Information provision method, information provision device, information provision system, and information provision program

Abstract

To provide an information provision method that recommends appropriate activity on the basis of a daily activity trend.SOLUTION: An information provision method comprises steps of: acquiring daily action information indicating a result of daily activity; carrying out clustering on the basis of the daily action information; classifying a plurality of users into a plurality of daily action characteristic sets; acquiring usage record information indicating a usage record of a sport facility; carrying out clustering on the basis of the usage record information; classifying the plurality of users into a plurality of facility usage characteristic sets; determining a correlation between a plurality of daily action characteristic sets and a plurality of usage characteristic sets; identifying, of the facility usage characteristic sets, a first facility usage characteristic set, whose correlation with the first action characteristic set satisfies a predetermined criterion; extracting a specific user who belongs to the first daily action characteristic set and also belongs to a second facility usage characteristic set different from the first facility usage characteristic set; and providing recommendation information that recommends usage of the sport facility corresponding to the first facility use characteristic set to the specific user.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information providing method, an information providing apparatus, an information providing system, and an information providing program.

Background Art

[0002] In recent years, it has been considered to manage by linking the trends of people's daily activities and the trends of people's hobbies. For example, with the increasing awareness of people's health, it is desired to manage daily activities in conjunction with activities (for example, training) at sports facilities such as gyms and fitness clubs.

[0003] For example, in Patent Document 1, a data management server is described that allows a user to set a target value for the amount of exercise, obtains data from a data input device capable of measuring the amount of exercise in daily activities and fitness activities, and extracts recommended activities and their recommended timing from a recommended activity DB according to the fulfillment rate with respect to the target value, the user's physical data, profile data, and external environment information, and presents them to the user.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in Patent Document 1, since a user is made to set a target value for the amount of exercise, there is a possibility that appropriate activities (for example, training) cannot be recommended when the amount of exercise with respect to the target value is sufficient.

[0006] Non-limiting embodiments of the present disclosure contribute to providing an information providing method, an information providing apparatus, an information providing system, and an information providing program that can recommend appropriate activities based on the trends of daily activities. [Means for solving the problem]

[0007] An information provision method according to one embodiment of the present disclosure includes the steps of: acquiring daily behavior information showing the daily behavior records of multiple users; performing clustering based on the daily behavior information to classify the multiple users into multiple daily behavior characteristic sets; acquiring usage record information showing the usage record of the multiple users to use facilities; performing clustering based on the usage record information to classify the multiple users into multiple facility usage characteristic sets; determining the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets; identifying a first facility usage characteristic set among the facility usage characteristic sets whose correlation with a first daily behavior characteristic set satisfies a predetermined criterion; extracting a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and providing the specific user with recommendation information that recommends the use of facilities corresponding to the first facility usage characteristic set.

[0008] An information providing device according to one embodiment of the present disclosure includes: a first acquisition unit that acquires daily behavior information showing the daily behavior records of multiple users; a first classification unit that performs clustering based on the daily behavior information and classifies the multiple users into multiple daily behavior characteristic sets; a second acquisition unit that acquires usage record information showing the usage record of the multiple users into multiple facility usage characteristic sets; a second classification unit that performs clustering based on the usage record information and classifies the multiple users into multiple facility usage characteristic sets; a correlation determination unit that determines the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets, identifies a first facility usage characteristic set among the facility usage characteristic sets whose correlation with the first daily behavior characteristic set satisfies a predetermined criterion, and extracts a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and an information providing unit that provides the specific user with recommendation information recommending the use of facilities corresponding to the first facility usage characteristic set.

[0009] An information provision system according to one embodiment of the present disclosure includes: a first acquisition unit that acquires daily behavior information showing the daily behavior records of multiple users; a first classification unit that performs clustering based on the daily behavior information and classifies the multiple users into multiple daily behavior characteristic sets; a second acquisition unit that acquires usage record information showing the usage record of the multiple users into multiple facility usage characteristic sets; a second classification unit that performs clustering based on the usage record information and classifies the multiple users into multiple facility usage characteristic sets; a correlation determination unit that determines the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets, identifies a first facility usage characteristic set among the facility usage characteristic sets whose correlation with the first daily behavior characteristic set satisfies a predetermined criterion, and extracts a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and an information provision unit that provides the specific user with recommendation information recommending the use of facilities corresponding to the first facility usage characteristic set.

[0010] An information provision program according to one embodiment of the present disclosure includes, on at least one processor, a process for acquiring daily behavior information showing the daily behavior records of multiple users, a process for performing clustering based on the daily behavior information and classifying the multiple users into multiple sets of daily behavior characteristics, and a process for acquiring usage record information showing the usage records of the multiple users. The system is configured to perform the following steps: clustering based on the usage history information and classifying the multiple users into multiple sets of facility usage characteristics; determining the correlation between each of the multiple sets of daily behavior characteristics and each of the multiple sets of facility usage characteristics; identifying a first set of facility usage characteristics from among the set of facility usage characteristics whose correlation with a first set of daily behavior characteristics satisfies a predetermined criterion; extracting a specific user who belongs to the first set of daily behavior characteristics and to a second set of facility usage characteristics that is different from the first set of facility usage characteristics; and providing the specific user with recommendation information that recommends the use of facilities corresponding to the first set of facility usage characteristics.

[0011] These comprehensive or specific embodiments may be implemented as systems, devices, methods, integrated circuits, computer programs, or recording media, or as any combination of systems, devices, methods, integrated circuits, computer programs, and recording media. [Effects of the Invention]

[0012] According to one embodiment of this disclosure, appropriate activities can be recommended based on trends in daily activities.

[0013] Further advantages and effects of one embodiment of this disclosure will be made apparent from the specification and drawings. Such advantages and / or effects are provided by several embodiments and features described in the specification and drawings, but not all of them are necessarily provided in order to obtain one or more identical features. [Brief explanation of the drawing]

[0014] [Figure 1] Block diagram showing an example of an information provision system according to one embodiment. [Figure 2] A diagram showing an example of how to represent information about daily activities. [Figure 3] A diagram showing the results of clustering based on daily behavioral information and an example of the characteristics of each class. [Figure 4] A diagram showing an example of how usage history information can be represented. [Figure 5] A diagram showing clustering results based on usage data and an example of the characteristics of each class. [Figure 6] A diagram showing an example of the correspondence between clustering results. [Figure 7] A flowchart illustrating the first example of the processing flow in an information provision device. [Figure 8] A flowchart illustrating a second example of the processing flow in an information provision device. [Modes for carrying out the invention]

[0015] Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present disclosure will be described in detail. In the present specification and drawings, components having substantially the same functions are denoted by the same reference numerals, and redundant descriptions are omitted.

[0016] (One embodiment) In the present embodiment, an information providing system that provides information regarding recommended exercises to a user will be described. Note that the user described below is a user who requests the provision of information from the information providing system according to the present embodiment. For example, the user installs an application for receiving the provision of information from the information providing system according to the present embodiment on a terminal, and receives the provision of information via the application. The terminal may be a mobile terminal, a tablet terminal, a wearable device worn by the user, or the like.

[0017] As an example, the information providing system according to the present embodiment acquires information regarding the daily activity records of each of a plurality of users and information regarding the utilization records of each of a plurality of users' exercise facilities, and based on the acquired information, provides information regarding the utilization of an exercise facility recommended to the user to the user.

[0018] Hereinafter, the information regarding the daily activity records is exemplified as "daily activity information", and the information regarding the utilization records of the exercise facilities is exemplified as "utilization record information".

[0019] <An example of the system configuration> FIG. 1 is a block diagram showing an example of the information providing system according to the present embodiment. The information providing system 1 shown in FIG. 1 includes an information providing device 10, a camera 20, a sensor 30, and a terminal 40.

[0020] Camera 20 is installed in sports facilities, shops, schools, workplaces, public facilities, or on the street, etc., and captures the user's daily activities and / or the user's use of sports facilities. Camera 20 may be installed for the information provision system 1, or it may be a camera installed for surveillance purposes. It may also be an imaging camera for biometric authentication such as facial recognition or an AI (Artificial Intelligence) camera.

[0021] Sensor 30 is installed in sports facilities, stores, schools, workplaces, public facilities, or on the street, and performs sensing related to the user's daily activities and / or the user's use of sports facilities. For example, sensor 30 may include a sensor that detects the user's location (GPS (Global Positioning System) or GNSS (Global Navigation Satellite System) sensor), a sensor that detects the user's movement speed, etc.

[0022] Terminal 40 may be a smartphone or other device owned by the user. Terminal 40 acquires daily activity information and / or usage history information entered by the user. Alternatively, terminal 40 acquires information from the information provision device 10 to the user regarding the use of exercise facilities recommended by the user, and displays the acquired information on the display unit of terminal 40.

[0023] The information providing device 10 may take the form of a server having, for example, a CPU (Central Processing Unit), memory, storage medium, communication interface, etc. Alternatively, the information providing device 10 may take the form of a cloud server. The information providing device 10 comprises a daily activity information acquisition unit 101, a daily activity characteristics classification unit 102, a usage record information acquisition unit 103, a facility usage characteristics classification unit 104, a correlation determination unit 105, and an information providing unit 106.

[0024] The daily activity information acquisition unit 101 is a communication interface that communicates with a device that provides daily activity information (for example, at least one of a camera 20, a sensor 30, and a terminal 40). The daily activity information acquisition unit 101 acquires the user's daily activity information and outputs the acquired daily activity information to the daily activity characteristic classification unit 102.

[0025] Daily behavior information shows the user's daily activity history. This history may consist of past activity records. Furthermore, daily behavior information may include information about the user's attributes. These attributes may include, for example, the user's gender, place of residence, occupation, age, and place of work.

[0026] For example, daily activity information includes attendance information, route information from origin to destination, entry and exit information for commercial facilities, activity information for commercial facilities, purchase information for commercial facilities, entry and exit information for restaurants, restaurant usage information, restaurant payment information, entry and exit information for retail stores, payment information for retail stores, entry and exit information for train station ticket gates, exercise information, online purchase information, and IoT home appliance usage information.

[0027] Attendance information includes the user's attendance record. For example, attendance information includes the user's number of working days per week, average working hours per day, whether or not overtime was worked, and the duration of any overtime work.

[0028] Route information from the origin to the destination may include, for example, route information from the user's place of residence to the user's workplace, and route information from the user's place of residence to the user's destination while out and about.

[0029] Commercial facility entry and exit information may include the name of the commercial facility used by the user (e.g., retail stores and clothing stores), the date of use, and the time of use (entry time and exit time). Commercial facility entry and exit information may also include information related to the user's hobbies and / or preferences.

[0030] Commercial facility behavior information may include information about activities within commercial facilities. Commercial facility behavior information may also include information indicating that a specific sport was played at a facility that offers that sport.

[0031] Commercial facility purchase information may include information about a user's purchasing activities at a commercial facility. For example, commercial facility purchase information may include the products purchased by the user at the commercial facility, the prices of those products, and the amounts paid by the user for activities performed at the commercial facility (such as facility usage fees or equipment rental fees).

[0032] Restaurant entry and exit information may include the name of the restaurant used by the user, the date of use, and the time of use (entry time and exit time). Restaurant entry and exit information may also include information related to the user's hobbies and / or preferences.

[0033] Restaurant usage information may include information about the user's use of restaurants. This information may include the type of food and drink consumed at the restaurant, the quantity of food and drink, the calories of the food and drink, and the time of consumption.

[0034] Restaurant payment information may include information about the user's payments at restaurants. Restaurant payment information may include the food and beverages the user consumed at restaurants and the amount paid for them.

[0035] Retail store entry and exit information may include the name of the retail store used by the user, the date of use, and the time of use (entry time and exit time). Retail store entry and exit information may also include information related to the user's hobbies and / or preferences.

[0036] Retail store payment information may include information about a user's payments at a retail store. For example, retail store payment information may include the items the user purchased at the retail store and the amount paid for those items.

[0037] Station ticket gate entry and exit information may include the station the user entered, the time of entry, the station the user exited, and the time of exit.

[0038] Exercise information may include information about the user's daily exercise. For example, exercise information may include the distance the user walks, the time spent walking, the distance traveled by bicycle, the time spent cycling, the distance climbed using stairs, and calories burned.

[0039] Online purchase information may include information about a user's online purchasing activities. For example, online purchase information may include the products a user has purchased online and their prices.

[0040] IoT (Internet of Things) appliance usage information may include information about the user's use of IoT appliances. For example, IoT appliance usage information may include the type of IoT appliance used by the user, the location where it was used, the time of use, etc.

[0041] Furthermore, information on daily activities is not limited to the examples described above, and some of the examples described above may be excluded.

[0042] Furthermore, the method for acquiring daily activity information is not particularly limited. The daily activity information acquisition unit 101 may acquire daily activity information reported by the user via the terminal 40. Alternatively, the daily activity information acquisition unit 101 may acquire daily activity information from a camera 20 that photographs the user's daily activities and / or a sensor 30 that acquires sensing information related to the user's daily activities.

[0043] Furthermore, if the management of working hours, entry times, and payment processing is carried out using biometric authentication such as facial recognition, daily activity information such as working hours, entry times, and payment information may be obtained from the server or other device that performs the biometric authentication.

[0044] The daily behavioral characteristics classification unit 102 clusters users based on their daily behavioral information and classifies them into sets of daily behavioral characteristics. Through clustering, each set of daily behavioral characteristics includes users whose daily behaviors, as indicated by their daily behavioral information, are similar to those of others. Daily behaviors that are common to or similar among users included in a set of daily behavioral characteristics may be associated with that set. Daily behaviors associated with a set of daily behavioral characteristics may be described as representative daily behavioral characteristics in that set. An example of clustering based on daily behavioral information will be described later.

[0045] The usage history information acquisition unit 103 is a communication interface that communicates with a device that provides usage history information (for example, at least one of the camera 20, sensor 30, and terminal 40). The daily activity information acquisition unit 103 acquires the user's usage history information and outputs the acquired usage history information to the facility usage characteristics classification unit 104.

[0046] Usage history information shows a user's usage history of sports facilities. This usage history may be a record of past use of sports facilities. Sports facilities include places where people exercise, such as training gyms, swimming pools, gymnasiums, and sports fields. Places where people exercise may also include facilities specializing in specific sports (e.g., bouldering, boxing, kickboxing).

[0047] Furthermore, usage data may include information on exercises performed by users, not limited to specific sports facilities. For example, usage data may include information on exercises such as mountain climbing, cycling, and running.

[0048] Usage data includes information such as the sports facilities used by the user, the duration of use, the type of exercise performed at the facility, and the duration of the exercise.

[0049] Furthermore, usage data is not limited to the examples described above, and some of the examples described above may be excluded.

[0050] Furthermore, the method for acquiring usage history information is not particularly limited. The usage history information acquisition unit 103 may acquire usage history information reported by the user via the terminal 40. Alternatively, the usage history information acquisition unit 103 may acquire usage history information from a camera 20 that photographs the user's use of the sports facility and / or a sensor 30 that acquires sensing information regarding the user's use of the sports facility.

[0051] Furthermore, if the management of the usage time of sports facilities, the management of the usage status of sports facilities, and the management of payments at sports facilities are carried out using biometric authentication such as facial recognition, usage history information such as the usage time of sports facilities, the usage status of sports facilities, and payment information at sports facilities may be obtained from the server or other device that performs the biometric authentication.

[0052] The facility usage characteristics classification unit 104 clusters users based on usage history information and classifies them into facility usage characteristics sets. Through clustering, each facility usage characteristics set includes users whose usage history of sports facilities, as indicated by the usage history information, is similar to that of others. Each facility usage characteristics set is associated with sports facility usage history that is common to or similar among the users included in the set. Sports facility usage history associated with each facility usage characteristics set may be described as a representative facility usage characteristic in that set. An example of clustering based on usage history information will be described later.

[0053] The correlation determination unit 105 determines the information to be provided to the user based on the set of daily behavior characteristics clustered by the daily behavior characteristics classification unit 102 and the set of facility usage characteristics clustered by the facility usage characteristics classification unit 104.

[0054] For example, the correlation determination unit 105 calculates a correlation between a set of daily behavioral characteristics clustered by the daily behavioral characteristics classification unit 102 and a set of facility utilization characteristics clustered by the facility utilization characteristics classification unit 104. Based on the calculated correlation, the correlation determination unit 105 determines whether each set of facility utilization characteristics is highly correlated with a particular set of daily behavioral characteristics, has a low correlation, or is uncorrelated. The correlation determination unit 105 may determine, for each set of daily behavioral characteristics, whether each set of facility utilization characteristics is highly correlated, has a low correlation, or is uncorrelated. The correlation determination unit 105 may set a threshold for comparison with the correlation value and determine whether a set of facility utilization characteristics has a correlation value higher than the threshold, whether a set of facility utilization characteristics has a correlation value below the threshold, or whether a set of facility utilization characteristics has a correlation value of zero. The correlation determination unit 105 may classify the set of facility utilization characteristics according to the presence or absence of correlation and the height of the correlation based on the determination result.

[0055] The correlation determination unit 105 extracts a specific user from a specific set of daily behavioral characteristics. The correlation determination unit 105 determines a specific set of facility usage characteristics for the extracted user based on the correlation with the specific set of daily behavioral characteristics. The correlation determination unit 105 then determines that the information regarding the representative facility usage characteristics associated with the specific set of facility usage characteristics is information regarding the use of exercise facilities recommended for the extracted user. Hereafter, the information provided to the user regarding the use of exercise facilities or the content of exercise recommended for the user may be referred to as recommendation information. Recommendation information may differ for each user, or it may be common to multiple users. An example of correlation determination and recommendation information determination will be described later.

[0056] The information provision unit 106 provides the user with recommendation information determined by the correlation determination unit 105. The method of providing recommendation information to the user is not particularly limited, but for example, it may be by transmitting the recommendation information to the terminal 40 that the user possesses.

[0057] The correlation determination unit 105 may also determine whether or not to provide recommendation information to the user. For example, if a user who is to be provided with recommendation information has already used or performed activities equivalent to those promoted by the recommendation information, the correlation determination unit 105 does not need to provide the recommendation information to that user. The correlation determination unit 105 may, for example, compare the user's usage history information with the recommendation information to determine whether or not the user has already used or performed activities equivalent to those promoted by the recommendation information.

[0058] Furthermore, the correlation determination unit 105 does not need to provide recommendation information to a user if the user is already performing exercises that are more strenuous than the exercises or use of the exercise facilities that the recommendation information encourages. The correlation determination unit 105 may, for example, compare the user's usage history information with the recommendation information to determine whether the user is already performing exercises that are more strenuous than the exercises or use of the exercise facilities that the recommendation information encourages. Note that a high level of strenuousness indicates a high degree of active use of the exercise facilities, and since the user is already actively using the exercise facilities, there is no need to provide recommendation information to the user. Note that the method for determining the degree of active use is not particularly limited. For example, the degree of active use of the exercise facilities may be determined based on at least one of the frequency of use of the exercise facilities (number of uses per unit period), the cost spent at the exercise facilities, the revenue received at the exercise facilities, and the time spent at the exercise facilities. For example, a higher frequency of use of the exercise facility, a higher expense incurred at the facility, a greater return on investment at the facility, or a longer duration of use at the facility may indicate a higher level of activity. Furthermore, the intensity of the exercise may be determined based on at least one of the following factors: calories burned, fat loss, muscle gain, etc.

[0059] Furthermore, the correlation determination unit 105 may determine the timing for providing recommendation information to users who are offered recommendation information, and provide the recommendation information to the user at the determined timing. For example, if the recommendation information provided to the user encourages the use of an exercise facility during a specific time period, the correlation determination unit 105 may provide the recommendation information to the user at a time before (for example, immediately before) that specific time period. For example, if a user works until 6 PM on weekdays as part of their daily routine, and the recommendation information provided to the user encourages the use of an exercise facility from 7 PM on weekdays, the correlation determination unit 105 may provide the recommendation information between the end of work and the start of use of the exercise facility (i.e., between 6 PM and 7 PM).

[0060] The information providing device 10 is not limited to the configuration shown in Figure 1. For example, the configuration included in the information providing device 10 in Figure 1 may be included in any of the multiple devices. For example, it may be divided into a first information processing device (e.g., a server) including a daily activity information acquisition unit 101 and a daily activity characteristic classification unit 102, a second information processing device including a usage history information acquisition unit 103 and a facility usage characteristic classification unit 104, and a third information processing device including a correlation determination unit 105 and an information providing unit 106. In this case, the three information processing devices may be able to communicate with each other directly or via a network. One of the three information processing devices may be a cloud server.

[0061] Note that the information provision system 1 is not limited to the configuration shown in Figure 1. The information provision system 1 may omit some of the configurations shown in Figure 1, or it may include configurations not shown in Figure 1. For example, the information provision system 1 may include a device that transmits daily activity information and / or usage history information to the information provision device 10.

[0062] <An example of clustering based on daily activity information> Next, we will describe an example of clustering based on daily behavior information, which is performed in the daily behavior characteristics classification unit 102 of the information provision device 10.

[0063] Figure 2 shows an example of how daily activity information is represented. Figure 2 shows the daily activity information for Nn users (Nu being an integer greater than or equal to 1), from User A to User Nu. Note that "A" may be referred to as User ID for User A. For each User ID, information on attributes and actions is associated in a tabular format. The attribute information includes information on Na attributes (Na being an integer greater than or equal to 1), from attribute a to attribute Na. The action information includes information on Nb actions (action 1 to action Nb).

[0064] Attributes a through Na and actions 1 through Nb may be quantified according to a predetermined method. The method of quantification may differ for each attribute and for each action.

[0065] In the example in Figure 2, attribute 'a' indicates gender. For example, if a user is male, the value of attribute 'a' for that user is 0, and if a user is female, the value of attribute 'a' for that user is 1. According to the example in Figure 2, user A is male and user B is female.

[0066] In the example in Figure 2, attribute c indicates the place of work. For example, a numerical value may be assigned to each region, and attribute c represents the user's work value, which is the numerical value assigned to the region that includes the user's place of work. For example, the format may be such that nearby regions are represented by closer numerical values. According to the example in Figure 2, user A and user D work in neighboring regions. Also, according to the example in Figure 2, user B and user Nu work in the same region.

[0067] For attributes other than attributes a and c in Figure 2, similar to attributes a and c, the numerical values ​​representing each attribute are associated with each user ID.

[0068] In the example in Figure 2, Action 1 indicates the number of times the user got off at station α. ​​According to the example in Figure 2, User A has gotten off at station α 22 times so far, and User C has gotten off at station α 11 times so far.

[0069] In the example in Figure 2, Action 2 represents the number of times store β has been used. According to the example in Figure 2, User A has used store β once, and User B has used store β 15 times.

[0070] For actions other than Action 1 and Action 2 in Figure 2, similar to Action 1 and Action 2, the numerical values ​​representing each action are associated with each user and shown.

[0071] The set of numerical values ​​for each user's attributes a through Na and actions 1 through Nb, arranged horizontally in the tabular format of Figure 2 (row vectors), can be referred to as the daily behavior vector. In the example in Figure 2, the daily behavior vector is a Na+Nb dimensional vector.

[0072] In clustering based on daily behavior information, the daily behavior vectors shown in Figure 2 are used. For example, by comparing the daily behavior vectors of each user, users are clustered based on their daily behavior information.

[0073] Figure 3 shows an example of clustering results based on daily behavior information and the characteristics of each class. For example, by performing clustering using principal component analysis and K-means on daily behavior vectors, users can be divided into one or more sets of daily behavior characteristics (hereinafter sometimes simply referred to as classes).

[0074] When principal component analysis is performed on multidimensional daily behavior vectors, the principal components of the vectors are extracted, and the dimensionality of the vectors is reduced. Clustering using the K-means method is then performed on the reduced-dimensional vectors to divide them into one or more classes.

[0075] In Figure 3, the two-dimensional plane defined by the vertical and horizontal axes represents a plane showing the daily behavior vectors with reduced dimensionality. The solid circles on the two-dimensional plane in Figure 3 represent each user's daily behavior vector. Users whose points representing daily behavior vectors (solid circles in Figure 3) are close together are classified into the same class. Users whose points representing daily behavior vectors are close correspond to users whose numerical trends in the daily behavior vectors are similar. In other words, users whose points representing daily behavior vectors are close correspond to users whose daily behaviors are similar.

[0076] In the example in Figure 3, users are divided into five sets of daily behavioral characteristics, from Class 1 to Class 5. Class 2 includes users A and Y, as shown in Figure 2. Each of the five classes is associated with a representative daily behavioral characteristic. For example, of the five classes, Class 1 is associated with the representative daily behavioral characteristics of "working half the month, eating out for lunch on days off, liking cafes, and buying coffee beans at specialty shops." Note that the representative daily behavioral characteristics may be determined based on principal components extracted by principal component analysis.

[0077] As shown in Figures 2 and 3, by converting daily behavior information into daily behavior vectors and performing clustering using principal component analysis and K-means on these daily behavior vectors, users are classified into one or more sets of daily behavior characteristics based on their daily behavior information.

[0078] Furthermore, the clustering methods based on daily behavioral information are not limited to those described above. For example, the algorithms used for clustering are not limited to those using principal component analysis and the K-means method.

[0079] Furthermore, each user's daily activity information may be updated whenever new daily activity information is acquired by the daily activity information acquisition unit 101, or it may be updated periodically or irregularly at an independent timing not synchronized with the acquisition timing. When daily activity information is updated, the clustering results based on the daily activity information may be updated in synchronization with that timing, or the clustering results based on the daily activity information may be updated periodically or irregularly at an independent timing not synchronized with the update of the daily activity information.

[0080] <An example of clustering based on usage data> Next, we will explain the clustering based on usage history information performed in the facility usage characteristics classification unit 104 of the information provision device 10.

[0081] Figure 4 shows an example of how usage history information is represented. Figure 4 shows the usage history information for Nn users, from User A to User Nu. In the example in Figure 4, information about the facilities used is associated with each user ID in a tabular format. The information about the facilities used includes information for Nd different facilities (where Nd is an integer greater than or equal to 1), from facility i to facility Nd.

[0082] The facilities used, i through Nd, include, for example, the number of times the gym was used, the sauna was used, the swimming pool was used, the weight training facilities were used, and the bouldering facilities were used. Each of the facilities used, i through Nd, may be quantified based on a predetermined method. Note that the method of quantification may differ for each facility used.

[0083] The set of numerical values ​​(row vectors) representing each user's facilities i through Nd, arranged horizontally in the tabular format of Figure 4, can be referred to as the facility usage vector. In the example in Figure 4, the facility usage vector is an Nd-dimensional vector.

[0084] In clustering based on usage history information, the facility usage vectors shown in Figure 4 are used. For example, by comparing the facility usage vectors of each user, users are clustered based on their usage history information.

[0085] Figure 5 shows an example of clustering results based on usage data and the characteristics of each class. For example, by performing clustering using principal component analysis and the K-means method on the usage facility vector, users can be divided into one or more classes. The clustering using principal component analysis and the K-means method is the same as the clustering based on daily behavior information described above.

[0086] In the example in Figure 5, users are divided into five sets of facility usage characteristics: Class α, β, γ, ω, and Σ. Class β includes users A and V, as shown in Figure 4. Class Σ includes user Y. Each of the five classes is associated with a representative facility usage characteristic. For example, of the five classes, Class α is associated with the representative usage history of "high-intensity training (pushing)." Note that the representative facility usage characteristics may be determined based on principal components extracted by principal component analysis.

[0087] As shown in Figures 4 and 5, usage data is converted into facility usage vectors, and by performing principal component analysis and clustering using the K-means method on these facility usage vectors, users are classified into one or more sets of facility usage characteristics based on their usage data.

[0088] Furthermore, each user's usage history information may be updated whenever new usage history information is acquired by the usage history information acquisition unit 103, or it may be updated periodically or irregularly at an independent timing not synchronized with the acquisition timing. When the usage history information is updated, the clustering results based on the usage history information may be updated in synchronization with that timing, or the clustering results based on the usage history information may be updated periodically or irregularly at an independent timing not synchronized with the update of the usage history information.

[0089] <An example of correlation determination and recommendation information selection> Next, an example of the determination of correlations between sets and the determination of recommendation information performed by the correlation determination unit 105 of the information providing device 10 will be explained.

[0090] Figure 6 shows an example of the correspondence between clustering results. Figure 6 shows the classification results of a set of daily behavioral characteristics similar to the example shown in Figure 3, and the classification results of a set of facility usage characteristics similar to the example shown in Figure 5.

[0091] Here, taking Class 2, which represents the set of daily behavioral characteristics, as an example, the correlation between the set of users included in Class 2 and the set of users included in each class, which represents the set of facility usage characteristics, is calculated. The calculated correlation can numerically represent the similarity between the elements in the two sets (for example, the users belonging to the sets). For example, the larger the correlation value, the higher the similarity between the two sets. In other words, the larger the correlation value, the greater the number of users who belong to both sets. For example, the correlation can be expressed as a percentage.

[0092] In the example in Figure 6, class β has a relatively high correlation with class 2, with a correlation value of 80%. Class Σ has a correlation with class 2, but with a correlation value of 20%, indicating a relatively low correlation. Class α has no correlation with class 2 (0%).

[0093] For example, a threshold may be set for the correlation value. If the threshold is 60%, then in the example in Figure 6, class β may be determined to have a correlation value higher than the threshold, and class Σ may be determined to have a correlation value below the threshold.

[0094] In this case, it is determined that the recommendation information for user Y, who belongs to class Σ (which has a low correlation with class 2) and also belongs to class 2, is information regarding the typical facility usage characteristics of class β (which has a high correlation with class 2). As shown in Figure 5, the typical facility usage characteristic of class β is "high-frequency aerobic training," so the recommendation information indicates that "high-frequency aerobic training" is recommended for user Y. Alternatively, the recommendation information may also present and recommend specific exercises for "high-frequency aerobic training." Specific exercises for "high-frequency aerobic training" include, for example, walking on a treadmill or a step dance program in a studio, but are not limited to these.

[0095] In this case, recommendation information for users belonging to Class 2 and not belonging to Class β, which has a high correlation with Class 2, is determined to be information regarding the representative facility usage characteristics of Class β, which has a high correlation with Class 2. Furthermore, in this case, recommendation information for users belonging to Class 2 that are correlated with a different set of facility usage characteristics than Class β, which has a high correlation with Class 2, and for users belonging to Class 2 that are not correlated with a different set of facility usage characteristics than Class β, which has a high correlation with Class 2, is determined to be information regarding the representative facility usage characteristics of Class β.

[0096] In Figure 6, an example is shown where one of the facility usage characteristics sets in class β has a correlation value higher than a threshold with class 2, which is a set of daily behavioral characteristics. However, this disclosure is not limited to this example. For instance, there may be two or more facility usage characteristic sets that have a relatively high correlation value (e.g., higher than a threshold) with a single set of daily behavioral characteristics, or there may be no facility usage characteristic sets that have a relatively high correlation value with a single set of daily behavioral characteristics. The following are examples of each case.

[0097] <Example of two highly correlated sets of facility usage characteristics> For example, using the classification of classes shown in Figure 6, class β may have a correlation value of 80% with class 2, and class γ may have a correlation value of 70% with class 2. In other words, there may be two sets of facility usage characteristics, class β and class γ, that have a relatively high correlation value with class 2. In this case, it may be determined that the recommendation information for user Y, who belongs to class Σ (which has a low correlation with class 2) and also belongs to class 2, is information about the representative facility usage characteristics of class β and class γ, which have a high correlation with class 2. For example, user Y may select either information about the representative facility usage characteristics of class β or information about the representative facility usage characteristics of class γ, and the selected information may be provided to user Y as recommendation information. Alternatively, content with a high correlation between information about the representative facility usage characteristics of class β and information about the representative facility usage characteristics of class γ may be provided as recommendation information to user Y. Furthermore, information that shows a high correlation between the information on typical facility usage characteristics of class β and the information on typical facility usage characteristics of class γ may, for example, be common or similar content between the two facility usage characteristics.

[0098] <Examples where no highly correlated set of facility usage characteristics exists> For example, using the classification results shown in Figure 6, class β may have a correlation value of 20% with class 2, and the other sets of facility usage characteristics may also have a correlation value of 20% or less with class 2. In other words, there may be no sets of facility usage characteristics with a relatively high correlation value with class 2. In this case, recommendation information may not be provided to any user belonging to class 2. Alternatively, in this case, the information of each user may be updated, the clustering results may be updated, and then recommendation information may be determined again.

[0099] Furthermore, the method for determining which users receive recommendation information and the method for determining the recommendation information itself are not limited to the examples described above.

[0100] Furthermore, in determining the users to whom recommendation information is provided and the recommendation information itself, the information providing device 10 may group together multiple sets of facility usage characteristics that have a high degree of similarity based on the similarity between the sets of facility usage characteristics. For example, multiple sets of facility usage characteristics whose similarity to the facility usage characteristics associated with a set of facility usage characteristics is above a predetermined level may be grouped together into one group. This group may be referred to as a facility usage characteristic set group below.

[0101] For example, if a user belonging to a specific set of daily activities belongs to one of several sets of facility usage characteristics, the information provider 10 groups together the sets of facility usage characteristics that have a similarity level of a predetermined level or higher, and generates a group of facility usage characteristics. The information provider 10 then determines the facility usage characteristics (hereinafter referred to as the grouped facility usage characteristics) that are associated with the group of facility usage characteristics. The information provider 10 also extracts users who belong to a specific set of daily activities but do not belong to any of the group of facility usage characteristics, and provides these extracted users with information about the facility usage characteristics associated with the group of facility usage characteristics as recommendation information.

[0102] The representation of usage information shown in Figure 4 is merely an example, and this disclosure is not limited thereto. For example, the information regarding Nd types of facilities used shown in Figure 4 may indicate the number of times each of the Nd types of exercise areas available within a single facility (e.g., a gym) was used. For example, among the number of times each of the exercise areas (or exercise equipment) available within a single gym was used, facility i may include the number of times the treadmill was used, facility ii may include the number of times the strength training machine was used, and facility iii may include the number of times the swimming pool was used. If various types of exercise such as yoga, dance, bouldering, and sauna are available within a single gym, the number of times each of these different types of exercise was used (or performed) may be included in the usage information, distinguished from each other. In this way, by showing usage information within a single facility, it is possible to recommend exercises that can be performed at that single facility to the user, thus recommending exercises that are easier for the user to practice.

[0103] The facility usage characteristics provided to users are not particularly limited. For example, when providing fitness content, the use of a nearby gym may be suggested in conjunction with the fitness program. Such coordinated suggestions can further contribute to improving the user's health. When suggesting gym use, additional information regarding gym use may be provided. For example, additional information may include gym usage fees and gym membership benefits. Additional information may include, for example, that gym members do not have to pay a gym usage fee, gym usage fees for non-members, and whether trial use is free. Additional information may also include information that improves user convenience, such as gym congestion levels and services provided by the gym (e.g., use of changing rooms, rental of clothing). Furthermore, additional information may include information encouraging non-members to become regular members, and information on membership benefits (e.g., discounts on registration fees, explanations of benefits for continuing members).

[0104] Furthermore, the suggested information may be shared with the sports facility. For example, by sharing information such as the number of people who should use the gym and the times of day when they should use the gym, gym staff can predict the level of congestion at different times of the day.

[0105] Alternatively, the information suggested may be determined based on actual gym congestion levels. For example, the suggested gym usage days and times may be determined based on actual congestion levels by day of the week and time of day.

[0106] <Processing flow of the information providing device 10> Next, we will explain the processing flow in the information providing device 10.

[0107] Figure 7 is a flowchart showing a first example of the processing flow in the information provision device 10. The flow shown in Figure 7 may be executed periodically or irregularly. Furthermore, the flow shown in Figure 7 may be executed based on instructions from the user or the administrator managing the information provision system 1.

[0108] The information provider 10 acquires daily behavior information for each of the multiple users (S101). The information provider 10 classifies the multiple users into multiple sets of daily behavior characteristics (S102).

[0109] The information provider 10 acquires usage history information (S103). The information provider 10 classifies the information into multiple facility usage characteristic sets (S104). The number of multiple facility usage characteristic sets is represented as N (where N is an integer greater than or equal to 2), and each of the multiple facility usage characteristic sets may be assigned an index from 1 to N. Hereafter, a facility usage characteristic set assigned an index n (where n is an integer greater than or equal to 1 or less than or equal to N) will be referred to as the nth facility usage characteristic set.

[0110] The information providing device 10 selects a specific set of daily behavioral characteristics (S105). The specific set of daily behavioral characteristics may be any one of several sets of daily behavioral characteristics.

[0111] The information providing device 10 sets k to 1 (S106). The following explanation assumes that the number N of facility usage characteristics is 3, and describes the processing from S107 to S114.

[0112] The information providing device 10 determines whether k is greater than N (S107).

[0113] If k is greater than N (YES in S107), for example, if k becomes N+1, the flow shown in Figure 7 terminates, indicating that the processing in S108-S113 for the N sets of facility usage characteristics from the 1st to the Nth has been completed.

[0114] If k is not greater than N (NO in S107), the information provider 10 calculates the correlation between a specific set of daily behavioral characteristics and the k-th set of facility usage characteristics (S108). For example, if k=1, since k=1 is not greater than N=3, in S108, the information provider 10 calculates the correlation between the specific set of daily behavioral characteristics and the k-th (i.e., 1st) set of facility usage characteristics. Here, the calculated correlation may numerically represent the similarity of the elements in the two sets (e.g., users belonging to the sets). For example, the larger the correlation value, the higher the similarity between the two sets. In other words, the larger the correlation value, the greater the number of users who belong to both sets. For example, the correlation may be expressed as a percentage. If the specific set of daily behavioral characteristics and the k-th (e.g., 1st) set of facility usage characteristics are a perfect match, for example, if the users in each set are a perfect match, the correlation will be 100 percent. For example, the proportion of users who belong to the k-th set of facility usage characteristics among users who belong to a specific set of daily behavioral characteristics is shown as a correlation.

[0115] The information provider 10 determines whether there is a correlation between a specific set of daily behavioral characteristics and the kth (for example, the 1st) set of facility usage characteristics (S109). For example, if there are no common users between the specific set of daily behavioral characteristics and the kth set of facility usage characteristics, it is determined that there is no correlation between the two sets.

[0116] If there is no correlation (NO in S109), the information providing device 10 classifies the k-th (for example, the 1st) set of facility usage characteristics into an uncorrelated set (S110).

[0117] If a correlation exists (YES in S109), the information provider 10 determines whether the correlation is above a threshold (S111). The threshold is not particularly limited, but for example, if the correlation is expressed as a percentage, the threshold may be greater than 50%.

[0118] If the correlation is above a threshold (YES in S111), the information providing device 10 classifies the k-th (for example, the 1st) set of facility usage characteristics into the set with high correlation (S112).

[0119] If the correlation is not above a threshold (NO in S111), the information provider 10 classifies the k-th (for example, the 1st) set of facility usage characteristics into a set with low correlation (S113).

[0120] After the k-th (for example, the 1st) set of facility usage characteristics is classified into one of the following: an uncorrelated set, a highly correlated set, or a lowly correlated set (after S110, S112, or S113), the information providing device 10 adds 1 to k (S114). That is, if k=1, in S114, 1 is added to k=1, setting it to k=2, and the flow returns to S107. In S107, it is determined that k=2 is not greater than N=3 (i.e., NO in S107), so the processing from S108 to S113 is executed for k=2, i.e., the 2nd set of facility usage characteristics. After the processing from S108 to S113 is executed for the 2nd set of facility usage characteristics, in the same way as in the case of k=1, 1 is added to k=2 in S114, setting it to k=3, and the flow returns to S107. In this case, in S107, it is determined that k=3 is not greater than N=3 (i.e., NO in S107), so the processes from S108 to S113 are executed for k=3, that is, the third set of facility usage characteristics. After the processes from S108 to S113 are executed for the third set of facility usage characteristics, in S114, 1 is added to k=3, setting it to k=4, and the flow returns to S107, just as in the case of k=1. In S107, it is determined that k=4 is greater than N=3 (i.e., YES in S107), so the flow shown in Figure 7 ends. Through this flow, the processes from S108 to S113 are executed for each of the first to Nth sets of facility usage characteristics.

[0121] Note that the order of the flow shown in Figure 7 is an example, and this disclosure is not limited thereto. For example, some processes may be executed simultaneously or in parallel. Exemplaryly, processes S101 and S102 and processes S103 and S104 may be executed in parallel. Also, processes S101 and S102 and processes S103 and S104 may be executed periodically or irregularly, independently of processes S105 and later.

[0122] As shown in Figure 7, for each of the N sets of facility usage characteristics, given a specific set of daily behavioral characteristics, each set is classified into one of three categories: uncorrelated, highly correlated, or poorly correlated.

[0123] In Figure 7, the flowchart shows an example of classifying each of the N sets of facility usage characteristics for a single specific set of daily behavioral characteristics. However, it is also possible to classify each of the N sets of facility usage characteristics for each of multiple sets of daily behavioral characteristics.

[0124] In the flowchart shown in Figure 7, the information provider 10 classifies the k-th set of facility usage characteristics into a highly correlated set if the correlation with respect to the k-th set of facility usage characteristics is above a threshold, and into a low-correlation set if the correlation is below a threshold. However, this disclosure is not limited to this example.

[0125] For example, multiple thresholds and correlations may be compared. For instance, a first threshold and a second threshold smaller than the first threshold may be provided, and the information provider 10 may classify the k-th set of facility usage characteristics into a highly correlated set if the correlation is greater than or equal to the first threshold, and classify the k-th set of facility usage characteristics into a low-correlation set if the correlation is less than the second threshold. In this case, if the correlation is less than the first threshold and greater than or equal to the second threshold, the k-th set of facility usage characteristics may be ignored. If the correlation is expressed as a percentage, and the first threshold is X percent (where X is an integer between 50 and 100), the second threshold may be 100 - X percent.

[0126] Next, we will explain how to determine what to propose to the user based on the classification results of the facility usage characteristics set.

[0127] Figure 8 is a flowchart illustrating a second example of the processing flow in the information provision device 10. The flow shown in Figure 8 may be executed periodically or irregularly. Furthermore, the flow shown in Figure 8 may be executed based on instructions from the user or the administrator managing the information provision system 1. In addition, the flow shown in Figure 8 may be executed after the completion of the flow shown in Figure 7, or it may be executed independently of the flow shown in Figure 7.

[0128] The information providing device 10 selects a specific set of daily behavioral characteristics (S201). The specific set of daily behavioral characteristics may be any one of several sets of daily behavioral characteristics.

[0129] The information providing device 10 selects a set of facility usage characteristics that have a high correlation with a specific set of daily behavioral characteristics (S202). Here, there may be only one set of facility usage characteristics that has a high correlation. For example, the set of facility usage characteristics with the highest correlation may be extracted.

[0130] The information provider 10 extracts facility usage characteristics that correspond to a set of highly correlated facility usage characteristics (S203). The extracted information regarding facility usage characteristics may be recommendation information.

[0131] The information provider 10 selects a set of facility usage characteristics that have a low correlation with a specific set of daily behavioral characteristics (S204). Here, the selected set of low-correlated facility usage characteristics may be one or more.

[0132] The information providing device 10 extracts users (target users) who belong to a specific set of daily behavioral characteristics that are correlated with a set of facility usage characteristics that have a low correlation (S205). In other words, the target users may be users who belong to a specific set of daily behavioral characteristics and do not belong to a set of facility usage characteristics that have a high correlation.

[0133] The information provider 10 provides the target person (target user) with information regarding facility usage characteristics extracted in S203 as recommendation information (S206).

[0134] The information providing device 10 described above acquires daily activity information and usage history information, performs clustering based on the daily activity information to classify multiple users into multiple daily activity characteristic sets, performs clustering based on the usage history information to classify multiple users into multiple facility usage characteristic sets, and determines the correlation between each of the multiple daily activity characteristic sets and each of the multiple usage characteristic sets. The information providing device 10 then identifies a first facility usage characteristic set from among the facility usage characteristic sets whose correlation with the first daily activity characteristic set satisfies a predetermined criterion, extracts a specific user who belongs to the first daily activity characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set, and provides the specific user with recommendation information recommending the use of exercise facilities corresponding to the first facility usage characteristic set. With this configuration, it is possible to provide a user with recommendation information based on the usage history of exercise facilities used by other users who perform daily activities similar to that user's daily activities, and therefore it is possible to recommend appropriate activities (e.g., training) based on the trends of daily activities.

[0135] In the embodiments described above, an example was shown in which the use of exercise facilities was suggested to a specific user belonging to a particular set of daily behavioral characteristics based on a comparison (e.g., correlation) between one specific set of daily behavioral characteristics and each of several sets of facility usage characteristics. However, this disclosure is not limited to this. For example, recommended daily behaviors may be suggested to a specific user belonging to a particular set of facility usage characteristics based on a comparison (e.g., correlation) between one specific set of facility usage characteristics and each of several sets of daily behavioral characteristics.

[0136] In the embodiments described above, an example was shown in which information on the daily activities of multiple users (i.e., daily activity information) and information on the usage history of multiple users of exercise facilities (i.e., usage history information) is used to provide users with information on which exercise facilities are recommended for them (i.e., recommendation information). However, this disclosure is not limited to this.

[0137] For example, recommendation information may include information that recommends users to use facilities other than sports facilities. For example, based on the daily activity information of multiple users and information on the usage history of each user of entertainment facilities (e.g., movie theaters, art museums), information on entertainment facilities that are recommended for that user (i.e., recommendation information) may be provided to the user. For example, based on the daily activity information of multiple users and information on the usage history of facilities that each user uses on a daily basis (e.g., supermarkets), information on facilities that the user uses on a daily basis (i.e., recommendation information) may be provided to the user.

[0138] In other words, in this embodiment, a specific activity to recommend to a particular user is determined based on the daily activity information of multiple users and information on the actual performance of each user in that activity, and the determined specific activity is recommended to that particular user. Here, the specific activity to recommend may be the use of sports facilities, recreational facilities, or facilities used on a daily basis, as in the embodiment described above. Alternatively, the specific activity to recommend may be a specific exercise performed at a sports facility, or a specific recreational activity performed at a recreational facility.

[0139] Furthermore, the correlation determination unit 105 may not need to provide the user with information about the entertainment facility recommended by the recommendation information (i.e., recommendation information) if the user has already used the entertainment facility recommended by the recommendation information with a higher degree of enthusiasm than the recommendation information suggests. A higher degree of enthusiasm may correspond to at least one of the following: using the facility more frequently, spending more money, receiving greater value, or using the facility for a longer period of time. In other words, the determination of the degree of enthusiasm for using a facility may be based on at least one of the following: the frequency of use of the facility (number of uses per unit period), the cost spent at the facility, the value received at the facility, and the time spent at the facility.

[0140] In the embodiments described above, terms such as "extraction," "determination," "selection," "identification," and "estimation" may be substituted for each other.

[0141] The flowchart diagram shown in the above-described embodiment does not limit the execution of processes to the order shown in the flowchart. For example, each process shown in the flowchart may be executed in a different order than shown in the flowchart, and multiple processes may be executed in parallel or simultaneously. The order of multiple processes shown in the flowchart may also be changed. Furthermore, some of the processes shown in the flowchart may be temporarily omitted.

[0142] In the embodiments described above, the notation "...part" used for each component may be replaced with other notations such as "...means," "...circuitry," "...assembly," "...device," "...unit," or "...module."

[0143] This disclosure can be implemented in software, hardware, or software in conjunction with hardware. Each functional block used in the description of the above embodiments may be implemented in part or in whole as an integrated circuit (LSI), and each process described in the above embodiments may be controlled in part or in whole by a single LSI or a combination of LSIs. An LSI may consist of individual chips, or it may consist of a single chip that includes some or all of the functional blocks. An LSI may have data inputs and outputs. Depending on the degree of integration, LSIs may be referred to as ICs, system LSIs, super LSIs, or ultra LSIs.

[0144] The method of integration is not limited to LSIs; it may also be implemented using dedicated circuits, general-purpose processors, or dedicated processors. Furthermore, FPGAs (Field Programmable Gate Arrays) that can be programmed after LSI manufacturing, or reconfigurable processors that allow for the reconfiguration of the connections and settings of circuit cells within the LSI, may also be used. This disclosure may be implemented as digital or analog processing.

[0145] Furthermore, if advancements in semiconductor technology or other derived technologies lead to the emergence of integrated circuit technologies that replace LSIs, then naturally, it would be possible to use those technologies to integrate functional blocks. The application of biotechnology, for example, is a possibility.

[0146] This disclosure is applicable to all types of devices, systems, and equipment having communication capabilities (collectively referred to as communication equipment). Communication equipment may include a radio transceiver and a processing / control circuit. A radio transceiver may include a receiver and a transmitter, or both as functions. A radio transceiver (transmitter, receiver) may include an RF (Radio Frequency) module and one or more antennas. The RF module may include an amplifier, an RF modulator / demodulator, or similar. Non-exclusive examples of communication devices include telephones (mobile phones, smartphones, etc.), tablets, personal computers (PCs) (laptops, desktops, notebooks, etc.), cameras (digital still / video cameras, etc.), digital players (digital audio / video players, etc.), wearable devices (wearable cameras, smartwatches, tracking devices, etc.), game consoles, digital book readers, telehealth / telemedicine devices, vehicles or mobile transport with communication capabilities (cars, airplanes, ships, etc.), and combinations of the above-mentioned devices.

[0147] Communication devices are not limited to portable or movable devices, but also include all kinds of non-portable or fixed devices, devices, and systems, such as smart home devices (appliances, lighting equipment, smart meters or measuring instruments, control panels, etc.), vending machines, and any other "things" that may exist on an IoT (Internet of Things) network.

[0148] Furthermore, in recent years, Cyber-Physical Systems (CPS), a new concept in IoT (Internet of Things) technology that creates new added value through information linkage between the physical and cyber spaces, has been attracting attention. This CPS concept can also be adopted in the above-described embodiment.

[0149] In other words, as a basic configuration of CPS, for example, edge servers located in physical space and cloud servers located in cyberspace are connected via a network, and processing can be distributed and performed by the processors installed on both servers. Here, it is preferable that each processing data generated on the edge server or cloud server is generated on a standardized platform, and by using such a standardized platform, it is possible to improve efficiency when building systems that include various diverse groups of sensors and IoT application software.

[0150] Communication includes data communication via cellular systems, wireless LAN systems, and communication satellite systems, as well as data communication using combinations of these.

[0151] Furthermore, the communication device also includes devices such as controllers and sensors that are connected to or linked to a communication device that performs the communication functions described in this disclosure. For example, this includes controllers and sensors that generate control signals and data signals used by the communication device that performs the communication functions of the communication device.

[0152] Furthermore, communication equipment includes infrastructure facilities such as base stations, access points, and any other devices, devices, and systems that communicate with or control the aforementioned non-limited types of equipment.

[0153] An information provision method according to one embodiment of the present disclosure includes the steps of: acquiring daily behavior information showing the daily behavior records of multiple users; performing clustering based on the daily behavior information to classify the multiple users into multiple daily behavior characteristic sets; acquiring usage record information showing the usage record of the multiple users to use facilities; performing clustering based on the usage record information to classify the multiple users into multiple facility usage characteristic sets; determining the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets; identifying a first facility usage characteristic set among the facility usage characteristic sets whose correlation with a first daily behavior characteristic set satisfies a predetermined criterion; extracting a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and providing the specific user with recommendation information that recommends the use of facilities corresponding to the first facility usage characteristic set.

[0154] In one embodiment of the present disclosure, the first set of facility usage characteristics has a value indicating a high correlation with the first set of daily behavior characteristics that is greater than or equal to a first threshold, and the second set of facility usage characteristics has a value indicating a high correlation with the first set of daily behavior characteristics that is less than or equal to a second threshold which is smaller than the first threshold.

[0155] In one embodiment of the present disclosure, the step of identifying the first set of facility usage characteristics is to identify the first set of facility usage characteristics as a group of one or more sets of facility usage characteristics with a high degree of similarity among the multiple sets of third set of facility usage characteristics that satisfy a predetermined criterion for correlation with the first set of daily behavior characteristics.

[0156] In one embodiment of the present disclosure, the step of providing the recommendation information is as follows: If the recommendation information recommending the use of a facility corresponding to the first set of facility usage characteristics is similar to the usage history information of the particular user, the recommendation information recommending the use of a facility corresponding to the first set of facility usage characteristics is not provided to the particular user.

[0157] In one embodiment of the present disclosure, the step of providing the recommendation information is to refrain from providing the specific user with the recommendation information recommending the use of a facility corresponding to the first set of facility usage characteristics if the recommendation information recommends use at a lower level of enthusiasm than the level of enthusiasm indicated by the specific user's usage history information.

[0158] In one embodiment of the present disclosure, the step of providing recommendation information determines the timing for providing the recommendation information to the specific user, and the step of providing recommendation information provides the recommendation information to the specific user at the timing determined.

[0159] An information providing device according to one embodiment of the present disclosure includes: a first acquisition unit that acquires daily behavior information showing the daily behavior records of multiple users; a first classification unit that performs clustering based on the daily behavior information and classifies the multiple users into multiple daily behavior characteristic sets; a second acquisition unit that acquires usage record information showing the usage record of the multiple users into multiple facility usage characteristic sets; a second classification unit that performs clustering based on the usage record information and classifies the multiple users into multiple facility usage characteristic sets; a correlation determination unit that determines the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets, identifies a first facility usage characteristic set among the facility usage characteristic sets whose correlation with the first daily behavior characteristic set satisfies a predetermined criterion, and extracts a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and an information providing unit that provides the specific user with recommendation information recommending the use of facilities corresponding to the first facility usage characteristic set.

[0160] An information provision system according to one embodiment of the present disclosure includes: a first acquisition unit that acquires daily behavior information showing the daily behavior records of multiple users; a first classification unit that performs clustering based on the daily behavior information and classifies the multiple users into multiple daily behavior characteristic sets; a second acquisition unit that acquires usage record information showing the usage record of the multiple users into multiple facility usage characteristic sets; a second classification unit that performs clustering based on the usage record information and classifies the multiple users into multiple facility usage characteristic sets; a correlation determination unit that determines the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets, identifies a first facility usage characteristic set among the facility usage characteristic sets whose correlation with the first daily behavior characteristic set satisfies a predetermined criterion, and extracts a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and an information provision unit that provides the specific user with recommendation information recommending the use of facilities corresponding to the first facility usage characteristic set.

[0161] An information provision program according to one embodiment of the present disclosure causes at least one processor to execute: a process for acquiring daily behavior information showing the daily behavior records of multiple users; a process for performing clustering based on the daily behavior information and classifying the multiple users into multiple daily behavior characteristic sets; a process for acquiring usage record information showing the usage record of the multiple users into multiple facility usage characteristic sets; a process for performing clustering based on the usage record information and classifying the multiple users into multiple facility usage characteristic sets; a process for determining the correlation between each of the multiple daily behavior characteristic sets and each of the multiple facility usage characteristic sets; a process for identifying a first facility usage characteristic set among the facility usage characteristic sets whose correlation with a first daily behavior characteristic set satisfies a predetermined criterion; a process for extracting a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set that is different from the first facility usage characteristic set; and a process for providing the specific user with recommendation information that recommends the use of facilities corresponding to the first facility usage characteristic set.

[0162] Although various embodiments have been described above with reference to the drawings, it goes without saying that this disclosure is not limited to such examples. It is clear to those skilled in the art that various modifications or alterations can be conceived within the scope of the claims, and these will naturally also fall within the technical scope of this disclosure. Furthermore, the components in the above embodiments may be combined in any way without departing from the spirit of the disclosure.

[0163] The specific examples of this disclosure have been described in detail above, but these are merely illustrative and do not limit the scope of the claims. The technologies described in the claims include various modifications and changes to the specific examples described above. [Industrial applicability]

[0164] One embodiment of this disclosure is useful for an information provision system that provides information. [Explanation of Symbols]

[0165] 1. Information Provision System 10 Information provision device 20 cameras 30 sensors 40 devices 101 Daily behavior information acquisition department 102 Daily behavior characteristics classification section 103 Usage History Information Acquisition Department 104 Facility Usage Characteristics Classification Section 105 Correlation determination unit 106 Information Provision Department

Claims

1. An information provision method that provides recommendation information recommending the use of a facility based on the behavioral data of multiple users and the usage data of the exercise facility, The steps include: acquiring daily behavior information that shows the daily actions of the aforementioned multiple users; The steps include: performing clustering based on the aforementioned daily behavior information and classifying the multiple users into multiple sets of daily behavior characteristics; The steps include: obtaining usage information that shows the usage history of the aforementioned multiple users of the facilities; The steps include: performing clustering based on the aforementioned usage history information and classifying the multiple users into multiple sets of facility usage characteristics; The steps include determining the correlation between each of the aforementioned sets of daily behavioral characteristics and each of the aforementioned sets of facility usage characteristics, The steps include identifying a first set of facility usage characteristics from the aforementioned set of facility usage characteristics whose correlation with a first set of daily behavior characteristics satisfies a predetermined criterion, A step of extracting specific users who belong to the first set of daily behavioral characteristics and to a second set of facility usage characteristics that is different from the first set of facility usage characteristics, and who do not belong to the first set of facility usage characteristics; The steps include providing the specific user with recommendation information that recommends the use of facilities corresponding to the first set of facility usage characteristics, Includes, The set of characteristics is different from the set of multiple daily behavioral characteristics and the set of multiple facility usage characteristics. Information provision method.

2. The first set of facility usage characteristics is defined as having a value greater than or equal to a first threshold that indicates a high correlation with the first set of daily behavior characteristics. The second set of facility usage characteristics has a value indicating a high correlation with the first set of daily behavior characteristics that is less than or equal to a second threshold which is smaller than the first threshold. The method for providing information according to claim 1.

3. The step of identifying the first set of facility usage characteristics is to identify the first set of facility usage characteristics if there are multiple sets of third set of facility usage characteristics that satisfy a predetermined criterion for correlation with the first set of daily behavior characteristics, and to group together one or more sets with a high degree of similarity among the multiple sets of third set of facility usage characteristics. The method for providing information according to claim 1.

4. The step of providing the recommendation information is to not provide the recommendation information recommending the use of facilities corresponding to the first set of facility usage characteristics to the specific user if the recommendation information recommending the use of facilities corresponding to the first set of facility usage characteristics is similar to the usage history information of the specific user. The method for providing information according to claim 1.

5. The step of providing the recommendation information is to not provide the specific user with the recommendation information recommending the use of a facility corresponding to the first set of facility usage characteristics if the recommendation information recommends use at a lower level of enthusiasm than the level of enthusiasm indicated by the specific user's usage history information. The method for providing information according to claim 1.

6. The step of providing the recommendation information involves determining the timing for providing the recommendation information to the specific user. The step of providing the recommendation information includes providing the recommendation information to the specific user at the determined timing. The method for providing information according to claim 1.

7. A first acquisition unit that acquires daily behavior information showing the daily actions of multiple users, A first classification unit performs clustering based on the aforementioned daily behavior information and classifies the multiple users into multiple sets of daily behavior characteristics, A second acquisition unit that acquires usage history information showing the usage history of the aforementioned multiple users of the facilities, A second classification unit performs clustering based on the aforementioned usage history information and classifies the multiple users into multiple sets of facility usage characteristics, A correlation determination unit determines the correlation between each of the plurality of sets of daily behavioral characteristics and each of the plurality of sets of facility usage characteristics, identifies a first set of facility usage characteristics from among the set of facility usage characteristics whose correlation with the first set of daily behavioral characteristics satisfies a predetermined criterion, and extracts a specific user who belongs to the first set of daily behavioral characteristics and belongs to a second set of facility usage characteristics that is different from the first set of facility usage characteristics. An information provision unit provides recommendation information to the aforementioned specific user, recommending the use of facilities corresponding to the first set of facility usage characteristics, An information-providing device equipped with the following features.

8. An information provision system that provides recommendation information recommending the use of a facility based on the behavioral data and usage data of multiple users of the sports facility, A first acquisition unit that acquires daily behavior information showing the daily actions of the aforementioned multiple users, A first classification unit performs clustering based on the aforementioned daily behavior information and classifies the multiple users into multiple sets of daily behavior characteristics, A second acquisition unit that acquires usage history information showing the usage history of the aforementioned multiple users of the facilities, A second classification unit performs clustering based on the aforementioned usage history information and classifies the multiple users into multiple sets of facility usage characteristics, A correlation determination unit that determines the correlation between each of the plurality of daily behavior characteristic sets and each of the plurality of facility usage characteristic sets, identifies a first facility usage characteristic set among the facility usage characteristic sets whose correlation with the first daily behavior characteristic set satisfies a predetermined criterion, extracts a specific user who belongs to the first daily behavior characteristic set and belongs to a second facility usage characteristic set different from the first facility usage characteristic set, and does not belong to the first facility usage characteristic set; and an information provision unit that provides the specific user with recommendation information recommending the use of facilities corresponding to the first facility usage characteristic set. Includes, The set of characteristics is different from the set of multiple daily behavioral characteristics and the set of multiple facility usage characteristics. Information provision system.

9. An information provision program that provides recommendation information recommending the use of a facility based on the behavioral data and usage data of multiple users of the sports facility, At least one processor, A process for acquiring daily behavior information that shows the daily actions of the aforementioned multiple users, A process of performing clustering based on the aforementioned daily behavior information and classifying the aforementioned multiple users into multiple sets of daily behavior characteristics, A process to obtain usage information showing the usage history of the aforementioned multiple users of the facilities, A process to perform clustering based on the aforementioned usage history information and classify the multiple users into multiple sets of facility usage characteristics, A process for determining the correlation between each of the aforementioned sets of daily behavioral characteristics and each of the aforementioned sets of facility usage characteristics, A process for identifying a first set of facility usage characteristics from the aforementioned set of facility usage characteristics whose correlation with a first set of daily behavior characteristics satisfies a predetermined criterion, A process for extracting specific users who belong to the first set of daily behavioral characteristics, and who belong to a second set of facility usage characteristics that is different from the first set of facility usage characteristics, and who do not belong to the first set of facility usage characteristics; A process that provides the aforementioned specific user with recommendation information that recommends the use of facilities corresponding to the first set of facility usage characteristics, Make it run, The set of characteristics is different from the set of multiple daily behavioral characteristics and the set of multiple facility usage characteristics. Information provision program.

Images