Behavioral analysis device, behavioral analysis method, and program

Abstract

Conventionally, it has not been possible to understand a person's physical strength and mental state using information about their behavior. [Solution] A behavior analysis device 10 includes a knowledge storage unit 1011 that stores a physical fitness score, which indicates the user's degree of physical recovery or exhaustion when performing a behavior, and a mental score, which indicates the degree of mental fatigue recovery or exhaustion, in association with each of two or more pieces of behavioral information that specify the user's behavior; a reception unit 102 that receives the user's behavioral information; a score acquisition unit 1031 that acquires from the knowledge storage unit 1011 the physical fitness score and mental score that correspond to the behavioral information received by the reception unit 102; and a score output unit 1041 that outputs the physical fitness score and mental score acquired by the score acquisition unit 1031 in an associated manner, thereby making it possible to grasp a person's physical and mental state using the person's behavioral information.

Description

[Technical Field]

[0001] The present invention relates to a behavior analysis device and the like that obtains and outputs a physical fitness score and a mental fitness score for a user's behavior. [Background technology]

[0002] Conventionally, there has been a behavior determination system that determines the sleep and other behavior of a resident using energy consumption data (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6470497 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the prior art, it has not been possible to grasp a person's physical strength and mental state using information about the person's behavior. [Means for solving the problem]

[0005] The behavioral analysis device of the first invention is a behavioral analysis device that includes a knowledge storage unit that stores a physical fitness score, which is the user's degree of recovery or exhaustion of physical fitness when the user performs a behavior, and a mental score, which is the user's degree of recovery or exhaustion of mental fatigue, in correspondence with each of two or more pieces of behavioral information that specify the user's behavior; a reception unit that receives the user's behavioral information; a score acquisition unit that acquires from the knowledge storage unit the physical fitness score and mental score that correspond to the behavioral information received by the reception unit; and a score output unit that outputs the physical fitness score and mental score acquired by the score acquisition unit in a corresponding manner.

[0006] With this configuration, it is possible to obtain the physical strength and mental state corresponding to the person's behavior information. Note that the physical strength state here is a score related to physical strength, and the mental state here is a score related to mental health.

[0007] Furthermore, in the behavioral analysis device of the second invention, compared to the first invention, the reception unit receives time series information including two or more pieces of time-series behavioral information of the user, and further includes a reference management unit in which reference information serving as a basis for obtaining the degree of behavioral disorder of the user corresponding to the time series information is stored, and the score acquisition unit uses the time series information received by the reception unit and the reference information of the reference management unit to obtain a disorder score, which is the degree of behavioral disorder of the user, and also uses the disorder score to obtain a physical fitness score and a mental score, and the score acquisition unit is a behavioral analysis device that obtains a smaller physical fitness score or a smaller mental score the larger the disorder score.

[0008] With this configuration, it is possible to acquire a person's physical strength and mental state, taking into consideration the degree of disorder in behavior.

[0009] In addition, the behavioral analysis device of the third invention is different from the first invention in that the receiving unit receives time series information including two or more pieces of chronological behavioral information of the user, the score acquisition unit acquires a physical fitness score and a mental score for each of the two or more pieces of behavioral information contained in the time series information, and uses the physical fitness score for each of the two or more pieces of behavioral information contained in the time series information to acquire a cumulative physical fitness score which is the user's accumulated degree of recovery or exhaustion of physical fitness, and uses the mental score for each of the two or more pieces of behavioral information contained in the time series information to acquire and accumulate a cumulative mental score which is the user's accumulated degree of recovery or exhaustion of mental fatigue, and the behavioral analysis device further includes a cumulative score acquisition unit that outputs the cumulative physical fitness score and cumulative mental score acquired by the cumulative score acquisition unit in a corresponding manner.

[0010] With this configuration, the physical strength and mental state of a person can be obtained using time-series behavior information of the person.

[0011] In addition, the behavioral analysis device of the fourth invention is a behavioral analysis device in which, compared to the third invention, the score acquisition unit uses the cumulative physical score acquired by the cumulative score acquisition unit to acquire a physical score corresponding to the behavioral information accepted by the reception unit, and uses the cumulative mental score acquired by the cumulative score acquisition unit to acquire a mental score corresponding to the behavioral information accepted by the reception unit, and the score acquisition unit acquires a larger physical score the larger the cumulative physical score, and acquires a larger mental score the larger the cumulative mental score.

[0012] With this configuration, the score for one behavior can be obtained using the accumulated scores from the past.

[0013] In addition, the behavioral analysis device of the fifth invention, compared to the third or fourth invention, further includes a model storage unit in which an internal state estimation model is stored for obtaining an updated cumulative physical score and an updated cumulative mental score using a newly acquired physical score, a newly acquired mental score, a cumulative physical score based on past behavior, and a cumulative mental score based on past behavior, and the cumulative score acquisition unit acquires the physical score acquired by the score acquisition unit, the mental score acquired by the score acquisition unit, the accumulated cumulative physical score, and the accumulated cumulative mental score, and applies the physical score, the mental score, the cumulative physical score, and the cumulative mental score to the internal state estimation model to obtain the cumulative physical score and the cumulative mental score.

[0014] With this configuration, the cumulative physical fitness score and cumulative mental score can be updated using the physical fitness score and mental fitness score for the behavioral information and the internal state estimation model.

[0015] In addition, the behavioral analysis device of the sixth invention is a behavioral analysis device that, compared to the fifth invention, further includes an external environment acquisition unit that acquires external environment data, and the cumulative score acquisition unit applies the physical fitness score, mental score, cumulative physical fitness score, cumulative mental score, and external environment data to an internal state estimation model to acquire the cumulative physical fitness score and cumulative mental score.

[0016] With this configuration, the external environment data can also be used to obtain the cumulative physical fitness score and cumulative mental score.

[0017] In addition, the behavioral analysis device of the seventh invention is a behavioral analysis device that, compared to the fifth or sixth invention, further comprises: a learning management unit that stores learning information created using two or more teacher data, which is one or more types of data from one or more vital data of the user or one or more sensing data obtained by sensing the user, with two or more pieces of data as explanatory variables and one or two types of scores from the cumulative physical fitness score and the cumulative mental score as objective variables; a data acquisition unit that acquires two or more pieces of data, which is one or more types of data from one or more vital data of the user or one or more sensing data obtained by sensing the user; a prediction unit that acquires a predicted cumulative physical fitness score and a predicted cumulative mental score using the two or more pieces of data acquired by the data acquisition unit and the learning information; and a predicted value output unit that outputs the predicted cumulative physical fitness score and the predicted cumulative mental score acquired by the prediction unit.

[0018] With this configuration, the cumulative physical fitness score and cumulative mental score can be obtained using one or two types of information from the vital data and the sensing data.

[0019] In addition, the behavioral analysis device of the eighth invention is a behavioral analysis device in which, compared to the seventh invention, the cumulative score acquisition unit uses the predicted cumulative physical fitness score to acquire a corrected cumulative physical fitness score by correcting the cumulative physical fitness score, and uses the predicted cumulative mental score to acquire a corrected cumulative mental score by correcting the cumulative mental score, and the cumulative score output unit outputs the predicted cumulative physical fitness score and the predicted cumulative mental score acquired by the cumulative score acquisition unit in a corresponding manner.

[0020] With this configuration, a more appropriate cumulative physical strength score and a more appropriate cumulative mental strength score can be obtained.

[0021] In addition, the behavioral analysis device of the ninth invention is a behavioral analysis device that, compared to any one of the fifth to eighth inventions, further includes a model update unit that updates the internal state estimation model based on the difference between the cumulative physical fitness score and the predicted cumulative physical fitness score, and the difference between the cumulative mental score acquired by the cumulative score acquisition unit and the predicted cumulative mental score.

[0022] With this configuration, the internal state estimation model can be updated appropriately. [Effects of the Invention]

[0023] According to the behavior analysis device of the present invention, it is possible to grasp a person's physical strength and mental state using the person's behavior information. [Brief explanation of the drawings]

[0024] [Figure 1] 1 is a conceptual diagram of an information system A including a location information production device 1 according to the first embodiment. [Figure 2] Block diagram of the same-location information production device 1 [Figure 3] Flowchart illustrating an example of the operation of the same-location information production device 1 [Figure 4] 10 is a flowchart illustrating an example of a simultaneous sequence intensity acquisition process. [Figure 5] A flowchart illustrating an example of the fixed information acquisition process [Figure 6] Flowchart illustrating an example of a process for determining the same type [Figure 7] Figure showing the simultaneous radio wave strength management table [Figure 8] Figure showing the same location information management table [Figure 9] Conceptual diagram of information system C in embodiment 2 [Figure 10] Block diagram of the terminal device 2 [Figure 11] 10 is a flowchart illustrating a first operation example of the terminal device 2. [Figure 12] A flowchart illustrating an example of the movement determination process [Figure 13]Flowchart illustrating an example of position estimation processing [Figure 14] 10 is a flowchart illustrating a second operation example of the terminal device 2. [Figure 15] Flowchart for explaining a second example of the same type determination process [Figure 16] Conceptual diagram of information system D in embodiment 3 [Figure 17] Block diagram of Information System D [Figure 18] Block diagram of the behavior acquisition device 3 [Figure 19] A flowchart illustrating an example of the operation of the behavior acquisition device 3 [Figure 20] A flowchart illustrating an example of the action source acquisition process [Figure 21] Flowchart illustrating an example of position estimation processing [Figure 22] 10 is a flowchart illustrating an example of the first behavior estimation process. [Figure 23] 10 is a flowchart illustrating an example of the second behavior estimation process. [Figure 24] 10 is a flowchart illustrating an example of the third behavior estimation process. [Figure 25] 10 is a flowchart illustrating an example of the first emotion estimation process. [Figure 26] 10 is a flowchart illustrating an example of the second emotion estimation process. [Figure 27] 10 is a flowchart illustrating an example of the third emotion estimation process. [Figure 28] Flowchart illustrating an example of the output configuration process [Figure 29] 10 is a flowchart illustrating an example of the first behavior learning process. [Figure 30] 10 is a flowchart illustrating an example of the second behavior learning process. [Figure 31] 10 is a flowchart illustrating an example of the first emotion learning process. [Figure 32] 10 is a flowchart illustrating an example of the second emotion learning process. [Figure 33] A diagram showing the action source management table [Figure 34] A diagram showing the behavior and emotion management chart [Figure 35] Figure showing the same time slot information management table [Figure 36] Figure showing an example of the output [Figure 37] Conceptual diagram of information system E in embodiment 4 [Figure 38] Block diagram of Information System E [Figure 39] Block diagram of the behavior acquisition device 5 [Figure 40] A flowchart illustrating an example of the operation of the behavior acquisition device 5 [Figure 41] A flowchart illustrating an example of the operation of the terminal device 6 [Figure 42] Conceptual diagram of information system F in embodiment 5 [Figure 43] Block diagram of Information System F [Figure 44] Block diagram of the behavioral analysis device 7 [Figure 45] A flowchart illustrating an example of the operation of the behavior analysis device 7 [Figure 46] 10 is a flowchart illustrating a first example of the score acquisition process. [Figure 47] 10 is a flowchart illustrating a second example of the score acquisition process. [Figure 48] 10 is a flowchart illustrating a third example of the score acquisition process. [Figure 49] Flowchart illustrating an example of the factor acquisition process [Figure 50] 10 is a flowchart illustrating an example of the recommendation acquisition process. [Figure 51] A flowchart illustrating an example of the long-term score acquisition process [Figure 52] A flowchart illustrating an example of the learning process [Figure 53] Figure 10 shows an example of a time slot information management table [Figure 54]A diagram showing an example of the recommendation management table [Figure 55] Figure showing an example of the output [Figure 56] Figure showing an example of the output [Figure 57] Block diagram of the behavioral analysis device 9 [Figure 58] Conceptual diagram of information system G in embodiment 6 [Figure 59] Block diagram of the information system G [Figure 60] Block diagram of the behavioral analysis device 10 [Figure 61] A flowchart illustrating an example of the operation of the behavior analysis device 10. [Figure 62] Flowchart illustrating an example of a process for obtaining scores by the same behavior [Figure 63] 10 is a flowchart illustrating a first example of the score acquisition process. [Figure 64] 10 is a flowchart illustrating a second example of the score acquisition process. [Figure 65] 10 is a flowchart illustrating a first example of the cumulative score acquisition process. [Figure 66] 10 is a flowchart illustrating a second example of the cumulative score acquisition process. [Figure 67] 10 is a flowchart illustrating a first example of the cumulative score correction process. [Figure 68] 10 is a flowchart illustrating a second example of the cumulative score correction process. [Figure 69] 10 is a flowchart illustrating a first example of the model update process. [Figure 70] 10 is a flowchart illustrating a second example of the model update process. [Figure 71] FIG. 2 is a diagram showing an example of an operation model of the behavior analysis device 10. [Figure 72] Figure showing an example of the output [Figure 73] Block diagram of a computer system according to the above embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0025] Hereinafter, embodiments of a behavior analysis device and the like will be described with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore repeated description may be omitted.

[0026] (Embodiment 1) In this embodiment, a location information production device will be described. The location information production device is a device that acquires location information (to be described later) of a specific location.

[0027] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is not important. Information X and information Y may be linked, may exist in the same buffer, information X may be included in information Y, or information Y may be included in information X, etc.

[0028] Furthermore, in this specification, selecting or determining information Z means obtaining information Z, obtaining a pointer to information Z, obtaining the ID of information Z, setting a flag on information Z, etc., and it is sufficient if information Z can be accessed.

[0029] 1 is a conceptual diagram of an information system A including a location information production device 1 according to this embodiment. The information system A has the location information production device 1 and three or more communication devices B.

[0030] Each of the three or more communication devices B is a device that transmits radio waves to other devices such as the location information production device 1. The communication device B transmits a device identifier that identifies the communication device B to the other devices. The communication device B is, for example, a Wi-Fi router or a communication device that uses BLE (Bluetooth Low Energy), but the type is not critical.

[0031] 2 is a block diagram of the location information production device 1 in this embodiment. The location information production device 1 includes a storage unit 11, a reception unit 12, a receiving unit 13, and a processing unit 14. The reception unit 12 includes a position reception unit 121. The processing unit 14 includes an intensity acquisition unit 141, a type determination unit 142, and an accumulation unit 143.

[0032] The reception unit 12 receives various instructions and information. The various instructions and information are, for example, position information, which will be described later. The instructions and information can be input using any means, such as a touch panel, a keyboard, a mouse, or a menu screen.

[0033] The position receiving unit 121 receives position information of specific points. The position receiving unit 121 typically receives position information of three or more specific points. The position receiving unit 121 receives, for example, position information input by a user. The position receiving unit 121 reads out the position information from the storage unit 11, for example.

[0034] The specific point is a specific indoor point, but may also be a specific outdoor point. Here, location information is information that identifies a location indoors or outdoors. The location information is, for example, three-dimensional coordinate values ​​(x, y, z) that indicate a relative indoor or outdoor position, but may also be two-dimensional coordinate values ​​(x, y). The origin of the coordinate values ​​used to identify a relative indoor or outdoor position does not matter. The specific outdoor point is preferably a location where GPS signals are difficult to reach, such as among high-rise buildings or in a forest, but this does not matter. The location information may also be information that allows a person to recognize a location (for example, a character string) or an ID. Such location information may also be, for example, a label such as "living room," "workroom," "conference room," "east side of the library," or "toy section of a department store."

[0035] The location receiving unit 121 may generate a unique ID. Such a unique ID may be considered to be a label and location information.

[0036] The position receiving unit 121 does not have to receive the position information. In this case, the position receiving unit 121 is not necessary.

[0037] At a specific location, the receiving unit 13 receives radio waves including device identifiers from each of three or more communication devices B. The receiving unit 13 usually receives radio waves including device identifiers from each of three or more communication devices B consecutively.

[0038] The device identifier is information that identifies the communication device B. The device identifier is, for example, the ID or name of the communication device B. Receiving radio waves can be considered as receiving information.

[0039] The processing unit 14 performs various types of processing, such as processing performed by an intensity acquisition unit 141, a type determination unit 142, and a storage unit 143.

[0040] The intensity acquisition unit 141 acquires the intensity of radio waves received from each of the three or more communication devices B. The intensity acquisition unit 141 acquires the radio wave intensity in pairs with the device identifier of the communication device B. The intensity acquisition unit 141 acquires radio wave intensity in a time series. The time series radio wave intensity means two or more radio wave intensities that are consecutive in time. It goes without saying that being consecutive in time may include a time interval.

[0041] The type determination unit 142 determines whether each of the three or more communication devices B is a fixed terminal or a mobile terminal, using the time-series radio wave intensity acquired by the intensity acquisition unit 141. A fixed terminal is a communication device whose installation location is fixed. A mobile terminal is a communication device whose installation location is not fixed and which moves.

[0042] For example, the type determination unit 142 acquires the degree of variation of two or more consecutive radio wave intensities in a time series paired with one device identifier, and if the degree of variation is equal to or greater than a threshold, determines that the communication device B identified by the one device identifier is a mobile terminal.Furthermore, the type determination unit 142 acquires the degree of variation of two or more consecutive radio wave intensities in a time series paired with one device identifier, and if the degree of variation is equal to or less than a threshold, determines that the communication device B identified by the one device identifier is a fixed terminal.

[0043] The degree of variation is information indicating the degree of variation or change in radio wave strength over time. The degree of variation is, for example, a number based on variance, standard deviation, or difference (for example, the sum of the difference between two consecutive radio wave strengths among three or more consecutive radio wave strengths).

[0044] The type determination unit 142 determines that the communication device B identified by a certain device identifier is a mobile terminal, for example, if the number of radio wave intensities obtained in a specified time period and the number of consecutive radio wave intensities in a time series paired with a certain device identifier is below or less than a threshold value.

[0045] The storage unit 143 configures and stores location information having a device identifier and radio wave intensity of the communication device B that the type determination unit 142 has determined to be a fixed terminal. It is preferable that the storage unit 143 configures and stores location information having a device identifier and radio wave intensity for each of the three or more communication devices B.

[0046] The accumulation unit 143, for example, configures and stores location information having a device identifier, radio wave intensity, and location information of a specific location of a communication device B that the type determination unit 142 has determined to be a fixed terminal. It is preferable that the accumulation unit 143 configures and stores location information having a device identifier, radio wave intensity, and location information of a specific location for each of three or more communication devices B. For example, the accumulation unit 143 stores the location information in the storage unit 11, but it may also store the location information in another device. It is preferable that the location information includes location information, but it does not have to include location information. The location information may also be composed of only a device identifier and radio wave intensity.

[0047] The radio wave intensity stored in the storage unit 143 is usually a representative value of the time-series radio wave intensity of the radio wave from the communication device B. The representative value is, for example, a median, an average, a maximum value, or a minimum value.

[0048] The storage unit 11 is preferably a non-volatile recording medium, but can also be realized as a volatile recording medium.

[0049] There is no restriction on the process by which information is stored in storage unit 11. For example, information may be stored in storage unit 11 via a recording medium, information transmitted via a communication line or the like may be stored in storage unit 11, or information input via an input device may be stored in storage unit 11.

[0050] The receiving unit 12 and the position receiving unit 121 can be realized by a device driver for an input means such as a touch panel or a keyboard, or control software for a menu screen.

[0051] The receiving unit 13 is usually realized by a wireless or wired communication means.

[0052] The processing unit 14, intensity acquisition unit 141, type determination unit 142, and storage unit 143 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 14, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type does not matter.

[0053] Next, an example of the operation of the location information production device 1 will be described with reference to the flowchart of FIG.

[0054] (Step S301) The position receiving unit 121 determines whether or not position information of a specific point has been received. If the position information has been received, the process proceeds to step S302, and if not, the process returns to step S301.

[0055] (Step S302) The accumulation unit 143 acquires the location information received in step S301.

[0056] (Step S303) The processing unit 14 and the like perform a time-series intensity acquisition process. The time-series intensity acquisition process is a process for acquiring the time-series radio wave intensity of radio waves from each of three or more communication devices B. An example of the time-series intensity acquisition process will be described with reference to the flowchart in FIG.

[0057] (Step S304) The processing unit 14 and the like perform fixed information acquisition processing. Return to step S301. The fixed information acquisition processing is processing for acquiring the strength of radio waves from the fixed terminal at the point identified by the location information accepted in step S301. An example of the fixed information acquisition processing will be described with reference to the flowchart in FIG. 5.

[0058] In the flowchart of Figure 3, it is preferable that a user holding the location information production device 1 moves to each of three or more specific locations, and the location information production device 1 accepts location information for each of the three or more specific locations and repeatedly performs the processes from S301 to S304.

[0059] In the flowchart of FIG. 3, the process ends when the power is turned off or an interrupt occurs to end the process.

[0060] Next, an example of the time-series intensity acquisition process in step S303 will be described with reference to the flowchart in FIG.

[0061] (Step S401) The receiving unit 13 determines whether or not it has received a radio wave from any of the communication devices B. If it has received a radio wave, it proceeds to step S402, and if it has not received a radio wave, it returns to step S401.

[0062] (Step S402) The accumulation unit 143 acquires the device identifier corresponding to the radio wave received in step S401.

[0063] (Step S403) The intensity acquisition unit 141 acquires the intensity of the radio wave received in step S401.

[0064] (Step S404) The accumulation unit 143 adds the radio wave intensity acquired in step S403 to a buffer (not shown) in association with the device identifier acquired in step S402.

[0065] (Step S405) The accumulation unit 143 determines whether the accumulation condition of the location information is met. If the accumulation condition is met, the process returns to the upper process, and if the accumulation condition is not met, the process returns to step S401. The accumulation condition may be, for example, that a threshold time or more has elapsed since the location information of the specific location was received, or that a threshold or more number of radio wave intensities paired with three or more device identifiers have been accumulated.

[0066] Next, an example of the fixed information acquisition process in step S304 will be described with reference to the flowchart in FIG.

[0067] (Step S501) The type determination unit 142 assigns 1 to a counter i.

[0068] (Step S502) The type determination unit 142 determines whether the i-th device identifier exists in a buffer (not shown). If the i-th device identifier exists, the process proceeds to step S503, and if the i-th device identifier does not exist, the process returns to the upper processing.

[0069] (Step S503) The type determination unit 142 determines the type of communication device B identified by the i-th device identifier. An example of such type determination processing will be described with reference to the flowchart of FIG.

[0070] (Step S504) If the determination result in step S503 is a "fixed terminal", the process proceeds to step S505, and if it is a "mobile terminal", the process proceeds to step S508.

[0071] (Step S505) The accumulation unit 143 acquires two or more radio wave intensities paired with the i-th device identifier from a buffer (not shown).

[0072] (Step S506) The accumulation unit 143 acquires two or more representative values ​​of radio field strength.

[0073] (Step S507) The accumulation unit 143 accumulates in the storage unit 11 a pair of the i-th device identifier and the representative value of the radio wave intensity acquired in step S506 in association with the location information accepted in step S301.

[0074] (Step S508) The type determination unit 142 increments the counter i by 1. The process returns to step S502.

[0075] In the flowchart of FIG. 5, the accumulation unit 143 may acquire the latest signal strength in step S506 instead of two or more representative values ​​of the signal strength.

[0076] Next, an example of the type determination process in step S503 will be described with reference to the flowchart in FIG.

[0077] (Step S601) The type determination unit 142 acquires two or more radio wave intensities paired with the i-th device identifier in step S502 from a buffer (not shown).

[0078] (Step S602) The type determination unit 142 acquires the two or more degrees of variation in radio wave intensity acquired in step S601.

[0079] (Step S603) The type determination unit 142 determines whether the degree of variation acquired in step S602 is equal to or less than the threshold value. If the degree of variation is equal to or less than the threshold value, the process proceeds to step S604, and if the degree of variation is equal to or greater than the threshold value, the process proceeds to step S605.

[0080] (Step S604) The type determination unit 142 determines the type of communication device B as "fixed terminal." The process returns to the upper level process.

[0081] (Step S605) The type determination unit 142 determines the type of communication device B as "mobile terminal", and returns to the upper level processing.

[0082] A specific example of the operation of the location information production device 1 in this embodiment will be described below. Here, the accumulation condition is that a predetermined time (for example, 3 minutes) has elapsed since the location information of a specific location was accepted.

[0083] For example, assume that user A is indoors (for example, at his / her home or a department store that user A often visits) and inputs location information (x1, y1) to the location information production device 1.

[0084] Next, the location receiving unit 121 of the location information production device 1 receives the location information (x1, y1) of the specific location. Next, the accumulation unit 143 acquires the received location information (x1, y1) in a buffer (not shown).

[0085] Then, the receiving unit 13 receives radio waves including the device identifiers from three or more communication devices B for a predetermined time (for example, three minutes). Then, the storage unit 143 acquires the device identifiers included in the received radio waves. Furthermore, the intensity acquisition unit 141 acquires the intensity of the received radio waves. Next, the storage unit 143 associates the acquired device identifiers with the acquired device identifiers and adds the acquired radio wave intensity to a buffer (not shown). As a result, a time-series radio wave intensity management table shown in FIG. 7 is configured in the buffer (not shown). The time-series radio wave intensity management table shown in FIG. 7 is a table for a specific location indicated by the location information (x1, y1).

[0086] The time-series radio wave strength management table is a table that manages the time-series radio wave strength for each communication device B. The time-series radio wave strength management table is a table that manages two or more records that have "ID", "device identifier", and "time-series radio wave strength". "ID" is information that identifies the record. "Time-series radio wave strength" is the radio wave strength that is continuous over time. "R 11 ","R 12 ","R 21 " etc. indicates radio wave strength.

[0087] After the management table of Figure 7 is constructed, a predetermined time (e.g., 3 minutes) has passed since the location information (x1, y1) of a specific location was accepted by the location accepting unit 121, so the storage unit 143 determines that the storage conditions for the location information are met.

[0088] Next, the type determination unit 142 acquires the degree of variation in time-series radio wave intensity of each record in Fig. 7 according to the operation of the flowchart in Fig. 6, and determines whether each communication device B is a fixed terminal or a mobile terminal. Then, it is assumed that the type determination unit 142 determines that the communication device B identified by the device identifiers "device 1, device 3, device 4, device 6, . . . " is a fixed terminal, and determines that the communication device B identified by the device identifiers "device 2, device 5, . . . " is a mobile terminal.

[0089] Next, the storage unit 143 configures radio wave strength information by pairing the device identifier of communication device B, which is a fixed terminal, with a representative value of radio wave strength. Then, the storage unit 143 stores each of the multiple pieces of radio wave strength information in association with location information (x1, y1). By this process, a record of "ID=1" in the location information management table of FIG. 8 is configured. Note that the storage unit 143 may store only the device identifier and radio wave strength. In such a case, each record in FIG. 8 does not have location information. In such a case, the location receiving unit 121 does not need to receive location information of a specific location.

[0090] The location information management table is a table that manages location information. The location information management table stores multiple records that correspond to location information and have an "ID," "device identifier," and "signal strength information." The "signal strength information" has a "device identifier" and "signal strength."

[0091] Through the above processing, the location information of the specific location 1 at the position indicated by the location information (x1, y1) is accumulated.

[0092] User A takes the point information production device 1 and moves to specific point 2, the position indicated by the location information (x2, y2), and does the same as above. As a result, the point information production device 1 creates and stores a record for "ID=2" in the point information management table of FIG. 8. Furthermore, user A takes the point information production device 1 and moves to one or more specific points, including specific point 3, and does the same as above. As a result, the point information production device 1 creates and stores a record (not shown) for "ID=3" in the point information management table of FIG. 8.

[0093] As described above, according to this embodiment, it is possible to obtain point information for obtaining the indoor position of a terminal device. In other words, according to this embodiment, it is possible to generate three or more pieces of point information for obtaining the indoor position of a terminal device.

[0094] The processing in this embodiment may be implemented by software. This software may be distributed by software download or the like. Furthermore, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software implementing the location information production device 1 in this embodiment is the following program. Specifically, this program causes a computer to function as: a location reception unit that receives location information of a specific location; a reception unit that receives radio waves from three or more communication devices at the specific location, each of which includes a device identifier identifying the communication device; an intensity acquisition unit that acquires time-series radio wave intensity for each of the three or more communication devices; a type determination unit that determines, using the time-series radio wave intensity acquired by the intensity acquisition unit, whether each of the three or more communication devices is a fixed terminal, i.e., a fixed communication device, or a mobile terminal, i.e., a mobile communication device; and a storage unit that configures and stores location information including the device identifiers and radio wave intensities of each of the three or more communication devices determined by the type determination unit to be a fixed terminal, and the location information of the specific location.

[0095] (Embodiment 2) In this embodiment, we will describe a terminal device that receives radio waves from three or more communication devices B, determines the type of each communication device B using the time-series radio wave strength, and obtains and outputs a terminal position indicating the location of the terminal device indoors using the radio wave strength from only communication devices B whose type is ``fixed terminal.''

[0096] In this embodiment, a terminal device will be described that determines whether the terminal device is moving or stationary, and acquires and outputs the terminal position using the determination result.

[0097] 9 is a conceptual diagram of an information system C according to this embodiment. The information system C includes one or more terminal devices 2 and three or more communication devices B.

[0098] The terminal device 2 is a terminal capable of acquiring indoor position information. The terminal device 2 may be, for example, a smartphone, a tablet terminal, a smartwatch, a so-called personal computer, or the like, and the type of the terminal device 2 is not important.

[0099] 10 is a block diagram of a terminal device 2 in this embodiment. The terminal device 2 includes a storage unit 21, a receiving unit 22, a processing unit 23, and an output unit 24. The storage unit 21 includes a point information storage unit 211. The processing unit 23 includes an intensity acquisition unit 231, a type determination unit 232, a movement determination unit 233, and a position acquisition unit 234. The position acquisition unit 234 includes intensity acquisition means 2341, point determination means 2342, and position acquisition means 2343. The output unit 24 includes a position output unit 241.

[0100] Various types of information are stored in the storage unit 21. The various types of information are, for example, location information, which will be described later.

[0101] Three or more pieces of spot information are stored in the spot information storage unit 211. It is preferable that the three or more pieces of spot information in the spot information storage unit 211 are information accumulated by the spot information production device 1.

[0102] Each of the three or more pieces of point information in the point information storage unit 211 has, for example, location information of a specific point, a device identifier, and radio wave intensity. It is preferable that three or more pieces of radio wave intensity information correspond to each of the three or more pieces of location information. The radio wave intensity information has a device identifier and radio wave intensity. The three or more pieces of radio wave intensity information may form a radio wave intensity vector. The radio wave intensity vector is a vector using radio wave intensity information, and has, for example, a structure of (radio wave intensity of device identifier 1, radio wave intensity of device identifier 2, radio wave intensity of device identifier 3, ...radio wave intensity of device identifier n). The point information storage unit 211 stores, for example, a point information management table having the structure shown in FIG. 8.

[0103] The terminal device 2 does not necessarily have to have the location information storage unit 211. In such a case, the terminal device 2 refers to the location information storage unit 211 of an external device (not shown) and acquires the terminal position, which will be described later.

[0104] The receiving unit 22 receives radio waves including a device identifier that identifies the communication device B from each of the three or more communication devices B. The receiving unit 22 normally performs the same function as the receiving unit 13 described above. The receiving unit 22 normally receives radio waves including a device identifier from each of the three or more communication devices B. The receiving unit 22 normally receives radio waves continuously.

[0105] The processing unit 23 performs various types of processing. The various types of processing are, for example, processing performed by an intensity acquisition unit 231, a type determination unit 232, a movement determination unit 233, and a position acquisition unit 234.

[0106] The intensity acquisition unit 231 acquires time-series radio wave intensity for each of the three or more communication devices B. The intensity acquisition unit 231 acquires radio wave intensity based on the radio waves received by the receiving unit 22. The intensity acquisition unit 231 performs the same function as the intensity acquisition unit 141 described above.

[0107] The type determination unit 232 determines whether each of the three or more communication devices B is a fixed terminal or a mobile terminal, using the time-series radio wave intensity acquired by the intensity acquisition unit 231. The type determination unit 232 performs the same function as the type determination unit 142 described above.

[0108] The movement determination unit 233 determines whether the terminal device 2 is moving or stopped, and acquires a movement determination result that is the result of the determination. The movement determination result is, for example, "moving" or "stopped".

[0109] The movement determination unit 233 acquires, for example, sensor information of the terminal device 2 and acquires a movement determination result using the sensor information. The sensor information is, for example, acceleration measured by a gyro and time-series position information.

[0110] For example, if the acceleration measured by the gyro is "0" or less than a threshold, the movement determination unit 233 obtains a movement determination result of "stopped." For example, if the acceleration measured by the gyro is greater than or equal to a threshold, the movement determination unit 233 obtains a movement determination result of "moving."

[0111] The movement determination unit 233, for example, uses the time-series radio wave strength of each of three or more communication devices B acquired by the strength acquisition unit 231 to determine that one or more communication devices B is stopped if there is no change in the time-series radio wave strength of the communication devices B, and acquires a movement determination result of "stopped."

[0112] The location acquisition unit 234 acquires the radio wave intensity of three or more communication devices B that the type determination unit 232 has determined to be fixed terminals, and uses the radio wave intensity of the fixed terminals to acquire the terminal location, which is location information of the terminal device 2 indoors.

[0113] The location acquisition unit 234 acquires, for example, the radio wave intensity of three or more communication devices B that the type determination unit 232 has determined to be fixed terminals, and uses the three or more radio wave intensities to refer to three or more pieces of location information in the location information storage unit 211 and acquires the terminal location by the fingerprint method.

[0114] It is preferable that the location acquisition unit 234 acquires location information using the movement determination result. For example, it is preferable that the location acquisition unit 234 acquires the terminal location only when the movement determination result is "stopped."

[0115] The location acquisition unit 234 may acquire the terminal location using location information including the device identifier only when the device identifier corresponding to the radio waves received by the receiving unit 22 is included in the location information in the location information storage unit 211. This is because the location information in the location information storage unit 211 is location information of a fixed terminal.

[0116] The intensity acquisition means 2341 acquires the radio wave intensity of three or more communication devices that the type determination unit 232 has determined to be fixed terminals, in association with the device identifiers.

[0117] The location determination means 2342 determines, from the location information in the location information storage unit 211, one or more pieces of location information that satisfy the radio wave intensity and similarity condition associated with each of the three or more device identifiers acquired by the intensity acquisition means 2341.

[0118] The point determination means 2342, for example, acquires a first radio wave intensity vector, which is a vector whose elements are the radio wave intensities paired with each of the three or more device identifiers contained in the point information. The point determination means 2342 also acquires a second radio wave intensity vector, which is a vector whose elements are the radio wave intensities corresponding to each of the three or more device identifiers acquired by the intensity acquisition means 2341. The point determination means 2342, for example, acquires the similarity between the two radio wave intensity vectors, and if the similarity is equal to or greater than a threshold, acquires point information corresponding to the first radio wave intensity vector.

[0119] The position acquisition means 2343 acquires the position information contained in the one or more pieces of location information determined by the location determination means 2342, and acquires the terminal position using the one or more pieces of location information.

[0120] The output unit 24 outputs various types of information, such as the terminal position and an indoor map.

[0121] Here, output is a concept that includes displaying on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage on a recording medium, and delivery of processing results to other processing devices or other programs.

[0122] The position output unit 241 outputs the terminal position acquired by the position acquisition unit 234. The position output unit 241 displays, for example, on an indoor map, a design that clearly indicates the position identified by the terminal position.

[0123] The storage unit 21 and the location information storage unit 211 are preferably non-volatile recording media, but can also be realized as volatile recording media.

[0124] There is no restriction on the process by which information is stored in the storage unit 21 etc. For example, information may be stored in the storage unit 21 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 21 etc., or information input via an input device may be stored in the storage unit 21 etc.

[0125] The receiver 22 is typically implemented by a wireless or wired communication means.

[0126] The processing unit 23, intensity acquisition unit 231, type determination unit 232, movement determination unit 233, position acquisition unit 234, intensity acquisition means 2341, point determination means 2342, and position acquisition means 2343 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 23, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type does not matter.

[0127] The output unit 24 and the position output unit 241 can be realized by, for example, driver software for an output device such as a display or a speaker, or driver software for an output device and the output device.

[0128] Next, a first operation example of the terminal device 2 will be described with reference to the flowchart of FIG.

[0129] (Step S1101) The movement determining unit 233 determines whether the terminal device 2 is moving or is stopped. An example of such movement determining processing will be described with reference to the flowchart of FIG.

[0130] (Step S1102) If the determination result in step S1101 is "stopped", the process proceeds to step S1103, and if it is "moving", the process returns to step S1101.

[0131] (Step S1103) The intensity acquisition unit 2341 performs a time-series intensity acquisition process. An example of the time-series intensity acquisition process has been described with reference to the flowchart of FIG.

[0132] (Step S1104) The type determination unit 232, the location determination means 2342, etc. perform fixed information acquisition processing. An example of the fixed information acquisition processing has been described with reference to the flowchart of FIG.

[0133] (Step S1105) The position acquisition unit 2343 performs a position estimation process to acquire the terminal position. An example of the position estimation process will be described with reference to the flowchart in FIG.

[0134] (Step S1106) The position output unit 241 outputs the terminal position acquired in step S1105. The process returns to step S1101.

[0135] In the flowchart of FIG. 11, the process ends when the power is turned off or an interrupt occurs to end the process.

[0136] Next, an example of the movement determination process in step S1101 will be described with reference to the flowchart in FIG.

[0137] (Step S1201) The movement determination unit 233 acquires a sensor value (for example, acceleration) of the terminal device 2 and temporarily stores it in a buffer (not shown).

[0138] (Step S1202) The movement determination unit 233 determines whether or not to make a movement determination using the sensor values ​​in a buffer (not shown). If a movement determination is to be made, the process proceeds to step S1203, and if a movement determination is not to be made, the process returns to step S1201. Note that the movement determination unit 233 may always make a movement determination, or may make a movement determination after, for example, a predetermined number of sensor values ​​or more have been accumulated in the buffer, or after a predetermined time has elapsed since the sensor values ​​were acquired.

[0139] (Step S1203) The movement determination unit 233 uses one or more sensor values ​​in a buffer (not shown) to determine whether the terminal device 2 is moving or stopped. If it is stopped, the process proceeds to step S1204, and if it is moving, the process proceeds to step S1205.

[0140] (Step S1204) The movement determination unit 233 determines the movement determination result as "stopped." Then, the process proceeds to step S1206.

[0141] (Step S1205) The movement determining unit 233 determines the movement determination result as "on the move."

[0142] (Step S1206) The movement determination unit 233 clears a buffer (not shown) and returns to the upper level processing.

[0143] Next, an example of the position estimation process in step S1105 will be described with reference to the flowchart in FIG.

[0144] (Step S1301) The location acquisition unit 2343 acquires three or more pieces of radio wave intensity information (pairs of device identifier and radio wave intensity) of the terminal device 2.

[0145] (Step S1302) The position acquisition means 2343 vectorizes three or more pieces of radio wave intensity information to acquire a radio wave intensity vector. Note that the radio wave intensity vector is, for example, (radio wave intensity of device identifier 1, radio wave intensity of device identifier 2, radio wave intensity of device identifier 3, ... radio wave intensity of device identifier n).

[0146] (Step S1303) The position obtaining means 2343 assigns 1 to the counter i.

[0147] (Step S1304) The position acquisition means 2343 determines whether or not the i-th point information exists in the point information storage unit 211. If the i-th point information exists, the process proceeds to step S1305, and if not, the process proceeds to step S1309.

[0148] (Step S1305) The position obtaining unit 2343 obtains the i-th radio wave intensity vector included in the i-th point information from the point information storage unit 211.

[0149] (Step S1306) The position acquisition means 2343 acquires the similarity between the radio wave intensity vector acquired in step S1302 and the i-th radio wave intensity vector acquired in step S1305. Next, the position acquisition means 2343 determines whether the similarity satisfies a similarity condition (for example, the similarity is equal to or greater than a threshold). If the similarity satisfies the similarity condition, the process proceeds to step S1307; if not, the process proceeds to step S1308.

[0150] (Step S1307) The position acquiring unit 2343 acquires the position information and the similarity included in the i-th point information, and stores them in a buffer (not shown).

[0151] (Step S1308) The position obtaining means 2343 increments the counter i by 1. The process returns to step S1304.

[0152] (Step S1309) The location acquisition unit 2343 uses three or more pairs of location information and similarity accumulated in a buffer (not shown) to acquire a terminal location that identifies the location of the terminal device 2. The process returns to the upper level process.

[0153] Next, a second operation example of the terminal device 2 will be described with reference to the flowchart of FIG.

[0154] (Step S1401) The intensity acquisition unit 2341 performs a time-series intensity acquisition process. An example of the time-series intensity acquisition process has been described with reference to the flowchart of FIG.

[0155] (Step S1402) The location determining means 2342 performs fixed information acquisition processing. An example of the fixed information acquisition processing has been described with reference to the flowchart in FIG.

[0156] (Step S1403) The position acquisition unit 2343 performs a position estimation process to acquire the terminal position. An example of the position estimation process has been described with reference to the flowchart in FIG.

[0157] (Step S1404) The position output unit 241 outputs the terminal position acquired in step S1403. The process returns to step S1401.

[0158] In the flowchart of FIG. 14, the process ends when the power is turned off or an interrupt occurs to end the process.

[0159] Next, a second example of the type determination process in the fixed information acquisition process in step S1402 in the flowchart of Fig. 14 will be described using the flowchart of Fig. 15. Note that the first example of the type determination process was described using the flowchart of Fig. 6.

[0160] (Step S1501) The type determination unit 232 acquires the device identifier of the communication device B whose type is to be determined.

[0161] (Step S1502) The type determination unit 232 determines whether the device identifier acquired in step S1501 exists in any of the location information in the location information storage unit 211. If the device identifier exists in any of the location information, the process proceeds to step S1503; if not, the process proceeds to step S1504.

[0162] (Step S1503) The type determination unit 232 determines the type as "fixed terminal." The process returns to the upper level process.

[0163] (Step S1504) The type determination unit 232 determines the type as "mobile terminal." The process returns to the upper level processing.

[0164] A specific example of the operation of the terminal device 2 in this embodiment will be described below.

[0165] It is assumed that user B, holding his / her terminal device 2, enters an indoor location identified by a location identifier (P). Then, the receiving unit 22 of the terminal device 2 transmits a location information request having the location identifier (P) to an external device (not shown) and receives the location information management table shown in Fig. 8 from the device. Then, it is assumed that the processing unit 23 temporarily stores the location information management table in the location information storage unit 211.

[0166] Then, the terminal device 2 operates as follows, in accordance with the processes from steps S1103 to S1106 in FIG. 11 or the processes in the flowchart in FIG.

[0167] That is, the intensity acquisition means 2341 performs the time-series intensity acquisition process described using the flowchart in FIG. 4, acquires the radio wave intensity of each of three or more communication devices B at point X where the terminal device 2 is located, and constructs a time-series radio wave intensity management table having the structure shown in FIG. 7.

[0168] Next, the strength acquisition means 2341 performs a time-series strength acquisition process to acquire the time-series radio wave strength of each communication device B that can receive radio waves at point X, and creates a time-series radio wave strength management table with the structure shown in FIG.

[0169] Next, the type determination unit 142 refers to the time-series radio wave intensity management table and determines whether each communication device B is a "fixed terminal" or a "mobile terminal" by the type determination process described using the flowchart in Figure 4.

[0170] Next, the location determination means 2342 acquires the radio wave strength of "device 1," "device 3," "device 4," "device 6," etc., which are determined to be fixed terminals. Then, the location determination means 2342 acquires the radio wave strength vector "(radio wave strength of device 1, radio wave strength of device 3, radio wave strength of device 4, radio wave strength of device 6,...) = (P1, P3, P4, P6,...)." Note that the radio wave strength of communication device B acquired by the location determination means 2342 here may be a representative value of two or more radio wave strengths, or may be a single radio wave strength such as the most recent radio wave strength of communication device B.

[0171] Next, the position acquisition means 2343 performs the position estimation process described using the flowchart in FIG. 13, and calculates the similarity between the radio wave intensity vector at point X and the radio wave intensity vector (vector configured by radio wave intensity information) of each record in FIG. 8. Next, the position acquisition means 2343 calculates the similarity between the radio wave intensity vector at point X and the radio wave intensity vector of each record in FIG. 8 (for example, the radio wave intensity vector (S) of "ID=1" in FIG. 8) that satisfies the similarity condition "similarity ≥ threshold". 11 ,S 12 ,S 13 , ), and the signal strength vector of "ID=2" (S 21 ,S 22 ,S 23 ,...),...). Next, the position acquisition means 2343 acquires a pair of location information and similarity (for example, "(x1,y1),DS1", "(x2,y2),DS2"...) that is paired with the radio wave intensity vector that satisfies the similarity condition. Next, the position acquisition means 2343 acquires the indoor position of point X (x1×DS1 / sum of similarities+x2×DS2 / sum of similarities+..., y1×DS1 / sum of similarities+y2×DS2 / sum of similarities+...). Note that the sum of similarities is "DS1+DS2+...".

[0172] Next, the position output unit 241 outputs the indoor or outdoor map stored in the storage unit 21, and places a pattern on the map at the position indicated by the position information (terminal position) acquired by the position acquisition means 2343.

[0173] As described above, according to this embodiment, the position of the terminal device 2 indoors or outdoors can be easily acquired.

[0174] The processing in this embodiment may be implemented by software. This software may be distributed by software download or the like. Furthermore, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software implementing the terminal device 2 in this embodiment is the following program. That is, this program causes a computer to function as: a receiving unit that receives radio waves including a device identifier identifying each of three or more communication devices from each of the three or more communication devices; an intensity acquiring unit that acquires a time series of radio wave intensity for each of the three or more communication devices; a type determining unit that determines whether each of the three or more communication devices is a fixed terminal or a mobile terminal using the time series of radio wave intensity acquired by the intensity acquiring unit; a location acquiring unit that acquires a terminal position, which is location information of the terminal device, using the radio wave intensity of the three or more communication devices that the type determining unit has determined to be fixed terminals; and a location output unit that outputs the terminal position acquired by the location acquiring unit.

[0175] (Embodiment 3) In this embodiment, a behavior acquisition device is described that acquires user behavior information and a time period using user location information corresponding to a time, and outputs the behavior information associated with the time period. Note that it is preferable that the behavior acquisition device also acquires user behavior information and a time period using the user's activity data and vital data. Furthermore, the location information used when acquiring behavior information may be indoor location information, etc., acquired by the terminal device 2 described in the second embodiment.

[0176] In this embodiment, a behavior acquisition device that acquires behavior information using past record information will be described. Note that the past record information may be information based on input from one or more users.

[0177] In this embodiment, a behavior acquisition device that also acquires and outputs emotional information of a user will be described. In this embodiment, it is preferable to acquire emotional information using past recorded information.

[0178] In this embodiment, the behavior acquisition device is a terminal. However, as will be explained in embodiment 4, the behavior acquisition device may also be a server. In other words, the processes of acquiring behavior information and emotional information, which will be described later, may be performed by the user's terminal or the server.

[0179] In addition, in this embodiment, a behavior acquisition device that acquires and outputs location information using a map when behavior information cannot be acquired will be described.

[0180] Furthermore, in this embodiment, a behavior acquisition device that displays estimated behavior information and confirmed behavior information in a manner that visually distinguishes them will be described.

[0181] 16 is a conceptual diagram of an information system D according to this embodiment. The information system D includes one or more behavior acquisition devices 3, a server device 4, and three or more communication devices B.

[0182] The behavior acquisition device 3 is a terminal. The behavior acquisition device 3 is a device that acquires and outputs behavior information. The behavior acquisition device 3 may be, for example, a smartphone, a tablet terminal, a smartwatch, a so-called personal computer, or the like, and its type does not matter.

[0183] The server device 4 is, for example, a device that stores sets of behavior source information and behavior information for two or more users, each set for each time period. The server device 4 is, for example, a device that stores learning information, which will be described later, and provides the learning information to the behavior acquisition device 3. The server device 4 is, for example, a cloud server or an ASP server, but the type is not important.

[0184] 17 is a block diagram of the information system D in this embodiment. FIG.

[0185] The behavior acquisition device 3 includes a storage unit 31, a receiving unit 32, a processing unit 33, and an output unit 34. The storage unit 31 includes a learning management unit 311, a map management unit 312, and a behavior management unit 313. Note that the behavior management unit 313 may be present in an external device (not shown). The processing unit 33 includes an intensity acquisition unit 231, a type determination unit 232, a time acquisition unit 331, a position acquisition unit 332, an activity acquisition unit 333, a vital sign acquisition unit 334, a behavior estimation unit 335, an emotion estimation unit 336, a location acquisition unit 337, an accumulation unit 338, and a configuration unit 339. The output unit 34 includes a behavior output unit 341 and an emotion output unit 342.

[0186] The server device 4 includes a server storage unit 41, a server receiving unit 42, a server processing unit 43, and a server transmitting unit 44.

[0187] The behavior acquisition device 3 accepts, for example, output instructions, confirmation instructions, and information input. An output instruction is an instruction to output output information, which will be described later. An output instruction usually includes period information. Period information is information that specifies the period for outputting behavioral information, etc. A confirmation instruction is an instruction to confirm estimated behavioral information or emotional information. Information input is information for changing estimated behavioral information or emotional information when the estimated behavioral information or emotional information is incorrect. Information input is updated behavioral information or updated emotional information.

[0188] Various types of information are stored in the storage unit 31 constituting the behavior acquisition device 3. The various types of information include, for example, learning information (to be described later), a map (to be described later), behavior information (to be described later), location information, a calendar template, behavior information associated with two or more behavior conditions, and emotion information associated with two or more emotion conditions.

[0189] The calendar template is information that indicates the template of the calendar to be output. The calendar template may be, for example, an ICS file, a file written in HTML, or a file written in XML, but the data structure is not important.

[0190] An action condition is a condition for acquiring action information. An action condition is a condition using two or more pieces of action source information. An action condition is associated with action information. For example, an action condition is "location information = office AND 8:00 <= time <= 19:00", and the action information associated with this action condition is "work". For example, an action condition is "location information = kitchen AND activity data = standing AND 7:00 <= time <= 8:00", and the action information associated with this action condition is "cooking". For example, an action condition is "location information = park AND activity data = standing AND 120 <= heart rate", and the action information associated with this action condition is "running".

[0191] Emotion conditions are conditions for acquiring emotion information. Emotion conditions are conditions that use two or more pieces of emotion source information. Emotion conditions are associated with emotion information. For example, an emotion condition is "location information = office AND 8:00 <= time <= 19:00", and the emotion information associated with this behavioral condition is "positive". For example, an emotion condition is "location information = kitchen AND activity data = standing AND 7:00 <= time <= 8:00", and the emotion information associated with this behavioral condition is "positive". For example, a behavioral condition is "location information = park AND activity data = standing AND 120 <= heart rate", and the emotion information associated with this behavioral condition is "negative".

[0192] The learning management unit 311 stores learning information. The learning information is information based on two or more pieces of teacher data. The learning information in the learning management unit 311 is, for example, behavioral learning information and emotional learning information. Each of the two or more pieces of learning information in the learning management unit 311 may correspond to a different user attribute value condition. A user attribute value condition is a condition related to one or two or more user attribute values.

[0193] The user attribute value is a user's attribute value, such as occupation, family structure, single or married status, gender, age, age group, morning or night type, and residential area, but is not limited thereto.

[0194] The behavior learning information is information based on two or more behavioral teacher data. The behavior learning information is, for example, a behavior learning model or a behavior correspondence table. The emotion learning information is information based on two or more emotion teacher data. The emotion learning information is, for example, an emotion learning model or an emotion correspondence table.

[0195] The behavior instructor data includes, for example, one or more pieces of behavior source information and behavior information. The emotion instructor data includes, for example, one or more pieces of behavior source information, behavior information, and emotion information.

[0196] Emotion teacher data, for example, has one or more pieces of action source information or action information, and emotion information. Emotion teacher data, for example, has one or more pieces of action source information, action information, and emotion information. In the emotion teacher data, one or more pieces of action source information, action information, or one or more pieces of action source information and action information are explanatory variables, and emotion information is a target variable.

[0197] The behavioral information is information that identifies the user's behavior, such as "work," "watching TV," "walking," "running," "gym," "bath," and "sleep."

[0198] Emotion information is information about the user's emotions. Emotion information is, for example, positive (e.g., "1") or negative (e.g., "0"). Emotion information is, for example, the degree of positivity or negativity. Emotion information is, for example, joy (e.g., "1"), anger (e.g., "2"), sadness (e.g., "3"), and happiness (e.g., "4").

[0199] Action source information is information that serves as a source for acquiring action information. Action source information includes location information. Action source information preferably includes activity data or one or more types of vital data. Action source information may also include emotional information. Action source information may also include one or more pieces of past action information. Past action information typically includes immediately preceding action information. Action source information may also include one or more pieces of future schedule information for the user. Schedule information is, for example, information stored in a calendar server (e.g., a Google Calendar (registered trademark) server) not shown. Action source information may also include the elapsed time since the user arrived at the same location information. Action source information may also include one or more user attribute values.

[0200] The location information is information that specifies the location of the behavior acquisition device 3. The location information is, for example, (latitude, longitude), (latitude, longitude, altitude), a three-dimensional relative position indoors (x, y, z), or a two-dimensional relative position indoors (x, y), or location information. The location information is information that expresses the meaning of a location. The location information is, for example, indoor location information or outdoor location information. The indoor location information is information that specifies an indoor location. Examples of the indoor location information are "living room," "kitchen," "workroom," and "office." The outdoor location information is information that specifies an outdoor location. Examples of the outdoor location information are "ABC Station," "library," "izakaya," and "point A."

[0201] Physical data is information about the user's body, such as activity data and vital data.

[0202] The activity data is information that identifies the activity of the user. For example, the activity data is "standing" or "on the ground (e.g., sitting)."

[0203] Vital data is information that can be acquired from a user's body. Vital data may also be referred to as biological information. Examples of vital data include heart rate, heart rate variability, blood pressure (systolic and / or diastolic), respiratory rate, and body temperature per unit time (e.g., 1 minute or 30 seconds). Learning information may be, for example, a learning model or a correspondence table. A learning model is information constructed through machine learning learning processing using two or more sets of training data, and is information used in machine learning prediction processing. A learning model may also be referred to as a learner, classifier, classification model, etc. Machine learning algorithms may include deep learning, random forest, decision tree, SVM, etc. Furthermore, various machine learning functions, such as the TensorFlow (registered trademark) library, the random forest module in the R language, and TinySVM, as well as various existing libraries, may be used for machine learning. Furthermore, when the learning information is a learning model, one or more behavioral source information of the training data is an explanatory variable, and the behavioral information is a target variable.

[0204] The learning model here is, for example, a behavioral learning model or an emotion learning model. The behavioral learning model is a learning model for acquiring behavioral information, and is information acquired by machine learning learning processing using behavioral teacher data. The behavioral teacher data has one or more behavior source information and behavioral information.

[0205] The emotion learning model is a learning model for acquiring emotion information, and is information acquired through machine learning learning processing using emotion training data. The emotion training data has one or more emotion source information and emotion information.

[0206] The correspondence table is an action correspondence table or an emotion correspondence table. The action correspondence table is a table for acquiring action information. The action correspondence table has two or more pieces of action correspondence information. The action correspondence information is information showing the correspondence between one or more pieces of action source information and action information. Note that the one or more pieces of action source information have, for example, a vector structure. Such a vector is called an action source vector. The action source vector is a vector that has one or more pieces of action source information as elements. The emotion correspondence table has two or more pieces of emotion correspondence information. The emotion correspondence information is information showing the correspondence between one or more pieces of emotion source information and emotion information. The one or more pieces of emotion source information have, for example, a vector structure. Such a vector is called an emotion source vector. The emotion source vector is a vector that has one or more pieces of emotion source information as elements.

[0207] Maps are stored in the map management unit 312. The map has location information corresponding to one or more pieces of location information. The map is in KIWI format, for example, but the structure is not critical.

[0208] The behavior management unit 313 stores behavior information associated with each of two or more time periods. The behavior information here is, for example, information acquired by the behavior estimation unit 335. The behavior information is information acquired by the behavior estimation unit 335 that has been changed by the user.

[0209] It is preferable that the behavioral information here can be determined whether it is confirmed behavioral information. For example, a confirmation flag is associated with the behavioral information. The confirmation flag is a flag that indicates that the behavioral information is confirmed. Whether it is confirmed behavioral information can be determined, for example, when the storage areas for confirmed behavioral information and unconfirmed behavioral information are different. Any other method can be used to determine whether it is confirmed behavioral information.

[0210] The receiving unit 32 receives radio waves including a device identifier that identifies the communication device B from one or more communication devices B. The receiving unit 32 typically receives radio waves from three or more communication devices B. The receiving unit 32 has the same functions as the receiving unit 22.

[0211] The processing unit 33 performs various types of processing, such as processing performed by the intensity acquisition unit 231, the type determination unit 232, the time acquisition unit 331, and the like.

[0212] The time acquisition unit 331 acquires the time. For example, the time acquisition unit 331 acquires the time from a clock (not shown). For example, the time acquisition unit 331 receives the time from the server device 4 or a device (not shown). The time may be in hours, minutes, and seconds, or may be in hours and minutes. The time may include one or more pieces of information from "year," "month," and "day." The time acquisition unit 331 may also acquire the day of the week. The day of the week may be considered to be information included in the acquired time.

[0213] The position acquisition unit 332 acquires position information. The position information is associated with time. The position acquisition unit 332 usually acquires position information in association with the time acquired by the time acquisition unit 331. The position acquisition unit 332 may perform the same processing as the position acquisition unit 234. In particular, when the behavior acquisition device 3 is located indoors, for example, and a GPS signal cannot be received, the position acquisition unit 332 preferably performs the same processing as the position acquisition unit 234. The position acquisition unit 332 preferably includes a GPS receiver. The position acquisition unit 332 acquires position information using, for example, the GPS receiver. Such position information is absolute position information. The position information acquired by the position acquisition unit 332 may be either outdoor or indoor position information.

[0214] It is preferable that the location acquisition unit 332 acquires indoor location information using the radio wave intensity of the communication device B that the type determination unit 232 has determined to be a fixed terminal. The radio wave intensity used here is preferably the radio wave intensity of three or more communication devices B, but may be the radio wave intensity of one or two or more communication devices B.

[0215] The activity acquisition unit 333 acquires activity data of the user associated with a time. The activity acquisition unit 333 usually acquires the activity data associated with the time acquired by the time acquisition unit 331. The process of acquiring activity data is a well-known technique.

[0216] The vital sign acquisition unit 334 acquires one or more types of vital sign data of the user associated with a time. The vital sign acquisition unit 334 typically acquires one or more types of vital sign data associated with a time acquired by the time acquisition unit 331. The process of acquiring vital sign data is a well-known technique.

[0217] The behavior estimation unit 335 uses two or more pieces of behavior source information including location information associated with time to acquire behavior information that identifies the user's behavior in a time period identified by the time included in each of the two or more pieces of behavior source information. It is preferable that the behavior source information also includes activity data. It is also preferable that the behavior source information also includes one or two or more types of vital data.

[0218] The behavior estimation unit 335 detects a behavior condition that matches two or more pieces of behavior source information including, for example, location information associated with a time, and acquires, from the storage unit 31, behavior information that pairs with the behavior condition.

[0219] For example, if the user is sitting at a desk indoors at home at 1:15 PM, the behavior estimation unit 335 acquires behavior information "work." For example, if the user is sitting indoors in the living room at home at 8:17 PM, the behavior estimation unit 335 acquires behavior information "watching TV." For example, if the user acquires location information "izakaya" at 8:17 PM, the behavior estimation unit 335 acquires behavior information "drinking party."

[0220] The behavior estimation unit 335 may acquire behavior information for a time period using the behavior learning information of the learning management unit 311 and two or more pieces of behavior source information including location information associated with time. Below, we will explain the processing of the behavior estimation unit 335 when the learning information is a learning model and when it is a correspondence table.

[0221] The behavior estimation unit 335 may acquire one or more user attribute values, acquire behavioral learning information that pairs with the user attribute value conditions that match the one or more user attribute values ​​from the learning management unit 311, and use the behavioral learning information to acquire behavioral information. (1) When the behavioral learning information is a behavioral learning model

[0222] The behavior estimation unit 335 acquires the learning model of the learning management unit 311. The behavior estimation unit 335 also acquires a time and one or more pieces of behavior source information corresponding to the time. Next, the behavior estimation unit 335 provides the time, the behavior source information, and the learning model to a module that performs machine learning prediction processing, executes the module, and acquires behavior information.

[0223] If the score output by the module is equal to or less than the threshold, the behavior estimation unit 335 does not need to acquire behavior information. (2) When the behavioral learning information is a behavioral correspondence table

[0224] The behavior estimation unit 335 acquires a time and behavior source information associated with the time. Next, the behavior estimation unit 335 acquires a behavior source vector whose elements are the time and the behavior source information. Next, the behavior estimation unit 335 calculates the similarity between the behavior source vector and the behavior source vector included in each of two or more pieces of behavior correspondence information included in the behavior correspondence table. Next, the behavior estimation unit 335 acquires behavior information paired with the behavior source vector with the highest similarity from the behavior correspondence table. Note that even if the similarity is highest, the behavior estimation unit 335 does not need to acquire the behavior information if the similarity is equal to or less than a threshold value.

[0225] The emotion estimation unit 336 acquires emotion information related to the emotion of the user in a time period using the behavior information or the behavior source information.

[0226] The emotion estimation unit 336 detects an emotion condition that matches two or more pieces of emotion source information including, for example, location information associated with a time, and acquires emotion information paired with the emotion condition from the storage unit 31.

[0227] For example, when the user is sitting at a desk indoors at home at 1:15 PM, the emotion deduction unit 336 acquires emotion information "positive." When the user is sitting indoors in the living room of the home at 8:17 PM, the emotion deduction unit 336 acquires emotion information "positive." When the user acquires location information "izakaya" at 8:17 PM, the emotion deduction unit 336 acquires emotion information "positive."

[0228] The emotion estimation unit 336 acquires emotion information for a time period using the emotion learning information of the learning management unit 311 and the behavior information acquired by the behavior estimation unit 335 or one or more pieces of behavior source information that were the basis for acquiring the behavior information. Note that the behavior information or one or more pieces of behavior source information are referred to as emotion source information here because they are used to acquire emotion information.

[0229] The emotion estimation unit 336 may acquire one or more user attribute values, acquire emotion learning information paired with a user attribute value condition that matches the one or more user attribute values ​​from the learning management unit 311, and acquire emotion information using the emotion learning information.

[0230] The emotion estimation unit 336 will now explain the processing of the behavior estimation unit 335 when the emotion learning information is an emotion learning model and when the emotion correspondence table is used. (1) When the emotion learning information is an emotion learning model

[0231] The emotion deduction unit 336 acquires the emotion learning model from the learning management unit 311. The emotion deduction unit 336 also acquires one or more pieces of action source information or action information associated with the time. Next, the emotion deduction unit 336 provides the acquired one or more pieces of action source information or action information and the emotion learning model to a module that performs machine learning prediction processing, executes the module, and acquires emotion information.

[0232] If the score output by the module is equal to or less than the threshold, the emotion estimation unit 336 does not need to acquire emotion information. (2) When the emotion learning information is an emotion correspondence table

[0233] The emotion deduction unit 336 acquires one or more pieces of action source information or action information associated with the time. Next, the emotion deduction unit 336 acquires an emotion source vector whose elements are the one or more pieces of action source information or action information. Next, the emotion deduction unit 336 calculates the similarity between the emotion source vector and the emotion source vectors included in each of two or more pieces of correspondence information included in the emotion correspondence table. Next, the emotion deduction unit 336 acquires, from the emotion correspondence table, emotion information paired with the emotion source vector with the highest similarity. Note that the emotion deduction unit 336 does not need to acquire emotion information if the similarity is equal to or less than a threshold, even if the similarity is at its highest.

[0234] The location acquisition unit 337 refers to the map in the map management unit 312 and acquires location information corresponding to the location information acquired by the location acquisition unit 332. The location information in this case is usually absolute location information (for example, (latitude, longitude)).

[0235] It is preferable that the location acquisition unit 337 acquires location information only for a time period during which the behavior estimation unit 335 did not acquire behavior information.

[0236] The accumulation unit 338 accumulates the behavior information acquired by the behavior estimation unit 335 in the behavior management unit 313 in association with the time period.

[0237] The storage unit 338 may store the emotion information acquired by the emotion estimation unit 336 in the behavior management unit 313 in association with the time period.

[0238] The composition unit 339 composes information to be output using the behavior information of the behavior management unit 313. The composition unit 339 composes information to be output using, for example, emotion information of the behavior management unit 313.

[0239] The composition unit 339, for example, composes output information having behavioral information paired with each time period in an area specified by each of two or more time periods on a calendar. In the output information, it is preferable that the two or more pieces of behavioral information are arranged so that confirmed behavioral information and unconfirmed behavioral information are visually distinguishable. It is preferable that the composition unit 339 composes output information that visually indicates emotion information corresponding to each of two or more time periods. It is preferable that the composition unit 339 composes output information that visually indicates time periods in which emotion information is "positive" and time periods in which emotion information is "negative." It is preferable that the composition unit 339 composes output information so that time periods in which emotion information is "positive" and time periods in which emotion information is "negative" have different background colors, for example.

[0240] The output unit 34 outputs various types of information, such as behavior information, emotion information, and location information.

[0241] Here, output usually means display on a display, but it may also be a concept that includes projection using a projector, printing on a printer, transmission to an external device, storage on a recording medium, and handing over the processing results to other processing devices or other programs.

[0242] The behavior output unit 341 outputs behavior information for each of one or more time periods.

[0243] It is preferable that the behavior output unit 341 outputs the location acquired by the location acquisition unit 337 when the behavior estimation unit 335 cannot acquire behavior information.

[0244] It is preferable that the behavior output unit 341 outputs two or more pieces of behavior information so that the confirmed behavior information and the unconfirmed behavior information can be visually distinguished.

[0245] The emotion output unit 342 outputs emotion information. For example, the emotion output unit 342 outputs emotion information acquired by the emotion estimation unit 336. The emotion output unit 342 preferably outputs emotion information for one or more time periods.

[0246] Various types of information are stored in the server storage unit 41 constituting the server device 4. The various types of information include, for example, the above-mentioned learning information, behavior source information and time corresponding to each of two or more user identifiers, two or more pieces of behavior teacher data, and two or more pieces of emotion teacher data.

[0247] The server receiving unit 42 receives various instructions and information. The various instructions and information are, for example, instructions to transmit information. The information here is, for example, learning information and behavior source information.

[0248] The server processing unit 43 performs various types of processing, such as learning processing, including behavior learning processing and emotion learning processing.

[0249] The behavioral learning process is a process of acquiring a behavioral learning model using two or more pieces of behavioral teacher data. The server processing unit 43, for example, provides two or more pieces of behavioral teacher data to a machine learning learning processing module, executes the module, acquires a behavioral learning model, and stores it in the server storage unit 41. For example, the server processing unit 43 provides two or more positive examples, which are teacher data including behavioral information, and two or more negative examples, which are teacher data not including behavioral information, to the machine learning learning processing module for each of two or more behavioral information candidates, executes the module, acquires a behavioral learning model for each behavioral information candidate, and stores it in the server storage unit 41 in association with the behavioral information. The server processing unit 43, for example, acquires a behavior correspondence table, which is a table in which each of two or more pieces of behavioral teacher data is a record, and stores it in the server storage unit 41.

[0250] Emotion learning processing is processing for acquiring an emotion learning model using two or more pieces of emotion teacher data. The server processing unit 43, for example, provides two or more pieces of emotion teacher data to a machine learning learning processing module, executes the module, acquires an emotion learning model, and stores it in the server storage unit 41. For example, the server processing unit 43 provides two or more positive examples that are teacher data including emotion information and two or more negative examples that are teacher data not including emotion information to the machine learning learning processing module for each of two or more emotion information candidates, executes the module, acquires an emotion learning model for each emotion information candidate, and stores it in the server storage unit 41 in association with the emotion information. The server processing unit 43, for example, acquires an emotion correspondence table, which is a table in which each of two or more pieces of emotion teacher data is a record, and stores it in the server storage unit 41.

[0251] The server transmitting unit 44 transmits various types of information, such as a behavior learning model, an emotion learning model, a behavior correspondence table, and an emotion correspondence table.

[0252] The storage unit 31, learning management unit 311, map management unit 312, behavior management unit 313, and server storage unit 41 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0253] There is no restriction on the process by which information is stored in the storage unit 31 etc. For example, information may be stored in the storage unit 31 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 31 etc., or information input via an input device may be stored in the storage unit 31 etc.

[0254] The receiving unit 32, the server receiving unit 42, and the server transmitting unit 44 are typically realized by wireless or wired communication means.

[0255] The processing unit 33, time acquisition unit 331, position acquisition unit 332, activity acquisition unit 333, vital sign acquisition unit 334, behavior estimation unit 335, emotion estimation unit 336, location acquisition unit 337, accumulation unit 338, configuration unit 339, and server processing unit 43 can typically be realized by a processor, memory, or the like. The processing procedures of the processing unit 33, etc., are typically realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, or the like, and the type does not matter.

[0256] The output unit 34, the behavior output unit 341, and the emotion output unit 342 may or may not include output devices such as a display, a speaker, etc. The output unit 34 may be realized by driver software for an output device, or by a combination of driver software for an output device and the output device, etc.

[0257] Next, an example of the operation of the behavior acquisition device 3 constituting the information system D will be described with reference to the flowchart of FIG.

[0258] (Step S1901) The processing unit 33 determines whether or not to acquire information. If the information is to be acquired, the process proceeds to step S1902, and if the information is not to be acquired, the process proceeds to step S1916. The processing unit 33 may always determine to acquire information, or may determine to acquire information when a flag indicating that the information is to be acquired is stored in the storage unit 31, for example. The conditions for such a determination are not important.

[0259] (Step S1902) The time acquiring unit 331 acquires the time from a clock (not shown). Here, the time acquiring unit 331 may also acquire the day of the week.

[0260] (Step S1903) The processing unit 33 acquires one or more pieces of action source information. An example of such action source acquisition processing will be described with reference to the flowchart of FIG.

[0261] (Step S1904) The behavior estimation unit 335 estimates behavior information that identifies the user's behavior, using one or more pieces of behavior source information acquired in step S1903. An example of such behavior estimation processing will be described with reference to the flowcharts of Figs. 22 to 24.

[0262] (Step S1905) The location acquisition unit 337 determines whether or not the behavior information was acquired in step S1904. If the behavior information was acquired, the process proceeds to step S1907, and if the behavior information was not acquired, the process proceeds to step S1906.

[0263] (Step S1906) The location acquisition unit 337 refers to the map in the map management unit 312 and acquires location information corresponding to the position information acquired in step S1903. Note that there may be times when location information cannot be acquired.

[0264] (Step S1907) The accumulation unit 338 determines whether the behavior information stored in a buffer (not shown) most recently accumulated matches the behavior information acquired in step S1904. If they match, the process proceeds to step S1908, and if they do not match, the process proceeds to step S1912.

[0265] (Step S1908) The accumulation unit 338 associates the acquired behavior information and the like with the time acquired in step S1902, and accumulates them in a buffer (not shown).

[0266] (Step S1909) The feeling estimation unit 336 performs a process of estimating feeling information. An example of the feeling estimation process will be described with reference to the flowcharts in FIGS. 25 to 27.

[0267] (Step S1910) Accumulation section 338 determines whether or not emotion information was acquired in step S1909. If emotion information was acquired, the process proceeds to step S1911, and if emotion information was not acquired, the process returns to step S1901.

[0268] (Step S1911) Accumulation section 338 accumulates the emotion information acquired in step S1909 in a buffer (not shown) in association with the time acquired in step S1902. Processing returns to step S1901.

[0269] (Step S1912) The accumulation unit 338 accumulates the time acquired in step S1902 and the acquired behavior information and the like in a buffer (not shown) in association with each other.

[0270] (Step S1913) The accumulation unit 338 acquires the immediately preceding behavior information and the like.

[0271] (Step S1914) The accumulation unit 338 acquires a time period specified by two or more times associated with the immediately preceding behavioral information or the like.

[0272] (Step S1915) The storage unit 338 associates the time period acquired in step S1914 with the immediately preceding behavior information, etc. acquired in step S1913, and stores them in the behavior management unit 313. Note that here, the storage unit 338 may also associate the time period with the immediately preceding behavior information, etc., and store them in association with the user identifier. In such a case, it is preferable that the storage destination be the server device 4.

[0273] (Step S1916) The behavior acquisition device 3 determines whether or not an output instruction has been accepted. If an output instruction has been accepted, the process proceeds to step S1917, and if not, the process proceeds to step S1919.

[0274] (Step S1917) The composition unit 339 composes output information using the behavior information and the like from the behavior management unit 313. An example of such output composition processing will be described with reference to the flowchart of FIG.

[0275] (Step S1918) The output unit 34 outputs the output information constructed in step S1917. The process returns to step S1901.

[0276] (Step S1919) The behavior acquisition device 3 determines whether or not input of information has been accepted for the output information being output. If input of information has been accepted, the process proceeds to step S1920, and if not, the process proceeds to step S1923.

[0277] (Step S1920) The processing unit 33 determines whether the information received in step S1919 is a confirmation instruction for the estimated behavioral information or the estimated emotion information. If it is a confirmation instruction, the processing unit 33 proceeds to step S1921, and if it is not a confirmation instruction, the processing unit 33 proceeds to step S1922.

[0278] (Step S1921) The accumulation unit 338 performs processing to confirm the behavioral information or emotion information corresponding to the confirmation instruction. Return to step S1901. Note that this processing is, for example, processing to associate a confirmation flag with the behavioral information corresponding to the confirmation instruction or the emotion information corresponding to the confirmation instruction.

[0279] (Step S1922) The storage unit 338 stores the input information. Return to step S1901. The input information is, for example, correct behavioral information or correct emotional information. Then, the storage unit 338 updates the estimated behavioral information or emotional information corresponding to the input information to the input behavioral information or emotional information. Furthermore, the storage unit 338 performs processing to confirm the behavioral information or emotional information.

[0280] (Step S1923) The behavior acquisition device 3 determines whether or not a learning instruction has been received. If a learning instruction has been received, the process proceeds to step S1924, and if not, the process returns to step S1901.

[0281] (Step S1924) A learning unit (not shown) or a learning device (not shown) of the behavior acquisition device 3 uses two or more pieces of behavioral teacher data including behavior information, etc. to configure behavioral learning information and accumulate it in the learning management unit 311. An example of such behavioral learning processing will be described using the flowcharts of Figures 29 and 30.

[0282] (Step S1925) A learning unit (not shown) or a learning device (not shown) of the behavior acquisition device 3 uses two or more pieces of emotion teacher data including emotion information, etc. to configure emotion learning information and store it in the learning management unit 311. Return to step S1901. An example of such emotion learning processing will be described using the flowcharts in FIGS. 31 and 32.

[0283] In the flowchart of FIG. 19, the process ends when the power is turned off or an interrupt occurs to end the process.

[0284] Next, an example of the action source acquisition process in step S1903 will be described with reference to the flowchart in FIG.

[0285] (Step S2001) The processing unit 33 determines whether or not the receiving unit 32 has acquired a GPS signal. If the GPS signal has been acquired, the process proceeds to step S2002, and if the GPS signal has not been acquired, the process proceeds to step S2003.

[0286] (Step S2002) The position acquisition unit 332 acquires absolute position information based on the GPS signal received by the receiving unit 32.

[0287] (Step S2003) The position acquisition unit 332 acquires position information. An example of such position estimation processing will be described with reference to the flowchart of FIG.

[0288] (Step S2004) The activity acquisition unit 333 acquires the activity data of the user.

[0289] (Step S2005) The vital sign acquisition unit 334 acquires one or more types of vital sign data of the user.

[0290] (Step S2006) The behavior estimation unit 335 acquires one or more pieces of past behavior information. The one or more pieces of past behavior information include behavior information immediately preceding the one in time.

[0291] (Step S2007) Behavior estimation unit 335 determines whether or not to use emotion information for behavior estimation processing. If emotion information is to be used, the process proceeds to step S2008, and if emotion information is not to be used, the process proceeds to step S2009. Note that whether or not emotion information is to be used for behavior estimation processing is usually determined in advance.

[0292] (Step S2008) The emotion estimation unit 336 acquires emotion information. An example of such emotion estimation processing will be described with reference to the flowcharts of FIGS.

[0293] (Step S2009) The behavior inferrer 335 acquires the elapsed time since the start of the new behavior specified by the new behavior information.

[0294] (Step S2010) The behavior estimation unit 335 uses two or more types of behavior source information including time and location information to configure information to be used in the behavior estimation process. The process returns to the upper level process. Here, the configured information is usually a collection of behavior source information, for example, a behavior source vector with two or more pieces of behavior source information as elements. The two or more types of behavior source information are, for example, two or more types of information from the following: time, day of the week, location information, activity data, vital data, past behavior information, emotion information, and elapsed time.

[0295] In the flowchart of FIG. 20, even if a GPS signal is acquired, the position acquisition unit 332 may acquire position information by a position estimation process which will be described using the flowchart of FIG.

[0296] 20, the behavior estimation unit 335 may acquire one or more user attribute values ​​and acquire behavior source information including the one or more user attribute values. The user attribute values ​​may be information stored in the storage unit 31 or may be information input by the user. Next, an example of the position estimation process of step S2003 will be described using the flowchart of FIG. 21. In the flowchart of FIG. 21, descriptions of steps that are the same as those in FIG. 13 will be omitted. The position estimation process of step S2003 may be the same process as that in the flowchart of FIG. 13.

[0297] (Step S2101) The position acquisition unit 332 acquires the similarity between the two radio wave intensity vectors, associates the similarity with the i-th point information, and temporarily stores the similarity in a buffer (not shown). Then, the process proceeds to step S1308.

[0298] (Step S2102) The location acquisition unit 332 acquires location information included in the spot information paired with the highest similarity. The process returns to the upper level process. The acquired location information is the terminal location.

[0299] Next, an example of the first behavior estimation process in step S1904 will be described with reference to the flowchart in Fig. 22. The flowchart in Fig. 22 illustrates a process for estimating behavior information through machine learning prediction processing using one behavior learning model. In other words, the flowchart in Fig. 22 illustrates a process for estimating behavior information through machine learning multi-value classification prediction processing.

[0300] (Step S2201) The behavior estimation unit 335 acquires two or more types of behavior source information (for example, behavior source vectors) acquired in step S1903.

[0301] (Step S2202) The behavior estimation unit 335 acquires a behavior learning model from the learning management unit 311.

[0302] (Step S2203) The behavior estimation unit 335 provides the two or more types of behavior source information and the behavior learning model acquired in step S2201 to a machine learning prediction processing module, and executes the module.

[0303] (Step S2204) The behavior estimation unit 335 acquires estimated behavior information and a score, which are the execution results in step S2203.

[0304] (Step S2205) The behavior estimation unit 335 determines whether the score acquired in step S2204 is equal to or greater than a threshold. If it is equal to or greater than the threshold, the process proceeds to step S2206, and if it is less than the threshold, the process proceeds to step S2207.

[0305] (Step S2206) The behavior estimation unit 335 acquires the behavior information acquired in step S2204 as behavior information to be output, and returns to the upper-level processing.

[0306] (Step S2207) The behavior estimation unit 335 acquires the behavior information of “empty.” The process returns to the upper level process.

[0307] In the flowchart of FIG. 22, the processes from step S2205 to step S2207 do not have to be performed.

[0308] Next, an example of the second behavior estimation process in step S1904 will be described with reference to the flowchart in Fig. 23. The flowchart in Fig. 23 illustrates a process for estimating behavioral information through machine learning prediction processing using a behavioral learning model for each of two or more behavioral information candidates. In other words, the flowchart in Fig. 22 illustrates a process for estimating behavioral information through machine learning binary classification prediction processing.

[0309] (Step S2301) The behavior estimation unit 335 acquires two or more types of behavior source information acquired in step S1903.

[0310] (Step S2302) The behavior estimation unit 335 assigns 1 to a counter i.

[0311] (Step S2303) The behavior estimation unit 335 determines whether or not a candidate for the i-th behavior information exists, with reference to the learning management unit 311. If a candidate for the i-th behavior information exists, the process proceeds to step S2304; if not, the process proceeds to step S2309.

[0312] (Step S2304) The behavior estimation unit 335 acquires, from the learning management unit 311, the i-th behavior learning model paired with the i-th behavior information candidate.

[0313] (Step S2305) The behavior estimation unit 335 provides the two or more types of behavior source information acquired in step S2301 and the i-th behavior learning model acquired in step S2304 to a prediction processing module that performs binary classification in machine learning, and executes the module.

[0314] (Step S2306) The behavior inferrer 335 determines whether the execution result in step S2305 is “true.” If “true,” the process proceeds to step S2307, and if “false,” the process proceeds to step S2308.

[0315] (Step S2307) The behavior inferrer 335 temporarily stores the score, which is part of the execution result in step S2305, in a buffer (not shown) in association with the i-th behavior information candidate.

[0316] (Step S2308) The behavior estimation unit 335 increments the counter i by 1. The process returns to step S2303.

[0317] (Step S2309) The behavior estimation unit 335 acquires the maximum score and determines whether the score is equal to or greater than a threshold. If the maximum score is equal to or greater than the threshold, the process proceeds to step S2310, and if it is less than the threshold, the process proceeds to step S2311.

[0318] (Step S2310) The behavior estimation unit 335 selects the behavior information paired with the maximum score and returns to the upper level process.

[0319] (Step S2311) The behavior estimation unit 335 acquires the behavior information of “empty.” Then, the process returns to the upper level process.

[0320] In the flowchart of FIG. 23, the processes from step S2308 to step S2311 do not have to be performed.

[0321] Next, an example of the third behavior estimation process in step S1904 will be described with reference to the flowchart in Fig. 24. The flowchart in Fig. 24 shows a process of estimating behavior information using a behavior correspondence table.

[0322] (Step S2401) The behavior estimation unit 335 acquires two or more types of behavior source information acquired in step S1903. The two or more types of behavior source information here are behavior source vectors.

[0323] (Step S2402) The behavior estimation unit 335 assigns 1 to a counter i.

[0324] (Step S2403) The behavior estimation unit 335 determines whether or not the i-th behavior correspondence information exists in the behavior correspondence table of the learning management unit 311. If the i-th behavior correspondence information exists, the process proceeds to step S2404; if not, the process proceeds to step S2407.

[0325] (Step S2404) The behavior estimation unit 335 acquires the i-th behavior source vector included in the i-th behavior correspondence information.

[0326] (Step S2405) The behavior estimation unit 335 obtains the similarity between the behavior origin vector obtained in step S2403 and the behavior origin vector obtained in step S2404, and associates it with the i-th behavior correspondence information.

[0327] (Step S2406) The behavior estimation unit 335 increments the counter i by 1. The process returns to step S2403.

[0328] (Step S2407) The behavior estimation unit 335 acquires the maximum similarity.

[0329] (Step S2408) The behavior estimation unit 335 determines whether the maximum similarity acquired in step S2407 is equal to or greater than a threshold. If it is equal to or greater than the threshold, the process proceeds to step S2409, and if it is less than the threshold, the process proceeds to step S2410.

[0330] (Step S2409) The behavior estimation unit 335 acquires behavior information associated with the i-th behavior correspondence information paired with the maximum similarity, and returns to the upper level processing.

[0331] (Step S2410) The behavior estimation unit 335 acquires the behavior information of “empty.” Then, the process returns to the upper level process.

[0332] In the flowchart of FIG. 24, the processes from step S2408 to step S2411 do not have to be performed.

[0333] Next, an example of the first emotion estimation process in step S1909 will be described using the flowchart in Fig. 25. The flowchart in Fig. 25 illustrates a process for estimating emotion information through machine learning prediction processing using one emotion learning model. In other words, the flowchart in Fig. 25 illustrates a process for estimating emotion information through machine learning multi-value classification prediction processing.

[0334] (Step S2501) The emotion estimation unit 336 acquires two or more types of behavior source information acquired in step S1903. Here, each of the two or more types of behavior source information is emotion source information. In addition, the two or more types of emotion source information are, for example, emotion source vectors.

[0335] (Step S2502) The emotion estimation unit 336 acquires an emotion learning model from the learning management unit 311.

[0336] (Step S2503) The emotion estimation unit 336 provides the two or more types of emotion source information and the emotion learning model acquired in step S2501 to a machine learning prediction processing module and executes the module.

[0337] (Step S2504) The emotion estimation unit 336 acquires the estimated emotion information and score, which are the execution results of step S2503.

[0338] (Step S2505) The feeling estimation unit 336 determines whether the score acquired in step S2504 is equal to or greater than a threshold. If it is equal to or greater than the threshold, the process proceeds to step S2506, and if it is less than the threshold, the process proceeds to step S2507.

[0339] (Step S2506) Emotion estimation unit 336 acquires the emotion information acquired in step S2504 as emotion information to be output, and returns to the upper-level processing.

[0340] (Step S2507) The emotion estimation unit 336 acquires emotion information of “sky.” The process returns to the upper level process.

[0341] In the flowchart of FIG. 25, the processes from step S2505 to step S2507 do not have to be performed.

[0342] Next, an example of the second emotion estimation process in step S1909 will be described using the flowchart in Fig. 26. The flowchart in Fig. 26 illustrates a process for estimating emotion information through machine learning prediction processing using an emotion learning model for each of two or more emotion information candidates. In other words, the flowchart in Fig. 26 illustrates a process for estimating emotion information through machine learning binary classification prediction processing.

[0343] (Step S2601) The emotion estimation unit 336 acquires two or more types of emotion source information acquired in step S1903.

[0344] (Step S2602) The feeling estimation unit 336 assigns 1 to a counter i.

[0345] (Step S2603) Emotion estimation unit 336 determines whether or not a candidate for the i-th emotion information exists, with reference to learning management unit 311. If a candidate for the i-th emotion information exists, proceed to step S2604; if not, proceed to step S2609.

[0346] (Step S2604) Emotion estimation unit 336 acquires, from learning management unit 311, the i-th emotion learning model paired with the i-th emotion information candidate.

[0347] (Step S2605) The emotion estimation unit 336 provides the two or more types of emotion source information acquired in step S2601 and the i-th emotion learning model acquired in step S2604 to a prediction processing module that performs binary classification in machine learning, and executes the module.

[0348] (Step S2606) The feeling estimation unit 336 determines whether the execution result in step S2605 is “true.” If “true,” the process proceeds to step S2607, and if “false,” the process proceeds to step S2608.

[0349] (Step S2607) The emotion estimation unit 336 temporarily accumulates the score, which is part of the execution result in step S2605, in a buffer (not shown), in association with the i-th emotion information candidate.

[0350] (Step S2608) The emotion estimation unit 336 increments the counter i by 1. The process returns to step S2603.

[0351] (Step S2609) The feeling estimation unit 336 acquires the maximum score and determines whether the score is equal to or greater than a threshold. If the maximum score is equal to or greater than the threshold, the process proceeds to step S2610, and if it is less than the threshold, the process proceeds to step S2611.

[0352] (Step S2610) The emotion estimation unit 336 selects the emotion information paired with the maximum score and returns to the upper level process.

[0353] (Step S2611) The emotion estimation unit 336 acquires emotion information of “sky.” The process returns to the upper level process.

[0354] In the flowchart of FIG. 26, the processes from step S2608 to step S2611 do not have to be performed.

[0355] Next, an example of the third emotion estimation process in step S1909 will be described using the flowchart in Fig. 27. The flowchart in Fig. 27 shows a process for estimating emotion information using an emotion correspondence table.

[0356] (Step S2701) The emotion estimation unit 336 acquires two or more types of emotion source information acquired in step S1903. The two or more types of emotion source information here are emotion source vectors.

[0357] (Step S2702) The feeling estimation unit 336 assigns 1 to a counter i.

[0358] (Step S2703) The emotion estimation unit 336 determines whether the i-th emotion correspondence information exists in the emotion correspondence table of the learning management unit 311. If the i-th emotion correspondence information exists, the process proceeds to step S2704; if not, the process proceeds to step S2707.

[0359] (Step S2704) The emotion estimation unit 336 acquires the i-th emotion source vector included in the i-th emotion correspondence information.

[0360] (Step S2705) The emotion estimation unit 336 obtains the similarity between the emotion source vector obtained in step S2703 and the emotion source vector obtained in step S2704, and associates it with the i-th emotion correspondence information.

[0361] (Step S2706) The emotion estimation unit 336 increments the counter i by 1. The process returns to step S2703.

[0362] (Step S2707) The emotion estimation unit 336 acquires the maximum similarity.

[0363] (Step S2708) The feeling estimation unit 336 determines whether the maximum similarity acquired in step S2707 is equal to or greater than a threshold. If it is equal to or greater than the threshold, the process proceeds to step S2709, and if it is less than the threshold, the process proceeds to step S2710.

[0364] (Step S2709) The emotion estimation unit 336 acquires emotion information associated with the i-th emotion association information paired with the highest similarity, and returns to the upper-level process.

[0365] (Step S2710) The emotion estimation unit 336 acquires emotion information of “sky.” The process returns to the upper level process.

[0366] In the flowchart of FIG. 27, the processes from step S2708 to step S2711 do not have to be performed.

[0367] Next, an example of the output configuration process in step S1917 will be described with reference to the flowchart in FIG.

[0368] (Step S2801) The configuration unit 339 acquires a template of a calendar from the storage unit 31.

[0369] (Step S2802) The configuration unit 339 assigns 1 to the counter i.

[0370] (Step S2803) The configuration unit 339 determines whether or not the i-th time period exists stored in the behavior management unit 313. If the i-th time period exists, the process proceeds to step S2804, and if not, the process returns to the upper level processing. Note that the behavior management unit 313 stores behavior information and emotion information in association with each of one or more time periods.

[0371] (Step S2804) The configuration unit 339 determines whether the i-th time period stored in the behavior management unit 313 is included in the period covered by the calendar template acquired in step S2801. If it is included, the process proceeds to step S2805; if it is not included, the process proceeds to step S2809.

[0372] (Step S2805) The configuration unit 339 acquires the behavior information paired with the i-th time period from the behavior management unit 313.

[0373] (Step S2806) Composition unit 339 acquires emotion information paired with the i-th time period from behavior management unit 313. Note that emotion information does not necessarily have to be acquired here.

[0374] (Step S2807) The composition unit 339 composes time zone information, which is information to be arranged in the i-th time zone of the calendar, and is information that can identify the behavioral information acquired in step S2805 and the emotion information acquired in step S2806.

[0375] (Step S2808) The composition unit 339 places the time period information composed in step S2807 at the position in the calendar specified by the i-th time period.

[0376] (Step S2809) The configuration unit 339 increments the counter i by 1. The process returns to step S2803.

[0377] Next, an example of the first behavior learning process in step S1924 will be described using the flowchart in Fig. 29. Note that the behavior learning process is performed, for example, by a learning unit (not shown). The learning unit may be a learning device different from the behavior acquisition device 3. The first behavior learning process is a process of acquiring a behavior learning model for multi-value classification.

[0378] (Step S2901) The learning unit assigns 1 to a counter i.

[0379] (Step S2902) The learning unit determines whether or not the i-th behavior information, etc. exists in the behavior management unit 313. If the i-th behavior information, etc. exists, the process proceeds to step S2903, and if not, the process proceeds to step S2905.

[0380] (Step S2903) The learning unit uses the i-th behavior information, etc. to construct behavioral teacher data and appends it to a buffer (not shown). Note that the behavioral teacher data is usually information that uses two or more types of behavior source information as explanatory variables and behavior information as a target variable.

[0381] (Step S2904) The learning unit increments the counter i by 1. The process returns to step S2902.

[0382] (Step S2905) The learning unit provides two or more pieces of behavioral teacher data stored in a buffer (not shown) to a machine learning learning processing module, executes the module, and acquires a behavioral learning model.

[0383] (Step S2906) The learning unit accumulates the behavior learning model acquired in step S2905 in the learning management unit 311.

[0384] In the flowchart of Figure 29, the learning unit may not perform the learning processing of steps S2905 and S2906, but may instead store in the learning management unit 311 a behavior correspondence table in a buffer not shown, with two or more behavior teacher data records (behavior correspondence information) for each behavior.

[0385] Next, an example of the second behavior learning process in step S1924 will be described with reference to the flowchart in Fig. 30. The second behavior learning process is a process for acquiring a binary classification behavior learning model for each of two or more behavior information candidates.

[0386] (Step S3001) The learning unit assigns 1 to a counter i.

[0387] (Step S3002) The learning unit determines whether or not the i-th type of behavioral information exists. If the i-th type of behavioral information exists, the process proceeds to step S3003, and if not, the process returns to the upper level process.

[0388] (Step S3003) The learning unit acquires the i-th type of behavior information.

[0389] (Step S3004) The learning unit acquires two or more positive examples, which are teacher data in the behavior management unit 313 and are behavior teacher data including the i-th type of behavior information.

[0390] (Step S3005) The learning unit acquires two or more negative examples, which are teacher data in the behavior management unit 313 and are behavior teacher data that do not include the i-th type of behavior information.

[0391] (Step S3006) The learning unit provides the two or more positive examples acquired in step S3004 and the two or more negative examples acquired in step S3005 to a machine learning learning processing module, executes the module, and acquires a behavioral learning model.

[0392] (Step S3007) The learning unit stores the behavior learning model acquired in step S3006 in the learning management unit 311 in pairs with the i-th type of behavior information.

[0393] (Step S3008) The learning unit increments the counter i by 1. The process returns to step S3002.

[0394] Next, an example of the first emotion learning process in step S1925 will be described using the flowchart in Fig. 31. Note that the behavior learning process is performed, for example, by a learning unit (not shown). The learning unit may be a learning device different from the behavior acquisition device 3. The first emotion learning process is a process for acquiring a multi-value classification emotion learning model.

[0395] (Step S3101) The learning unit assigns 1 to a counter i.

[0396] (Step S3102) The learning unit determines whether or not the i-th emotion information, etc. exists in the behavior management unit 313. If the i-th emotion information, etc. exists, the process proceeds to step S3103, and if not, the process proceeds to step S3105.

[0397] (Step S3103) The learning unit uses the i-th emotion information, etc. to create emotion teacher data and adds it to a buffer (not shown). Note that the emotion teacher data is information that uses two or more types of emotion source information as explanatory variables and emotion information as a target variable.

[0398] (Step S3104) The learning unit increments the counter i by 1. The process returns to step S3102.

[0399] (Step S3105) The learning unit provides two or more pieces of emotion teacher data stored in a buffer (not shown) to a machine learning learning processing module, executes the module, and acquires an emotion learning model.

[0400] (Step S3106) The learning unit accumulates the emotion learning model acquired in step S3105 in the learning management unit 311.

[0401] In the flowchart of FIG. 31, the learning unit may store an emotion correspondence table in a buffer (not shown) in learning management unit 311, with two or more emotion teacher data records (emotion correspondence information) instead of performing the learning processes in steps S3105 and S3106.

[0402] Next, an example of the second emotion learning process of step S1925 will be described using the flowchart in Fig. 32. The second emotion learning process is a process for acquiring an emotion learning model for binary classification for each of two or more emotion information candidates.

[0403] (Step S3201) The learning unit assigns 1 to a counter i.

[0404] (Step S3202) The learning unit determines whether or not the i-th type of emotion information exists. If the i-th type of emotion information exists, the process proceeds to step S3203; if not, the process returns to the upper level processing.

[0405] (Step S3203) The learning unit acquires the i-th type of emotion information.

[0406] (Step S3204) The learning unit acquires two or more positive examples, which are emotion teacher data in the behavior management unit 313 and which are emotion teacher data including emotion information of the ith type.

[0407] (Step S3205) The learning unit acquires two or more negative examples, which are emotion teacher data in the behavior management unit 313 and which are emotion teacher data that do not contain emotion information of the i-th type.

[0408] (Step S3206) The learning unit provides the two or more positive examples acquired in step S3204 and the two or more negative examples acquired in step S3205 to a machine learning learning processing module, executes the module, and acquires an emotion learning model.

[0409] (Step S3207) The learning unit stores the emotion learning model acquired in step S3206 in learning management unit 311, paired with the i-th type of emotion information.

[0410] (Step S3208) The learning unit increments the counter i by 1. The process returns to step S3202.

[0411] A specific example of the operation of the information system D in this embodiment will be described below. Currently, the storage unit 31 of the server device 4 stores a behavior learning model acquired by a machine learning learning process using a large amount of teacher data including behavior source information of one or more users. The storage unit 31 also stores an emotion learning model acquired by a machine learning learning process using a large amount of teacher data including emotion source information of one or more users.

[0412] In addition, in the storage unit 31 of the behavior acquisition device 3, which is a terminal (e.g., a smart watch) held by the user "U1", a large number of behavior source information at each of two or more consecutive times acquired by the processing unit 33 through the above-mentioned processing is stored in the behavior source management table shown in Figure 33.

[0413] The activity source management table (Figure 33) is a record that has "ID," "time information," "physical data," "location information," and "elapsed time." "ID" is information that identifies the record. "Time information" is information that specifies the time, and in this case, it has "date," "time of day," and "day of the week." "Physical data" has "activity data" and "vital data." "Vital data" has "heart rate," "blood pressure (systolic)," "blood pressure (diastolic)," and "body temperature." "Heart rate" is the heart rate per unit time (here, "1 minute"). "blood pressure (systolic)" is the systolic blood pressure, and "blood pressure (diastolic)" is the diastolic blood pressure. "Location information" is, for example, location information obtained by the processing described in embodiment 2. "Elapsed time" is the time that has elapsed since the same activity began.

[0414] Then, it is assumed that the user "U1" inputs an output instruction to the behavior acquisition device 3. Then, the behavior acquisition device 3 accepts the output instruction.

[0415] Next, the behavior estimation unit 335, for example, accesses the server device 4, receives the behavior learning model and the emotion learning model from the server device 4, and stores the behavior learning model and the emotion learning model in the learning management unit 311.

[0416] Next, the behavior estimation unit 335 constructs a behavior origin vector having time information, body data, location information, elapsed time, etc. for each record in FIG. 33, for example, by the process described using the flowchart in FIG. 22. Next, the behavior estimation unit 335 acquires a behavior learning model from the learning management unit 311. Next, the behavior estimation unit 335 provides the behavior origin vector and the behavior learning model to a machine learning prediction processing module and executes the module. Then, the behavior estimation unit 335 acquires behavior information "A1" for the behavior origin vector from the record "ID=1" to the record "ID=289", and acquires behavior information "A2" for the behavior origin vector from the record "ID=290" onwards up to "ID=N". Then, the accumulation unit 338 accumulates the behavior information and a behavior confirmation flag "0" for each record in the behavior management unit 313. Note that "0" for the behavior confirmation flag and emotion confirmation flag indicates that the flag is unconfirmed, and "1" indicates that the flag is confirmed.

[0417] Furthermore, the emotion deduction unit 336 constructs an emotion source vector having time information, physical data, location information, elapsed time, behavioral information, etc. for each record in FIG. 33 , for example, by the process described using the flowchart in FIG. 25 . Next, the emotion deduction unit 336 acquires an emotion learning model from the learning management unit 311. Next, the emotion deduction unit 336 provides the emotion source vector and the emotion learning model to a machine learning prediction processing module and executes the module. Then, the emotion deduction unit 336 acquires emotion information “E1” for the behavior source vector from record “ID=1” to record “ID=289,” and acquires emotion information “E2” for the behavior source vector from record “ID=290” onwards up to record “ID=N.” Then, the accumulation unit 338 accumulates emotion information and an emotion confirmation flag “0” for each record in the behavior management unit 313.

[0418] As a result of the above processing, the behavior / emotion management table shown in Fig. 34 is stored in the behavior management unit 313. The behavior / emotion management table has two or more records each having an "ID," "behavior information," "behavior confirmation flag," "emotion information," and "emotion confirmation flag."

[0419] Next, the accumulation unit 338 stores, for each record in FIG. 33 and FIG. 34, the time (for example, T 001 ,···,T 002 ,T 289 ) time period (e.g., "T 001 From T 289 " "TZ1" (which is "time zone") is acquired, and the time zone and behavioral information are stored in association with each other.

[0420] 33 and 34, the storage unit 338 stores the time (for example, T 001 ,···,T 002 ,T 289 ) time period (e.g., "T 001 From T 289 " is obtained, and the time period and emotion information are associated and stored. At this stage, the behavior confirmation flag and emotion confirmation flag corresponding to each time period are both "0". An example of the stored information is shown in Figure 35. Figure 35 is a time period information management table. The time period information management table has one or more records that have an "ID", "time period", "behavior information", "behavior confirmation flag", "emotion information", and "emotion confirmation flag".

[0421] Then, the configuration unit 339 performs the processing described using the flowchart in FIG. 28 using one or more sets of time periods, behavioral information, and emotion information stored by the storage unit 338, configures time period information for each piece of behavioral information, arranges it in a calendar template, and configures output information.

[0422] Next, the output unit 34 outputs the output information. An example of such output is shown in Fig. 36. In Fig. 36, estimated behavior information for each time period on each day on the calendar is displayed.

[0423] If the behavioral information for each time period is correct, user "U1" inputs a "confirmation command" for the displayed behavioral information, and if the estimated behavioral information is incorrect, user "U1" inputs the correct behavioral information. If the emotion information for each time period is correct, user "U1" inputs a "confirmation command" for the output emotion information, and if the estimated emotion information is incorrect, user "U1" inputs the correct emotion information. The user's input changes the "behavioral information," "behavior confirmation flag," "emotion information," and "emotion confirmation flag" in Figure 35.

[0424] As described above, according to this embodiment, the user's behavior can be estimated using location information corresponding to time.

[0425] Furthermore, according to this embodiment, the user's behavior can be estimated using the location information corresponding to a time and the user's activity data corresponding to that time.

[0426] Furthermore, according to this embodiment, the user's behavior can be estimated with higher accuracy using location information corresponding to the time, the user's activity data corresponding to the time, and the user's vital data corresponding to the time.

[0427] Furthermore, according to this embodiment, it is possible to estimate the user's emotions during the action.

[0428] Furthermore, according to this embodiment, the user's behavior can be estimated with higher accuracy using past records.

[0429] Furthermore, according to this embodiment, the past records of two or more users can be used to estimate the user's behavior with higher accuracy.

[0430] Furthermore, according to this embodiment, when the user's behavior cannot be estimated, the location where the user was can be output.

[0431] Furthermore, according to this embodiment, by using indoor location information, etc., acquired by the location information acquisition method described in embodiment 2, it is possible to accurately estimate user behavior even in places where GPS signals cannot be received.

[0432] The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. This software may also be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software that realizes the information system D in this embodiment is the following program. That is, this program causes a computer to function as a time acquisition unit that acquires time, a location acquisition unit that acquires location information associated with the time, a behavior estimation unit that uses two or more pieces of behavior source information including the location information associated with the time to acquire behavior information that identifies the user's behavior in a time period identified by the time contained in each of the two or more pieces of behavior source information, and a behavior output unit that outputs the behavior information in the time period.

[0433] (Fourth embodiment) The difference between this embodiment and embodiment 3 is as follows: In other words, in this embodiment, the behavior acquisition device is a server, and estimates behavioral information and emotional information of a user using location information and the like received from the user's terminal device.

[0434] 37 is a conceptual diagram of an information system E according to this embodiment. The information system E includes a behavior acquisition device 5, one or more terminal devices 6, and one or more communication devices B.

[0435] The behavior acquisition device 5 is a server, for example, a cloud server or an ASP server, but the type is not important. The behavior acquisition device 5 is a device that receives behavior source information such as location information from the user's terminal device 6, estimates the user's behavior information using the behavior source information, and transmits the behavior information to the terminal device 6. The behavior acquisition device 5 is a device that receives emotion source information from the user's terminal device 6, estimates the user's emotion information using the emotion source information, and transmits the behavior information to the terminal device 6.

[0436] The terminal device 6 is a terminal used by a user. The terminal device 6 may be, for example, a smartphone, a tablet device, a smartwatch, a so-called personal computer, or the like, and the type does not matter. The terminal device 6 is a terminal that transmits behavior source information and emotion source information including location information and the like to the behavior acquisition device 5, and receives and outputs behavior information and emotion information from the behavior acquisition device 5. Note that the device that transmits the behavior source information and emotion source information to the behavior acquisition device 5 may be a different device from the device that receives and outputs behavior information and emotion information from the behavior acquisition device 5.

[0437] 38 is a block diagram of the information system E in this embodiment. FIG. 39 is a block diagram of the behavior acquisition device 5.

[0438] The behavior acquisition device 5 includes a storage unit 51, a receiving unit 52, a processing unit 53, and a transmitting unit 54. The storage unit 51 includes a learning management unit 311 and a behavior management unit 313. The receiving unit 52 includes a position acquisition unit 521, an activity acquisition unit 522, and a vital sign acquisition unit 523. The processing unit 53 includes a time acquisition unit 331, a behavior estimation unit 335, an emotion estimation unit 336, an accumulation unit 338, and a configuration unit 339. The transmitting unit 54 includes a behavior output unit 341 and an emotion output unit 342.

[0439] The terminal device 6 includes a terminal storage unit 61, a terminal reception unit 62, a terminal reception unit 63, a terminal processing unit 64, a terminal transmission unit 65, and a terminal output unit 66. The terminal storage unit 61 includes a map management unit 312. The device processing unit 64 includes an intensity acquisition unit 231, a type determination unit 232, a position acquisition unit 332, an activity acquisition unit 333, a vital sign acquisition unit 334, and a location acquisition unit 337.

[0440] Various types of information are stored in the storage unit 51 constituting the behavior acquisition device 5. The various types of information are, for example, the above-mentioned learning information and the above-mentioned behavior information.

[0441] The receiving unit 52 receives various instructions and information from the terminal device 6. The various instructions and information include, for example, location information, activity data, vital data, output instructions, confirmation instructions, behavior information to be corrected, and emotion information to be corrected.

[0442] The receiving unit 52 preferably receives location information, activity data, vital data, etc. from the terminal device 6 all at once. The receiving unit 52 preferably receives location information, etc. associated with a user identifier all at once. The user identifier is information that identifies the user who uses the terminal device 6. The user identifier is, for example, a user ID, a telephone number, an email address, or an identifier of the terminal device 6. The identifier of the terminal device 6 is, for example, an IP address.

[0443] The location acquisition unit 521 receives location information from the terminal device 6. The location information is associated with time. When the location acquisition unit 521 receives the location information, it is preferable that the location acquisition unit 521 acquires the time from a clock (not shown) and associates the time with the location information. It is preferable that the location information is associated with a user identifier.

[0444] The activity acquisition unit 522 receives activity data from the terminal device 6. The activity data is associated with a time. When the activity acquisition unit 522 receives the activity data, it is preferable that the activity acquisition unit 522 acquires the time from a clock (not shown) and associates the time with the activity data. It is preferable that the activity data is associated with a user identifier.

[0445] The vital sign acquisition unit 523 receives one or more types of vital sign data from the terminal device 6. Such vital sign data is associated with time. When receiving vital sign data, the vital sign acquisition unit 523 preferably acquires the time from a clock (not shown) and associates the time with the vital sign data. Such vital sign data is preferably associated with a user identifier.

[0446] The processing unit 53 performs various types of processing. The various types of processing are, for example, processing performed by the time acquisition unit 331, the behavior estimation unit 335, the emotion estimation unit 336, and the accumulation unit 338.

[0447] The transmitting unit 54 transmits various types of information to the terminal device 6. The various types of information are, for example, estimated behavior information, estimated emotion information, and output information configured by the configuration unit 339.

[0448] The behavior output unit 341 transmits the behavior information acquired by the behavior estimation unit 335 and associated with the time period to the terminal device 6.

[0449] The emotion output unit 342 transmits to the terminal device 6 emotion information acquired by the emotion estimation unit 336 and associated with the time period.

[0450] Various types of information are stored in the terminal storage unit 61 constituting the terminal device 6. The various types of information include, for example, location information, activity data, and vital data.

[0451] The terminal receiving unit 62 receives various instructions and information, such as an output instruction, a confirmation instruction, behavioral information that the user modifies the estimated behavioral information, and emotion information that the user modifies the estimated emotion information.

[0452] The means for inputting various instructions and information may be any means, such as a touch panel, keyboard, mouse, or menu screen.

[0453] The terminal receiving unit 63 receives various types of information from the behavior acquisition device 5. The various types of information include, for example, output information, behavior information, and emotion information.

[0454] The device processing unit 64 performs various types of processing, such as changing instructions, information, etc. received by the device receiving unit 62 into instructions, information, etc. with a structure to be transmitted, and changing information received by the device receiving unit 63 into a structure to be output.

[0455] The terminal transmitting unit 65 transmits various instructions and information, such as an output instruction, a confirmation instruction, behavioral information to be changed, and emotion information to be changed.

[0456] The terminal output unit 66 outputs various types of information, such as output information, behavioral information, and emotional information.

[0457] The storage unit 51 and the terminal storage unit 61 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0458] There is no restriction on the process by which information is stored in the storage unit 51 etc. For example, information may be stored in the storage unit 51 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 51 etc., or information input via an input device may be stored in the storage unit 51 etc.

[0459] The receiving unit 52, the position acquiring unit 521, the activity acquiring unit 522, the vital sign acquiring unit 523, the transmitting unit 54, the behavior output unit 341, the emotion output unit 342, the terminal receiving unit 63, and the terminal transmitting unit 65 are realized, for example, by wireless or wired communication means.

[0460] The processing unit 53 and the device processing unit 64 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 53, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type does not matter.

[0461] The terminal reception unit 62 can be realized by a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

[0462] The terminal output unit 66 may or may not be considered to include an output device such as a display, a speaker, etc. The terminal output unit 66 may be realized by driver software for an output device, or by a combination of driver software for an output device and the output device, etc.

[0463] Next, an example of the operation of the behavior acquisition device 5 will be described using the flowchart in Fig. 40. In the flowchart in Fig. 40, the description of the same steps as in Fig. 19 will be omitted.

[0464] (Step S4001) The receiving unit 52 determines whether or not location information, etc. paired with a user identifier has been received from the terminal device 6. If location information, etc. has been received, the process proceeds to step S4002; if not, the process proceeds to step S4004. The location information, etc. is, for example, a user identifier and location information. The location information, etc. is, for example, one or more types of information selected from a user identifier and location information, activity data, and vital data.

[0465] (Step S4002) The time acquisition unit 331 acquires the time from a clock (not shown). Here, the time acquisition unit 331 may acquire the day of the week. The time usually includes the hour and minute. The time may also include one or more pieces of information from the year, month, and day.

[0466] (Step S4003) The storage unit 338 stores the location information and the time received in step S4001 in association with the user identifier in the behavior management unit 313. The process returns to step S4001.

[0467] (Step S4004) The receiving unit 52 determines whether or not an output instruction has been received from the terminal device 6. If an output instruction has been received, the process proceeds to step S4005; if not, the process proceeds to step S4009. The received output instruction is usually associated with a user identifier. The output instruction also usually includes period information specifying the period for which behavioral information is to be acquired (e.g., "from December 17, 2023 to December 23, 2023").

[0468] (Step S4005) The behavior estimation unit 335 assigns 1 to a counter i.

[0469] (Step S4006) The behavior estimation unit 335 determines whether or not the i-th behavior source information paired with the user identifier associated with the output instruction received in step S4004 exists in the behavior management unit 313. If the i-th behavior source information exists, the process proceeds to step S4007, and if not, the process proceeds to step S1917.

[0470] (Step S4007) The behavior estimation unit 335 judges whether or not behavior information corresponding to the i-th behavior source information exists. If behavior information exists, the process proceeds to step S4008, and if not, the process proceeds to step S1904. Note that if behavior information corresponding to the behavior source information exists, this usually means that behavior information has already been estimated using the behavior source information.

[0471] (Step S4008) The behavior estimation unit 335 increments the counter i by 1. The process returns to step S4006.

[0472] (Step S4009) The receiving unit 52 determines whether or not information, etc. has been received from the terminal device 6. If information, etc. has been received, the process proceeds to step S1920, and if not, the process proceeds to step S4010. The information, etc. is, for example, a confirmation instruction, behavioral information to be corrected, or emotion information to be corrected.

[0473] (Step S4010) The receiving unit 52 determines whether or not a learning instruction has been received from the terminal device 6. If a learning instruction has been received, the process proceeds to step S1924, and if not, the process returns to step S4001.

[0474] (Step S4011) The transmitting unit 54 transmits the output information constructed in step S1917 to the terminal device 6. Return to step S4001.

[0475] In the flowchart of FIG. 40, the process ends when the power is turned off or an interrupt occurs to end the process.

[0476] Next, an example of the operation of the terminal device 6 will be described with reference to the flowchart of Fig. 41. In the flowchart of Fig. 41, the description of the same steps as in Fig. 19 will be omitted.

[0477] (Step S4101) The terminal transmitting unit 65 obtains the user identifier from the terminal storage unit 61, and transmits the position information and the like obtained in step S1903 to the behavior acquisition device 5 in association with the user identifier.

[0478] (Step S4102) The terminal transmitting unit 65 transmits the output instruction accepted in step S1916 to the behavior acquisition apparatus 5 in association with the user identifier in the terminal storage unit 61. Note that the output instruction usually includes period information.

[0479] (Step S4103) The terminal receiving unit 63 determines whether or not output information has been received from the behavior acquisition device 5. If output information has been received, the process proceeds to step S4104, and if not, the process returns to step S4103.

[0480] (Step S4104) The terminal processing unit 64 uses the received output information to compose output information to be output. The terminal output unit 66 outputs the output information. The process returns to step S1901.

[0481] (Step S4105) The terminal transmitting unit 65 transmits the information acquired from the information input accepted in step S1919 to the behavior acquisition device 5 in association with the user identifier in the terminal storage unit 61. The process returns to step S1901.

[0482] The information may be, for example, a confirmation instruction, changed behavioral information, or changed emotion information. The confirmation instruction includes information that specifies the behavioral information to be confirmed or the emotion information to be confirmed. The changed behavioral information corresponds to information that specifies the behavioral information to be modified. The changed emotion information corresponds to information that specifies the emotion information to be modified.

[0483] In the flowchart of FIG. 41, the process ends when the power is turned off or an interrupt occurs to end the process.

[0484] As described above, according to this embodiment, the user's behavior can be estimated using location information corresponding to time.

[0485] Furthermore, according to this embodiment, the user's behavior can be estimated using the location information corresponding to a time and the user's activity data corresponding to that time.

[0486] Furthermore, according to this embodiment, the user's behavior can be estimated with higher accuracy using location information corresponding to the time, the user's activity data corresponding to the time, and the user's vital data corresponding to the time.

[0487] Furthermore, according to this embodiment, it is possible to estimate the user's emotions during the action.

[0488] Furthermore, according to this embodiment, the user's behavior can be estimated with higher accuracy using past records.

[0489] Furthermore, according to this embodiment, the past records of two or more users can be used to estimate the user's behavior with higher accuracy.

[0490] Furthermore, according to this embodiment, when the user's behavior cannot be estimated, the location where the user was can be output.

[0491] Furthermore, the software that realizes the behavior acquisition device 5 in this embodiment is the following program. That is, this program causes a computer to function as a time acquisition unit that acquires time, a location acquisition unit that acquires location information associated with the time, a behavior estimation unit that acquires behavior information that identifies user behavior in a time period identified by the time contained in each of the two or more pieces of behavior source information, using two or more pieces of behavior source information including the location information associated with the time, and a behavior output unit that outputs the behavior information in the time period.

[0492] (Embodiment 5) In this embodiment, a behavior analysis device is described that acquires and outputs a disorder score that specifies the degree of disorder in a user's behavior. In particular, in this embodiment, a behavior analysis device is described that acquires and outputs a disorder score using the user's time-series behavior information and reference information. Furthermore, the reference information is, for example, one or more types of information selected from information based on the user's past time-series information, a learning model based on the time-series behavior information, recommended behavior information, and other person's reference information. The reference information may also include, for example, environmental information.

[0493] In this embodiment, a behavior analysis device that acquires and outputs causes of behavioral disturbances will be described.

[0494] In this embodiment, a behavior analysis device that makes recommendations for improving behavioral irregularities will be described.

[0495] In this embodiment, a behavior analysis device that acquires and outputs an improvement degree for a behavioral disorder will be described. In this embodiment, a behavior analysis device that acquires and outputs an improvement degree when an improvement degree output condition is satisfied will be described.

[0496] In this embodiment, a behavior analysis device that acquires and outputs a recovery period from a behavioral disturbance will be described.

[0497] In this embodiment, a behavior analysis device that acquires and outputs a long-term disorder score will be described.

[0498] 42 is a conceptual diagram of an information system F in this embodiment. The information system F comprises a behavior analysis device 7, one or more terminal devices 8, and two or more communication devices B.

[0499] The behavior analysis device 7 is a device that acquires one or more pieces of information from the disorder score (described later), the disorder factor (described later), the recommendation information (described later), the improvement degree (described later), the recovery period (described later), and the long-term disorder score (described later), and transmits the information to the terminal device 8. The behavior analysis device 7 is also a device that receives behavior source information such as location information from the user's terminal device 8, estimates the user's behavior information using the behavior source information, and transmits the behavior information to the terminal device 8. The behavior analysis device 7 is a device that receives emotion source information from the user's terminal device 8, estimates the user's emotion information using the emotion source information, and transmits the behavior information to the terminal device 8. The behavior analysis device 7 is typically a server, for example, a cloud server or an ASP server, but the type is not important.

[0500] However, the behavior analysis device 7 may also be a terminal device. In such a case, the behavior analysis device 7 may have all or part of the functions of the terminal device 2 or the functions of the behavior acquisition device 3. In such a case, the behavior analysis device 7 may be, for example, a smartphone, a tablet terminal, a smartwatch, a so-called personal computer, or the like, and its type does not matter.

[0501] The terminal device 8 is a terminal used by a user. The terminal device 8 may be, for example, a smartphone, a tablet device, a smartwatch, a so-called personal computer, or the like, and the type does not matter. The terminal device 8 is a terminal that transmits behavior source information and emotion source information including location information and the like to the behavior analysis device 7, and receives and outputs a disorder score (described later), disorder factors (described later), recommendation information (described later), an improvement degree (described later), a recovery period (described later), a long-term disorder score (described later), behavior information, or emotion information, etc. from the behavior analysis device 7. Note that the device that transmits the behavior source information and emotion source information to the behavior analysis device 7 may be a different device from the device that receives and outputs the disorder score, disorder factors, etc. from the behavior analysis device 7.

[0502] 43 is a block diagram of information system F in this embodiment. FIG. 44 is a block diagram of behavior analysis apparatus 7.

[0503] The behavior analysis device 7 includes a storage unit 71, a reception unit 72, a processing unit 73, and an output unit 74. The behavior analysis device 7 may include all or some of the components included in the behavior acquisition device 5. If the behavior analysis device 7 is a standalone device, the behavior analysis device 7 may include all or some of the components included in the behavior acquisition device 3 or the terminal device 2.

[0504] The storage unit 71 includes a learning management unit 311, a behavior management unit 313, a reference management unit 711, and a recommendation management unit 712. The reception unit 72 includes a position acquisition unit 521, an activity acquisition unit 522, and a vital sign acquisition unit 523. The processing unit 73 includes a time acquisition unit 331, a behavior estimation unit 335, an emotion estimation unit 336, an accumulation unit 338, a configuration unit 339, a learning unit 731, a score acquisition unit 732, a long-term score acquisition unit 733, a determination unit 734, a factor acquisition unit 735, a recommendation acquisition unit 736, an improvement degree acquisition unit 737, and a recovery period acquisition unit 738. The output unit 74 includes a behavior output unit 341, an emotion output unit 342, a score output unit 741, a long-term score output unit 742, a factor output unit 743, a recommendation output unit 744, an improvement degree output unit 745, and a recovery period output unit 746.

[0505] The terminal device 8 includes a terminal storage unit 61, a terminal reception unit 62, a terminal reception unit 83, a device processing unit 64, a terminal transmission unit 65, and a terminal output unit 86. The terminal storage unit 61 includes a map management unit 312. The device processing unit 64 includes an intensity acquisition unit 231, a type determination unit 232, a position acquisition unit 332, an activity acquisition unit 333, a vital sign acquisition unit 334, and a location acquisition unit 337.

[0506] Various types of information are stored in the storage unit 71 that constitutes the behavior analysis device 7. The various types of information include, for example, the learning information described above, the behavioral information described above, the reference information described below, the recommendation information described below, the learning model described below, and various conditions described below. It goes without saying that the various conditions may be embedded in the program.

[0507] The reference management unit 711 stores one or more pieces of reference information. The reference information may be managed for each of two or more users. The reference information is associated with, for example, a user identifier.

[0508] The reference information is information that serves as a reference when obtaining a disorder score, which is the degree of disorder in a user's behavior. Disorder in behavior can also be referred to as disorder in daily life. The reference information is information that serves as a basis for obtaining the degree of disorder in a user's behavior corresponding to time-series information. The reference information is, for example, one or more types of information selected from self-reference information, learning model, recommended behavior information, and other-person reference information. The reference information also includes, for example, environmental reference information.

[0509] The disorder score is information that specifies the degree of disorder in behavior. Disorder in behavior can also be said to be disorder in lifestyle. The disorder score is, for example, 0 to 100, or a 5-point scale or a 10-point scale. The disorder score may be a 2-point scale (disordered or not). The disorder score may also be the degree of well-being of lifestyle (degree of disorder).

[0510] The disorder score may be the degree of disorder rather than the degree of disorder. The degree of disorder can be said to be the degree of good living.

[0511] Examples of reference information, namely, self-reference information, learning model, recommended behavior information, other-person reference information, and environmental reference information, will be described in detail below. (1) Self-standard information

[0512] Self-reference information is information based on a user's past time-series information. The reference information is, for example, a collection of time information and average behavioral information (in the case of normal behavior) of a user over a predetermined period (e.g., one day or one week). The reference information is, for example, a collection of time information and average behavioral information of a user when there is no disturbance over a predetermined period. The behavioral information contained in the reference information may correspond to the time (length) of the behavior. The behavioral information contained in the reference information includes, for example, the start time and end time of the behavior. The reference information is, for example, a vector. For example, the vector is (time of behavior information 1, start time of behavior information 1, end time of behavior information 1, time of behavior information 2, start time of behavior information 2, end time of behavior information 2, . . ., time of behavior information n, start time of behavior information n, end time of behavior information n). For example, the vector is (time-related information of behavior information 1, time-related information of behavior information 2, . . ., time-related information of behavior information n). Time-related information is one or more of the following: time, start time, or end time. Examples of "behavioral information 1," "behavioral information 2," "behavioral information 3," and so on, are "sleep," "breakfast," "travel," "work," "shopping," "dinner," "drinking party," and "game." (2) Learning Model

[0513] The learning model is a model obtained by performing a machine learning learning process using two or more pieces of training data. The training data here has explanatory variables based on past time-series information of one or more users and a target variable that is turbulence information related to the degree of turbulence in the user's behavior. The two or more pieces of training data are data for creating a learning model to be used for one user, and may be information based on the time-series information of the one user. Furthermore, the two or more pieces of training data are data for creating a learning model to be used for two or more users, and may be information based on the time-series information of one or more users including other users. The learning model is typically a model created by the learning unit 731.

[0514] The disturbance information is information relating to the disturbance of the user's behavior. The disturbance information is, for example, a disturbance score, information indicating whether or not the user is disturbed, information indicating the level of physical condition, information indicating whether or not the user is in good physical condition, information indicating the level of mental condition, information indicating whether or not the user is in good mental condition, information indicating the level of overall mental and physical condition, and information indicating whether or not the user is in good overall mental and physical condition. The disturbance information is, for example, information input by the user. The disturbance information is, for example, a score obtained from one or more types of vital data of the user (for example, heart rate, heart rate variability, blood pressure (systolic and / or diastolic), respiratory rate per unit time, body temperature) or information indicating whether or not the user is in good physical condition. Note that the technology for obtaining a score or information indicating whether or not the user is in good physical condition from vital data is a well-known technology. The disturbance information may also be information input by the user in association with time-series information.

[0515] A learning model is information configured by a machine learning learning process and is information used in a machine learning prediction process. A learning model may also be called a learner, a classifier, a classification model, etc. The machine learning algorithm may be any algorithm, such as deep learning, random forest, decision tree, SVR, or SVM. For machine learning, various machine learning functions, such as the TensorFlow (registered trademark) library, the random forest module of the R language, fastText, or TinySVM, or various existing libraries, may be used.

[0516] Furthermore, a learning model based on the time series information of one user may be considered to be an example of self-reference information, and a learning model based on the time series information of one or more users including other users may be considered to be an example of other-reference information. (3) Recommended Action Information

[0517] Recommended behavior information is information that specifies recommended behavior. Recommended behavior information is, for example, information that specifies common sense that is less likely to cause behavioral disorders, and information that specifies common sense that is likely to cause behavioral disorders. Examples of recommended behavior information that specifies recommended behavior are "number of meals = 3 times / day," "6 hours <= sleep time <= 10 hours," "8 PM <= bedtime <= midnight," and "5 AM <= wake-up time <= 9 AM." Examples of recommended behavior information that specifies non-recommended behavior are "number of drinking parties >= 3 times / week," "drinking parties 3 days in a row," and "game time >= 3 hours / day." Note that recommended behavior information may also be information that specifies non-recommended behavior. However, in this specification, recommended behavior information is usually described as information that specifies recommended behavior. (4) Other reference information

[0518] Other-reference information is information based on the behavioral information of one or more other people other than the user. Other-reference information is typically information based on the behavioral information of two or more people. Other-reference information may also include self-reference information. Other-reference information is, for example, a collection of average behavioral information and time information of two or more users over a predetermined period (e.g., one day, one week). The data structure of other-reference information is, for example, the same as the data structure of self-reference information.

[0519] It is preferable that the criteria management unit 711 stores other person criteria information associated with each of two or more user attribute value conditions. (5) Environmental standard information

[0520] Environmental standard information is environmental information that serves as a standard. Environmental information is information that specifies the environment of the place of activity. Environmental information is, for example, information that specifies the weather, temperature, humidity, and amount of ultraviolet rays. Environmental standard information is, for example, appropriate weather as "sunny," appropriate temperature range as "15 degrees <= temperature <= 25 degrees," appropriate humidity range as "40% <= humidity <= 60%," and appropriate amount of ultraviolet rays.

[0521] The recommendation management unit 712 stores recommendation source information in association with one or more factor conditions. Factor conditions are conditions related to disruption factors. The factor conditions may be the same as the disruption conditions. Disruption factors are factors that disrupt behavior. Disruption factors are, for example, "sleep" (e.g., short sleep time, late bedtime, late wake-up time), "breakfast" (e.g., late breakfast time, skipping breakfast), and "drinking parties" (frequent drinking parties).

[0522] Recommendation source information is information that serves as the basis for recommendation information. Recommendation source information is information for configuring recommendation information. Recommendation source information has, for example, one or more variables. For example, a disturbance factor and element information corresponding to the disturbance factor are substituted into the variables. Recommendation source information may be recommendation information. Recommendation information is information that is recommended to a user to improve the disturbance of the user's behavior. Recommendation information is, for example, a character string, audio, a still image, or a video, and the data type is not important.

[0523] The receiving unit 72 receives one or more pieces of time-series information. There is no restriction on the method by which the receiving unit 72 receives the time-series information. The receiving unit 72 only needs to acquire the time-series information.

[0524] Time series information is chronological behavioral information of a user. Time series information includes two or more pieces of behavioral information in chronological order. Behavioral information is information that identifies a user's behavior. Behavioral information is associated with, for example, time information. Time information is information that identifies the time when a user performed an action. Time information is, for example, a start time and an end time. Time information is, for example, an hour.

[0525] The receiving unit 72 receives, for example, the behavior information acquired by the behavior estimation unit 335 for each of two or more time periods.

[0526] Here, "reception" typically refers to the reception of information transmitted via a wired or wireless communication line, but may also be a concept that includes the reception of information input from an input device such as a keyboard, mouse, or touch panel, or the reception of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0527] The processing unit 73 performs various types of processing. The various types of processing are, for example, processing performed by the time acquisition unit 331, the behavior estimation unit 335, the emotion estimation unit 336, the accumulation unit 338, the configuration unit 339, the learning unit 731, the score acquisition unit 732, the long-term score acquisition unit 733, the determination unit 734, the factor acquisition unit 735, the recommendation acquisition unit 736, the improvement degree acquisition unit 737, and the recovery period acquisition unit 738.

[0528] The learning unit 731 creates a learning model using two or more pieces of teacher data and stores it in the reference management unit 711. The learning unit 731 creates a learning model by machine learning learning processing using two or more pieces of teacher data. The teacher data here has explanatory variables based on past time-series information of one or more users and a target variable that is disturbance information related to the degree of disturbance in the user's behavior.

[0529] The learning unit 731 provides, for example, two or more sets of teacher data for each of one or more users, each set having an explanatory variable based on the user's past time-series information and a target variable that is disorder information related to the degree of disorder in the user's behavior, to a module that performs machine learning learning processing, executes the module, and acquires a learning model. As described above, any machine learning algorithm is used.

[0530] The score acquisition unit 732 acquires a disorder score, which is the degree of disorder in the user's behavior, using the time-series information accepted by the acceptance unit 72 and the reference information of the reference management unit 711. The score acquisition unit 732 normally acquires a disorder score, which is a score related to the difference between the time-series information accepted by the acceptance unit 72 and the reference information of the reference management unit 711.

[0531] The score acquiring unit 732 may acquire a first disorder score and a second disorder score, which are disorder scores for each of the two periods. The score acquiring unit 732 may acquire a disorder score for each of two or more pieces of time-series information.

[0532] Below, examples of the processing of the score acquisition unit 732 will be described for each of the cases where the reference information is self-reference information, learning model, recommended behavior information, and other-person reference information. (1) Self-standard information

[0533] The score acquisition unit 732 acquires difference information regarding the difference between the time-series information for a predetermined period (e.g., one day, one week) accepted by the acceptance unit 72 and the self-reference information for the predetermined period, and acquires a larger disturbance score as the difference information increases. (1-1) When the self-reference information is a vector (self-reference vector)

[0534] The score acquiring unit 732 acquires a vector from the time-series information for a predetermined period (for example, one day or one week) accepted by the accepting unit 72. Such a vector is called a test vector. Next, the score acquiring unit 732 acquires a larger disturbance score the greater the difference between the test vector and the self reference vector.

[0535] For example, the score acquiring unit 732 acquires the distance between the test vector and the self reference vector. Next, the score acquiring unit 732 acquires the disturbance score using the distance or an increasing function with the distance as a parameter.

[0536] Also, for example, the score acquisition unit 732 acquires the difference between each element of the acquired inspection vector and each element of the self-reference vector for each element, and for each element, if the difference between the elements is greater than or equal to a threshold value, counts up the disturbance score to acquire the final disturbance score.

[0537] Also, for example, the score acquisition unit 732 acquires the difference between each element of the test vector and each element of the self reference vector for each element, and acquires a disturbance score that is the sum of the absolute values ​​of the differences for each element. (1-2) When self-reference information is a set of pairs of behavioral information and time information

[0538] The score acquisition unit 732 determines whether or not each piece of behavioral information included in the time-series information for the predetermined period received by the receiving unit 72 exists in the personal reference information.

[0539] For example, if there is behavioral information that does not exist in the self-reference information, the score acquisition unit 732 counts up the disorder score. The behavioral information that does not exist in the self-reference information is, for example, information about behavior that is not normally performed, and can be a cause of behavioral disorder.

[0540] Furthermore, the score acquiring unit 732 acquires a difference (for example, one or more pieces of information among a difference in length of time, a difference in start time, and a difference in end time) between time information paired with behavior information included in the time-series information for a predetermined period accepted by the accepting unit 72 and time information paired with behavior information present in the self-reference information. The larger the difference, the larger the disturbance score acquired by the score acquiring unit 732.

[0541] Furthermore, the score acquiring unit 732 acquires the frequency of behavioral information (for example, "dining" or "drinking party") contained in the time-series information for a predetermined period accepted by the accepting unit 72. The score acquiring unit 732 acquires the frequency of behavioral information in the self-reference information. Next, if the difference between the two frequencies is equal to or greater than a threshold, the score acquiring unit 732 acquires a large disorder score. (2) Learning Model

[0542] The score acquisition unit 732 performs machine learning prediction processing using the time-series information and learning model received by the reception unit 72, and acquires a disturbance score.

[0543] For example, the score acquiring unit 732 constructs a test vector from the time-series information received by the receiving unit 72. The test vector here is, for example, (time of behavior information 1, start time of behavior information 1, end time of behavior information 1, time of behavior information 2, start time of behavior information 2, end time of behavior information 2, . . ., time of behavior information n, start time of behavior information n, end time of behavior information n), or (time-related information of behavior information 1, time-related information of behavior information 2, . . ., time-related information of behavior information n), but the structure is not important.

[0544] Next, the score acquisition unit 732 provides the test vector and the learning model to a module that performs machine learning prediction processing, executes the module, and acquires a disorder score. The score acquisition unit 732 may provide the vector and the learning model to a module that performs machine learning prediction processing, execute the module, acquire information on whether or not the vector is disordered, and, if an objective variable indicating "disordered" is acquired, acquire a score returned by the module that performs prediction processing and acquire a disorder score based on the score. The disorder score is the score returned by the module, or a score acquired by an increasing function that uses the score returned by the module as a parameter. For example, if an objective variable indicating "not disordered" is acquired, the score acquisition unit 732 acquires a disorder score of "0."

[0545] The module that performs the machine learning prediction process may be a module that returns a disturbance score, or may be a module that returns a predicted value that is the basis of the disturbance score.

[0546] Furthermore, the algorithm for machine learning prediction processing can be any of deep learning, random forest, decision tree, SVM, etc. However, it is preferable that the algorithm for machine learning prediction processing is random forest. This is because random forest can obtain the influence of each explanatory variable on the output target variable. Behavioral information corresponding to explanatory variables with high influence constitutes the disturbance factors described below. Explanatory variables with high influence are, for example, explanatory variables with the highest influence ranking, those with an influence ranking of N or higher, and those with an influence equal to or greater than the threshold. (3) Recommended Action Information (3-1) When the recommended action information is a vector (recommended action vector)

[0547] The score acquiring unit 732 acquires an inspection vector from time-series information for a predetermined period (for example, one day or one week) received by the receiving unit 72. Next, the score acquiring unit 732 acquires a larger disturbance score as the difference between the inspection vector and the recommended action vector increases.

[0548] For example, the score acquiring unit 732 acquires the distance between the test vector and the recommended action vector, and then acquires the disturbance score using the distance or an increasing function with the distance as a parameter.

[0549] Also, for example, the score acquisition unit 732 acquires the difference between each element of the test vector and each element of the recommended action vector for each element, and for each element, if the difference between the elements is equal to or greater than a threshold, counts up the disorder score to acquire the final disorder score.

[0550] Furthermore, for example, the score acquisition unit 732 acquires the difference between each element of the test vector and each element of the recommended action vector for each element, and acquires a disturbance score that is the sum of the absolute values ​​of the differences for each element. (3-2) When the recommended action information is a set of pairs of action information and time information

[0551] For example, the score acquiring unit 732 determines whether or not each piece of behavior information included in the time-series information for a predetermined period received by the receiving unit 72 is present in the recommended behavior information. When the recommended behavior information is information specifying a recommended behavior, if the behavior information is not present in the recommended behavior information, the score acquiring unit 732 acquires a larger disorder score than when the behavior information is present in the recommended behavior information. When the recommended behavior information is information specifying a non-recommended behavior, if the behavior information is present in the recommended behavior information, the score acquiring unit 732 acquires a larger disorder score than when the behavior information is not present in the recommended behavior information.

[0552] For example, the score acquiring unit 732 acquires time information (e.g., time, start time, end time) paired with the behavior information contained in the time-series information for the predetermined period accepted by the accepting unit 72. For each behavior information, the score acquiring unit 732 determines whether the time information paired with the behavior information satisfies the condition (e.g., a suitable range of sleep time) of the time information paired with the behavior information contained in the recommended behavior information. When the condition of the time information paired with the behavior information contained in the recommended behavior information is not satisfied, the score acquiring unit 732 acquires a larger disturbance score than when the condition is satisfied. (4) Other reference information (4-1) When other-reference information is a vector (other-reference vector)

[0553] The score acquiring unit 732 acquires a test vector from time-series information for a predetermined period (for example, one day or one week) accepted by the accepting unit 72. Next, the score acquiring unit 732 acquires a larger disturbance score as the difference between the test vector and the other's reference vector increases.

[0554] For example, the score acquiring unit 732 acquires the distance between the test vector and the other reference vector, and then acquires the disorder score using the distance or an increasing function with the distance as a parameter.

[0555] Also, for example, the score acquisition unit 732 acquires the difference between each element of the test vector and each element of the other reference vector for each element, and for each element, if the difference between the elements is greater than or equal to a threshold value, counts up the disorder score to acquire the final disorder score.

[0556] Furthermore, for example, the score acquisition unit 732 acquires the difference between each element of the test vector and each element of the other's reference vector for each element, and acquires a disorder score that is the sum of the absolute values ​​of the differences for each element. (4-2) When other-reference information is a set of pairs of behavioral information and time information

[0557] The score acquisition unit 732 determines whether or not each piece of behavior information included in the time-series information for a predetermined period received by the receiving unit 72 exists in the other person reference information.

[0558] If there is behavior information that does not exist in the other person's reference information, the score acquisition unit 732 counts up the disorder score. The behavior information that does not exist in the other person's reference information is information on behavior that two or more people do not normally perform.

[0559] Furthermore, the score acquiring unit 732 acquires a difference (for example, one or more pieces of information among a difference in length of time, a difference in start time, and a difference in end time) between time information paired with behavior information included in the time-series information for a predetermined period accepted by the accepting unit 72 and time information paired with behavior information present in the other person's reference information. The larger the difference, the larger the disturbance score acquired by the score acquiring unit 732.

[0560] Furthermore, the score acquiring unit 732 acquires the frequency of behavioral information (for example, "dining" or "drinking party") contained in the time-series information for a predetermined period accepted by the accepting unit 72. The score acquiring unit 732 acquires the frequency of behavioral information in the other person's reference information. Next, if the difference between the two frequencies is equal to or greater than a threshold, the score acquiring unit 732 acquires a large disorder score.

[0561] Furthermore, the score acquisition unit 732 may, for example, acquire a comparison result of scores for two or more periods and acquire a score based on the comparison result. The score acquisition unit 732 acquires, for example, the change (e.g., difference or percentage) in score for the same month of the previous year (June 2023 and June 2024) or for one week in the previous month, and acquires a score using a function that uses the change as a parameter. This score is called a change score, and the greater the degree of improvement in the score, the larger the change score that is acquired.

[0562] The long-term score acquiring unit 733 acquires a long-term disorder score that specifies the degree of long-term behavioral disorder, using two or more disorder scores acquired by the score acquiring unit 732. Here, the long term is, for example, three months (each season), one year, one month, etc. The long term is a period longer than one day. The long term is usually a period of one week or more.

[0563] The long-term score acquisition unit 733 acquires the number of times that the judgment unit 734 has determined that the disturbance condition is satisfied, and acquires a long-term disturbance score using the number of times. The longer the number of times that the judgment unit 734 has determined that the disturbance condition is satisfied, the larger the long-term disturbance score that the long-term score acquisition unit 733 acquires.

[0564] The determination unit 734 determines whether the disturbance score acquired by the score acquisition unit 732 satisfies a disturbance condition. The disturbance condition is a condition for acquiring a disturbance factor. For example, the disturbance condition is that the disturbance score is equal to or greater than a threshold value.

[0565] A disturbance factor is information about behavioral information that causes a disturbance. A disturbance factor typically includes behavioral information. It also includes time information. A disturbance factor is, for example, information obtained using behavioral information corresponding to explanatory variables with a high degree of influence obtained when a prediction process is performed using a random forest. A disturbance factor is, for example, information obtained using behavioral information in which difference information identifying a difference from reference information is equal to or greater than a threshold. A disturbance factor may be information about only specific behavioral information (for example, "sleeping," "drinking party," or "eating"). A disturbance factor may also be information about behavioral information excluding specific behavioral information (for example, "movement").

[0566] The determination unit 734 determines whether the first disorder score and the second disorder score satisfy a recovery condition. The recovery condition is a condition for acquiring a recovery period. Examples of the recovery condition include: the disorder condition is no longer met; the disorder condition is met but then no longer met; the degree of improvement is equal to or greater than a threshold; the degree of improvement is equal to or greater than a threshold and the second disorder score is equal to or less than a threshold; and the second disorder score is equal to or less than a threshold.

[0567] The determination unit 734 determines whether each of the two or more disturbance scores satisfies a disturbance condition. The disturbance condition is a condition for the factor acquisition unit 735 to acquire a disturbance factor. The disturbance condition is, for example, that the disturbance score is equal to or greater than a threshold value.

[0568] The factor acquiring unit 735 acquires a disturbance factor related to behavioral information that is a factor of disturbance, which is time-series information corresponding to the disturbance score, from the behavioral information included in the time-series information accepted by the accepting unit 72. It is preferable that the factor acquiring unit 735 acquires the disturbance factor when the determining unit 734 determines that the disturbance condition is satisfied.

[0569] The factor acquisition unit 735 acquires, for example, behavioral information corresponding to explanatory variables with a high degree of influence acquired as a result of prediction processing using random forest, and acquires disturbance factors having the behavioral information and time information paired with the behavioral information.

[0570] The factor acquiring unit 735 acquires behavioral information that has become a factor in increasing the disorder score acquired by the score acquiring unit 732, for example, to the extent that the adoption condition is satisfied. The factor acquiring unit 735 acquires disorder factors that have the behavioral information and time information paired with the behavioral information. The adoption condition is a condition for behavioral information to be adopted as a disorder factor. For example, the adoption condition is that the number of increases in the disorder score is equal to or greater than a threshold. For example, the adoption condition is that the number of occurrences of specific behavioral information in a predetermined period for adoption as a disorder factor is equal to or greater than a threshold (for example, the number of drinking parties is three or more times per week).

[0571] The recommendation acquisition unit 736 refers to the recommendation management unit 712 and acquires, from the recommendation management unit 712, recommendation source information corresponding to the factor conditions that match the disturbance factors acquired by the factor acquisition unit 735. The recommendation acquisition unit 736 acquires the recommendation information by substituting the disturbance factors into the recommendation information that is the recommendation source information or into the variable parts of the recommendation source information.

[0572] The improvement degree acquiring unit 737 acquires the improvement degree using the first disorder score and the second disorder score. The first disorder score and the second disorder score are disorder scores acquired by the score acquiring unit 732 using time-series information at different times.

[0573] The improvement degree is information that specifies the degree of improvement of the disorder. The improvement degree is usually information regarding the difference between the first disorder score and the second disorder score. For example, if the disorder score is information indicating the degree of disorder, the improvement degree is "first disorder score - second disorder score," and if the disorder score is information indicating the goodness of behavior, the improvement degree is "second disorder score - first disorder score."

[0574] It is preferable that the improvement degree acquiring unit 737 acquires the improvement degree when the first disorder score and the second disorder score satisfy an improvement degree output condition. Note that the improvement degree output condition is, for example, that the improvement degree is equal to or greater than a threshold value, or that the improvement degree is equal to or less than a threshold value.

[0575] The recovery period acquisition unit 738 acquires a recovery period that is the difference between the first time information corresponding to the first disorder score and the second time information corresponding to the second disorder score. It is preferable that the recovery period acquisition unit 738 acquires the recovery period when the determination unit 734 determines that the recovery condition is satisfied. The recovery condition is a condition for acquiring the recovery period. For example, the recovery condition is that the second disorder score does not satisfy the disorder condition.

[0576] The output unit 74 outputs various types of information, such as a disorder score, a long-term disorder score, behavior information, emotion information, or location information.

[0577] Here, output usually means output to terminal device 8, but it may also be a concept that includes display on a display, projection using a projector, printing on a printer, sound output, transmission to an external device, storage on a recording medium, and delivery of processing results to other processing devices or other programs.

[0578] The score output unit 741 outputs the disorder score acquired by the score acquisition unit 732. There is no limitation on the manner in which the disorder score is output. It is preferable that the score output unit 741 outputs the disorder score in association with a user identifier. It is preferable that the score output unit 741 outputs the disorder score for each predetermined period (for example, one week, one day).

[0579] The long-term score output unit 742 outputs the long-term disorder score acquired by the long-term score acquisition unit 733. There is no limitation on the output form of the long-term disorder score. It is preferable that the long-term score output unit 742 outputs the long-term disorder score in association with the user identifier.

[0580] The factor output unit 743 outputs one or more disturbance factors acquired by the factor acquisition unit 735. It is preferable that the factor output unit 743 outputs one or more disturbance factors in association with the time-series information.

[0581] The recommendation output unit 744 outputs one or more pieces of recommendation information acquired by the recommendation acquisition unit 736 .

[0582] The improvement degree output unit 745 outputs the degree of improvement acquired by the improvement degree acquisition unit 737 .

[0583] The recovery period output unit 746 outputs the recovery period acquired by the recovery period acquisition unit 738 .

[0584] The terminal receiving unit 83 included in the terminal device 8 receives various types of information. The terminal receiving unit 83 receives various types of information from the behavior analysis apparatus 7. The various types of information include, for example, behavioral information, emotional information, disorder score, long-term disorder score, disorder factor, recommendation information, improvement degree, or recovery period.

[0585] The terminal output unit 86 outputs various types of information, such as behavioral information, emotional information, disturbance score, long-term disturbance score, disturbance factor, recommendation information, improvement degree, or recovery period.

[0586] The storage unit 71, learning management unit 311, reference management unit 711, and recommendation management unit 712 are preferably non-volatile recording media, but may also be realized as volatile recording media.

[0587] There is no restriction on the process by which information is stored in the storage unit 71 etc. For example, information may be stored in the storage unit 71 etc. via a recording medium, information transmitted via a communication line etc. may be stored in the storage unit 71 etc., or information input via an input device may be stored in the storage unit 71 etc.

[0588] The reception unit 72 is preferably realized by a wireless or wired communication means, but may also be realized by a means for receiving broadcasts, a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

[0589] The processing unit 73, learning unit 731, score acquisition unit 732, long-term score acquisition unit 733, judgment unit 734, factor acquisition unit 735, recommendation acquisition unit 736, improvement degree acquisition unit 737, and recovery period acquisition unit 738 can usually be realized by a processor, memory, etc. The processing procedures of the processing unit 73, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuit). The processor may be a CPU, MPU, GPU, etc., and the type does not matter.

[0590] The output unit 74, which includes the behavior output unit 341, emotion output unit 342, score output unit 741, long-term score output unit 742, factor output unit 743, recommendation output unit 744, improvement degree output unit 745, and recovery period output unit 746, is preferably realized by wireless or wired communication means, but may also be realized by driver software for an output device such as a display or speaker, or by a combination of driver software for an output device and the output device, etc.

[0591] The terminal receiving unit 83 is usually realized by a wireless or wired communication means, but may also be realized by a means for receiving broadcasts.

[0592] The terminal output unit 86 may or may not be considered to include an output device such as a display, a speaker, etc. The terminal output unit 86 may be realized by driver software for an output device, or by a combination of driver software for an output device and the output device, etc.

[0593] Next, an example of the operation of the behavior analysis device 7 will be described using the flowchart in Fig. 45. The flowchart in Fig. 45 does not include the same processes as those in the behavior acquisition device 5. The processes that are the same as those in the behavior acquisition device 5 are the processes in the flowchart in Fig. 40.

[0594] (Step S4501) The processing unit 73 determines whether or not the score acquisition condition is satisfied. If the score acquisition condition is satisfied, the process proceeds to step S4502, and if the score acquisition condition is not satisfied, the process proceeds to step S4519.

[0595] The score acquisition condition is a condition for acquiring a disordered score. The score acquisition condition is, for example, that a predetermined time (e.g., midnight every day) has arrived, that the reception unit 72 has received a score acquisition instruction from a user, or that the reception unit 72 has received time-series information. The score acquisition instruction received by the reception unit 72 includes a user identifier. The time-series information received by the reception unit 72 is associated with the user identifier.

[0596] (Step S4502) The processing unit 73 assigns 1 to the counter i.

[0597] (Step S4503) The processing unit 73 determines whether or not there is an i-th user for which a disorder score is to be acquired. If there is an i-th user, the process proceeds to step S4504, and if there is not, the process returns to step S4501.

[0598] (Step S4504) The score obtaining unit 732 obtains the disorder score of the i-th user. An example of the score obtaining process will be described with reference to the flowcharts of FIGS.

[0599] (Step S4505) The score output unit 741 stores the disorder score acquired in step S4504 in the behavior management unit 313 in association with the i-th user identifier and the time-series information used to acquire the disorder score.

[0600] (Step S4506) The judgment unit 734 judges whether or not the disorder score acquired in step S4504 matches the disorder condition. If the disorder condition is met, the process proceeds to step S4507, and if the disorder condition is not met, the process proceeds to step S4512.

[0601] (Step S4507) The cause acquisition unit 735 acquires the cause of the user's irregular behavior. An example of the cause acquisition process will be described with reference to the flowchart in FIG.

[0602] (Step S4508) The recommendation acquisition unit 736 acquires recommendation information. An example of such recommendation acquisition processing will be described with reference to the flowchart in FIG.

[0603] (Step S4509) The processing unit 73 or a component not shown in the figure composes output information. The output information is information that is output. The output information has a disturbance score. The output information here has, for example, one or more disturbance factors and one or more pieces of recommendation information.

[0604] (Step S4510) The output unit 74 outputs the output information configured in step S4509. The output unit 74 transmits the output information to, for example, the i-th user.

[0605] (Step S4511) The processing unit 73 increments the counter i by 1. The process returns to step S4503.

[0606] (Step S4512) The improvement degree obtaining unit 737 obtains the past disorder score of the i-th user. The past disorder score is preferably the most recent disorder score.

[0607] (Step S4513) The improvement degree acquisition unit 737 determines whether the disorder score acquired in step S4504 and the disorder score acquired in step S4512 satisfy the improvement degree output condition. If the improvement degree output condition is satisfied, the process proceeds to step S4514, and if not, the process proceeds to step S4515.

[0608] (Step S4514) The improvement degree acquisition unit 737 acquires the degree of improvement using the disorder score acquired in step S4504 and the disorder score acquired in step S4512. The improvement degree output unit 745 stores the degree of improvement in the behavior management unit 313 in association with the i-th user identifier and the time-series information used to acquire the disorder score.

[0609] (Step S4515) The judgment unit 734 judges whether or not the disorder score acquired in step S4504 and the disorder score acquired in step S4512 satisfy the recovery condition. If the recovery condition is satisfied, the process proceeds to step S4516, and if the recovery condition is not satisfied, the process proceeds to step S4517.

[0610] (Step S4516) The recovery period acquisition unit 738 acquires a recovery period which is the difference between the time information associated with the disorder score acquired in step S4504 and the time information associated with the disorder score acquired in step S4512. The recovery period output unit 746 stores the recovery period in the behavior management unit 313 in association with the i-th user identifier and the time-series information used to acquire the disorder score.

[0611] (Step S4517) The processing unit 73 or a component not shown in the figures composes output information. The output information includes a disorder score. Here, the output information includes, for example, an improvement degree and a recovery period.

[0612] (Step S4518) The output unit 74 outputs the output information configured in step S4517. The output unit 74 transmits the output information to, for example, the i-th user.

[0613] (Step S4519) Processing unit 73 determines whether or not the long-term score acquisition conditions are met. If the long-term score acquisition conditions are met, the process proceeds to step S4520, and if the score acquisition conditions are not met, the process proceeds to step S4525. The long-term score acquisition conditions include, for example, that a disorder score has been accumulated for a predetermined period of time, or that an instruction from the user has been accepted.

[0614] (Step S4520) The processing unit 73 assigns 1 to the counter i.

[0615] (Step S4521) Processing unit 73 determines whether or not there is an i-th user for which a long-term disorder score is to be acquired. If there is an i-th user, the process proceeds to step S4522, and if there is no i-th user, the process returns to step S4501.

[0616] (Step S4522) Long-term score acquisition unit 733 acquires the long-term disorder score of the i-th user. An example of such long-term score acquisition processing will be described with reference to the flowchart in FIG.

[0617] (Step S4523) The long-term score output unit 742 stores the long-term disorder score acquired in step S4522 in the behavior management unit 313 in association with the i-th user.

[0618] (Step S4524) The processing unit 73 increments the counter i by 1. The process returns to step S4503.

[0619] (Step S4525) The processing unit 73 determines whether or not the learning conditions are met. If the learning conditions are met, the process proceeds to step S4526, and if the score acquisition conditions are not met, the process returns to step S4501. The learning conditions are conditions for creating a learning model. Examples of the learning conditions include the number of user time-series information items being equal to or greater than a threshold value, and the receipt of an instruction from the user.

[0620] (Step S4526) The processing unit 73 assigns 1 to the counter i.

[0621] (Step S4527) The processing unit 73 determines whether or not there is an i-th user for which a learning model is to be created. If there is an i-th user, the process proceeds to step S4528, and if there is no i-th user, the process returns to step S4521.

[0622] (Step S4528) The learning unit 731 performs learning processing using the time-series information of the i-th user to acquire a learning model. An example of such learning processing will be described with reference to the flowchart in FIG.

[0623] (Step S4529) The output unit 74 stores the learning model acquired in step S4528 in the reference management unit 711 in association with the i-th user.

[0624] (Step S4530) The processing unit 73 increments the counter i by 1. The process returns to step S4527.

[0625] In the flowchart of FIG. 45, the process ends when the power is turned off or an interrupt occurs to end the process.

[0626] Next, a first example of the score acquisition process in step S4504 will be described with reference to the flowchart in Fig. 46. The first example of the score acquisition process is a case where a disturbance score is acquired based on the similarity between an inspection vector based on the user's time-series information and reference information in the case of a vector.

[0627] (Step S4601) The score acquiring unit 732 acquires time-series information of the target user. The time-series information is, for example, time-series information paired with the user identifier of the target user, or time-series information accepted by the accepting unit 72.

[0628] (Step S4602) Score acquisition unit 732 determines whether or not to use environmental information to acquire the disturbance score. If environmental information is to be used, the process proceeds to step S4603, and if environmental information is not to be used, the process proceeds to step S4604.

[0629] (Step S4603) The score acquiring unit 732 acquires environmental information paired with the time-series information of the target user.

[0630] (Step S4604) The score acquiring unit 732 constructs a vector using the time-series information of the target user, or the time-series information of the target user and the environmental information. Such a vector is called a test vector.

[0631] The test vector is, for example, (time of behavior information 1, start time of behavior information 1, end time of behavior information 1, time of behavior information 2, start time of behavior information 2, end time of behavior information 2,..., time of behavior information n, start time of behavior information n, end time of behavior information n, environment information 1,..., environment information m). For example, environment information 1 is the weather, and environment information m is the temperature. Note that m is a natural number greater than or equal to 1.

[0632] (Step S4605) The score acquisition unit 732 acquires the reference vector of the reference management unit 711.

[0633] (Step S4606) Score obtaining unit 732 calculates the distance (for example, cos Θ) between the test vector and the reference vector.

[0634] (Step S4607) The score acquisition unit 732 acquires the disorder score using an increasing function with the distance acquired in step S4606 as a parameter, and returns to the upper level processing.

[0635] Next, a second example of the score acquisition process in step S4504 will be described using the flowchart in Fig. 47. In the flowchart in Fig. 47, descriptions of the same steps as in the flowchart in Fig. 46 will be omitted. The second example of the score acquisition process is based on machine learning.

[0636] (Step S4701) The score acquiring unit 732 acquires a learning model from the reference managing unit 711. Here, it is preferable that the score acquiring unit 732 acquires a learning model paired with the user identifier of the target user.

[0637] (Step S4702) The score acquisition unit 732 provides the test vector and the learning model acquired in step S4701 to a module that performs machine learning prediction processing, executes the module, and acquires a prediction result. The prediction result is, for example, a disorder score. The prediction result is, for example, a score returned by the module indicating whether or not there is disorder.

[0638] (Step S4703) The score acquisition unit 732 acquires the disturbance score based on the prediction result, and returns to the upper process.

[0639] For example, if the prediction result is "not disturbed (e.g., "0"), the score acquisition unit 732 acquires a disturbance score of "0", and if the prediction result is "disturbed (e.g., "1"), it acquires a disturbance score calculated using an increasing function that uses the score returned by the module as a parameter.

[0640] Next, a third example of the score acquisition process in step S4504 will be described with reference to the flowchart in Fig. 48. In the flowchart in Fig. 48, the description of the same steps as in the flowchart in Fig. 46 will be omitted. Note that the third example is a case where a difference between each element information contained in the time-series information and the element information of the reference information is determined.

[0641] (Step S4801) The score acquisition unit 732 acquires reference information including time-series information from the reference management unit 711. The reference information may include one or more pieces of environmental information. For example, the one or more pieces of environmental information may be "<Weather> Sunny <Temperature> 15 to 25 degrees <Humidity> 40 to 60%."

[0642] (Step S4802) The score acquisition unit 732 assigns 1 to the counter i.

[0643] (Step S4803) The score acquisition unit 732 determines whether or not the i-th element information exists in the acquired time-series information of the target user, etc. If the i-th element information exists, the process proceeds to step S4804, and if not, the process proceeds to step S4811.

[0644] (Step S4804) The score acquiring unit 732 acquires the i-th element information from the time-series information of the target user, etc. The element information is behavior information and time information, or environment information.

[0645] (Step S4805) The score acquisition unit 732 determines whether the behavioral information or environmental information acquired in step S4804 exists in the reference information. If it exists in the reference information, the process proceeds to step S4806, and if it does not exist, the process proceeds to step S4809.

[0646] (Step S4806) The score acquiring unit 732 acquires the difference between the time information paired with the behavior information included in the i-th element information and the time information paired with the behavior information included in the reference information, or the difference between the environmental information (e.g., temperature) included in the i-th element information and the environmental information (e.g., temperature) included in the reference information. The score acquiring unit 732 temporarily stores the difference in association with the i-th element information.

[0647] The difference may be, for example, one or more of a difference in time, a difference in start time, and a difference in end time. The difference may be, for example, a difference in environmental information, or whether the environmental information is within the range of the environmental information conditions of the standard information.

[0648] (Step S4807) The score acquisition unit 732 determines whether or not the difference acquired in step S4806 satisfies the addition condition. If the addition condition is satisfied, the process proceeds to step S4808, and if the addition condition is not satisfied, the process proceeds to step S4809.

[0649] The addition condition is a condition for increasing the disturbance score. For example, the addition condition is that the difference is equal to or greater than a threshold value. For example, the addition condition is that the condition of the element information in the reference information is not satisfied. For example, the condition of the element information is "sleep time is 6 to 9 hours."

[0650] (Step S4808) The score acquisition unit 732 adds α to the disorder score. The process proceeds to step S4810. The initial value of the disorder score is, for example, "0." α may be a fixed positive number, or may be a positive number that varies depending on the magnitude of the difference or the element information.

[0651] (Step S4809) The score acquisition unit 732 adds β to the disorder score. Note that β may be a fixed positive number, or may be a positive number that varies depending on the element information.

[0652] (Step S4810) The score acquisition unit 732 increments the counter i by 1. The process returns to step S4803.

[0653] (Step S4811) The score obtaining unit 732 assigns 1 to the counter j.

[0654] (Step S4812) The score acquisition unit 732 determines whether or not the jth overall condition exists. If the jth overall condition exists, the process proceeds to step S4813; if not, the process returns to the upper level process. The overall condition is a condition relating to one or more element information in the entire time-series information. Examples of overall conditions are "time-series information including a collection of activity information for one week includes activity information 'drinking party' four or more times" and "time-series information including a collection of activity information for one week includes activity information 'sleep' for a duration of less than six hours three or more times."

[0655] (Step S4813) The score acquisition unit 732 determines whether or not the time-series information satisfies the j-th overall condition. If the j-th overall condition is satisfied, the process proceeds to step S4814, and if not, the process proceeds to step S4815.

[0656] (Step S4814) The score acquisition unit 732 adds γ to the disorder score. Note that γ may be a fixed positive number, or may be a positive number that varies depending on the element information.

[0657] (Step S4815) The score obtaining unit 732 increments the counter j by 1. The process returns to step S4812.

[0658] Next, an example of the cause acquisition process in step S4507 will be described with reference to the flowchart in FIG.

[0659] (Step S4901) The factor acquiring unit 735 assigns 1 to the counter i.

[0660] (Step S4902) The factor acquisition unit 735 determines whether or not the i-th element information exists in the time-series information. If the i-th element information exists, the process proceeds to step S4903; if not, the process returns to the upper level process.

[0661] (Step S4903) The factor acquiring unit 735 acquires element information included in the reference information corresponding to the i-th element information. The factor acquiring unit 735 acquires the difference between the two pieces of element information.

[0662] (Step S4904) The factor acquisition unit 735 determines whether or not the difference acquired in step S4903 satisfies the adoption conditions. If the adoption conditions are met, the process proceeds to step S4905, and if not, the process proceeds to step S4906.

[0663] (Step S4905) The factor acquiring unit 735 temporarily stores the i-th element information in a buffer (not shown). The i-th element information is information that constitutes the disturbance factor.

[0664] (Step S4906) The cause acquiring unit 735 increments the counter i by 1. The process returns to step S4902.

[0665] Next, an example of the recommendation acquisition process in step S4508 will be described with reference to the flowchart in FIG.

[0666] (Step S5001) The recommendation acquiring unit 736 assigns 1 to a counter i.

[0667] (Step S5002) The recommendation acquisition unit 736 determines whether the i-th disturbance factor exists in the buffer (not shown) in which the disturbance factors temporarily accumulated in step S4905 are stored. If the i-th disturbance factor exists, the process proceeds to step S5004; if not, the process returns to the upper process.

[0668] (Step S5003) The recommendation acquisition unit 736 acquires element information corresponding to the i-th disturbance factor.

[0669] (Step S5004) The recommendation obtaining unit 736 assigns 1 to a counter j.

[0670] (Step S5005) The recommendation acquisition unit 736 determines whether or not the jth factor condition exists in the recommendation management unit 712. If the jth factor condition exists, the process proceeds to step S5006; if not, the process proceeds to step S5010.

[0671] (Step S5006) The recommendation acquisition unit 736 determines whether the element information acquired in step S5003 satisfies the j-th factor condition. If the j-th factor condition is satisfied, the process proceeds to step S5007; if not, the process proceeds to step S5009.

[0672] (Step S5007) The recommendation acquisition unit 736 acquires recommendation source information paired with the j-th factor condition from the recommendation management unit 712.

[0673] (Step S5008) The recommendation acquisition unit 736 uses the recommendation source information and the element information acquired in step S5003 to compose recommendation information, and temporarily stores the recommendation information in a buffer (not shown).

[0674] (Step S5009) The recommendation acquisition unit 736 increments the counter j by 1. The process returns to step S5005.

[0675] (Step S5010) The recommendation obtaining unit 736 increments the counter i by 1. The process returns to step S5002.

[0676] Next, an example of the long-term score acquisition process in step S4522 will be described with reference to the flowchart in FIG.

[0677] (Step S5101) The long-term score acquiring unit 733 acquires from the behavior management unit 313 all disorder scores for a predetermined period that are paired with the user identifier of the target user.

[0678] (Step S5102) The long-term score acquisition unit 733 detects disorder scores that meet the disorder conditions from among the disorder scores acquired in step S5101, and acquires the number of such disorder scores. The disorder score is the number of times the user's behavior has become disordered in a predetermined period of time.

[0679] (Step S5103) The long-term score acquiring unit 733 acquires a long-term disorder score using all the disorder scores and the number of disorder scores that match the disorder condition. The process returns to the upper level processing. Note that the longer the disorder score is and the greater the number of disorder scores that match the disorder condition, the larger the long-term score acquiring unit 733 acquires a long-term disorder score.

[0680] Next, an example of the learning process in step S4528 will be described with reference to the flowchart in FIG.

[0681] (Step S5201) The learning unit 731 assigns 1 to a counter i.

[0682] (Step S5202) The learning unit 731 determines whether or not the i-th time-series information to be learned exists in the behavior management unit 313. If the i-th time-series information exists, the process proceeds to step S5203; if not, the process proceeds to step S5208.

[0683] (Step S5203) The learning unit 731 acquires the i-th time-series information from the behavior management unit 313.

[0684] (Step S5204) The learning unit 731 constructs a vector from the i-th time-series information. This vector is called an explanatory variable vector.

[0685] (Step S5205) The learning unit 731 acquires disturbance information corresponding to the i-th time-series information. Note that the disturbance information is stored in the behavior management unit 313, for example, paired with the time-series information.

[0686] (Step S5206) The learning unit 731 acquires training data having explanatory variable vectors and disturbance information, and temporarily stores the training data in a buffer (not shown).

[0687] (Step S5207) The learning unit 731 increments the counter i by 1. The process returns to step S5202.

[0688] (Step S5208) The learning unit 731 provides two or more pieces of training data in a buffer (not shown) to a module that performs machine learning learning processing, executes the module, and acquires a learning model. The process returns to the upper level processing.

[0689] A specific example of the operation of the information system F in this embodiment will be described below.

[0690] It is now assumed that the behavior management unit 313 of the behavior analysis device 7 stores the time period information management table shown in FIG. 53. The time period information management table is a table that manages the behavior information of one or more users for each time period. Here, the time period information management table has one or more records each having an "ID," "date," "time period," "behavior information," and "promiscuity score." For convenience, FIG. 53 is a table that manages the behavior information of one user (user U). It is also assumed here that the promiscuity score is obtained for each time period from waking up to just before the next wake-up (for each day).

[0691] 53 is information accumulated in the behavior management unit 313 by the behavior acquisition device 5. Also, each record in FIG. 53 may be information input by the user U.

[0692] It is also assumed that a reference vector is stored in reference management unit 711 of behavior analysis apparatus 7. The reference vector may be a self-reference vector, an other-person reference vector, or a recommended behavior vector.

[0693] The recommendation management unit 712 also stores a recommendation management table shown in Fig. 54. The recommendation management table is a table that includes one or more factor conditions and recommendation source information that pairs with the factor conditions.

[0694] In this situation, two specific examples will be described below. Specific Example 1 is a case where a disorder score and recommendation information are output. Specific Example 2 is a case where an improvement degree and a recovery period are output.

[0695] (Example 1) It is assumed that the receiving unit 72 of the behavior analysis device 7 has received time-series information, which is information from waking up to sleeping (until just before the next wake-up) including the combination of the date, time period, and behavioral information of "ID=538-548" in Fig. 53, paired with the user identifier of the user U. Then, the processing unit 73 determines that the score acquisition condition (receiving time-series information for the time period from waking up to just before the next wake-up) is met.

[0696] Next, it is assumed that the score acquisition unit 732 acquires a disorder score of "6" for the user U through the score acquisition process described above (see FIG. 46, FIG. 47, or FIG. 48) using the received time-series information of the user U. Here, it is assumed that the disorder score can take any rank from "0" to "10." It is also assumed that the disorder condition is "disorder score >= 5." Next, the score output unit 741 associates the disorder score "6" with the behavioral information, etc., and accumulates it as the attribute value of the "disorder score" in FIG. 53.

[0697] Next, the determining unit 734 determines that the acquired disorder score "6" meets the disorder condition "disorder score >= 5".

[0698] Next, the factor acquiring unit 735 acquires the time period "0:30-5:00", the behavioral information "sleep", and the reference information corresponding to "sleep" in the reference information of the reference managing unit 711 (for example, "<time> 6 hours to 10 hours <start time> until 11pm"), which is the difference in time "1.5 hours" and the difference in start time "1.5 hours", totaling "3 hours". Then, the factor output unit 743 temporarily stores the time period "0:30-5:00", the behavioral information "sleep", and the difference "3 hours" in a buffer not shown. In other words, the factor acquiring unit 735 acquires the disturbance factor "sleep".

[0699] Next, the recommendation acquisition unit 736 acquires recommendation information. It determines that the information temporarily stored in a buffer (not shown) by the factor output unit 743 satisfies the factor condition of "ID=1" in FIG. 54. The recommendation acquisition unit 736 acquires the recommendation source information of "ID=1" in FIG. 54. The recommendation acquisition unit 736 also acquires element information "<behavioral information> sleep <time period> 0:30-5:00" that pairs with the disturbance factor "sleep". The recommendation acquisition unit 736 assigns the acquired element information "<behavioral information> sleep <time period> 0:30-5:00" to the variable <element information> of the recommendation source information to construct recommendation information.

[0700] Next, the processing unit 73 generates output information having a disorder score of "6" and recommendation information.

[0701] Next, the output unit 74 transmits the constructed output information to the user U. The output unit 74 transmits the output information to, for example, the email address of the user U. The output unit 74 outputs the output information on, for example, a mobile application on the user's terminal device 8.

[0702] Then, the terminal device 8 of the user U outputs, for example, the disorder score and recommendation information as shown in FIG.

[0703] (Example 2) Next, suppose that one week has passed since the disorder score "6." Then, for each day of that week, the score acquisition unit 732 acquires disorder scores of "5," "4," "3," "3," "2," "2," and "0" using the accumulated time-series information, etc. Then, suppose that the score output unit 741 accumulates disorder scores of "5," "4," "3," "3," "2," "2," and "0" in association with the user U after the disorder score "6," respectively.

[0704] Then, the determining unit 734 determines that the improvement output condition "after the disturbance condition is satisfied, the disturbance score becomes 0" is satisfied.

[0705] Next, the improvement degree acquisition unit 737 acquires a disturbance score of "6" when the disturbance condition is met from a situation where the disturbance condition is not met, and a disturbance score of "0" when the improvement degree output condition is met, thereby acquiring an improvement degree of "6-0=6".

[0706] In addition, the judgment unit 734 judges that the disorder score "6" obtained when the disorder condition is met and the most recent disorder score "0" satisfy the recovery condition (the disorder score becoming "0" after the disorder condition is met).

[0707] Next, the recovery period acquisition unit 738 acquires the recovery period of "7 days", which is the difference between the date "10 / 20" included in the time information corresponding to the disorder score "6" and the date "10 / 27" included in the time information corresponding to the disorder score.

[0708] Next, the processing unit 73 obtains the disorder score of "0," the degree of improvement of "6," and the recovery period of "7 days," and generates output information containing the information. The output information contains the disorder score, the degree of improvement, and the recovery period.

[0709] Next, the output unit 74 transmits the constructed output information to the user U. The output unit 74 transmits the output information to, for example, the email address of the user U. The output unit 74 outputs the output information on, for example, a mobile application on the user's terminal device 8.

[0710] Then, the terminal device 8 of the user U outputs the disorder score, the degree of improvement, and the recovery period, for example, as shown in FIG.

[0711] As described above, according to this embodiment, it is possible to obtain a disorder score, which is the degree of disorder in the user's behavior. Note that according to this embodiment, for example, the disorder score can be obtained using self-reference information. Also, according to this embodiment, it is possible to obtain a disorder score by, for example, machine learning prediction processing. Also, according to this embodiment, it is possible to obtain a disorder score by, for example, using one or more of recommended behavior information and other-reference information. Also, according to this embodiment, it is possible to obtain a disorder score by also using, for example, environmental information.

[0712] Furthermore, according to this embodiment, the cause of the user's behavioral disturbance can be acquired.

[0713] Furthermore, according to this embodiment, recommendations can be made to improve irregular user behavior.

[0714] Furthermore, according to this embodiment, the degree of improvement in the user's behavioral irregularities can be acquired. Note that, according to this embodiment, the degree of improvement in the user's behavioral irregularities can be output at an appropriate timing when the improvement degree output condition is satisfied.

[0715] As mentioned above, behavior analysis apparatus 7 in this embodiment may be a terminal. A block diagram of a case in which behavior analysis apparatus 7 is a terminal is shown in FIG. 57. This behavior analysis apparatus becomes behavior analysis apparatus 9. In other words, behavior analysis apparatus 9 has the functions of behavior acquisition apparatus 3.

[0716] Furthermore, the software that realizes the behavior analysis device 7 in this embodiment is the following program. In other words, this program causes a computer that can access a reference management unit that stores reference information that is the basis for acquiring the degree of disordered behavior of a user to function as: a reception unit that receives time-series information that includes two or more pieces of time-series behavioral information that is information associated with time information that identifies when the user performed a behavior and that is information that identifies the behavior of the user; a score acquisition unit that uses the time-series information received by the reception unit and the reference information from the reference management unit to acquire a disorder score that is the degree of disordered behavior of the user; and a score output unit that outputs the disorder score acquired by the score acquisition unit.

[0717] (Embodiment 6) In this embodiment, a behavior analysis device that acquires behavior information of a user, and acquires and outputs a physical fitness score and a mental fitness score for the behavior information will be described.

[0718] In this embodiment, we will describe a behavioral analysis device that acquires a physical fitness score and a mental score for acquired behavioral information by also using a cumulative physical fitness score and a cumulative mental score acquired based on time series information, which is information on two or more of the user's past behaviors.

[0719] In this embodiment, a behavior analysis device is described that acquires a disorder score using time-series information and also acquires a physical fitness score and a mental fitness score for the acquired behavior information using the disorder score. Note that the disorder score is the degree to which behavior is disordered relative to a steady state, so the disorder score may also be referred to as a constancy score. The constancy score is a score that indicates the degree to which behavior is steady or unsteady.

[0720] In this embodiment, a behavior analysis device will be described that uses a physical score and a mental score for behavioral information and an internal state estimation model to obtain and output a cumulative physical score and a cumulative mental score.

[0721] In this embodiment, a behavior analysis device that acquires a cumulative physical fitness score and a cumulative mental fitness score using external environment data will be described.

[0722] In this embodiment, a behavior analysis device that uses one or two types of information from among vital data and sensing data to obtain and output a cumulative physical fitness score and a cumulative mental fitness score will be described.

[0723] In this embodiment, we describe a behavioral analysis device that estimates a cumulative physical fitness score and a cumulative mental score using one or two types of information, either vital data or sensing data, and obtains and outputs a corrected cumulative physical fitness score and a corrected cumulative mental score based on the estimated cumulative physical fitness score and the estimated cumulative mental score.

[0724] In this embodiment, a behavior analysis device that changes an internal state estimation model in accordance with an updated cumulative physical fitness score and an updated cumulative mental score will be described.

[0725] 58 is a conceptual diagram of information system G in this embodiment. Information system G comprises behavior analysis apparatus 10, one or more terminal devices 11, and two or more communication devices B.

[0726] 59 is a block diagram of information system G in this embodiment. FIG. 60 is a block diagram of behavior analysis apparatus 10.

[0727] Behavior analysis apparatus 10 includes a storage unit 101, a reception unit 102, a processing unit 103, and an output unit 104. Note that behavior analysis apparatus 10 may have all or part of the configuration of behavior analysis apparatus 7 or behavior analysis apparatus 9. In other words, behavior analysis apparatus 10 may implement all or part of the functions of behavior analysis apparatus 7 or behavior analysis apparatus 9. Storage unit 101 includes a knowledge storage unit 1011, a reference management unit 711, a model storage unit 1013, and a learning management unit 1014. Processing unit 103 includes a score acquisition unit 1031, an external environment acquisition unit 1032, a cumulative score acquisition unit 1033, a data acquisition unit 1034, a prediction unit 1035, and a model update unit 1036. Output unit 104 includes a score output unit 1041, a cumulative score output unit 1042, and a predicted value output unit 1043.

[0728] The terminal device 11 includes a terminal storage unit 61, a terminal reception unit 62, a terminal reception unit 83, a device processing unit 114, a terminal transmission unit 65, and a terminal output unit 86. The terminal storage unit 61 includes a map management unit 312. The device processing unit 114 includes an intensity acquisition unit 231, a type determination unit 232, a position acquisition unit 332, an activity acquisition unit 333, a vital sign acquisition unit 334, a location acquisition unit 337, and a sensor information acquisition unit 1141.

[0729] Various types of information are stored in storage unit 101 that constitutes behavior analysis apparatus 10. The various types of information include, for example, knowledge information, reference information, an internal state estimation model, learning information, behavior information, and various conditions, which will be described later. It goes without saying that the various conditions may be embedded in the program.

[0730] The various conditions include, for example, a model update condition and a recommendation condition.

[0731] The model update condition is a condition for updating the internal state estimation model. The model update condition is, for example, that after the internal state estimation model is constructed, newly accumulated teacher data is stored in an amount equal to or greater than a threshold, and that the difference between the cumulative score obtained using the internal state estimation model and the predicted cumulative score obtained by prediction unit 1035 (described later) is equal to or greater than a threshold. The cumulative score is a cumulative physical score and a cumulative mental score. The predicted cumulative score is a predicted cumulative physical score and a predicted cumulative mental score.

[0732] The recommendation conditions are conditions for recommending an action to be taken from candidate actions. For example, the recommendation conditions are that the score is equal to or greater than a threshold, and that the score ranking is equal to or higher than a threshold. The scores are physical and mental scores.

[0733] Two or more pieces of knowledge information are stored in the knowledge storage unit 1011. The knowledge information is a physical strength score corresponding to the behavior information, or a mental score corresponding to the behavior information.

[0734] The activity information may be, for example, "work," "watching TV," "walking," "running," "gym," "bath," or "sleeping." The activity information may also include the time when the activity was performed and the time period when the activity was performed. The time period is the start time and / or end time.

[0735] The stamina score is the degree to which the user's stamina is recovered or depleted when performing the action specified by the action information. The stamina score can be, for example, "+3" or "-2". A stamina score of "+3" indicates that stamina will be recovered by "3" when performing the action specified by the action information. A stamina score of "-2" indicates that stamina will be depleted by "2" when performing the action specified by the action information. The range of values ​​that the stamina score can take and the number of stages of the stamina score are not important.

[0736] The mental score is the degree to which the user recovers from mental fatigue or the degree to which mental fatigue is consumed when performing the behavior specified by the behavioral information. Mental scores are, for example, "+3" or "-2." A mental score of "+3" indicates that mental fatigue will be recovered by "3" when performing the behavior specified by the behavioral information. A mental score of "-2" indicates that mental fatigue will be consumed by "2" when performing the behavior specified by the behavioral information. The range of values ​​that the mental score can take and the number of stages of the mental score are not important.

[0737] As described above, the reference management unit 711 stores reference information that is the basis for acquiring the degree of disorder in the user's behavior corresponding to the time-series information.

[0738] One or more internal state estimation models are stored in the model storage unit 1013. The internal state estimation model may be different for each user, or may be common to two or more users. The internal state estimation model in the model storage unit 1013 is associated with, for example, a user identifier.

[0739] The internal state estimation model is a model for obtaining an updated cumulative physical fitness score and an updated cumulative mental fitness score using a newly acquired physical fitness score, a newly acquired mental fitness score, a cumulative physical fitness score based on past actions, and a cumulative mental fitness score based on past actions. Note that the cumulative physical fitness score based on past actions is preferably the cumulative physical fitness score immediately before receiving the latest action information. Also, it is preferably that the cumulative mental fitness score based on past actions is the cumulative mental fitness score immediately before receiving the latest action information.

[0740] The internal state estimation model for obtaining only the cumulative physical fitness score is referred to as the first internal state estimation model, as appropriate. The internal state estimation model for obtaining only the cumulative mental score is referred to as the second internal state estimation model, as appropriate. The internal state estimation model for obtaining both the cumulative physical fitness score and the cumulative mental score is referred to as the comprehensive internal state estimation model, as appropriate. It is preferable that the model storage unit 1013 has a first internal state estimation model and a second internal state estimation model. In other words, it is preferable that the internal state estimation model for obtaining the cumulative physical fitness score and the internal state estimation model for obtaining the cumulative mental score are different models. The internal state estimation model is, for example, an arithmetic formula, a learning model, or a correspondence table. (1) When the internal state estimation model is an arithmetic expression (1-1) When obtaining the cumulative physical and mental scores using different models,

[0741] The first internal state estimation model is a first arithmetic expression that uses a newly acquired physical fitness score and a cumulative physical fitness score based on past actions as parameters and outputs an updated cumulative physical fitness score. The first arithmetic expression is an increasing function that uses the physical fitness score and the cumulative physical fitness score as parameters.

[0742] The second internal state estimation model is a second arithmetic expression that uses the newly acquired mental score and the cumulative mental score based on past behavior as parameters and outputs an updated cumulative mental score. The second arithmetic expression is an increasing function that uses the mental score and the cumulative mental score as parameters. (1-2) When obtaining cumulative physical and mental scores using one model

[0743] The comprehensive internal state estimation model is a comprehensive calculation formula that uses a newly acquired physical fitness score, a newly acquired mental score, a cumulative physical fitness score based on past actions, and a cumulative mental score based on past actions as parameters, and outputs an updated cumulative physical fitness score and an updated cumulative mental score.

[0744] The above various arithmetic expressions are obtained by, for example, multiple regression analysis, polynomial regression, Bayesian regression, etc. using two or more sets of training data. (2) When the internal state estimation model is a learning model (2-1) When obtaining the cumulative physical and mental scores using different models,

[0745] The first internal state estimation model is a first learning model acquired by a machine learning learning process using two or more pieces of training data in which a newly acquired physical fitness score and a cumulative physical fitness score based on past behavior are used as explanatory variables, and the updated cumulative physical fitness score is used as a response variable. Note that the response variable, the cumulative physical fitness score, is, for example, a value input by a user. The method for generating the training data is not important.

[0746] The second internal state estimation model is a second learning model obtained by a machine learning learning process using two or more pieces of training data with the newly acquired mental score and the cumulative mental score based on past behavior as explanatory variables and the updated cumulative mental score as the objective variable. Note that the cumulative mental score, which is the objective variable, is, for example, a value entered by the user. Furthermore, the method for creating the training data is not important.

[0747] A learning model is information configured by a machine learning learning process and is information used in machine learning prediction processes. A learning model may also be called a learner, a classifier, a classification model, or the like. Any machine learning algorithm may be used, such as deep learning, random forest, decision tree, or SVR. For machine learning, various machine learning functions, such as the TensorFlow (registered trademark) library, the random forest module of the R language, or TinySVM, or various existing libraries, may be used. (2-2) When obtaining cumulative physical and mental scores using one model

[0748] The comprehensive internal state estimation model is a learning model obtained by a machine learning learning process using two or more pieces of training data in which a newly acquired physical fitness score, a newly acquired mental fitness score, a cumulative physical fitness score based on past actions, and a cumulative mental fitness score based on past actions are used as explanatory variables, and a pair of an updated cumulative physical fitness score and an updated cumulative mental fitness score is used as a response variable. Note that the response variables, the cumulative physical fitness score and the cumulative mental fitness score, are values ​​input by the user, for example. The method for generating the training data is not important. (3) When the internal state estimation model is a correspondence table (3-1) When obtaining the cumulative physical and mental scores using different models,

[0749] The first internal state estimation model is a first correspondence table having two or more pieces of correspondence information, including a newly acquired physical fitness score, a cumulative physical fitness score based on past actions, and an updated cumulative physical fitness score.

[0750] The second internal state estimation model is a second correspondence table having two or more pieces of correspondence information including a newly acquired mental score, a cumulative mental score based on past behavior, and an updated cumulative mental score. (3-2) When obtaining cumulative physical and mental scores using one model

[0751] The comprehensive internal state estimation model is a comprehensive correspondence table having two or more correspondence information pairs, including a newly acquired physical fitness score, a newly acquired mental score, a cumulative physical fitness score based on past behavior, a cumulative mental score based on past behavior, and an updated cumulative physical fitness score and an updated cumulative mental score.

[0752] The learning management unit 1014 stores one or more pieces of learning information. The learning information may be different for each user or may be common to two or more users. The learning information in the learning management unit 1014 may be associated with a user identifier.

[0753] The learning information of the learning management unit 1014 is, for example, behavior-specific learning information or actual measurement learning information.

[0754] The behavior-specific learning information is learning information used when the score acquisition unit 1031 acquires a score for one piece of behavior information. The actual measurement learning information is learning information used when the prediction unit 1035 acquires a cumulative score.

[0755] The behavior-specific learning information is information created using two or more pieces of teacher data. Such teacher data has two or more explanatory variables and a target variable. Each of the two or more explanatory variables includes, for example, a physical fitness score and a mental fitness score obtained using knowledge information. It is preferable that each of the two or more explanatory variables includes a past cumulative physical fitness score, a past cumulative mental fitness score, and a disturbance score. It is preferable that the past cumulative physical fitness score and the past cumulative mental fitness score are the cumulative physical fitness score and the cumulative mental fitness score immediately before acquiring the behavior, respectively. The target variables are the cumulative physical fitness score and the cumulative mental fitness score.

[0756] The behavior-specific learning information is, for example, a learning model, a correspondence table, or an arithmetic formula. The learning management unit 1014 may have behavior-specific learning information that outputs a physical fitness score and behavior-specific learning information that outputs a mental fitness score, or behavior-specific learning information that outputs both a physical fitness score and a mental fitness score. (1) When behavioral learning information is a learning model

[0757] The behavior-specific learning information is a learning model obtained by machine learning using two or more pieces of teacher data. The behavior-specific learning model is a first behavior-specific learning model, a second behavior-specific learning model, or a comprehensive behavior-specific learning model. (1-1) When obtaining physical and mental scores using different models

[0758] The first behavior-specific learning model is a learning model obtained by performing a machine learning learning process using two or more pieces of information, including a physical fitness score obtained using knowledge information, as explanatory variables and two or more pieces of training data with the physical fitness score as a target variable. Preferably, the explanatory variables include a past cumulative physical fitness score and a disturbance score.

[0759] The second behavior-specific learning model is a learning model obtained by performing machine learning learning processing using two or more pieces of information, including the mental score obtained using knowledge information, as explanatory variables and two or more pieces of training data with the mental score as the objective variable. Note that it is preferable that the explanatory variables include the past cumulative mental score and the disturbance score.

[0760] The training data for constructing the first behavior-specific learning model and the second behavior-specific learning model may be the same or different. (1-2) When obtaining physical and mental scores using one model

[0761] The comprehensive behavior-specific learning model is a learning model obtained by performing a machine learning learning process using two or more pieces of information, including a physical fitness score obtained using knowledge information and a mental fitness score obtained using knowledge information, as explanatory variables, and two or more pieces of training data, with the physical fitness score and the mental fitness score as objective variables. Preferably, the explanatory variables include a past cumulative physical fitness score, a past cumulative mental fitness score, and a disturbance score. (2) When the learning information is a correspondence table (2-1) When obtaining physical and mental scores using different models

[0762] The first behavior-specific correspondence table is a correspondence table that has two or more pieces of information, including the physical fitness score obtained using knowledge information, as explanatory variables, and has two or more pieces of teacher data, each of which has the physical fitness score as a response variable, as correspondence information. Note that it is preferable that the explanatory variables include the past cumulative physical fitness score and the disturbance score.

[0763] The second behavior-specific correspondence table is a correspondence table that has two or more pieces of information including the mental score obtained using knowledge information as explanatory variables, and has two or more pieces of teacher data as correspondence information with the mental score as the objective variable. Note that it is preferable that the explanatory variables include the past cumulative mental score and the disturbance score.

[0764] The training data for constructing the first prediction correspondence table and the second prediction correspondence table may be the same or different. (2-2) Obtaining physical and mental fitness scores using a single model

[0765] The comprehensive correspondence table is a correspondence table having two or more pieces of information including a physical fitness score obtained using knowledge information and a mental fitness score obtained using knowledge information as explanatory variables, and having two or more pieces of teacher data with the physical fitness score and the mental fitness score as objective variables as correspondence information. Note that it is preferable that the explanatory variables include a past cumulative physical fitness score, a past cumulative mental fitness score, and a disturbance score. (3) When the learning information is an arithmetic formula

[0766] The learning information is an arithmetic expression that uses two or more explanatory variables as parameters and outputs a target variable. The arithmetic expression is a first behavior-specific arithmetic expression, a second behavior-specific arithmetic expression, or a comprehensive behavior-specific arithmetic expression. (3-1) When obtaining physical and mental scores using different models

[0767] The first behavior-specific arithmetic formula is an arithmetic formula that returns a stamina score using one or more parameters including a stamina score obtained using knowledge information. Preferably, the parameters include a past cumulative stamina score and a disturbance score.

[0768] The second behavior-specific arithmetic formula is an arithmetic formula that takes one or more pieces of information, including the mental score obtained using the knowledge information, as parameters and returns the mental score. Note that the parameters preferably include the past accumulated mental score and the disturbance score.

[0769] The general behavior-specific arithmetic formula is an arithmetic formula that returns a physical fitness score and a mental fitness score using one or more parameters including a physical fitness score obtained using knowledge information and a mental fitness score obtained using knowledge information. Preferably, the parameters include a past cumulative physical fitness score, a past cumulative mental fitness score, and a disturbance score.

[0770] The learning information used by the prediction unit 1035 is referred to as actual measurement learning information as appropriate. The actual measurement learning information is information created using two or more pieces of teacher data. Such teacher data has two or more explanatory variables and a dependent variable. Here, each of the two or more explanatory variables is one or more types of data from one or more vital data of the user or one or more sensing data obtained by sensing the user. The dependent variable is one or two types of scores from the cumulative physical fitness score and the cumulative mental score. The cumulative physical fitness score acquired by the prediction unit 1035 is referred to as the predicted cumulative physical fitness score. The cumulative mental score acquired by the prediction unit 1035 is referred to as the predicted cumulative mental score.

[0771] Vital data is information that can be obtained from the user's body. Vital data may also be called biometric information. Examples of vital data include walking speed, walking acceleration, heart rate variability, changes in respiratory rate, heart rate per unit time (e.g., 1 minute or 30 seconds), heart rate variability, blood pressure (upper and / or lower), respiratory rate per unit time, and body temperature.

[0772] Sensing data is information resulting from sensing a user or information acquired from that information. Examples of sensing data include images of the user, voice information of the user, the user's temperature, information that quantifies the user's smell, and information that quantifies the user's sense of taste. Examples of sensing data include emotional information of the user acquired from images of the user, emotional information of the user acquired from the user's voice information, and one or more feature quantities of the voice information.

[0773] The learning information of the learning management unit 1014 is, for example, a learning model, a correspondence table, and an arithmetic formula. The learning management unit 1014 may contain learning information that outputs a cumulative physical fitness score and learning information that outputs a cumulative mental fitness score, or learning information that outputs both a cumulative physical fitness score and a cumulative mental fitness score. (1) When the learning information is a learning model

[0774] The learning information is a learning model obtained by a machine learning learning process using two or more pieces of training data. The learning model is a first predictive learning model, a second predictive learning model, or a comprehensive predictive learning model. (1-1) When obtaining predicted cumulative physical fitness scores and predicted cumulative mental fitness scores using different models, respectively

[0775] The first predictive learning model is a learning model obtained by performing a machine learning learning process using two or more pieces of training data with the cumulative physical fitness score as the objective variable and two or more pieces of data acquired by the data acquisition unit 1034 described later as explanatory variables.

[0776] The second predictive learning model is a learning model obtained by performing a machine learning learning process using two or more pieces of training data with the cumulative mental score as the objective variable and two or more pieces of data acquired by the data acquisition unit 1034 described later as explanatory variables.

[0777] The training data for constructing the first predictive learning model and the second predictive learning model may be the same or different. (1-2) Obtaining a predicted cumulative physical fitness score and a predicted cumulative mental fitness score using a single model

[0778] The comprehensive predictive learning model is a learning model obtained by performing a machine learning learning process using two or more pieces of training data that are used as explanatory variables and a pair of cumulative physical fitness score and cumulative mental score as a target variable, each of which is acquired by the data acquisition unit 1034 described later. (2) When the learning information is a correspondence table

[0779] The learning information is a correspondence table having two or more pieces of correspondence information each having two or more explanatory variables and a response variable. The correspondence table is a first prediction correspondence table, a second prediction correspondence table, or an overall prediction correspondence table. (2-1) When obtaining predicted cumulative physical fitness scores and predicted cumulative mental fitness scores using different models, respectively

[0780] The first prediction correspondence table is a first correspondence table that has two or more pieces of data acquired by the data acquisition unit 1034 described later as explanatory variables and two or more pieces of teacher data with the cumulative physical fitness score as the objective variable as correspondence information.

[0781] The second predicted correspondence table is a second correspondence table that has two or more pieces of data acquired by the data acquisition unit 1034 described later as explanatory variables and two or more pieces of teacher data with the cumulative mental score as the objective variable as correspondence information.

[0782] The training data for constructing the first prediction correspondence table and the second prediction correspondence table may be the same or different. (2-2) Obtaining a predicted cumulative physical fitness score and a predicted cumulative mental fitness score using a single model

[0783] The comprehensive correspondence table is a correspondence table that has, as correspondence information, two or more pieces of data and teacher data acquired by the data acquisition unit 1034 described later. (3) When the learning information is an arithmetic formula

[0784] The learning information is an arithmetic expression that uses two or more explanatory variables as parameters and outputs a response variable. The arithmetic expression is a first prediction arithmetic expression, a second prediction arithmetic expression, or an overall prediction arithmetic expression. (3-1) When obtaining predicted cumulative physical fitness scores and predicted cumulative mental fitness scores using different models, respectively

[0785] The first prediction calculation formula is a calculation formula that returns a predicted cumulative physical strength score using two or more pieces of data acquired by the data acquisition unit 1034 (described later) as parameters.

[0786] The second prediction calculation formula is a calculation formula that returns a predicted cumulative mental score using two or more pieces of data acquired by a data acquisition unit 1034 (described later) as parameters. (3-2) Obtaining a predicted cumulative physical fitness score and a predicted cumulative mental fitness score using a single model

[0787] The comprehensive prediction calculation formula is a calculation formula that uses two or more pieces of data acquired by the data acquisition unit 1034 (described later) as parameters and returns a predicted cumulative physical strength score and a predicted cumulative mental score.

[0788] The receiving unit 102 receives various instructions and information, such as behavior information, time-series information, and behavior recommendation instructions.

[0789] An action recommendation instruction is an instruction to recommend one or more actions from two or more actions. An action recommendation instruction is usually an instruction to recommend one or more actions from two or more actions that can be performed in the future. An action recommendation instruction has, for example, two or more pieces of action information that identify two or more candidate actions.

[0790] The receiving unit 102 receives, for example, behavioral information. The behavioral information here is information that identifies a behavior that the user has performed or a behavior that the user may perform in the future.

[0791] The receiving unit 102 receives, for example, time-series information. The time-series information is information that identifies two or more pieces of behavioral information in a time series. It is preferable that such behavioral information be information that corresponds to time information that identifies the time when the user performed an action.

[0792] Here, acceptance typically refers to the reception of information transmitted via a wired or wireless communication line, but may also be a concept that includes the reception of information input from an input device such as a keyboard, mouse, or touch panel, or the reception of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

[0793] The processing unit 103 performs various types of processing. The various types of processing are, for example, processing performed by the score acquisition unit 1031, the external environment acquisition unit 1032, the cumulative score acquisition unit 1033, the data acquisition unit 1034, the prediction unit 1035, or the model update unit 1036.

[0794] The score acquiring unit 1031 acquires the physical fitness score and the mental fitness score associated with the behavioral information accepted by the accepting unit 102. For example, the score acquiring unit 1031 acquires the physical fitness score and the mental fitness score associated with the behavioral information accepted by the accepting unit 102 from the knowledge storage unit 1011.

[0795] The score acquiring unit 1031 preferably acquires a total score using the acquired physical fitness score and mental fitness score. The score acquiring unit 1031 normally acquires a larger total score the larger the physical fitness score and the mental fitness score. The score acquiring unit 1031 calculates the total score using, for example, an increasing function with the physical fitness score and the mental fitness score as parameters.

[0796] The score acquiring unit 1031 acquires, for example, a physical strength score and a mental score for each of two or more pieces of behavior information included in the time-series information accepted by the accepting unit 102.

[0797] The score acquisition unit 1031, for example, uses the time series information received by the reception unit 102 and the standard information of the standard management unit 711 to acquire a disorder score, which is the degree of disorder in the user's behavior, and also uses the disorder score to acquire a physical fitness score and a mental score.

[0798] The score acquiring unit 1031 acquires a physical fitness score and a mental fitness score for one piece of behavioral information, for example, using behavior-specific learning information. An example of processing by the score acquiring unit 1031 when the behavior-specific learning information is a learning model, a correspondence table, or an arithmetic expression will be described. First, the score acquiring unit 1031 acquires a physical fitness score and a mental fitness score corresponding to the behavioral information accepted by the accepting unit 102. Furthermore, if a past cumulative score exists in the storage unit 101, it is preferable that the score acquiring unit 1031 acquires a physical fitness score and a mental fitness score using the past cumulative score. Furthermore, if a disorder score exists in the storage unit 101, it is preferable that the score acquiring unit 1031 acquires a physical fitness score and a mental fitness score using the disorder score. (1) When behavioral learning information is a learning model (1-1) When obtaining physical and mental scores using different models

[0799] The score acquisition unit 1031 acquires, for example, a physical fitness score associated with the behavioral information received by the reception unit 102 from the knowledge storage unit 1011. The score acquisition unit 1031 performs machine learning prediction processing using, for example, the physical fitness score, or the physical fitness score and the cumulative physical fitness score, or the physical fitness score and the disturbance score, or the physical fitness score, the cumulative physical fitness score and the disturbance score, and a first behavior-specific learning model, to acquire the physical fitness score.

[0800] Furthermore, the score acquisition unit 1031 acquires, for example, a mental score corresponding to the behavioral information received by the reception unit 102 from the knowledge storage unit 1011. The score acquisition unit 1031 performs machine learning prediction processing using, for example, the mental score, or the mental score and the cumulative mental score, or the mental score and the disturbance score, or the mental score, the cumulative mental score and the disturbance score, and a second behavior-specific learning model, to acquire the mental score. (1-2) When obtaining physical and mental scores using one model

[0801] The score acquisition unit 1031 acquires, for example, a physical fitness score and a mental fitness score corresponding to the behavioral information accepted by the acceptance unit 102 from the knowledge storage unit 1011. The score acquisition unit 1031 performs machine learning prediction processing using, for example, the physical fitness score and the mental fitness score, or the physical fitness score, the mental fitness score, the cumulative physical fitness score, and the cumulative mental fitness score, or the physical fitness score, the mental fitness score, the cumulative physical fitness score, the cumulative mental fitness score, and the cumulative mental fitness score, and a comprehensive behavior-specific learning model, to acquire the physical fitness score and the mental fitness score. (2) When the learning information is a correspondence table (2-1) When obtaining physical and mental scores using different models

[0802] The score acquiring unit 1031 acquires, for example, a physical fitness score corresponding to the behavior information accepted by the accepting unit 102 from the knowledge storage unit 1011. The score acquiring unit 1031 constructs a vector from, for example, the physical fitness score, or the physical fitness score and the cumulative physical fitness score, or the physical fitness score and the disturbance score, or the physical fitness score, the cumulative physical fitness score and the disturbance score. Next, the score acquiring unit 1031 acquires, from the first behavior-specific correspondence table, the physical fitness score paired with the vector that is most similar to the vector.

[0803] The score acquiring unit 1031 acquires, for example, a mental score corresponding to the behavioral information accepted by the accepting unit 102 from the knowledge storage unit 1011. The score acquiring unit 1031 constructs a vector from, for example, the mental score, or the mental score and the cumulative mental score, or the mental score and the disturbance score, or the mental score, the cumulative mental score and the disturbance score. Next, the score acquiring unit 1031 acquires, from the second behavior-specific correspondence table, the mental score that pairs with the vector that is most similar to the vector. (2-2) Obtaining physical and mental fitness scores using a single model

[0804] The score acquiring unit 1031 acquires, for example, a physical score and a mental score corresponding to the behavioral information accepted by the accepting unit 102 from the knowledge storage unit 1011. The score acquiring unit 1031 constructs a vector from, for example, the physical score and the mental score, or the physical score, the mental score, the cumulative physical score, and the cumulative mental score, or the physical score, the mental score, the cumulative physical score, the cumulative mental score, and the disorder score. Next, the score acquiring unit 1031 acquires, from the comprehensive behavior correspondence table, the physical score and the mental score paired with the vector that is most similar to the vector. (3) When the learning information is an arithmetic formula (3-1) When obtaining physical and mental scores using different models

[0805] The score acquiring unit 1031 acquires, for example, a physical fitness score associated with the behavioral information accepted by the accepting unit 102 from the knowledge storage unit 1011. The score acquiring unit 1031 acquires, for example, the physical fitness score, or the physical fitness score and a cumulative physical fitness score, or the physical fitness score and a disturbance score, or the physical fitness score, a cumulative physical fitness score, and a disturbance score. Next, the score acquiring unit 1031 substitutes the acquired information as parameters into a first behavior-specific arithmetic formula, executes the first behavior-specific arithmetic formula, and acquires the physical fitness score.

[0806] Furthermore, the score acquiring unit 1031 acquires, for example, a mental score corresponding to the behavioral information accepted by the accepting unit 102 from the knowledge storage unit 1011. The score acquiring unit 1031 acquires, for example, the mental score, or the mental score and the cumulative mental score, or the mental score and the disorder score, or the mental score, the cumulative mental score and the disorder score. Next, the score acquiring unit 1031 substitutes the acquired information as parameters into a second behavior-specific arithmetic formula, executes the second behavior-specific arithmetic formula, and acquires the mental score. (3-2) Obtaining physical and mental fitness scores using a single model

[0807] The score acquiring unit 1031 acquires, for example, a physical fitness score and a mental fitness score corresponding to the behavioral information accepted by the accepting unit 102 from the knowledge storage unit 1011. The score acquiring unit 1031 acquires, for example, the physical fitness score and the mental fitness score, or the physical fitness score, the mental fitness score, the cumulative physical fitness score, and the cumulative mental fitness score, or the physical fitness score, the mental fitness score, the cumulative physical fitness score, the cumulative mental fitness score, and the disorder score. Next, the score acquiring unit 1031 substitutes the acquired information as parameters into an overall behavior-specific arithmetic formula, executes the overall behavior-specific arithmetic formula, and acquires the physical fitness score and the mental fitness score.

[0808] The external environment acquisition unit 1032 acquires one or more pieces of external environment data. The external environment acquisition unit 1032 receives one or more pieces of external environment data from, for example, a server (not shown). The external environment acquisition unit 1032 receives one or more pieces of external environment data from, for example, the terminal device 11. The external environment acquisition unit 1032 acquires one or more pieces of external environment data using a sensor.

[0809] The external environment data is, for example, the temperature where the user is located, the air pressure where the user is located, the weather where the user is located, the humidity where the user is located, communication information, and search logs. Communication information is information related to communication conducted by the user. Communication information is, for example, user-input information or user-received information. User-input information is information entered by the user. User-input information is, for example, emails sent by the user, information posted by the user on an SNS, and information entered by the user in a chat. User-received information is, for example, emails received by the user, and information entered by others in a channel of a group to which the user belongs.

[0810] The cumulative score acquisition unit 1033 acquires a cumulative physical score using a physical score for each of two or more pieces of behavioral information included in the time-series information. The cumulative score acquisition unit 1033 acquires a cumulative mental score using a mental score for each of two or more pieces of behavioral information included in the time-series information. The cumulative score acquisition unit 1033 may accumulate the cumulative physical score and the cumulative mental score in the storage unit 101 or the like. The cumulative score acquisition unit 1033 may accumulate the cumulative physical score and the cumulative mental score in the storage unit 101 or the like in association with a user identifier.

[0811] It is preferable that the cumulative score acquisition unit 1033 acquires a total cumulative score using the acquired cumulative physical score and cumulative mental score. The cumulative score acquisition unit 1033 normally acquires a larger total cumulative score the larger the cumulative physical score and the larger the cumulative mental score. The cumulative score acquisition unit 1033 calculates the total cumulative score, for example, using an increasing function with the cumulative physical score and the cumulative mental score as parameters. The total cumulative score may also be called an internal state score.

[0812] If there is no cumulative physical score or cumulative mental score, the cumulative score acquisition unit 1033 may use the physical score acquired by the score acquisition unit 1031 as the cumulative physical score, and the mental score acquired by the score acquisition unit 1031 as the cumulative mental score.

[0813] The cumulative score acquiring unit 1033 acquires the cumulative physical strength score using, for example, an increasing function with the physical strength score for each of two or more pieces of behavior information included in the time-series information as a parameter. The cumulative score acquiring unit 1033 acquires the cumulative physical strength score by, for example, adding up the physical strength scores for each of two or more pieces of behavior information included in the time-series information. Note that it is preferable that the cumulative score acquiring unit 1033 acquires a cumulative physical strength score that does not exceed the maximum value of the cumulative physical strength score.

[0814] The cumulative score acquisition unit 1033 acquires the cumulative mental score using, for example, an increasing function with the mental score for each of two or more pieces of behavior information contained in the time-series information as a parameter. The cumulative score acquisition unit 1033 acquires the cumulative mental score by, for example, adding up the mental scores for each of two or more pieces of behavior information contained in the time-series information. It is preferable that the cumulative score acquisition unit 1033 acquires a cumulative mental score that does not exceed the maximum value of the cumulative mental score.

[0815] The cumulative physical strength score is the cumulative recovery or depletion of the user's physical strength, and the cumulative mental score is the cumulative recovery or depletion of the user's mental fatigue.

[0816] The cumulative score acquisition unit 1033, for example, acquires the physical fitness score acquired by the score acquisition unit 1031, the mental score acquired by the score acquisition unit 1031, the accumulated cumulative physical fitness score, and the accumulated cumulative mental score, and applies the physical fitness score, the mental score, the accumulated physical fitness score, and the accumulated mental score to an internal state estimation model to acquire and accumulate the cumulative physical fitness score and the cumulative mental score.

[0817] The cumulative score acquisition unit 1033, for example, applies the physical fitness score, mental score, cumulative physical fitness score, cumulative mental score, and one or more external environmental data to an internal state estimation model, and acquires and accumulates the cumulative physical fitness score and cumulative mental score.

[0818] The processing of the cumulative score acquisition unit 1033 in each case where the internal state estimation model is an arithmetic expression, a learning model, or a correspondence table will be described below. (1) When the internal state estimation model is an arithmetic expression (1-1) When obtaining the cumulative physical and mental scores using different models,

[0819] The cumulative score acquiring unit 1033 acquires the physical strength score acquired by the score acquiring unit 1031. Furthermore, the cumulative score acquiring unit 1033 acquires the cumulative physical strength score accumulated in the storage unit 101. Note that the cumulative score acquiring unit 1033 may acquire one or more pieces of external environment data acquired by the external environment acquiring unit 1032.

[0820] Next, the cumulative score acquisition unit 1033 substitutes the physical strength score and the cumulative physical strength score into a first arithmetic expression. Note that the cumulative score acquisition unit 1033 may also substitute one or more pieces of external environment data into the first arithmetic expression. Next, the cumulative score acquisition unit 1033 executes the first arithmetic expression to acquire an updated cumulative physical strength score.

[0821] The cumulative score acquisition unit 1033 acquires the mental score acquired by the score acquisition unit 1031. The cumulative score acquisition unit 1033 also acquires the cumulative mental score accumulated in the storage unit 101. Note that the cumulative score acquisition unit 1033 may also acquire one or more pieces of external environment data acquired by the external environment acquisition unit 1032.

[0822] Next, the cumulative score acquisition unit 1033 substitutes the mental score and the cumulative mental score into a second arithmetic expression. Note that the cumulative score acquisition unit 1033 may also substitute one or more pieces of external environment data into the second arithmetic expression. Next, the cumulative score acquisition unit 1033 executes the second arithmetic expression to acquire an updated cumulative mental score. (1-2) When obtaining cumulative physical and mental scores using one model

[0823] The cumulative score acquiring unit 1033 acquires the physical strength score acquired by the score acquiring unit 1031 and the mental score acquired by the score acquiring unit 1031. Furthermore, the cumulative score acquiring unit 1033 acquires the cumulative physical strength score and the cumulative mental score accumulated in the storage unit 101. Note that the cumulative score acquiring unit 1033 may acquire one or more pieces of external environment data acquired by the external environment acquiring unit 1032.

[0824] Next, the cumulative score acquisition unit 1033 substitutes the physical strength score, mental score, cumulative physical strength score, and cumulative mental score into the overall calculation formula. Note that the cumulative score acquisition unit 1033 may also substitute one or more pieces of external environment data into the overall calculation formula.

[0825] Next, the cumulative score acquisition unit 1033 executes the comprehensive calculation formula and acquires the updated cumulative physical strength score and the updated cumulative mental score. (2) When the internal st...

Claims

1. a knowledge storage unit that stores a physical fitness score, which indicates the degree of recovery or depletion of physical fitness of the user when the user performs an action, and a mental fitness score, which indicates the degree of recovery or depletion of mental fatigue, in association with each of two or more pieces of action information that specify the user's action; a reference management unit that stores reference information that is the basis for acquiring the degree of disruption of user behavior corresponding to the time-series information; a receiving unit that receives time-series information including two or more pieces of time-series behavior information of a user; a score acquisition unit that acquires, for each of two or more pieces of behavioral information included in the time-series information received by the reception unit, a physical fitness score and a mental fitness score associated with the behavioral information from the knowledge storage unit; a score output unit that outputs the physical fitness score and the mental fitness score acquired by the score acquisition unit in a manner that correlates them with each other for each of two or more pieces of behavioral information included in the time-series information accepted by the acceptance unit, The score acquisition unit A behavioral analysis device that uses the time series information received by the reception unit and the standard information of the standard management unit to obtain a disorder score, which is the degree of disorder in the user's behavior, and also uses the disorder score to obtain the physical fitness score and the mental score for each of two or more pieces of behavioral information contained in the time series information received by the reception unit.

2. A knowledge storage unit that stores a physical fitness score, which indicates the degree of recovery or depletion of the user's physical fitness when the user performs an action, and a mental fitness score, which indicates the degree of recovery or depletion of mental fatigue, in association with each of two or more pieces of behavioral information that identify the user's behavior; a receiving unit that receives time-series information including two or more pieces of time-series behavior information of a user; a score acquisition unit that acquires, for each of the two or more pieces of behavioral information included in the time-series information, a physical fitness score and a mental fitness score associated with the behavioral information from the knowledge storage unit; a cumulative score acquisition unit that acquires a cumulative physical fitness score, which is a degree of recovery or exhaustion of the user's accumulated physical fitness, using the physical fitness score for each of the two or more pieces of behavioral information contained in the time-series information, and acquires and accumulates a cumulative mental fitness score, which is a degree of recovery or exhaustion of the user's accumulated mental fatigue, using the mental fitness score for each of the two or more pieces of behavioral information contained in the time-series information; The reception unit After receiving the time series information, further behavioral information is received; The score acquisition unit After the cumulative score acquisition unit acquires the cumulative physical score and the cumulative mental score, the cumulative score acquisition unit uses the cumulative physical score acquired to acquire the physical score for the further behavioral information accepted by the reception unit, and the cumulative mental score acquired by the cumulative score acquisition unit is used to acquire the mental score for the further behavioral information accepted by the reception unit; The behavior analysis device further comprises a score output unit that outputs the physical fitness score and the mental score acquired by the score acquisition unit in a manner that correlates them.

3. A knowledge storage unit that stores a physical fitness score, which indicates the degree of recovery or depletion of the user's physical fitness when the user performs an action, and a mental fitness score, which indicates the degree of recovery or depletion of mental fatigue, in association with each of two or more pieces of behavioral information that identify the user's behavior; a model storage unit in which an internal state estimation model is stored for obtaining an updated cumulative physical fitness score and an updated cumulative mental score using a newly acquired physical fitness score, a newly acquired mental fitness score, a cumulative physical fitness score based on past actions, and a cumulative mental fitness score based on past actions; a receiving unit that receives time-series information including two or more pieces of time-series behavior information of a user; a score acquisition unit that acquires, for each of two or more pieces of behavioral information included in the time-series information received by the reception unit, a physical fitness score and a mental fitness score associated with the behavioral information from the knowledge storage unit; a cumulative score acquisition unit that acquires a cumulative physical fitness score, which is a degree of recovery or exhaustion of the user's accumulated physical fitness, using the physical fitness score for each of the two or more pieces of behavioral information contained in the time-series information, and acquires and accumulates a cumulative mental fitness score, which is a degree of recovery or exhaustion of the user's accumulated mental fatigue, using the mental fitness score for each of the two or more pieces of behavioral information contained in the time-series information; The cumulative score acquisition unit acquiring the physical fitness score acquired by the score acquisition unit, the mental score acquired by the score acquisition unit, the accumulated cumulative physical fitness score, and the accumulated cumulative mental score, and applying the physical fitness score, the mental score, the accumulated physical fitness score, and the accumulated cumulative mental score to the internal state estimation model to acquire a new cumulative physical fitness score and a new cumulative mental score; The behavior analysis device further comprises a cumulative score output unit that outputs the new cumulative physical fitness score and the new cumulative mental score acquired by the cumulative score acquisition unit in a manner that correlates them.

4. Further comprising an external environment acquisition unit that acquires external environment data, The cumulative score acquisition unit The behavior analysis device according to claim 3 , wherein the physical fitness score, the mental score, the cumulative physical fitness score, the cumulative mental score, and the external environment data are applied to an internal state estimation model to obtain the cumulative physical fitness score and the cumulative mental score.

5. a learning management unit that stores learning information created using two or more pieces of teacher data, which are one or more types of data selected from one or more vital data of the user or one or more pieces of sensing data obtained by sensing the user, and which uses two or more pieces of data as explanatory variables and one or two types of scores selected from the cumulative physical fitness score and the cumulative mental score as objective variables; a data acquisition unit that acquires two or more types of data, the data being one or more types of vital data of the user or one or more types of sensing data obtained by sensing the user; a prediction unit that obtains a predicted cumulative physical fitness score and a predicted cumulative mental fitness score using the two or more pieces of data obtained by the data obtaining unit and the learning information; The behavior analysis device according to claim 3 , further comprising a predicted value output unit that outputs the predicted cumulative physical fitness score and the predicted cumulative mental score acquired by the prediction unit.

6. The cumulative score acquisition unit Using the predicted cumulative physical fitness score to correct the cumulative physical fitness score to obtain a corrected cumulative physical fitness score, and using the predicted cumulative mental fitness score to correct the cumulative mental fitness score to obtain a corrected cumulative mental fitness score; The cumulative score output unit The behavior analysis device according to claim 5 , wherein the predicted cumulative physical fitness score and the predicted cumulative mental score acquired by the cumulative score acquisition unit are output in a manner in which they are associated with each other.

7. The behavioral analysis device of claim 5, further comprising a model update unit that updates the internal state estimation model based on the difference between the cumulative physical fitness score and the predicted cumulative physical fitness score, and the difference between the cumulative mental score acquired by the cumulative score acquisition unit and the predicted cumulative mental score.

8. A behavior analysis method including all processes performed by the behavior analysis device according to any one of claims 1 to 7.

9. Computer, A program for causing the behavioral analysis device according to any one of claims 1 to 7 to function.

Images