Estimation device

Abstract

In the present invention, an acquisition unit acquires at least one of: a life log, in which is recorded a history of one or more specific behaviors that affect a change in a user's immunity; and a meteorological log, in which is recorded a history of one or more meteorological elements that are of a place at which the user was, and that affect a change in the user's immunity. An estimation unit estimates an immunity index, which is for immunity over a prescribed period starting from an estimation target time point, on the basis of at least one of the history of one or more specific behaviors recorded in the life log, and the history of one or more meteorological elements recorded in the meteorological log. The estimation unit estimates the immunity index on the basis of at least one of: the history of one specific behavior from among the one or more specific behaviors, at a first time point which precedes the estimation target time point by a first expression period corresponding to the one specific behavior; and the history of one meteorological element from among the one or more meteorological elements, at a second time point which precedes the estimation target time point by a second expression period corresponding to the one meteorological element. The first expression period is from the time point at which the user performed the one specific behavior to when a change in the immunity index caused by the one specific behavior is expressed. The second expression period is from the time point at which the user was at a place having the one meteorological element to when a change in the immunity index caused by the one meteorological element is expressed.

Description

estimation device

[0001] The present disclosure relates to an estimation device.

[0002] There are known technologies for managing health using a life log that records a user's daily life (see, for example, Patent Document 1 and Patent Document 2). On the other hand, there have also been attempts to build a predictive model for predicting a user's immune status using machine learning (see, for example, Patent Document 3).

[0003] JP 2022-73115 A JP 2022-130962 A Japanese Patent No. 7220822 A

[0004] However, none of Patent Documents 1 to 3 discloses estimating an index of immunity based on log data such as a user's life log.

[0005] The present disclosure aims to provide an estimation device that can accurately estimate an index of immunity based on log data such as a user's life log.

[0006] An estimation device according to one aspect of the present disclosure includes an acquisition unit that acquires at least one of a life log in which a history of one or more types of specific behaviors that affect a change in a user's immunity is recorded, and a weather log in which a history of one or more types of weather elements at a location where the user was located that affect a change in the user's immunity is recorded, and an estimation unit that estimates an immunity index that is an index of immunity over a predetermined period from a time point to be estimated, based on at least one of the history of the one or more types of specific behaviors recorded in the life log and the history of the one or more types of weather elements recorded in the weather log, and the estimation unit estimates an immunity index that is an index of immunity over a predetermined period from a time point to be estimated, based on one type of specific behavior out of the one or more types of specific behaviors. The immunity index is estimated based on at least one of the history of the one type of specific behavior at a first time point that precedes the estimation target time point by a first expression period corresponding to the one type of weather element, and the history of the one type of weather element at a second time point that precedes the estimation target time point by a second expression period corresponding to the one type of weather element among the one or more types of weather elements, wherein the first expression period is the period from the time point at which the user performed the one type of specific behavior to the time at which the immunity index caused by the one type of specific behavior is expressed, and the second expression period is the period from the time point at which the user was in a place having the one type of weather element to the time at which the immunity index caused by the weather element is expressed.

[0007] According to one aspect of the present disclosure, it is possible to accurately estimate the trend of immunity based on log data such as a user's life log.

[0008] FIG. 1 is a diagram illustrating an example of a configuration of an information providing system according to an embodiment of the present disclosure. FIG. 2 is an explanatory diagram of immunity trends. FIG. 3 is a diagram illustrating an example of the electrical configuration of a user device. FIG. 4 is a diagram illustrating an example of the electrical configuration of an immunity trend information providing device. FIG. 5 is a diagram schematically illustrating an example of learning data used for training an estimation model. FIG. 6 is a matrix diagram illustrating an example of an analysis result of sample data. FIG. 7 is a diagram illustrating an example of data used for estimating immunity trends from the history of specific behaviors. FIG. 8 is a conceptual diagram of group-specific machine learning of learning data. FIG. 9 is an explanatory diagram of clustering of learning data. FIG. 10 is a diagram illustrating an example of the operation of the information providing system.

[0009] 1. Embodiment FIG. 1 is a diagram illustrating an example of the configuration of an information providing system 1 according to an embodiment of the present disclosure. The information providing system 1 estimates an immunity trend D2A of a user U based on the user U's life log D1, and provides the user U with immunity trend information D2 including the estimated immunity trend D2A. The immunity trend D2A is an example of an "immunity index" in the present disclosure. The information providing system 1 of this embodiment also uses a weather log D3 in which weather information D3A is recorded to estimate the immunity trend D2A. In this embodiment, a form in which the information providing system 1 provides a service via a network A will be described.

[0010] The life log D1 is data recording the actions of the user U in their daily lives. The life log D1 includes information that enables identification of an action history indicating when, what actions the user U performed, and for how long. Specifically, the life log D1 records the actions performed by the user U in association with the date and time. The actions recorded in the life log D1 are actions that affect the immunity trend D2A. Specifically, they include actions classified as lifestyle habits. Examples of such actions include sleeping, walking, exercising, going out, returning home, commuting, eating, drinking, bathing, and smoking. "Actions classified as lifestyle habits" are hereinafter referred to as "specific actions." In the life log D1 of this embodiment, specific actions are recorded in association with the date and time.

[0011] Furthermore, the life log D1 records user U's location information in association with date and time. This record makes it possible to identify information such as when, where, and for how long user U was there. Furthermore, based on this record and the location information of user U's home and other arbitrary locations, the following information can be identified: at-home time length, which is the length of time user U spent at home; out-of-home time length, which is the length of time user U stayed at an arbitrary location other than home; the length of time and distance taken to travel from a first location to a second location; and home-coming time, which is the time when user U returned home.

[0012] FIG. 2 is an explanatory diagram of the immunity trend D2A. The immunity trend D2A means the trend of changes in the user U's immunity from the estimation target time B to the predetermined period T. In this embodiment, the immunity trend D2A is shown in three categories: "upward trend," "downward trend," and "flat trend," as shown in FIG. 2. The "upward trend" means a trend of increasing immunity from the estimation target time B to the predetermined period T. The "downward trend" means a trend of decreasing immunity from the estimation target time B to the predetermined period T. The "flat trend" means a trend of almost no change in immunity from the estimation target time B to the predetermined period T.

[0013] The unit of the predetermined period T may be an appropriate unit such as an hour, a day, a week, or a month. The length of the predetermined period T may be an appropriate length such as one period unit or two or more period units. That is, the length of the predetermined period T may be, for example, "1 day," "2 days," "1 week," "2 weeks," "1 month," "2 months," or any other period length.

[0014] The estimation target time point B refers to the time point for which the immunity trend D2A is to be estimated. The estimation target time point B may be the estimated execution time itself, such as the "current time" or "today" of the estimated execution time at which the immunity trend estimation is performed in the information provision system 1. The estimation target time point B may also be any time in the future based on the estimated execution time point, such as "one week later" or "one month later" from the estimated execution time point. In other words, the information provision system 1 estimates the immunity trend D2A from the estimation target time point B over any predetermined period T based on the estimation target time point B. The estimation target time point B is the estimated execution time point or any time in the future from the estimated execution time point. As an example, if the estimation target time point B is the "today" of the estimated execution time point, the unit of the predetermined period T is "day," and the length of the predetermined period T is "one day," the information provision system 1 will estimate the immunity trend D2A from "today" to "the next day" based on the "today" of the estimated execution time point.

[0015] Returning to FIG. 1 , the weather information D3A is information about weather elements at the location where the user U is located, which affect the immunity trend D2A. Weather elements are elements that represent weather conditions and phenomena. Examples of weather elements that affect the immunity trend D2A include temperature, humidity, atmospheric pressure, wind speed, sunshine, cloud cover, precipitation, snowfall, snow accumulation, and weather. In particular, humidity and temperature are known to be environmental factors that favor the proliferation of viruses that cause infectious diseases. Therefore, humidity and temperature are estimated to affect the immunity trend D2A.

[0016] In the weather log D3 of this embodiment, weather information D3A is recorded in association with date and time. Therefore, information such as when, what weather element environment the user U was in, and for how long, in other words, the history of weather elements at the location where the user U was, can be identified from the weather log D3. The frequency and timing at which the weather information D3A is recorded in the weather log D3 are appropriate.

[0017] The life log D1 and the weather log D3 may be recorded together as one piece of log data.

[0018] As shown in Fig. 1, the information providing system 1 of this embodiment includes a user device 2, an immunity trend information providing device 4, and a weather information providing device 6. The user device 2, the immunity trend information providing device 4, and the weather information providing device 6 are each devices that access a network A such as the Internet and communicate via the network A. The immunity trend information providing device 4 is an example of an "estimation device" in the present disclosure. Note that although Fig. 1 shows only one user device 2, there may be multiple user devices 2.

[0019] 3 is a diagram showing an example of the electrical configuration of the user device 2. The user device 2 is a portable electronic device that sequentially records a life log D1 and a weather log D3 and transmits the life log D1 and the weather log D3 to the immunity trend information providing device 4 via a network A. Specific forms of the user device 2 include, for example, a mobile phone, a smartphone, and a wearable device.

[0020] As shown in Figure 3, the user device 2 includes a first communication device 20, a first storage device 22, a first control device 24, a measuring device 26, an operating device 27, and a display device 28, each of which is connected to a bus 29 and transmits and receives signals via the bus 29.

[0021] The first communication device 20 is hardware that accesses the network A, and includes a transmitting circuit and a receiving circuit.

[0022] The first storage device 22 is a recording medium readable by the first control device 24. The first storage device 22 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM). The volatile memory is, for example, a random access memory (RAM).

[0023] The first control device 24 includes one or more processors, such as a central processing unit (CPU). Some of the functions of the first control device 24 may be achieved by using circuits such as a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA) instead of or in addition to the CPU.

[0024] The operation device 27 accepts operations from the user U. The display device 28 displays various information.

[0025] The measurement device 26 measures the behavior of the user U. The measurement device 26 includes one or more sensors required for measurement. The measurement device 26 of this embodiment includes at least a first sensor for measuring the walking and movement of the user U, a second sensor for measuring sleep, and a third sensor for measuring location information. The first sensor is, for example, an acceleration sensor. The second sensor is, for example, a pulse wave sensor and a heart rate sensor. The third sensor is a device that receives a signal including location information indicating the location of the user device 2. Examples of signals including location information include GNSS signals, radio waves emitted by base stations included in a mobile communication network, and beacon signals. "GNSS" is an abbreviation for Global Navigation Satellite System.

[0026] In addition, the measuring device 26 may be equipped with other sensors for measuring or recognizing any state, such as a fourth sensor for recognizing images and videos, a fifth sensor for recognizing voice and external sounds, and a sixth sensor for recognizing the use of the user device 2 by the user U and the history of that use, etc.

[0027] In this embodiment, the first storage device 22 stores the above-described life log D1, weather log D3, and first program PR1. The first program PR1 is a program for controlling the user device 2. By executing the first program PR1, the first control device 24 functions as a measurement control unit 240, a weather information acquisition control unit 242, a life log recording control unit 244, and a weather log recording control unit 246.

[0028] The measurement control unit 240 is a functional unit that controls the measurement device 26 to sequentially acquire measurement values ​​from the measurement device 26 and, based on the measurement values, identifies at least the specific behavior among the behaviors of the user U. The measurement control unit 240 also sequentially acquires position information based on the measurement values. The timing and frequency at which the measurement control unit 240 acquires the measurement values ​​are appropriate.

[0029] The weather information acquisition control unit 242 is a functional unit that acquires weather information D3A for the location indicated by the location information based on the location information included in the measurement values ​​of the measuring device 26. In this embodiment, the weather information acquisition control unit 242 controls the first communication device 20 to acquire weather information D3A from the weather information providing device 6 over network A. The weather information providing device 6 is a network node that provides a service of distributing weather information D3A over network A. Note that the measuring device 26 may include a seventh sensor that measures weather, and the weather information acquisition control unit 242 may acquire weather information D3A from the seventh sensor. The seventh sensor may be, for example, a temperature sensor or a humidity sensor.

[0030] The life log recording control unit 244 is a functional unit that records the specific behavior and location information identified by the measurement control unit 240 in association with the date and time.

[0031] The weather log recording control unit 246 is a functional unit that records the weather information D3A acquired by the weather information acquisition control unit 242 in the weather log D3 in association with the date and time.

[0032] Fig. 4 is a diagram showing an example of the electrical configuration of the immunity trend information providing device 4. As shown in Fig. 4, the immunity trend information providing device 4 includes a second communication device 40, a second storage device 42, and a second control device 44, each of which is connected to a bus 46 and transmits and receives signals to and from each other via the bus 46.

[0033] The second communication device 40 is hardware that accesses the network A, and includes a transmitting circuit and a receiving circuit.

[0034] The second storage device 42 is a recording medium readable by the second control device 44. The second storage device 42 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM, an EPROM, or an EEPROM. The volatile memory is, for example, a RAM.

[0035] The second control device 44 includes one or more processors such as a CPU. Some of the functions of the second control device 44 may be performed by a circuit such as a DSP, an ASIC, a PLD, or an FPGA, instead of or in combination with the CPU.

[0036] In this embodiment, the second storage device 42 stores a second program PR2 and user information D4.

[0037] User information D4 is information about user U, and includes attribute information and information that can be used to identify lifestyle habits. Attribute information includes, for example, information such as age, gender, address, and family composition. Information that can be used to identify lifestyle habits includes, for example, location information of home and other arbitrary locations. Home location information is an example of information used to identify outings. Location information of arbitrary locations is an example of information used to identify movement to arbitrary locations and the length of stay at arbitrary locations.

[0038] The second program PR2 is a program for controlling the immunity trend information providing device 4. By executing this second program PR2, the second control device 44 functions as a data acquisition control unit 440, an estimation unit 442, and a providing unit 444. These functions will be described in detail below.

[0039] The data acquisition control unit 440 is an example of an “acquisition unit” in the present disclosure. The data acquisition control unit 440 controls the second communication device 40 to acquire the life log D1 and the weather log D3 from the user device 2 via the network A.

[0040] The estimation unit 442 estimates the immunity trend D2A based on the life log D1. In this embodiment, the estimation unit 442 estimates the immunity trend D2A based on the life log D1, the weather log D3, and the lifestyle type of the user U. Details of the estimation unit 442 will be described later.

[0041] The providing unit 444 controls the second communication device 40 to transmit immunity trend information D2 including the estimation result of the immunity trend D2A to the user device 2 via the network A.

[0042] The estimation unit 442 estimates the immunity trend D2A using artificial intelligence. Specifically, the estimation unit 442 includes an estimation model 442A, which is a trained model constructed in advance by machine learning, as one form of means for estimating the immunity trend D2A. An appropriate method is used for the machine learning. For example, a classical linear model, a support vector machine (SVM), an eXtreme Gradient Boosting (XGBoost), a Light Gradient Boosting Machine (LightGBM), or the like may be used for the machine learning. Furthermore, deep learning such as a deep neural network (DNN) may be used for the machine learning.

[0043] The estimation model 442A is a machine learning model that receives as input at least one of the histories of one or more specific behaviors obtained from the user U's life log D1 and the histories of one or more weather elements obtained from the weather log D3, and outputs the immunity trend D2A of the user U. Note that the above-described attribute information included in the user information D4 may also be input to the estimation model 442A. An example of the estimation model 442A is a machine learning model that receives as input the histories of one or more specific behaviors and the histories of one or more weather elements, and outputs the immunity trend D2A of the user U.

[0044] FIG. 5 is a diagram illustrating an example of training data D5 used to train the estimation model 442A. The training data D5 is a data set for learning the relationship between at least one of the explanatory variables, i.e., the history of one or more specific behaviors and the history of one or more weather elements, and the dependent variable, i.e., the immunity trend D2A. The training data D5 may additionally use the above-described attribute information included in the user information D4 as an explanatory variable. The illustrated training data D5 includes, as explanatory variables, training histories of one or more specific behaviors and training histories of one or more weather elements. Specifically, the illustrated training data D5 includes, as information related to the explanatory variables, specific behavior history information D5A for training and weather element history information D5B for training. The illustrated training data D5 also includes, as information related to the dependent variable, an immunity evaluation value D5C for training.

[0045] The specific behavior history information D5A is information related to the history of specific behaviors performed by the user U. The specific behavior history information D5A includes information specifying what type of specific behavior the user U performed, when, and for how long. That is, the specific behavior history information D5A includes information such as the type of specific behavior, the duration of the specific behavior, and the date and time. Note that in the specific behavior history information D5A of this embodiment, the types of specific behavior include sleeping, walking, exercising, going out, and returning home.

[0046] The weather element history information D5B is information relating to the history of weather elements experienced by the user U. The weather element history information D5B includes information specifying what weather element the user U was in, when, and for how long. The weather element history information D5B includes information such as the type of weather element, the state or measurement value of the weather element, the length of stay, and the date and time. In the illustrated example, the weather element history information D5B includes two types of weather elements: humidity and temperature.

[0047] The immunity evaluation value D5C is an evaluation value that enables identification of an immunity index (in this embodiment, immunity trend D2A) that has actually occurred in the user U due to the history of each type of specific behavior identified by the specific behavior history information D5A and the history of each type of weather element identified by the weather element history information D5B. The immunity evaluation value D5C may be, for example, an actual measurement value of each type of index used for quantitatively evaluating immunity, an approximate value obtained by fitting the actual measurement value, or an interpolated value of the actual measurement value. Alternatively, the immunity evaluation value D5C may be the actually occurred immunity trend D2A itself.

[0048] Here, the inventor collected sample data including specific behavior history information D5A, weather element history information D5B, and daily immunity from a large number of subjects, and by analyzing this sample data, obtained the following first and second findings.

[0049] (First Finding) The first manifestation period E1, which is the period from when the subject performs a specific behavior to when a change in the immunity index (in this embodiment, the immunity trend D2A) due to that specific behavior occurs, differs for each type of specific behavior. In other words, the first manifestation period E1 is the period from when the user U performs a certain type of specific behavior to when a change in the immunity index due to that type of specific behavior occurs. Similarly, the second manifestation period E2, which is the period from when the subject is in an environment with a weather element to when a change in the immunity index due to that weather element occurs, differs for each type of weather element. In other words, the second manifestation period E2 is the period from when the user U is in a place with a certain type of weather element to when a change in the immunity index due to that type of weather element occurs. Hereinafter, the first manifestation period E1 and the second manifestation period E2 will sometimes be referred to as the "manifestation period E" without any distinction being made between them.

[0050] (Second finding) A change in the immunity index (in this embodiment, immunity trend D2A) is correlated with a statistical value related to a specific behavior (hereinafter referred to as the "first statistical value"). The degree to which a change in the immunity index is clearly apparent (hereinafter referred to as "conspicuousness") is affected by the length of the period (statistical period) used to calculate the first statistical value. The length of the period during which the conspicuity of a change in the immunity index is highest varies depending on the type of specific behavior. Similarly, a change in the immunity index is correlated with a statistical value related to a meteorological element (hereinafter referred to as the "second statistical value"). The conspicuity of a change in the immunity index is affected by the length of the period (statistical period) used to calculate the second statistical value. The length of the period during which the conspicuity of a change in the immunity index is highest varies depending on the type of meteorological element. Hereinafter, the statistical value refers to, for example, an average value or a standard deviation. Hereinafter, the length of the period used to calculate the first statistical value will be referred to as the first adopted period length F1, and the length of the period used to calculate the second statistical value will be referred to as the second adopted period length F2. In addition, the first employment period length F1 and the second employment period length F2 may be referred to as the employment period length F without distinction.

[0051] In other words, the first adoption period length F1 is a statistical period in which the change in the immunity index is most likely to be detected by the statistical value of one type of specific behavior (first statistical value), and the second adoption period length F2 is a statistical period in which the change in the immunity index is most likely to be detected by the statistical value of one type of weather element (second statistical value).

[0052] 6 is a matrix diagram showing an example of the analysis results of sample data. The sample data to be analyzed is data including specific behavior history information D5A and daily immunity evaluation values ​​D5C. The specific behavior history information D5A includes appropriate information on the specific behaviors described above. The immunity evaluation values ​​D5C include appropriate index values ​​used for quantitatively evaluating immunity. Examples of the immunity evaluation values ​​D5C include IgA concentration, its secretion rate or secretion amount, a quantification index value of immunoglobulins in the blood, and a quantification index value of immune cells.

[0053] The inventor analyzed the sample data by calculating an evaluation value of the correlation between the daily specific behaviors specified by the specific behavior history information D5A, the duration of adoption F used to calculate the statistical values ​​of the specific behaviors, and the immunity evaluation value D5C. Note that a publicly known or well-known appropriate method is used to evaluate the correlation.

[0054] The matrix diagram shown in Figure 6 shows the relevance evaluation value for each combination of the chronological order of the immunity evaluation value D5C and the length of employment period F. The vertical axis corresponds to the chronological order of the immunity evaluation value D5C, and the horizontal axis corresponds to the length of employment period F. The chronological order indicates the order within the chronological order of the immunity evaluation value D5C for each day used to evaluate the relevance. Note that the starting date for the chronological order and the length of employment period F is the oldest day in the history. In the illustrated matrix diagram, "1 day later" on the vertical axis means the day after the oldest day, and "1 day" on the horizontal axis means the oldest day.

[0055] In the illustrated example, it can be seen that the evaluation value of relevance is greatest for the combination X of the immunity evaluation value D5C, whose chronological order is "one day later," and the adoption period F of "six days." Therefore, according to the analysis results of Fig. 6, it can be concluded that the specific behavior recorded in the specific behavior history information D5A has the strongest influence on the formation of the immunity trend D2A of the next day, that is, that the manifestation period E is "one day," and that the adoption period F, which maximizes the prominence of changes in the immunity trend D2A, is "six days."

[0056] The inventors performed the analysis shown in Figure 6 on various specific behaviors such as sleeping, walking, and exercise, as well as various types of weather elements such as humidity and temperature, to determine the occurrence period E and adoption period length F for each type of specific behavior and weather element.

[0057] 7, the specific behavior history information D5A in the learning data D5 uses data for a period length corresponding to the adoption period length F, which is obtained by going back from the measurement date of the data on which the immunity evaluation value D5C is based by the expression period E corresponding to the type of specific behavior. Similarly, the weather element history information D5B in the learning data D5 uses data for a period length corresponding to the adoption period length F, which is obtained by going back from the measurement date of the data on which the immunity evaluation value D5C is based by the expression period E corresponding to the type of weather element. In other words, the specific behavior history information D5A and the weather element history information D5B use data for the adoption period length F preceding the base point, which is obtained by going back from the measurement date of the data on which the immunity evaluation value D5C is based by the expression period E.

[0058] In other words, the learning data D5 includes a learning immunity evaluation value D5C, which is an evaluation value of the immunity index. The learning data D5 also includes at least one of specific behavior history information D5A, which is a learning history of a specific behavior of one type, and weather element history information D5B, which is a learning history of a weather element of one type. The specific behavior history information D5A includes a history of the specific behavior of the one type at a third time point that precedes the actual measurement date of the immunity index by an expression period E (first expression period E1) corresponding to the specific behavior of the one type. The history of the specific behavior of the one type at the third time point includes a history of the specific behavior of the one type during a third adoption period that precedes the third time point. The third adoption period is a statistical period in which the conspicuity of changes in the immunity index to the statistical value of the specific behavior of the one type is maximized. The third adoption period may be the first adoption period F1. Furthermore, the weather element history information D5B includes a history of a type of weather element at a fourth time point that precedes the actual measurement date of the immunity index by an expression period E (second expression period) corresponding to the type of weather element. The history of a type of specific behavior at the fourth time point includes a history of a type of weather element for a fourth adoption period that precedes the fourth time point. The fourth adoption period is a statistical period in which the prominence of changes in the immunity index relative to the statistical value of a type of weather element is maximized. The fourth adoption period may be the second adoption period F2.

[0059] Therefore, by constructing an estimation model 442A through machine learning using this learning data D5, a trained model is obtained that estimates with high accuracy the relationship between the history of specific behaviors and the history of meteorological elements and the immunity trend D2A.

[0060] FIG. 8 is a conceptual diagram of group-based machine learning of training data D5, and FIG. 9 is an explanatory diagram of clustering of training data D5. In this embodiment, the training data D5 is divided into one or more groups G based on the similarity of the lifestyle habits of the subjects from which the training data D5 is derived. The training data D5 is machine-learned for each group G. The grouping is performed, for example, by the following steps. First, at least three or more feature quantities representing the subjects' lifestyle habits are compressed to two dimensions using an appropriate dimensionality reduction algorithm, thereby converting the distribution of each subject's lifestyle habits into a two-dimensional distribution, as shown in FIG. 9 . Then, using an appropriate clustering method, the subjects are divided into groups with similar lifestyle habits, and the training data D5 is classified into one or more groups G based on the grouping results. Note that, for example, t-SNE (Stochastic Neighbor Embedding) or the like is used as the dimensionality reduction algorithm. For example, K-means or the like is used as the clustering method.

[0061] In the illustrated example, a large number of pieces of training data D5 are classified into two groups, group G1 and group G2, by the above-mentioned grouping. Group G1 is a group of training data D5 obtained from relatively active subjects. Group G2 is a group of training data D5 obtained from subjects who do not belong to group G1. In this case, features indicative of the subjects' lifestyle habits include, for example, length of sleep, number of steps, walking speed, walking time, exercise time, time at home, time outside, number of places visited while outside, and time of return home.

[0062] In this case, the learning data D5 of group G1 contains a relatively large amount of data obtained from subjects who exercise regularly, while the learning data D5 of group G2 contains a relatively large amount of data obtained from subjects who exercise less regularly. Generally, for people who exercise regularly, exercising is thought to lead to an increase in IgA concentration. Conversely, for people who exercise less regularly, exercising is thought to lead to fatigue and a decrease in IgA concentration.

[0063] More specifically, for example, specific exercise-related behaviors such as long exercise duration, walking a lot, or traveling to many places lead to an increase in IgA concentration in a person who exercises regularly, and therefore are factors that form an "upward trend" in the immunity trend D2A. Conversely, for a person who does not exercise regularly, the specific exercise-related behaviors lead to a decrease in IgA concentration, and therefore are factors that form a "downward trend" in the immunity trend D2A.

[0064] The estimation model 442A is constructed by machine learning of the learning data D5 for each of the groups G1 and G2. Therefore, for example, in response to input of a specific exercise behavior of a certain user U, an immunity trend D2A is accurately output depending on whether the user U is a relatively active person.

[0065] 4, the estimation unit 442 includes an estimation model 442A for each of one or more groups G, and estimates an immunity trend D2A using the estimation model 442A corresponding to the lifestyle type of the user U. The lifestyle type indicates a group G with similar lifestyle habits of the user U, i.e., indicates a classification based on the similarity of the lifestyle habits of the user U, and the estimation unit 442 identifies the lifestyle type based on the user information D4. Note that the estimation unit 442 may use the life log D1 instead of the user information D4 to identify the lifestyle type.

[0066] 10 is a diagram showing an example of the operation of the information providing system 1. Note that the following describes the operation when the immunity trend information providing device 4 estimates an immunity trend D2A based on the life log D1, the weather log D3, and the lifestyle habit type of the user U.

[0067] First, the user device 2 sequentially records the life log D1 and the weather log D3 and stores them in the first storage device 22 (step Sa1). Next, when the user U wants to know the immunity trend D2A, he or she performs a predetermined operation on the user device 2. When the predetermined operation is performed, the user device 2 transmits an estimation request for requesting estimation of the immunity trend D2A to the immunity trend information providing device 4 (step Sa2).

[0068] When the immunity trend information providing device 4 receives an estimation request from the user device 2 (step Sb1), the data acquisition control unit 440 acquires the user U's life log D1 and weather log D3 (step Sb2), and the estimation unit 442 acquires the user U's user information D4 from the second storage device 42 (step Sb3). The estimation unit 442 identifies the user U's lifestyle type by determining which of the groups G1 and G2 the user U belongs to based on the user U's lifestyle habits indicated by the user information D4 (step Sb4). As described above, the estimation unit 442 may use the life log D1 instead of the user information D4 to identify the lifestyle type.

[0069] The estimation unit 442 also extracts a history of one type of specific behavior from the life log D1 and a history of one type of weather element from the weather log D3 (step Sb5). In step Sb5, the estimation unit 442 extracts a history of the one type of specific behavior at a first time point that precedes the estimation target time point B, "today," by an occurrence period E (first occurrence period E1) corresponding to the type of specific behavior. From the history of the one type of specific behavior at the first time point, the estimation unit 442 extracts a history of the one type of specific behavior during an employment period length F (first employment period length F1) that precedes the first time point. In step Sb5, the estimation unit 442 also extracts a history of the one type of weather element at a second time point that precedes the estimation target time point B, "today," by an occurrence period E (second occurrence period E2) corresponding to the type of weather element. The estimation unit 442 extracts a history of one type of specific behavior during the adoption period F (second adoption period F2) preceding the second time point from the history of one type of weather element at the second time point.

[0070] Then, the estimation unit 442 inputs the history of each type of specific behavior and the history of each type of weather element into an estimation model 442A corresponding to the type of lifestyle habit, and obtains an estimation result of the immunity trend D2A from the estimation model 442A (step Sb6).

[0071] Next, the providing unit 444 transmits immunity trend information D2 including the estimation result of the immunity trend D2A to the user device 2 (step Sb7). The estimating unit 442 may identify lifestyle habits that are the basis for estimating the immunity trend D2A. For example, if a "downward trend" is estimated as the immunity trend D2A, the estimating unit 442 identifies lifestyle habits that contributed to the "downward trend." To identify the lifestyle habits, for example, interpretation tool methods such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (Shapley Additive Explanations) may be used.

[0072] Upon receiving the immunity trend information D2 (step Sb8), the user device 2 displays the immunity trend D2A to present it to the user U (step Sb9). This display allows the user U to know the immunity trend D2A.

[0073] As described above, the immunity trend information providing device 4 of this embodiment includes a data acquisition control unit 440 that acquires a life log D1 in which the history of one or more types of specific behavior that affect changes in immunity of a user U is recorded, and an estimation unit 442 that estimates an immunity trend D2A, which is a trend of changes in immunity over a predetermined period T from an estimation target time point B, based on the history of one type of specific behavior. The estimation unit 442 estimates the immunity trend D2A based on the history of one type of specific behavior at a first time point that precedes the estimation target time point B by a first manifestation period E1. The manifestation period E differs depending on the type of specific behavior.

[0074] According to this configuration, the estimation of the immunity trend D2A reflects the occurrence period E during which a specific type of behavior contributes to the formation of the immunity trend D2A, so that the immunity trend D2A can be accurately estimated based on the history of the specific type of behavior.

[0075] In the immunity trend information providing device 4 of this embodiment, the estimation unit 442 estimates the immunity trend D2A based on the history of one type of specific behavior for an adoption period F (first adoption period F1) preceding the first time point. The first adoption period F1 is a statistical period in which the prominence of changes in the immunity trend D2A with respect to the statistical value of the one type of specific behavior is maximized.

[0076] According to this configuration, the immunity trend D2A is estimated using history for a period during which the likelihood of changes in the immunity trend D2A becoming more apparent, thereby enabling the immunity trend D2A to be estimated more accurately.

[0077] In the immunity trend information providing device 4 of this embodiment, the data acquisition control unit 440 acquires a weather log D3, which is a history of weather elements at the location of the user U and records one or more weather elements that affect changes in the user U's immunity. The estimation unit 442 estimates an immunity trend D2A based on the history of one type of specific behavior recorded in the life log D1 and the history of one type of weather element recorded in the weather log D3. The estimation unit 442 further estimates the immunity trend D2A based on the history of the one type of specific behavior at a first time point that precedes the estimation target time point B by an expression period E (first expression period E1) corresponding to the one type of specific behavior, and the history of the one type of weather element at a second time point that precedes the estimation target time point B by an expression period E (second expression period E2) corresponding to the one type of weather element.

[0078] According to this configuration, the immunity trend D2A is estimated using the history of one type of weather element in addition to one type of specific behavior, and also reflects the occurrence period E of the one type of weather element. Therefore, the immunity trend D2A can be estimated more accurately.

[0079] Furthermore, the estimation unit 442 estimates the immunity trend D2A based on the history of one type of specific behavior for an adoption period F (first adoption period F1) preceding the first time point and the history of one type of weather element for an adoption period F (second adoption period F2) preceding the second time point. The second adoption period F2 is a statistical period in which the prominence of changes in the immunity trend D2A relative to the statistical values ​​of one type of weather element is maximized.

[0080] According to this configuration, the immunity trend D2A is estimated using the history of meteorological elements in addition to the specific behavior, and also reflects the weather element manifestation period E. In addition, for each type of specific behavior and each type of weather element, the immunity trend D2A is estimated using the history for the period during which the manifestation is highest, thereby making it possible to estimate the immunity trend D2A more accurately.

[0081] In the immunity trend information providing device 4 of this embodiment, the estimation unit 442 may use attribute information of the user U in addition to either the history of a specific behavior or the history of weather elements to estimate the immunity trend D2A.

[0082] According to this configuration, the immunity trend D2A is estimated based on the attributes of the user U.

[0083] In the immunity trend information providing device 4 of this embodiment, the estimation unit 442 estimates the immunity trend D2A based on the history of a specific behavior, the history of meteorological elements, and the type of lifestyle habit of the user.

[0084] According to this configuration, the immunity trend D2A can be accurately estimated according to the type of lifestyle habits of the user.

[0085] In the immunity trend information providing device 4 of this embodiment, the estimation unit 442 includes an estimation model 442A that learns the relationship between the histories of one or more types of specific behaviors and one or more types of weather elements and the immunity trend through machine learning of learning data D5. The learning data D5 also includes an immunity evaluation value D5C, specific behavior history information D5A, which is a learning history of a specific behavior of one type, and weather element history information D5B, which is a learning history of a weather element of one type. The specific behavior history information D5A includes a history of the specific behavior of the one type at a third time point that precedes the actual measurement date of the immunity index by an expression period E (first expression period) corresponding to the specific behavior of the one type. The history of the specific behavior of the one type at the third time point includes a history of the specific behavior of the one type during a third adoption period preceding the third time point. The third adoption period is a statistical period in which the prominence of changes in the immunity index relative to the statistical value of the specific behavior of the one type is maximized. Furthermore, the weather element history information D5B includes a history of a type of weather element at a fourth time point that precedes the actual measurement date of the immunity index by an expression period E (second expression period) corresponding to the type of weather element. The history of a type of specific behavior at the fourth time point includes a history of a type of weather element for a fourth employment period that precedes the fourth time point. The fourth employment period is a statistical period in which the prominence of changes in the immunity index relative to the statistical value of a type of weather element is maximized.

[0086] According to this configuration, machine learning is performed using the histories of specific behaviors and weather elements that correspond to the manifestation periods E for each type of specific behavior and weather element and that correspond to the periods when the specific behaviors and weather elements are most likely to manifest. Therefore, an estimation model 442A that accurately estimates the immunity trend D2A is obtained.

[0087] Note that the learning data D5 may additionally use attribute information included in the user information D4.

[0088] In the immunity trend information providing device 4 of this embodiment, the estimation model 442A is a model that is machine-learned to determine the relationship between the history of one or more specific behaviors and the history of one or more weather elements and the immunity trend D2A for each group of learning data D5 obtained from subjects with similar lifestyle habits.

[0089] This configuration provides an estimation model 442A that can accurately estimate the immunity trend D2A in accordance with the type of lifestyle habits of the user.

[0090] 2. Modifications Examples of modifications that can be added to the above-described embodiments are given below. Two or more of the following examples may be arbitrarily selected and combined as long as they are not mutually contradictory.

[0091] (1) In the above-described embodiment, the immunity trend D2A, which is a trend of changes in immunity, has been described as an example of an "immunity index" of the present disclosure. However, the immunity index may be any suitable index, such as the steepness of the rise and fall of immunity, the level of the user U's immunity relative to the average immunity, or the absolute value of immunity. In this case, the "steepness of the rise and fall of immunity" is evaluated based on, for example, the magnitude of the slope of the arrow illustrated in FIG. 2. Furthermore, the "level of the user U's immunity relative to the average immunity" is evaluated based on, for example, a comparison of the level of immunity shown in the bar graph illustrated in FIG. 2 with the average value of the bar graph for an arbitrary period in the past, or the difference between the two. The "absolute value of immunity" is evaluated based on, for example, the height of the bar graph illustrated in FIG. 2 itself.

[0092] (2) In the above-described embodiment, the estimation unit 442 of the immunity trend information providing device 4 estimates the immunity trend D2A, which is an example of an immunity index, based on both the life log D1, in which the history of one or more specific behaviors is recorded, and the weather log D3, in which the history of one or more weather elements is recorded. However, the estimation unit 442 may estimate the immunity index based on at least one of the life log D1, in which the history of one or more specific behaviors is recorded, and the weather log D3, in which the history of one or more weather elements is recorded.

[0093] (3) In the above-described embodiment, the estimation model 442A is a machine learning model that has been machine-learned to determine the relationship between the immunity index and both the histories of one or more specific behaviors and the histories of one or more weather elements. However, the estimation model 442A may be a machine learning model that has been machine-learned to determine the relationship between the immunity index and at least one of the histories of one or more specific behaviors and the histories of one or more weather elements.

[0094] (4) In the above-described embodiment, the learning data D5 is classified into two groups G1 and G2 by clustering based on lifestyle habits, and machine learning of the estimation model 442A is performed for each of the groups G1 and G2. However, it is sufficient that the learning data D5 is classified into at least one group G.

[0095] That is, the learning data D5 may not be clustered, and the number of groups G in the learning data D5 may be one. Even if the number of groups G is one, an estimation model 442A corresponding to various lifestyle habits indicated in at least one of the history of specific behaviors and the history of weather elements can be obtained, and therefore the immunity index of the user U can be estimated regardless of the lifestyle habits of the user U. In this case, since the type of lifestyle habits of the user U does not need to be identified, the estimation unit 442 does not need to execute step Sb4 in FIG. 10.

[0096] Furthermore, by classifying the learning data D5 into two or more groups G based on clustering of lifestyle habit similarities, it is possible to accurately estimate the immunity index for each classification. In this case, instead of a configuration in which the estimation unit 442 is provided with an estimation model 442A for each of the two or more groups G, the estimation unit 442 may be provided with one estimation model 442A that has learned the relationship between at least one of the histories of one or more specific behaviors and the histories of one or more weather elements and the immunity trend D2A for each group G.

[0097] (5) In the above-described embodiment, the user device 2 may include the estimation unit 442 of the immunity trend information providing device 4, and the user device 2 may estimate the immunity index using the estimation unit 442.

[0098] 3. Others (1) In the above-described embodiment, ROM and RAM are exemplified as the first storage device 22 and the second storage device 42, but the first storage device 22 and the second storage device 42 may be a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory device (e.g., a card, a stick, a key drive), a CD-ROM (Compact Disc-ROM), a register, a removable disk, a hard disk, a floppy (registered trademark) disk, a magnetic strip, a database, a server, or other suitable storage medium.

[0099] (2) In the above-described embodiments, the described information, signals, etc. may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0100] (3) In the above-described embodiment, input and output information may be stored in a specific location (for example, a memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0101] (4) In the above-described embodiment, the determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a comparison of numerical values ​​(e.g., a comparison with a predetermined value).

[0102] (5) The order of the process procedures, sequences, flowcharts, etc. illustrated in the above-described embodiments may be rearranged unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0103] (6) Each function illustrated in one or more figures referenced in the embodiments is realized by any combination of hardware and / or software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. A functional block may also be realized by combining software with the single device or multiple devices.

[0104] (7) The programs exemplified in the above-described embodiments should be broadly construed to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., regardless of whether they are called software, firmware, middleware, microcode, hardware description language, or by other names.

[0105] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0106] (8) In each of the foregoing embodiments, the terms "system" and "network" are used interchangeably.

[0107] (9) The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0108] (10) In the above-described embodiments, the terms "connected" and "coupled," or any variations thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0109] (11) In the above embodiments, unless otherwise specified, the phrase "based on" does not mean "based only on." In other words, the phrase "based on" means both "based only on" and "based at least on."

[0110] (12) As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining something as "determining" or "determining," and the like. Furthermore, "judgment" and "decision" may include regarding receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and accessing (e.g., accessing data in memory) as having been "judgment" or "decision." Furthermore, "judgment" and "decision" may include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judgment" or "decision." In other words, "judgment" and "decision" may include regarding some action as having been "judgment" or "decision." Furthermore, "judgment" may be interpreted as "assuming," "expecting," "considering," etc.

[0111] (13) In the above embodiments, when "include," "including," and variations thereof are used, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used in this disclosure, is not intended to be an exclusive or.

[0112] (14) In this disclosure, when articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are plural.

[0113] (15) In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

[0114] (16) The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to being explicit, but may be implicit (e.g., not notifying the predetermined information).

[0115] 1...information providing system, 2...user device, 4...immunity trend information providing device, 440...data acquisition control unit, 442...estimation unit, 442A...estimation model, 444...providing unit, A...network, B...estimation target time point, D1...life log, D2...immunity trend information, D2A...immunity trend, D3...weather log, D3A...weather information, D4...user information, D5...learning data, D5A...specific behavior history information, D5B...weather element history information, D5C...immunity evaluation value, E...manifestation period, F...adoption period length, T...specified period, U...user.

Claims

1. an acquisition unit that acquires at least one of a life log in which a history of one or more specific actions that affect changes in the user's immunity is recorded, and a weather log in which a history of one or more weather elements that affect changes in the user's immunity, which are weather elements of a location where the user was, is recorded; an estimation unit that estimates an immunity index, which is an index of immunity over a predetermined period from a time point to be estimated, based on at least one of the history of the one or more types of specific behaviors recorded in the life log and the history of the one or more types of weather elements recorded in the weather log; and Equipped with The estimation unit estimating the immunity index based on at least one of a history of a specific behavior of one type among the one or more types of specific behaviors at a first time point that precedes the estimation target time point by a first onset period corresponding to the specific behavior, and a history of a weather element of one type among the one or more types of weather elements at a second time point that precedes the estimation target time point by a second onset period corresponding to the weather element, the first onset period is a period from when the user performs the one type of specific behavior to when a change in the immunity index caused by the one type of specific behavior is manifested; The second manifestation period is a period from when the user is in a place having the one type of weather element to when a change in the immunity index caused by the one type of weather element appears. Estimation device.

2. the history of the one type of specific behavior includes a history of the one type of specific behavior during a first employment period preceding the first time point; the first adoption period length is a statistical period in which the prominence of a change in the immunity index with respect to the statistical value of the one type of specific behavior is maximized; The history of the one type of weather element includes a history of the one type of weather element in a second adopted period preceding the second time point, The second adoption period length is a statistical period in which the prominence of changes in the immunity index with respect to the statistical value of the one type of meteorological element is maximized; The estimation device according to claim 1 .

3. The estimation unit The immune strength index is estimated by further using attribute information of the user. The estimation device according to claim 2 .

4. The estimation unit The immunity index is estimated according to the type of lifestyle habits of the user. The estimation device according to claim 1 .

5. The estimation unit an estimation model that learns a relationship between at least one of a history of one or more types of specific behaviors and a history of one or more types of weather elements and an immunity index through machine learning of learning data; The learning data is a learning immunity evaluation value, which is an evaluation value of the immunity index; and at least one of a learning history of the one type of specific behavior and a learning history of the one type of weather element, the learning history of the one type of specific behavior includes a history of the one type of specific behavior at a third time point that precedes the actual measurement date of the immunity index by the first onset period, the history of the one type of specific behavior includes a history of the one type of specific behavior during a third employment period preceding the third time point; the third adoption period length is a statistical period in which the prominence of a change in the immunity index with respect to the statistical value of the one type of specific behavior is maximized; the learning history of the one type of meteorological element includes a history of the one type of meteorological element at a fourth time point that precedes the actual measurement date of the immunity index by the second expression period, The history of the one type of weather element includes a history of the one type of weather element in a fourth employment period preceding the fourth time point, The fourth adoption period length is a statistical period in which the prominence of changes in the immunity index with respect to the statistical value of the one type of meteorological element is maximized; The estimation device according to claim 1 .

6. The estimation model is a model obtained by machine learning of a relationship between at least one of the one or more types of specific behavior history and the one or more types of weather element history and the immune strength index according to the subject's lifestyle; The estimation device according to claim 5 .