.048 is detected at time 5.212, and a sensor value of 0.036 is detected at time 5.242.

[0133] The tolerable defect histogram generation unit 142 corrects this detection result D51 by a cleansing process using a common interpolation algorithm such as linear interpolation, bicubic interpolation, and Bezier interpolation, for example, as shown in the detection result D52 on the right side of Figure 9.

[0134] In the detection result D52 of FIG. 9, the sensor 59 detects a sensor value of 0.061 at time 5.000, a sensor value of 0.020 at time 5.020, a sensor value of 0.033 at time 5.040, and a sensor value of 0.046 at time 5.060.

[0135] It also shows that at time 5.080, a sensor value of 0.040 is detected, at time 5.100, a sensor value of 0.041 is detected, at time 5.120, a sensor value of 0.042 is detected, at time 5.140, a sensor value of 0.043 is detected, at time 5.160, a sensor value of 0.044 is detected, at time 5.180, a sensor value of 0.045 is detected, at time 5.200, a sensor value of 0.046 is detected, at time 5.220, a sensor value of 0.047 is detected, and at time 5.240, a sensor value of 0.036 is detected.

[0136] Because the sensor 59 operates at 50 Hz, theoretically data should be detected every 0.02 seconds. However, data T111 surrounded by a dotted line in the figure, which is the detection result from time 5.080 to 5.220 of detection result D52 and which corresponds to time 5.074 to 5.121 of detection result D51, was not detected, indicating that a missing data has occurred (a missing state).

[0137] That is, in the case of FIG. 9, the allowable loss histogram generating unit 142 calculates the data loss time to be 0.140 seconds from time 5.080 to 5.220.

[0138] Based on the detection result of the sensor 59, the allowable loss histogram generating unit 142 generates a histogram as shown in Fig. 10 from the loss time as shown in Fig. 9 and the corresponding number of occurrences of loss, as an allowable loss histogram, and outputs it together with the terminal information to the server 32. In other words, the allowable loss histogram is a histogram that indicates the number of occurrences of loss that occurs for each loss time as shown in Fig. 9.

[0139] FIG. 10 shows an example of an allowable defect histogram in which the horizontal axis represents defect time and the vertical axis represents the number of occurrences.

[0140] 10, the allowable defect histogram generating unit 142 detects the time during which the detection results for generating the allowable defect histogram are continuously obtained as a continuous drive time, and outputs the allowable defect histogram and the terminal information to the server 32. The continuous drive time may be, for example, the time from when an application for driving the corresponding sensor 59 is started to when it is ended, or the time from when the data collection terminal 31 is started to when it is stopped.

[0141] The data collection unit 101 of the server 32 includes a normalized allowable histogram generation unit 151 and a query generation unit 152 .

[0142] The normalized allowable defect histogram generating unit 151 generates a normalized allowable defect histogram for each piece of terminal information, based on the allowable defect histogram transmitted from the data collection terminal 31 and the continuous driving time.

[0143] More specifically, the normalized allowable defect histogram generating unit 151 accumulates and adds the continuous drive times of the same terminal information to generate the accumulated continuous drive time.

[0144] In addition, the normalized allowable defect histogram generation unit 151 divides the number of occurrences at each defect time in the allowable defect histogram for the same terminal information transmitted from the data collection terminal 31 by the cumulative continuous driving time, to calculate a statistical allowable defect histogram per unit time for each terminal information as a normalized allowable defect histogram.

[0145] The query generation unit 152 generates a query that identifies a combination of information such as the manufacturer name, model name, sensor model number, OS type, and OS version, which is terminal information associated with the allowable defect histogram transmitted from the data collection terminal 31, and outputs the generated query to the normalized allowable defect histogram generation unit 151.

[0146] The query may be composed of degenerate information of any of the terminal information that constitutes a combination of the manufacturer name, the machine name, the model name, the sensor model number, the OS type, and the OS version.

[0147] For example, if the terminal information consists of a combination of manufacturer name, model name, model name, sensor model number, OS type, and OS version, a query may be constructed from the manufacturer name and model name, or a query may be constructed from only the manufacturer name, only the model name, or only the sensor model number.

[0148] Furthermore, the terminal information may include information other than the manufacturer name, model name, and sensor model number of the data collection terminal 31, as well as the OS type and OS version, such as the individual manufacturer name of the sensor 59, and a query may be constructed for each manufacturer name of the sensor 59.

[0149] Then, the normalized allowable defect histogram 151 outputs a query generated in response to the terminal information supplied by the query generating unit 152 to the service providing unit 102 in association with the generated normalized allowable defect histogram and the accumulated continuous drive time.

[0150] Here, the normalized volume deficit histogram indicates the number of occurrences of deficit times in the detection results of the sensor 59 that occur per unit time for each query.

[0151] The service providing unit 102 includes an allowable missing value generating unit 171 , a whitelist generating unit 172 , a whitelist storage unit 173 , and a service providing processing unit 174 .

[0152] The allowable defect value generating unit 171 calculates an allowable defect value based on the normalized allowable defect histogram and the accumulated continuous drive time, and outputs the allowable defect value to the whitelist generating unit 172 in association with the query.

[0153] More specifically, the allowable missing value generation unit 171 sets a weighting coefficient wi according to the importance of each missing time in processing the detection result for a normalized allowable missing time histogram in which the cumulative continuous driving time is equal to or longer than a predetermined time that can be regarded as being long enough to statistically guarantee sufficient accuracy, and calculates the sum of the product with the number of occurrences of the missing time xi as the allowable missing value S using the following formula (1).

[0154]

number

[0155] Here, in formula (1), i represents a missing time (or an identifier of a missing time), S represents the allowable missing value, wi represents the weighting coefficient of missing time i, and xi represents the number of occurrences of missing time i.

[0156] Moreover, the weighting coefficient wi is set, for example, as a value indicated by a straight line Lw for each loss time i in the normalized allowable loss histogram in Fig. 11. Note that in Fig. 11, the change in the weighting coefficient wi is expressed as a continuous variable corresponding to the loss time i by a thick solid line, but more precisely, the weighting coefficient wi is a discrete variable set for each loss time i, and therefore here, the change corresponding to the loss time when the values ​​of the weighting coefficient wi, which is a discrete variable, are linearly connected is expressed by the straight line Lw.

[0157] That is, in the case of the straight line Lw in FIG. 11, since a missing time shorter than a predetermined missing time (i=7 in FIG. 11) can be interpolated with high accuracy, the impact is small, and therefore the impact on the estimation of the driving state is considered to be small, and therefore the weighting coefficient wi is set to 0.

[0158] In addition, for a missing time that is longer than a predetermined missing time (i=7 in FIG. 11) and shorter than a predetermined missing time (i=31 in FIG. 11), it is considered that the influence on the estimation of the driving state increases depending on the length of the missing time, so a weighting coefficient wi is set according to the length of the missing time.

[0159] Furthermore, for missing times longer than a predetermined missing time (i=31 in FIG. 11), the number of occurrences is small and therefore the influence on the estimation of the driving state is considered to be small, so the weighting coefficient wi is set to 0.

[0160] In other words, the allowable missing value calculated in this manner is calculated by multiplying the number of missing times that have a large impact on the estimation of the driving state by a large weighting coefficient wi and adding them up. Therefore, the larger the allowable missing value, the more likely it is that the detection results of the sensors required to provide the service will be missing, indicating that the communication terminal is unsuitable for providing discount services.

[0161] Conversely, the smaller the allowable missing value, the smaller the impact on the estimation of the driving state, so the detection results of the sensors required to provide discount services are less likely to be missing, indicating that the communications terminal is suitable for providing discount services.

[0162] Incidentally, since the calculation represented by equation (1) is a calculation for converting matrix information into a scalar, a nonlinear matrix calculation may be applied.

[0163] In addition, the weighting coefficient wi may be determined by applying a machine learning model such as Bayesian deep learning or a neural network using the normalized allowable defect histograms and accumulated continuous operation times of terminals that can provide the service and terminals that cannot provide the service, obtained during the operation of the provided service, as training data.

[0164] The whitelist generation unit 172 compares the allowable missing value calculated for each query with the threshold value of the allowable missing value for which the service can be provided, associates queries for which the service can be provided with queries for which the service cannot be provided, registers the associations as a whitelist 111, and stores the associations in the whitelist memory unit 173.

[0165] For example, as shown in FIG. 12, when the allowable missing value Sa for query a, the allowable missing value Sb for query b, and the allowable missing value Sc for query c are calculated and the allowable missing value Sc>Sb>Sa, consider the case where a threshold value Sth is set that is greater than the allowable missing value Sb and smaller than the allowable missing value Sc.

[0166] In such a case, the whitelist generating unit 172 registers the queries a and b having the allowable missing values ​​Sa and Sb smaller than the threshold value Sth in the whitelist 111 as terminals for which the service can be provided.

[0167] Furthermore, the whitelist generating unit 172 registers in the whitelist 111 a query c with an allowable missing value Sc greater than the threshold value Sth as a terminal for which service cannot be provided.

[0168] In FIG. 12, the allowable missing value Sa of query a, the allowable missing value Sb of query b, the threshold value Sth, and the allowable missing value Sc of query c are listed from left to right on the axis of the allowable missing value S, and it is shown that a communication terminal represented by queries a and b with allowable missing values ​​Sa and Sb smaller than the threshold value Sth is considered to be able to provide service, and a communication terminal represented by query c with an allowable missing value Sc larger than the threshold value Sth is considered to be unable to provide service.

[0169] The whitelist 111 has a configuration, for example, as shown in FIG.

[0170] That is, at the top of the whitelist 111 in Figure 13, the manufacturer name of the data collection terminal 31 for query a corresponding to Figure 12 is A, the model name is Q, the OS type is OS12, the OS version is OS12.1, and "OK" is registered, indicating that the service can be provided.

[0171] In addition, in the second row from the top of the whitelist 111 in Figure 13, the manufacturer name of the data collection terminal 31 for query b corresponding to Figure 12 is B, the model name is R, the OS type is OS11, the OS version is OS11.0, and "OK" is registered, indicating that the service can be provided.

[0172] Furthermore, in the third row from the top of the whitelist 111 in Figure 13, the manufacturer name of the data collection terminal 31 for query c corresponding to Figure 12 is C, the model name is S, the OS type is OS12, the OS version is OS12.1, and "NG" is registered, indicating that service cannot be provided.

[0173] Note that only queries for which the discount service can be provided may be registered in the whitelist 111. Also, a so-called blacklist may be configured in which only queries for which the discount service cannot be provided are registered instead of the whitelist 111. Furthermore, if the user is using a terminal that is known to be a terminal capable of providing the service, the user may be allowed to add and register queries to the whitelist 111, regardless of the normalized allowable defect histogram, or to delete registered queries.

[0174] In addition, in FIG. 13, an example is shown in which the manufacturer name, model name, OS type, and OS version are registered for each query as information to be registered in the whitelist 111, but at least one of the manufacturer name, model name, model name, and sensor model number, as well as the OS type and OS version may be registered, and other information may also be registered.

[0175] The service provision processing unit 174 accepts a request for service provision supplied along with terminal information from the service receiving terminal 33, and accesses the whitelist 111 stored in the whitelist memory unit 173, searches for a query corresponding to the terminal information, and determines whether the service can be provided.

[0176] The service provision processing unit 174 notifies the service receiving terminal 33 that has requested the service provision of the result of the determination as to whether or not the service can be provided.

[0177] The service provision processing unit 174 provides a service to the service receiving terminal 33 for which the service can be provided, based on the detection result detected by the sensor 129 of the service receiving terminal 33. That is, here, the service provision processing unit 174 estimates the driving state of the service receiving terminal 33 for which the service can be provided, based on the detection result detected by the sensor 129 of the service receiving terminal 33, and provides an insurance premium discount service according to the driving state.

[0178] The service request section 131 of the service receiving terminal 33 includes a service request processing section 191 and a terminal information collecting section 192 .

[0179] When the service request processing unit 191 is instructed to request the provision of a discount service from the server 32, for example by a user operating the input unit 122, the service request processing unit 191 controls the terminal information collection unit 192 to collect its own terminal information.

[0180] The terminal information collection unit 192 has a configuration similar to that of the terminal information collection unit 141 of the data collection terminal 31, and collects terminal information consisting of the combination of the manufacturer name, model name, model name, and sensor model number of the service receiving terminal 33, as well as the OS type and OS version, and supplies it to the service request processing unit 191.

[0181] The service request processor 191 sends a request to the server 32 for a discount service together with its own terminal information.

[0182] The service request processor 191 receives a notification from the server 32 as to whether or not the service can be provided.

[0183] At this time, if the service can be provided, the service request processing unit 191 subsequently transmits the detection results of the sensor 129 to the server 32 in sequence.

[0184] The server 32 provides a service based on the detection result of the sensor 129 transmitted from the service receiving terminal 33 capable of providing the service.

[0185] That is, for example, in the case of automobile insurance, the driving condition of the driver is analyzed based on the acceleration, angular velocity, and position information detected by the sensor 129 of the service receiving terminal 33 held by the driver who is the policyholder, and if the accident occurrence rate falls below a predetermined value, an insurance premium discount service is provided in which the insurance premium is discounted.

[0186] On the other hand, when the service cannot be provided, the policyholder can be notified of the impossibility of the service at the timing when the service is requested. This makes it possible to avoid accepting a request for service even when the policyholder has a service receiving terminal 33 that cannot provide the service and is physically unable to provide the appropriate service.

[0187] In the above, we have described an example in which a whitelist is generated in advance using weighting coefficients and allowable missing values ​​to determine whether or not a terminal is capable of providing a service. However, if there is a sufficient amount of training data and a data set of detection results, a machine learning model may be used to learn a model that directly calculates whether or not a service can be provided.

[0188] <Whitelist generation process> Next, the whitelist generation process performed by the information processing system 11 in FIG. 8 will be described with reference to the flowchart in FIG.

[0189] In step S11, the terminal information collection unit 141 collects terminal information consisting of a combination of the manufacturer name, model name, model name, and sensor model number of the data collection terminal 31, as well as the OS type and OS version, and outputs it to the allowable loss histogram generation unit 142.

[0190] In step S12, the allowable defect histogram generating unit 142 determines whether or not a sensor value has been supplied from the sensor 59 as a detection result.

[0191] In step S12, if a sensor value is supplied as a detection result from the sensor 59, the process proceeds to step S13.

[0192] In step S13, the allowable defect histogram generating unit 142 stores the detection result together with information on the detection time.

[0193] In step S14, the allowable defect histogram generating unit 142 determines whether or not it is time to generate an allowable defect histogram.

[0194] Here, the timing for generating the tolerable defect histogram may be, for example, the timing when an operation is stopped for longer than a predetermined time, or, for example, whether or not a predetermined time has elapsed.

[0195] If it is determined in step S14 that it is not time to generate an allowable loss histogram, the process proceeds to step S18.

[0196] In step S18, the allowable defect histogram generating unit 142 determines whether the operation of the data collection terminal 31 has been terminated, that is, whether an operation such as turning off the power has been performed, and if an instruction to terminate has been received, the process ends.

[0197] On the other hand, if it is determined in step S18 that the end of the operation has not been instructed, the process returns to step S12.

[0198] In other words, unless an instruction to end the operation is given, the processing of steps S12, S13, and S18 is repeated until it is deemed time to generate an allowable defect histogram, and each time a sensor value of sensor 59 is detected, the detection result and the detection time are stored.

[0199] If it is determined in step S14 that it is time to generate an allowable loss histogram, the process proceeds to step S15.

[0200] In step S15, the allowable defect histogram generating unit 142 generates an allowable defect histogram based on the stored detection results and time information.

[0201] More specifically, the allowable loss histogram generation unit 142 cleanses the stored detection results using an interpolation algorithm or the like, and based on the cleansed detection results, calculates the number of occurrences of a loss state for each loss time, and generates an allowable loss histogram.

[0202] In step S16, the allowable defect histogram generating unit 142 determines the time from the time when the previous allowable defect histogram is generated to the time when the current allowable defect histogram is generated as the continuous drive time.

[0203] In step S17, the allowable defect histogram generating unit 142 controls the communication unit 55 to transmit the allowable defect histogram and information on the continuous drive time together with the terminal information to the server 32.

[0204] In step S31, the normalized allowable defect histogram generation unit 151 of the data collection unit 101 controls the communication unit 95 to determine whether or not information on the allowable defect histogram and continuous driving time has been transmitted from the data collection terminal 31 together with terminal information.

[0205] In step S31, if the information on the allowable defect histogram and the continuous drive time has been transmitted together with the terminal information, the process proceeds to step S38.

[0206] In step S38, normalized allowable defective histogram generating unit 151 determines whether or not an instruction to stop the operation has been received, and if an instruction to stop the operation has been received, the process ends.

[0207] Also, in step S38, if an instruction to stop the operation has not been given, the process returns to step S31, and the subsequent processes are repeated.

[0208] That is, if the information on the allowable loss histogram and the continuous driving time is not transmitted together with the terminal information, the processes of steps S31 and S are repeated until an instruction to stop the operation is given.

[0209] In step S31, if the information on the allowable loss histogram and the continuous drive time has been transmitted from the data collection terminal 31 together with the terminal information, the process proceeds to step S32.

[0210] In step S32, the normalized allowable defect histogram generation unit 151 controls the communication unit 95 to receive the information on the allowable defect histogram and the continuous driving time together with the terminal information transmitted from the data collection terminal 31. At this time, the query generation unit 152 acquires the transmitted terminal information.

[0211] In step S33, the query generating unit 152 generates a query based on the terminal information of the data collection terminal 31 that has transmitted the information on the allowable defect histogram and the continuous drive time, and outputs the query to the normalized allowable defect histogram generating unit 151.

[0212] In step S34, the normalized allowable defect histogram generating unit 151 accumulates the continuous drive time and calculates the accumulated continuous drive time.

[0213] In step S35, the normalized allowable defect histogram generating unit 151 generates a normalized allowable defect histogram based on the allowable defect histogram and the information on the accumulated continuous drive time, and outputs the normalized allowable defect histogram to the allowable defect value generating unit 171 of the service providing unit 102.

[0214] More specifically, the normalized allowable defect histogram generation unit 151 divides the allowable defect histogram by the cumulative continuous driving time to obtain a normalized allowable defect histogram per unit time, and outputs the normalized allowable defect histogram together with the query to the allowable defect value generation unit 171 of the service providing unit 102.

[0215] In step S36, the allowable missing value generating unit 171 of the service providing unit 102 calculates an allowable missing value based on the normalized allowable missing value histogram, and outputs the allowable missing value to the whitelist generating unit 172 together with the query.

[0216] More specifically, the allowable missing value generating unit 171 calculates the allowable missing value by multiplying the number of occurrences for each missing time in the normalized allowable missing value histogram by a weighting coefficient and finding the sum, as shown in formula (1).

[0217] In step S37, the whitelist generation unit 172 compares the allowable missing value with the threshold value for providing the service, associates the comparison result with the terminal information, which is the query information, registers it in the whitelist 111, stores it in the whitelist memory unit 173, and the processing proceeds to step S38.

[0218] That is, by the above processing, the data collection terminal 31 generates terminal information, an allowable loss histogram, and information on continuous drive time, and transmits them to the server 32.

[0219] In addition, in the server 32, a query is generated based on the terminal information, and the continuous driving time is accumulated to generate a cumulative continuous driving time.The number of occurrences of each loss time in the allowable loss histogram is divided by the cumulative continuous driving time to generate a normalized allowable loss histogram of the allowable loss per unit time.

[0220] Then, based on the normalized allowable missing value histogram, a sum of products using weighting coefficients is calculated as an allowable missing value, and by comparing with a threshold value, it is determined whether or not the service can be provided, and the value is registered in the whitelist 111.

[0221] As a result, when a service is requested, it is possible to immediately determine, based on the whitelist 111, whether the service can be provided.

[0222] <Service provision process> Next, the service providing process by the information processing system 11 in FIG. 8 will be described with reference to the flowchart in FIG.

[0223] In step S51, the service request processing unit 191 of the service request unit 131 in the service receiving terminal 33 determines whether or not a service has been requested, for example by a user operating the input unit 122, and repeats the same processing until a service is requested.

[0224] That is, the provision of a service here means, for example, the provision of a discount service for automobile insurance premiums according to driving conditions.

[0225] If it is determined in step S51 that a service provision has been requested, for example by a user operating the input unit 122, the process proceeds to step S52.

[0226] In step S52, the service request processing unit 191 controls the terminal information collection unit 192 to collect terminal information.

[0227] In step S53, the service request processing unit 191 controls the communication unit 125 to notify the server 32 of a request for service provision together with the terminal information.

[0228] In step S71, the service provision processing unit 174 of the service providing unit 102 in the server 32 controls the communication unit 95 to determine whether or not a request for service provision has been received from the service receiving terminal 33 along with terminal information, and repeats the same process until a request is received.

[0229] If it is determined in step S71 that a request for service provision has been received from the service receiving terminal 33 together with the terminal information, the process proceeds to step S72.

[0230] In step S72, the service providing processing unit 174 controls the communication unit 95 to obtain terminal information together with a request for service provision from the service receiving terminal 33. Then, the service providing processing unit 174 accesses the whitelist storage unit 173, and searches the whitelist 111 for a corresponding query based on the obtained terminal information.

[0231] In step S73, the service provision processing unit 174 determines whether or not the query corresponding to the terminal information of the service receiving terminal 33 that has requested the service provision is registered in the whitelist 111 as a terminal for which the service can be provided.

[0232] If it is determined in step S73 that the query corresponding to the terminal information of the service receiving terminal 33 that has requested the service is registered in the whitelist 111 as a terminal for which the service can be provided, the process proceeds to step S74.

[0233] In step S74, the service provision processing unit 174 determines that the service can be provided, and controls the communication unit 95 to notify the service receiving terminal 33 that has requested the service that the service can be provided.

[0234] Thereafter, the service providing processing unit 174 controls the communication unit 95 to provide a service based on the detection result of the sensor 129 of the service receiving terminal 33 .

[0235] Also, in step S73, if it is determined that the query corresponding to the terminal information of the service receiving terminal 33 that has requested the service provision is registered in the whitelist 111 as a terminal for which the service cannot be provided, the process proceeds to step S75.

[0236] In step S75, the service provision processing unit 174 determines that the service cannot be provided, and controls the communication unit 95 to notify the service receiving terminal 33 that has requested the service that the service cannot be provided.

[0237] In step S 54 , the service request processing unit 191 of the service request unit 131 of the service receiving terminal 33 controls the communication unit 125 to receive the notification sent from the server 32 .

[0238] In step S55, the service request processor 191 determines whether the received notification indicates that the service can be provided.

[0239] If it is determined in step S55 that the notification indicates that the service is available, the process proceeds to step S56.

[0240] In step S56, the service request processing unit 191 controls the communication unit 125 to notify the server 32 of the detection result detected by the sensor 129, and receives the service provided based on the detection result.

[0241] Through the above processing, information indicating whether or not a service can be provided is pre-registered as a whitelist in correspondence with a query (terminal information). Therefore, when a request for service provision is made, it is possible to determine whether or not the service can be provided based on the query corresponding to the terminal information consisting of a combination of the manufacturer name, model name, model name, and sensor model number of the service receiving terminal 33 requesting the service, as well as the OS type and OS version.

[0242] As a result, when a service is provided using a mobile terminal, it becomes possible to determine at low cost and with high accuracy whether or not the mobile terminal being used is capable of providing the service.

[0243] As a result, when a service is provided, it is possible to properly obtain the detection results of the sensor built into the user's smartphone, thereby enabling the provision of an appropriate service.

[0244] In addition, when a service is requested and an appropriate service cannot be provided depending on the smartphone model, etc., it is possible to notify the user that the appropriate service cannot be provided before the service is provided. This makes it possible to prevent situations in which the detection results from the smartphone's sensors cannot be obtained properly and the appropriate service cannot be provided.

[0245] Furthermore, it will be possible to reduce the occurrence of complaints from users due to the inability to properly obtain detection results from the smartphone sensor and therefore to provide services appropriately, thereby reducing the costs associated with responding to complaints about the provision of services.

[0246] Furthermore, the whitelist 111 will continue to be updated as long as the data collection terminal 31 continues to send information on the allowable loss histogram and continuous operating time along with the terminal information. Therefore, even if a new model of data collection terminal 31 appears, for example, it will be registered by a new query, making it possible to respond appropriately to new models.

[0247] Furthermore, since the whitelist 111 is continuously updated over time, it becomes possible to appropriately reflect cases where a missing state occurs due to deterioration over time, and even if a service is possible at the time of launch, it becomes impossible to provide the service over time.

[0248] However, in this case, for a service receiving terminal 33 that has once accepted the provision of a service, a process is required to periodically search the whitelist 111 based on the terminal information to check whether the provision of the service is not disabled.

[0249] In the above, we have described an example in which the driving pattern of the driver who is the policyholder is recognized using the detection results of a sensor built into a smartphone carried by the policyholder in an automobile insurance policy, and a discount service for insurance premiums is provided according to the recognized driving pattern.

[0250] However, the technology disclosed herein may be applied not only to the technology for providing the above-mentioned insurance premium discount service, but also to other technologies, so long as the processing uses the continuous detection results of a sensor. For example, the technology may be applied to a technology that provides a service that detects the daily walking distance and amount of exercise of a user who owns a smartphone, and indicates whether or not the user is experiencing a lack of exercise.

[0251] Furthermore, instead of an information processing system consisting of a smartphone and a server, the present invention may be applied to an information processing system consisting of, for example, a vibration detection device equipped with a vibration sensor that continuously detects vibrations of equipment that operates continuously, and a server.

[0252] In this case, the vibration detection device may continuously detect the vibration of the equipment and transmit the information to a server, so that when the server detects abnormal vibration in the equipment, it may provide a technology that provides a service to notify a communication terminal of the owner of the equipment, etc.

[0253] To provide this service, the server generates a whitelist of queries for vibration detection devices that can provide the service based on the detection results of each vibration detection device in advance, and when a request for service is made, it is possible to immediately determine whether the service can be provided by searching the corresponding query from the whitelist.

[0254] In addition, since the allowable missing value can be regarded as the reliability of the missing state of the communication terminal, it is possible to adjust the reliability when providing a service by increasing the threshold value of the allowable missing value.

[0255] For example, by increasing the threshold value of the allowable missing value, it is possible to provide a highly reliable service.

[0256] Furthermore, by lowering the threshold for the allowable missing value, it becomes possible to realize a service that increases the number of communication terminals that can provide the service, although reliability is somewhat sacrificed.

[0257] Furthermore, as explained with reference to equation (1) and the straight line Lw in FIG. 11, the weighting coefficient wi for the number of occurrences can be set according to the effect on subsequent processing (e.g., driving pattern recognition processing), so that an appropriate allowable missing value can be set according to the subsequent processing, thereby making it possible to appropriately determine whether or not to provide the service.

[0258] Furthermore, although the above describes an example in which the data collection terminal 31 and the service receiving terminal 33 are different, it is assumed that the data collection terminal 31 and the service receiving terminal 33 are communications terminals having basically the same functions, so an information processing system may be configured from a communications terminal having both the functions of the data collection terminal 31 and the functions of the service receiving terminal 33 and the server 32.

[0259] However, in this case, it is assumed that a whitelist will be generated in advance by using a communication terminal functioning as a data collection terminal 31, and after the whitelist is generated, the provision of a service must be requested by the communication terminal functioning as a service receiving terminal 33.

[0260] <<3. Example of execution by software>> The above-mentioned series of processes can be executed by hardware, but can also be executed by software. When the series of processes are executed by software, the programs constituting the software are installed from a recording medium into a computer built into dedicated hardware, or into, for example, a general-purpose computer capable of executing various functions by installing various programs.

[0261] 16 shows an example of the configuration of a general-purpose computer. This personal computer has a built-in CPU (Central Processing Unit) 1001. An input / output interface 1005 is connected to the CPU 1001 via a bus 1004. A ROM (Read Only Memory) 1002 and a RAM (Random Access Memory) 1003 are connected to the bus 1004.

[0262] An input unit 1006 consisting of input devices such as a keyboard and a mouse through which a user inputs operation commands, an output unit 1007 for outputting a processing operation screen and an image of the processing result to a display device, a storage unit 1008 consisting of a hard disk drive for storing programs and various data, and a communication unit 1009 consisting of a LAN (Local Area Network) adapter and the like for executing communication processing via a network such as the Internet are connected to the input / output interface 1005. Also connected is a drive 1010 for reading and writing data from and to a removable storage medium 1011 such as a magnetic disk (including a flexible disk), an optical disk (including a CD-ROM (Compact Disc-Read Only Memory) and a DVD (Digital Versatile Disc)), a magneto-optical disk (including an MD (Mini Disc)), or a semiconductor memory.

[0263] The CPU 1001 executes various processes according to a program stored in a ROM 1002 or a program read from a removable storage medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory and installed in a storage unit 1008, and loaded from the storage unit 1008 to a RAM 1003. The RAM 1003 also stores data and the like necessary for the CPU 1001 to execute various processes, as appropriate.

[0264] In a computer configured as described above, the CPU 1001 loads a program stored in the memory unit 1008, for example, into the RAM 1003 via the input / output interface 1005 and the bus 1004, and executes the program, thereby performing the series of processes described above.

[0265] The program executed by the computer (CPU 1001) can be provided by being recorded on a removable storage medium 1011 such as a package medium, for example. The program can also be provided via a wired or wireless transmission medium such as a local area network, the Internet, or digital satellite broadcasting.

[0266] In the computer, the program can be installed in the storage unit 1008 via the input / output interface 1005 by mounting the removable storage medium 1011 in the drive 1010. The program can also be received by the communication unit 1009 via a wired or wireless transmission medium and installed in the storage unit 1008. Alternatively, the program can be pre-installed in the ROM 1002 or the storage unit 1008.

[0267] In addition, the program executed by the computer may be a program in which processing is performed chronologically in the order described in this specification, or it may be a program in which processing is performed in parallel or at the required timing, such as when called.

[0268] 16. Incidentally, a CPU 1001 in FIG. 16 realizes the functions of the control units 51, 91, and 121 in FIGS.

[0269] In this specification, a system refers to a collection of multiple components (devices, modules (parts), etc.), regardless of whether all the components are in the same case. Therefore, multiple devices housed in separate cases and connected via a network, and a single device in which multiple modules are housed in a single case, are both systems.

[0270] The embodiments of the present disclosure are not limited to the above-described embodiments, and various modifications are possible without departing from the gist of the present disclosure.

[0271] For example, the present disclosure can take the form of cloud computing in which a single function is shared and processed collaboratively by multiple devices via a network.

[0272] Furthermore, each step described in the above flow chart can be executed by one device, or can be shared and executed by a plurality of devices.

[0273] Furthermore, when a single step includes multiple processes, the multiple processes included in the single step can be executed by a single device, or can be shared and executed by multiple devices.

[0274] The present disclosure can also be configured as follows.

[0275] <1> a missing value generating unit that generates a missing value indicating the degree of loss of data detected by the communication terminal; a list generation unit that generates a list of the communication terminals that are capable of processing based on data detected by the communication terminals based on the missing value; An information processing device comprising: <2> An acquisition unit that acquires information indicating a degree of data loss detected by the communication terminal, the information being transmitted from the communication terminal, The missing value generating unit generates the missing value based on information indicating a degree of loss of data detected in the communication terminal, the information being acquired by the acquiring unit. <1> The information processing device described in <3> The information indicating the degree of data loss detected by the communication terminal is a loss histogram consisting of the number of occurrences for each loss time, which is the time when data detected by the communication terminal is lost. <2> The information processing device described in <4> The defect histogram is a normalized defect histogram normalized by an accumulated operating time, which is an accumulated time of continuous operating time of the communication terminal. <3> The information processing device described in <5> The missing value generating unit calculates, as the missing value, a sum of the number of occurrences for each missing time in the normalized missing histogram multiplied by a predetermined weighting coefficient. <4> The information processing device described in <6> The predetermined weighting coefficient is a coefficient that increases as the missing time increases within a range of the missing time that is longer than a first predetermined time and shorter than a second predetermined time that is longer than the first predetermined time. <5> The information processing device described in <7> The predetermined weighting coefficient is a coefficient determined by machine learning. <5> The information processing device described in <8> The acquisition unit acquires information indicating a degree of data loss of the communication terminal in association with information indicating a type of the communication terminal; the missing value generation unit generates the missing value in association with information indicating a type of the communication terminal, based on information indicating a degree of loss in data detected at the communication terminal acquired by the acquisition unit; The list generation unit generates a list of types of the communication terminal capable of processing based on data detected in the communication terminal. <2> The information processing device described in <9> The list generation unit generates a list of types of the communication terminal capable of processing based on data detected by the communication terminal based on a comparison between the missing value and a predetermined threshold. <8> The information processing device described in <10> When the missing value is smaller than the predetermined threshold, the list generation unit registers the missing value in the list as a type of the communication terminal capable of processing based on data detected by the communication terminal. <9> The information processing device described in <11> The type of the communication terminal includes at least one of information on the manufacturer, the model name, the model name, the sensor type, the OS name, and the OS version of the communication terminal. <8> The information processing device described in <12> the information indicating the type of the communication terminal is managed as a query; the missing value generation unit generates the missing value in association with a query indicating a type of the communication terminal; The list generation unit registers in a list a query of the communication terminal that can be processed based on the data detected by the communication terminal. <9> The information processing device described in <13> The processing based on the data detected by the communication terminal detects a driving state when a user who holds the communication terminal drives a vehicle while holding the communication terminal, and performs processing according to the driving state. <8> The information processing device described in <14> The process according to the driving state is a discount service for insurance premiums according to the driving state when the user is a contract holder of automobile insurance. <13> The information processing device described in <15> The data detected by the communication terminal is data detected by a sensor built into the communication terminal, and the sensor includes at least one of an acceleration sensor, a gyro sensor, a geomagnetic sensor, an air pressure sensor, a microphone, a light amount sensor, a human presence sensor, and a position information sensor. <1> ~ <14> 13. An information processing device according to claim 12, <16> The communication terminal further includes a determination unit that obtains a request for processing based on data detected in another communication terminal different from the communication terminal, together with information on a type of the other communication terminal, and determines whether processing based on the data detected in the communication terminal is possible by searching the list. <1> ~ <15> 13. An information processing device according to claim 12, <17> generating missing values ​​indicating the degree of missing data detected by the communication terminal; Generate a list of communication terminals capable of processing based on data detected at the communication terminal based on the missing values. An information processing method comprising the steps of: <18> a missing value generating unit that generates a missing value indicating the degree of loss of data detected by the communication terminal; a list generation unit that generates a list of the communication terminals that are capable of processing based on data detected by the communication terminals based on the missing value; programs that make a computer function. [Explanation of symbols]

[0276] 11 information processing system, 31, 31-1 to 31-n data collection terminal, 32 server, 33, 33-1 to 33-m service receiving terminal, 51 control unit, 59, 59-1 to 59-s sensor, 71 data collection unit, 91 control unit, 101 data collection unit, 102 service providing unit, 111 whitelist, 121 control unit, 131 service request unit, 129, 129-1 to 129-t sensor, 141 terminal information collection unit, 142 allowable missing value histogram generation unit, 151 normalized allowable missing value histogram generation unit, 152 query generation unit, 171 allowable missing value generation unit, 172 whitelist generation unit, 173 whitelist storage unit, 174 service provision processing unit, 191 service request unit, 192 terminal information collection unit

Claims

1. An information processing device that determines whether a predetermined service can be provided to a service receiving terminal, a list generating unit that generates a missing value representing the degree of missingness of the sensor data based on a missing value histogram consisting of the number of occurrences of each missing time related to a time when sensor data is missing that is collected from a plurality of communication terminals equipped with sensors and detected by the communication terminal, and a continuous driving time related to the measurement of the missing value histogram, and generates a list including information of terminals that can provide the specified service based on a comparison between the missing value for each piece of terminal information of the communication terminal associated with the missing value histogram and a predetermined threshold value for the missing value that is required by the communication terminal to receive the specified service; a determination unit which, in response to a request for provision of the predetermined service and terminal information of the service receiving terminal sent from the service receiving terminal requesting provision of the predetermined service, determines whether or not the predetermined service can be provided to the service receiving terminal by referring to a list generated by the list generation unit; An information processing device comprising:

2. The defect histogram is a normalized defect histogram normalized by dividing the number of occurrences of each defect time by a cumulative continuous drive time, which is a cumulative time obtained by accumulating and adding up the continuous drive time of the communication terminal. The information processing device according to claim 1 .

3. The list generating unit calculates a sum of the number of occurrences for each of the missing times in the normalized missing data histogram multiplied by a predetermined weighting coefficient as a missing data value representing the degree of missing data in the sensor data. The information processing device according to claim 2 .

4. The predetermined weighting coefficient is a coefficient that increases as the missing time increases with respect to a range of the missing time that is longer than a first predetermined time and shorter than a second predetermined time that is longer than the first predetermined time and that has a large influence on the estimation of the driving state. The information processing device according to claim 3 .

5. The predetermined weighting coefficient is a coefficient calculated by machine learning using the normalized defect histogram and the cumulative continuous drive time as training data. The information processing device according to claim 3 .

6. The terminal information includes at least one of information on the manufacturer, the model name, the model name, the sensor type, the OS name, and the OS version of the communication terminal. The information processing device according to claim 1 .

7. The predetermined service is a service corresponding to a driving state that is a detection result of the communication terminal when a user who holds the communication terminal drives a vehicle while holding the communication terminal. The information processing device according to claim 1 .

8. The service according to the driving state is a discount service for insurance premiums according to the driving state when the user is a contract holder of automobile insurance. The information processing device according to claim 7.

9. The data detected by the communication terminal is data detected by a sensor built into the communication terminal, and the sensor includes at least one of an acceleration sensor, a gyro sensor, a geomagnetic sensor, an air pressure sensor, a microphone, a light amount sensor, a human presence sensor, and a position information sensor. The information processing device according to claim 1 .

10. An information processing method of an information processing device that determines whether a predetermined service can be provided to a service receiving terminal, comprising: performing a list generation process of generating a missing value representing the degree of missingness of the sensor data based on a missing value histogram consisting of the number of occurrences of each missing time related to a time when sensor data is missing that is collected from a plurality of communication terminals equipped with the sensor and detected by the communication terminal, and a continuous driving time related to the measurement of the missing value histogram, and generating a list including information of terminals capable of providing the specified service based on a comparison between the missing value for each piece of terminal information of the communication terminal associated with the missing value histogram and a predetermined threshold value of the missing value required by the communication terminal to receive the specified service; performing a determination process for determining whether or not the predetermined service can be provided to the service receiving terminal by referring to the list generated in the list generation process in response to terminal information of the service receiving terminal and a request for the predetermined service sent from the service receiving terminal requesting the provision of the predetermined service; An information processing method comprising:

11. the defect histogram is a normalized defect histogram normalized by dividing the number of occurrences of each defect time by a cumulative continuous operation time, which is a cumulative time of a continuous operation time of the communication terminal, the list generation process calculates a sum of the number of occurrences of each of the loss times in the normalized loss histogram multiplied by a predetermined weighting coefficient as a loss value representing the degree of loss of the sensor data; The predetermined weighting coefficient is a coefficient calculated by machine learning using the normalized defect histogram and the cumulative continuous drive time as training data. The information processing method according to claim 10.

12. The terminal information includes at least one of information on the manufacturer, the model name, the model name, the sensor type, the OS name, and the OS version of the communication terminal. The information processing method according to claim 10.

13. The predetermined service is a service corresponding to a driving state that is a detection result of the communication terminal when a user who holds the communication terminal drives a vehicle while holding the communication terminal. The information processing method according to claim 10.

14. The service according to the driving state is a discount service for insurance premiums according to the driving state when the user is a contract holder of automobile insurance. The information processing method according to claim 13.

15. The data detected by the communication terminal is data detected by a sensor built into the communication terminal, and the sensor includes at least one of an acceleration sensor, a gyro sensor, a geomagnetic sensor, an air pressure sensor, a microphone, a light amount sensor, a human presence sensor, and a position information sensor. The information processing method according to claim 10.

Citation Information

Patent Citations

  • Content delivery server apparatus, content delivery method, content delivery program, and recording medium having the program recorded therein

    JP2009290571A

  • Information processing device, system, information processing method, and program

    WO2014136466A1