JP7801901B2 - Information providing device, information providing system, information providing method and program - Google Patents

Description

The present disclosure relates to an information providing device , an information providing system, an information providing method, and a program.

A collaboration system has been proposed that includes a collaboration server that links devices and an adapter that connects the collaboration server to the devices. The system controls the devices to provide services tailored to the user according to scenarios pre-installed on a scenario platform, triggered by the user's unconscious behavior, environmental changes, or physical changes (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2020-154945

In the linked system described in Patent Document 1, there is a demand for scenarios that identify user behavior patterns based on the user's route search logs and location information history, and incorporate into the scenario platform a scenario that introduces programs that the user tends to watch in accordance with the identified behavior patterns. This would allow scenarios that introduce programs to users based on the user's behavior patterns for each day of the week, for example.

The present disclosure has been made in consideration of the above reasons, and aims to provide an information providing device , an information providing system, an information providing method, and a program that can guide users to programs that they prefer based on their location and behavioral patterns.

In order to achieve the above object, an information providing device according to the present disclosure includes:
a location information acquisition unit that acquires location information indicating the location of a user;
a location identification unit that identifies at least one stop-off location that the user will stop off at based on the location information of the user and the stay time of the user at the location indicated by the location information within a predetermined period of time;
a travel status determination unit that determines a travel status of the user based on a stay time of the user at each of the at least one stop-off places;
an estimation unit that estimates the travel route using a route estimation model that estimates the travel route of the user from the travel status, and estimates the user's return home time using a return home time estimation model that estimates the user's return home time from a stay period at each of the at least one stop-off places included in the estimated travel route;
a program selection unit that selects a program that belongs to the same program type as the program type of at least one broadcast program that the user has viewed in the past and that the user likes;
a notification determination unit that determines whether or not to transmit program information of the selected program to a terminal device carried by the user based on the start time of the selected program and the time of returning home;
The program notification unit transmits the program information to the terminal device carried by the user when it is determined that the program information should be transmitted to the terminal device.

According to the present disclosure, an estimation unit estimates a user's travel route using a route estimation model, and estimates the user's time of return home from the estimated travel route using a home-time estimation model. Furthermore, a program selection unit selects programs that belong to the same program type as the program type of at least one program that the user has previously viewed and that the user prefers. Then, when the notification determination unit determines that program information for programs of the program type should be transmitted to a terminal device carried by the user, the program notification unit transmits the program information to the terminal device carried by the user. This makes it possible to provide the user with program information for at least one program that the user prefers based on the user's time of return home, thereby making it possible to guide the user to programs that the user prefers based on the user's location and behavioral patterns.

1 is a schematic configuration diagram of an information providing system according to a first embodiment of the present disclosure; FIG. 1 is a block diagram showing a hardware configuration of an information providing system according to a first embodiment. FIG. 1 is a block diagram showing a functional configuration of a terminal device according to a first embodiment; 1 is a block diagram showing a functional configuration of a cloud server according to a first embodiment; FIG. 1 is a diagram showing an example of information stored in a travel status storage unit according to the first embodiment; FIG. 1 is a diagram showing an example of information stored in a viewing history storage unit according to the first embodiment; 1A is a diagram for explaining a route estimation process of a cloud server according to the first embodiment, and FIG. 1B is a diagram for explaining a return home time estimation process of a cloud server. FIG. 1 is a sequence diagram illustrating an operation of the information providing system according to the first embodiment. FIG. 1 is a sequence diagram illustrating an operation of the information providing system according to the first embodiment. FIG. 1 is a sequence diagram illustrating an operation of the information providing system according to the first embodiment. FIG. 1 is a sequence diagram illustrating an operation of the information providing system according to the first embodiment. 1 is a flowchart showing an example of the flow of information provision processing executed by the information provision system according to the first embodiment; 1 is a flowchart showing an example of the flow of information provision processing executed by the information provision system according to the first embodiment; FIG. 10 is a block diagram showing a functional configuration of a cloud server according to a second embodiment of the present disclosure. FIG. 10 is a diagram showing an example of information stored in a viewing history storage unit according to the second embodiment. 10 is a flowchart showing an example of the flow of information providing processing executed by a cloud server according to a second embodiment. 10 is a flowchart showing an example of the flow of information providing processing executed by a cloud server according to a second embodiment. 1 is a schematic configuration diagram of an information providing system according to a third embodiment of the present disclosure. FIG. 10 is a block diagram showing a functional configuration of a terminal device according to a third embodiment. 10 is a block diagram showing the functional configuration of a cloud server according to a third embodiment. FIG. 10 is a sequence diagram illustrating the operation of the information providing system according to the third embodiment. 10 is a flowchart showing an example of the flow of information providing processing executed by a cloud server according to the third embodiment. 1 is a schematic configuration diagram of an information providing system according to a fourth embodiment of the present disclosure; FIG. 10 is a block diagram showing a functional configuration of a terminal device according to a fourth embodiment. 10 is a block diagram showing the functional configuration of a cloud server according to a fourth embodiment. 10 is a flowchart showing an example of the flow of information providing processing executed by a cloud server according to the fourth embodiment.

The control system according to each embodiment of the present disclosure will be described below with reference to the drawings.

(Embodiment 1)
The information providing device of this embodiment includes a location information acquisition unit that acquires location information indicating the location of a user; a location identification unit that identifies at least one stop-off location where the user will stop off based on the user's location information within a predetermined period and the user's stay time at the location indicated by the location information; a travel status determination unit that determines the user's travel status based on the user's stay time at each of the at least one stop-off location; an estimation unit that estimates the user's return home time using a return home time estimation model that estimates the user's return home time from the travel status; a program selection unit that selects programs that belong to the same program type as the program type of at least one program that the user has viewed in the past and that is preferred by the user; a notification determination unit that determines whether to send program information for programs of the program type to a terminal device carried by the user based on the start time and return home time of the selected program; and a program notification unit that sends the program information to the terminal device when the notification determination unit determines that program information for programs of the program type should be sent to the terminal device carried by the user.

As shown in FIG. 1, the information provision system according to this embodiment includes a television receiver 91 and a recording device 92 installed in building H, a cloud server 1, a location management server 2, a relay server 3, and a terminal device 5. Terminal device 5 has the ability to receive GNSS (Global Navigation Satellite System) signals emitted from artificial satellites SAT. Also installed in building H is a router 82 connected to a local network NW2 constructed within building H, and a data circuit-terminating device 81 connected to the router 82 and a wide area network NW1. The wide area network NW1 is, for example, the Internet. The local network NW2 is, for example, a wired LAN (Local Area Network) or a wireless LAN. The data circuit-terminating device 81 is, for example, an ONU (Optical Network Unit), a modem, a gateway, or the like.

The television receiver 91 and the recording device 92 can communicate with the cloud server 1 via the local network NW2 and the wide area network NW1, respectively. The television receiver 91 starts displaying video when the user manually performs a viewing start operation to start viewing, and ends displaying video when the user manually performs a viewing end operation to end viewing. The television receiver 91 then tallies the viewing time of at least one program viewed by the user and identifies programs that the user continued to watch for a preset reference time or longer. The television receiver 91 then generates viewing history information for the identified program, including program identification information, day of the week information indicating the day the program was broadcast, start time information and end time information indicating the broadcast start and end times, and program type information indicating the program type (e.g., "news," "variety show," etc.). The television receiver 91 then transmits the generated viewing history information to the cloud server 1.

When the recording device 92 acquires control information for reserving a recording from the cloud server, it executes the recording reservation process based on the acquired control information. Furthermore, the recording device 92 starts recording when the program start time set in the recording reservation process arrives, and then ends recording when the program end time arrives, when the program end time arrives. Here, the recording device 92 generates viewing history information including the program identification information, day of the week information, start time information, end time information, and program type information of the recorded program, and transmits the generated viewing history information to the cloud server 1.

The location management server 2 manages location information indicating the location of the terminal device 5 transmitted from the terminal device 5, by associating it with terminal device identification information that identifies the terminal device 5 that transmitted the location information. When a preset location information acquisition time arrives, the location management server 2 acquires the location information transmitted from the terminal device 5 by transmitting to the terminal device 5 location information request information requesting the terminal device 5 to transmit the terminal device 5's location information. Furthermore, when the location of the terminal device 5 transitions from being inside a preset area that includes the user's home to being outside the area, the location management server 2 determines that the user has left the house with the terminal device 5, and begins periodically transmitting to the cloud server 1 the location information of the terminal device 5 and time information indicating the time the location information was acquired. Meanwhile, when the location management server 2 receives from the cloud server 1 return-home notification information notifying the user that they have returned home, it stops transmitting the location information of the terminal device 5 to the cloud server 1.

When the relay server 3 acquires various information sent from the terminal device 5 to the cloud server 1, it transmits the acquired information to the cloud server 1. Furthermore, when the relay server 3 acquires various information sent from the cloud server 1 to the terminal device 5, it transmits the acquired information to the terminal device 5.

The terminal device 5 is, for example, a smartphone, and as shown in FIG. 2, includes a CPU (Central Processing Unit) 501, a main memory 502, an auxiliary memory 503, a display 504, an input unit 505, a wide-area communication unit 506, a GNSS receiving unit 508, and a bus 509 connecting these units to one another. The main memory 502 has volatile memory such as RAM (Random Access Memory) and is used as a working area for the CPU 501. The auxiliary memory 503 is non-volatile memory such as semiconductor flash memory and stores programs for the CPU 501 to execute various processes. The display 504 is a display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The input unit 505 is, for example, a transparent touchpad placed on top of the display 504. The wide area communication unit 506 is connected to the wide area network NW1 and transmits information transferred from the CPU 501 to the relay server 3 via the wide area network NW1, and transfers information received from the relay server 3 via the wide area network NW1 to the CPU 501. The GNSS receiving unit 508 receives GNSS signals emitted from the artificial satellite SAT, and generates reference position information indicating the position of the artificial satellite SAT, time information, etc. based on the GNSS signals and transfers this information to the CPU 501.

By loading the program stored in the auxiliary memory unit 503 into the main memory unit 502 and executing it, the CPU 501 functions as a reception unit 511, a display control unit 512, a positioning unit 513, a location information notification unit 514, a program information acquisition unit 515, an operation information generation unit 516, and an operation information transmission unit 517, as shown in FIG. 3. Furthermore, the auxiliary memory unit 503 shown in FIG. 2 has an image storage unit 531, as shown in FIG. 3, that stores information about images constituting the operation screen image to be displayed on the display unit 504. Furthermore, the main memory unit 502 shown in FIG. 2 has a location storage unit 521, as shown in FIG. 3, that temporarily stores location information indicating the location of the terminal device 5.

When the reception unit 511 receives an operation performed by the user on the input unit 505, it notifies the display control unit 512 of information indicating the content of the received operation. Furthermore, when the reception unit 511 receives an operation performed by the user on the input unit 505 to start positioning of the terminal device 5, it notifies the positioning unit 513 of positioning start command information. Based on the information notified from the reception unit 511, the display control unit 512 generates an operation screen image using the information stored in the image storage unit 531 and displays it on the display unit 504.

The positioning unit 513 estimates the position of the terminal device 5 based on the reference position information, time information, etc. input from the GNSS receiving unit 508. The positioning unit 513 then updates the position information stored in the position memory unit 521 with position information indicating the estimated position of the terminal device 5. When the position information notification unit 514 acquires position information request information from the position management server 2, it transmits the position information stored in the position memory unit 521 to the position management server 2. The program information acquisition unit 515 acquires program information indicating the content of programs that are estimated to be preferred by the user, transmitted from the cloud server 1, and notifies the display control unit 512 of the acquired program information. Here, when the display control unit 512 is notified of the program information from the program information acquisition unit 515, it generates an operation screen image including the notified program information and displays it on the display unit 504.

When the operation information generation unit 516 receives from the reception unit 511 information indicating the operation content for performing recording reservation processing on the recording device 92 to the cloud server 1, it generates operation information indicating that recording reservation processing will be performed. The operation information generation unit 516 then notifies the generated operation information to the operation information transmission unit 517, and the operation information transmission unit 517 transmits the notified operation information to the cloud server 1 via the relay server 3.

Returning to Figure 2, the cloud server 1 comprises a CPU 101, a main memory unit 102, an auxiliary memory unit 103, a wide area communication unit 106, a clock unit 107, and a bus 109 interconnecting these units. The CPU 101 is, for example, a multi-core processor. The main memory unit 102 is composed of volatile memory and is used as a working area for the CPU 101. The auxiliary memory unit 103 is composed of large-capacity non-volatile memory and stores programs for implementing the various functions of the cloud server 1. The wide area communication unit 106 is connected to the wide area network NW1. The clock unit 107 is, for example, a real-time clock.

By loading the programs stored in the auxiliary memory unit 103 into the main memory unit 102 and executing them, the CPU 101 functions as a location information acquisition unit 111, a location identification unit 112, a movement status determination unit 113, a homecoming notification unit 114, an estimation unit 115, a notification determination unit 116, a program selection unit 117, a program notification unit 118, a viewing history acquisition unit 119, a device control unit 120, and a model generation unit 121, as shown in FIG. 4. Furthermore, the auxiliary memory unit 103 shown in FIG. 2 has a location memory unit 131, a location memory unit 132, a movement status memory unit 133, a viewing history memory unit 134, and a model memory unit 135, as shown in FIG. 4.

The location memory unit 131 stores location information indicating the location of the terminal device 5 carried by the user, obtained from the location management server 2, and time information indicating the time when the location management server 2 obtained the location information from the terminal device 5, in association with user identification information that identifies the user. The location memory unit 132 stores location information indicating the location of at least one of the user's drop-off locations in association with the user identification information. Here, the location information is, for example, information indicating a circular range of position coordinates centered at the center of the drop-off location and with a diameter equal to a preset reference distance.

As shown in FIG. 5 , the travel status storage unit 133 stores travel status information including location information indicating at least one stop-off location of the user included in the user's travel route and stay time information indicating the time the user stayed at each stop-off location in association with travel status identification information that identifies the travel status and weekday information indicating the day of the week corresponding to the travel status. Location information P[*] is information indicating the location coordinates of the stop-off location. The stay time information includes arrival time information indicating the time the user arrived at each stop-off location on Wednesday, and departure time information indicating the time the user departed from that location. For example, the travel status information identified by the travel status identification information " _a2 " indicates that the user left home corresponding to location information P[0] at 8:00, arrived at the workplace corresponding to location information P[1] at 9:00, stayed there until 17:00, then passed through the nearest station corresponding to location information P[2], stayed at a nearby supermarket corresponding to location information P[3] from 18:20 to 18:50, and returned home at 19:10.

Returning to Figure 4, the viewing history storage unit 134 stores information indicating the viewing history of programs viewed by the user on the television receiver 91. As shown in Figure 6, for example, the viewing history storage unit 134 stores, in chronological order, program identification information of programs viewed by the user, day of the week information indicating the day on which the program was aired, start time information and end time information indicating the start and end times of the program's airing, and program type information indicating the type of program, all in association with one another. The example shown in Figure 6 indicates that the user watched a news program that aired from 7:00 to 8:00 on Monday.

Returning to FIG. 4, the model storage unit 135 stores route estimation model information indicating a route estimation model for estimating a route to return home from location information of stop-off locations where the user has stopped off and day-of-week information indicating the day of the week on which the user stopped off at the stop-off locations. The route estimation model is, for example, a recurrent neural network. In this case, the model storage unit 135 stores information indicating the structure of the route estimation model and information indicating weighting coefficients in the route estimation model. The information indicating the structure of the route estimation model includes information indicating the number of nodes and layers of the route estimation model, as well as weighting coefficients and activation functions corresponding to each node. Here, the weighting coefficients include weighting coefficients used when feeding back the output from the layer to which each node belongs to the input. This route estimation model has an input layer L110, a hidden layer L120, and an output layer L130, as shown in FIG. 7(A). Day-of-week information indicating the day of the week on which the user stopped off at a stop-off location and location information indicating the location at which the user stopped off are input to the input layer L110.

The hidden layer L120 is composed of three layers, each containing a preset number N[j] of nodes y[j,i,t] (1≦i≦N[j], N[j] is a positive integer). Here, the output y[2,j,t] of each node, excluding the node immediately after the input layer L110 and the node immediately before the output layer L130, is expressed by the following relational expression (1).
...Formula (1)
Here, w _in [k,i] and w _feedback [k,j] are weighting coefficients, and f(*) is an activation function. Furthermore, t is a positive integer reflecting the number of places visited by the user. As described above, nonlinear functions such as sigmoid functions, ramp functions, and step functions are used as activation functions. The output of each node at the t-th estimation is the output of an activation function whose arguments are the sum of the outputs of multiple nodes belonging to the layer preceding the layer to which the node belongs at the t-th estimation, multiplied by a weighting coefficient, and the sum of the outputs of multiple nodes belonging to the same layer as the node at the immediately preceding (t-1)-th estimation, multiplied by a weighting coefficient. Based on the outputs from nodes belonging to the final layer of the hidden layer L120, the output layer L130 outputs an expectation vector whose elements are the expected values for multiple types of travel routes, i.e., combinations of stopovers. Here, the output layer L130 performs processing using, for example, a softmax function.

The model storage unit 135 also stores home-coming time estimation model information, which indicates a home-coming time estimation model for estimating the user's home-coming time based on location information included in the user's travel route, stay period information indicating the user's stay period at at least one stop-off location included in the travel route, and day-of-week information indicating the day of the week on which the user travels along the travel route. The home-coming time estimation model is, for example, a forward propagation neural network. In this case, the model storage unit 135 stores, similar to the route estimation model, information indicating the structure of the home-coming time estimation model and information indicating weighting coefficients in the home-coming time estimation model. Here, the information indicating the structure of the home-coming time estimation model includes information indicating the number of nodes and layers of the home-coming time estimation model, as well as the weighting coefficients and activation functions corresponding to each node. This home-coming time estimation model has an input layer L210, a hidden layer L220, and an output layer L230, as shown in Figure 7(B). The input layer L210 receives location information for at least one stop-off location included in the user's travel route, stay period information for each stop-off location, and day-of-week information.

The hidden layer L220 is composed of N (N is a positive integer) layers, each containing a preset number M[j] of nodes x[j,i] (1≦i≦M[j], M[j] is a positive integer). That is, the hidden layer L220 has a structure in which each node column is connected to another. Here, the output y[j,i] of each node x[j,i] is expressed by the relational expression (2) below.
...Formula (2)
Here, W[j,i,k] denotes a weighting coefficient, and f(*) denotes an activation function. A nonlinear function such as a sigmoid function, a ramp function, or a step function is used as the activation function. In the hidden layer L220, the information input to the node is the sum of the outputs of each node in the previous layer multiplied by a weighting coefficient. The output of the activation function, which uses the sum as an argument, is then transmitted to the next layer. The output layer L230 outputs the time of return home when the expected value is maximized based on the output y[j,i] from the final layer of the hidden layer L220. Here, the output layer L230 performs processing using, for example, a softmax function.

Returning to Figure 4, the location information acquisition unit 111 acquires the location information and time information of the terminal device 5 that are periodically notified by the location management server 2, and stores the acquired location information and time information in the location storage unit 131 in association with user identification information that identifies the user.

Each time a predetermined stopover location identification period arrives, the location identification unit 112 identifies at least one stopover location where the user will stop based on the user's location information and the user's stay time at the location indicated by the location information during a predetermined location identification period for identifying the user's stopover locations. For example, when a predetermined reference time or more has elapsed while the distance traveled over time by the terminal device 5 remains below a predetermined reference distance, the location identification unit 112 identifies, as a stopover location, a circular range of position coordinates centered on the center position of the terminal device 5 during that reference time, with a diameter equal to the reference distance. Here, the reference distance is set, for example, to 100 m, and the reference time is set, for example, to 5 minutes. The location identification period is set, for example, to the most recent month. In this case, the location identification unit 112 identifies, as a stopover location, a circular range of position coordinates with a diameter of 100 m corresponding to a location where the user stayed within the 100 m diameter circular area for 5 minutes or more during the most recent month. The location identification unit 112 associates location information indicating the identified user's stop-off locations with user identification information that identifies the user and stores the information in the location storage unit 132.

The movement status determination unit 113 determines the movement status of the user based on the user's stay time at each of the user's stopover locations. Specifically, the movement status determination unit 113 references location information for at least one of the user's stopover locations stored in the location memory unit 132, and determines that the terminal device 5 has arrived at a stopover location when the location of the terminal device 5 indicated by the most recent location information stored in the location memory unit 131 transitions from being outside the range of the location coordinates of the stopover location to being within the range of the location coordinates. The movement status determination unit 113 also determines the time of arrival at the stopover location based on the time information corresponding to the location information stored in the location memory unit 131. On the other hand, the movement status determination unit 113 determines that the terminal device 5 has departed from a stopover location when the location of the terminal device 5 indicated by the most recent location information stored in the location memory unit 131 transitions from being within the range of the location coordinates of the stopover location to being outside the range of the location coordinates. Furthermore, the travel status determination unit 113 determines the time of departure from the stop-off location based on the time information corresponding to the location information. Then, each time the user departs from or arrives at one of the stop-off locations, the travel status determination unit 113 associates information indicating the center position coordinates of the range of position coordinates of that stop-off location and time information indicating the time of departure or arrival of the user with the travel route identification information and stores them in chronological order in the travel status storage unit 133. Furthermore, when the travel status determination unit 113 determines that the user has arrived home, it notifies the return home notification unit 114 of return home notification information. Then, when the return home notification unit 114 is notified of the return home notification information by the travel status determination unit 113, it notifies the model generation unit 121 of the return home notification information and transmits it to the location management server 2.

The estimation unit 115 uses the route estimation model described above to estimate the user's travel route based on location information for the stopover locations visited by the user and day-of-week information indicating the day of the week on which the user visited the stopover locations. Specifically, each time the estimation unit 115 determines that the user has arrived at a stopover location, it uses the route estimation model indicated by the route estimation model information stored in the model storage unit 135 to calculate the expected value of each of multiple travel routes from the stopover locations to the user's home location, based on location information indicating each of at least one stopover location visited by the user after leaving home and before arriving at the stopover location, and day-of-week information indicating the day of the week on which the user visited each stopover location. Here, a travel route corresponds to a collection of location information indicating at least one stopover location visited by the user on the way home from the stopover locations visited by the user. The estimation unit 115 then estimates the travel route with the largest calculated expected value as the travel route to be taken by the user. For example, suppose that on Wednesday, the user travels from location P[0] (home), to location P[1] (workplace), to location P[2] (nearest station), and arrives at location P[2] (nearest station). In this case, the estimation unit 115 estimates that the travel route taken by the user is, for example, from location P[3] (supermarket) to home P[0].

The estimation unit 115 also estimates the user's time of return home using the aforementioned home-coming time estimation model based on location information corresponding to the estimated travel route, stay period information indicating the time of stay at each stop-off location, and day-of-week information indicating the day of the week on which the user stopped at each stop-off location. Specifically, the estimation unit 115 uses the aforementioned home-coming time estimation model stored in the model storage unit 135 to calculate the expected value of the user's return home at each time in the time slot after the user arrives at or departs from the stop-off location based on location information corresponding to the determined travel route, stay period information indicating the time of stay at each stop-off location indicated by the determined travel route, and day-of-week information indicating the day of the week on which the user stopped at each stop-off location. The estimation unit 115 then estimates the time with the largest calculated expected value as the user's time of return home, and notifies the notification determination unit 116 of the expected value of the user's return home, indicating the estimated time of return home. For example, if the arrival time at location P[2] (nearest station) on Wednesday is "18:00", and the estimation unit 115 estimates that the user's travel route from location P[2] (nearest station) to home is one that passes through location P[3] (supermarket) and then returns to home P[0], the estimation unit 115 estimates the return home time to be "19:10".

The program selection unit 117 selects programs that belong to the same program type as the program type of at least one program that the user has viewed in the past and that the user likes. Specifically, the program selection unit 117 searches the program identification information stored in the viewing history storage unit 134 for program identification information that is of the same program type and that appears on the same day of the week as the day the user stopped by the stop-off location, and if such program identification information is found, it selects that program identification information and the start time information and end time information for that program. The program selection unit 117 then notifies the notification determination unit 116 of the selected program identification information, start time information, and end time information.

The notification determination unit 116 compares the time of arrival home indicated by the arrival home time information notified by the estimation unit 115 with the start time of the program indicated by the start time information notified by the program selection unit 117. If the user's arrival home time is before the program start time and the time difference between the user's arrival home time and the program start time is less than or equal to a predetermined first time difference threshold and greater than a predetermined second time difference threshold, the notification determination unit 116 determines to transmit program information to the user's terminal device 5. The first time difference threshold is a criterion for avoiding transmission of program information to the terminal device 5 for programs for which the time between the user's arrival home time and the program start time is long and there is no need to notify the user of program information while the user is traveling, and is set to, for example, one hour. The second time difference threshold can be determined, for example, based on the variance of the user's arrival home time when traveling the same route in the past, and is set to, for example, five minutes. If the user's arrival time is before the program start time and the time from the user's arrival time to the program start time is less than a preset second time difference threshold, or if the user's arrival time is after the program start time, the notification determination unit 116 determines to send to the terminal device 5 recording necessity inquiry information to inquire of the user about whether or not to record the program. On the other hand, if the user's arrival time is before the program start time and the time from the user's arrival time to the program start time is greater than a preset first time difference threshold, the notification determination unit 116 determines to avoid sending program information and recording necessity inquiry information to the terminal device 5.

When the notification determination unit 116 determines that program information should be sent to the terminal device 5 carried by the user, the program notification unit 118 generates program information for the program identified by the program identification information selected by the program selection unit 117 and sends it to the terminal device 5. Furthermore, when the notification determination unit 116 determines that the above-mentioned recording necessity inquiry information should be sent to the terminal device 5, the program notification unit 118 generates recording necessity inquiry information to inquire about the necessity of recording the program identified by the program identification information selected by the program selection unit 117 and sends it to the terminal device 5.

When the viewing history acquisition unit 119 acquires viewing history information transmitted from the television receiver 91 or the recording device 92, it associates the program identification information, day of the week information, start time information, end time information, and program type information contained in the acquired viewing history information with each other and stores them in the viewing history storage unit 134. When the device control unit 120 acquires operation information transmitted from the terminal device 5, it generates control information for causing the recording device 92 to execute a recording reservation process based on the acquired operation information. The device control unit 120 then transmits the generated control information to the recording device 92.

Each time it is determined that the user has returned home, the model generation unit 121 generates route estimation model information indicating a route estimation model using location information indicating the user's stopover locations, stay time information, and day of the week information. Here, the model generation unit 121 generates route estimation model information indicating a new route estimation model, for example, using the BPTT (Back Propagation Through Time) method. Specifically, the model generation unit 121 first uses the route estimation model stored in the model storage unit 135 to calculate expected values for each travel route, which is a combination of location information and stay time information, from a point in time going back a predetermined number of estimations from the most recent estimation to the most recent estimation, based on the location information, stay time information, and day of the week information. Next, the model generation unit 121 sets expected values so that the expected values of the travel routes corresponding to each time going back a predetermined number of estimations from the most recent estimation to the most recent estimation, stored in the travel status storage unit 133, are higher than the expected values of other travel routes. For example, the model generation unit 121 sets the expected value of the most recent movement route stored in the movement status storage unit 133 to a number greater than 0, and sets the expected values of other movement routes to "0." Next, the model generation unit 121 calculates the error between the expected value calculated using the route estimation model and the expected value of the most recent movement route stored in the movement status storage unit 133. The model generation unit 121 then determines a weighting coefficient for the route estimation model using the BUTT method based on the calculated error, and updates the route estimation model information stored in the model storage unit 135 with route estimation model information including information indicating the determined weighting coefficient.

Furthermore, each time it is determined that the user has returned home, the model generation unit 121 generates home-home time estimation model information indicating a home-home time estimation model using the most recent user location information, stay period information, and day of the week information stored in the movement status storage unit 133, and home-home time information indicating the user's actual home-home time. Specifically, the model generation unit 121 first calculates the expected value of the user's return home at each time, based on the most recent user location information, stay period information, and day of the week information, using the home-home time estimation model indicated by the home-home time estimation model information stored in the model storage unit 135. Next, the model generation unit 121 sets the Q value so that the expected value of the home-home time indicated by the most recent home-home time information stored in the movement status storage unit 133 is higher than the expected values of other times. For example, the model generation unit 121 sets the expected value of the most recent home-home time stored in the movement status storage unit 133 to a number greater than 0, and sets the expected values of other times to "0." The model generation unit 121 then calculates the error between the expected value calculated using the home-coming time estimation model and the expected value set for the home-coming time indicated by the most recent home-coming time information stored in the movement status storage unit 133. The model generation unit 121 then determines a weighting coefficient for the home-coming time estimation model using backpropagation based on the calculated error, and updates the home-coming time estimation model information stored in the model storage unit 135 with information indicating the determined weighting coefficient.

Next, the operation of the information provision system according to this embodiment will be described with reference to Figures 8 to 11. Note that in Figures 8 to 11, the relay process at the relay server 3 is omitted for communications between the terminal device 5 and the cloud server 1 via the relay server 3. As shown in Figure 8, first, when a preset location information acquisition time arrives, location information request information requesting the terminal device 5 to transmit location information of the terminal device 5 is transmitted from the location management server 2 to the terminal device 5 (step S1). Meanwhile, upon receiving the location information request information, the terminal device 5 generates location information for the terminal device 5 (step S2). Next, the generated location information is transmitted from the terminal device 5 to the location management server 2 (step S3). Here, the location management server 2 manages the location information acquired from the terminal device 5 in association with terminal device identification information that identifies the terminal device 5.

Here, assume that the location of terminal device 5 transitions from a state where it is inside a predetermined area including the user's home to a state where it is outside, and location management server 2 determines that the user has gone out carrying terminal device 5 (step S4). In this case, when the predetermined location information transmission time arrives, location information of terminal device 5 is transmitted from location management server 2 to cloud server 1 (step S5). Meanwhile, upon acquiring location information from location management server 2, cloud server 1 determines the user's movement status based on the acquired location information. Then, when cloud server 1 determines that the user has arrived at or departed from a location included in the movement route, it generates movement status information based on the acquired location information and time information notified by timing unit 107 and stores it in movement status storage unit 133 (step S6). Thereafter, the series of processes in steps S5 and S6 are executed each time the location information transmission time arrives.

Next, the preset location information transmission time arrives, and the location information of the terminal device 5 is transmitted from the location management server 2 to the cloud server 1 (step S7). The cloud server 1 determines the user's movement status based on the location information obtained from the location management server 2, generates movement status information, and stores it in the movement status storage unit 133 (step S8). The cloud server 1 then determines that the user has arrived at a stopover location (step S9). In this case, the cloud server 1 uses the aforementioned route estimation model to estimate the user's movement route, i.e., the combination of the user's stopover locations and the time of stay (step S10). The cloud server 1 then uses the aforementioned return-home time estimation model to estimate the user's return-home time if the user takes the estimated movement route (step S11). Next, the cloud server 1 selects programs that belong to the same program type as at least one program that the user has viewed in the past and that is preferred by the user (step S12). Next, let's assume that the cloud server 1 determines that the user's return home time is before the program start time and that the time difference ΔT between the user's return home time and the program start time is less than or equal to the first time difference threshold ΔTth1 and greater than the second time difference threshold ΔTth2 (step S13). In this case, as shown in FIG. 9, the cloud server 1 generates program information for the selected program (step S14), and the generated program information is transmitted from the cloud server 1 to the terminal device 5 (step S15). Meanwhile, upon acquiring the program information, the terminal device 5 generates a program introduction image including the acquired program information and displays it on the display unit 504 (step S16).

Furthermore, after the aforementioned location information transmission time arrives and the series of processes from steps S7 to S12 are executed, the cloud server 1 determines that the user's return home time is before the program start time and that the time difference ΔT between the user's return home time and the program start time is less than or equal to the aforementioned second time difference threshold ΔTth2 (step S17). In this case, the cloud server 1 generates recording necessity inquiry information for the selected program (step S18), and the generated recording necessity inquiry information is transmitted from the cloud server 1 to the terminal device 5 (step S19). Meanwhile, upon receiving the recording necessity inquiry information, the terminal device 5 generates a recording necessity inquiry image including the program information of the program being queried about that is included in the obtained recording necessity inquiry information, and displays the image on the display unit 504 (step S20).

Here, assume that a user performs a recording request operation via the input unit 505 of the terminal device 5 to cause the recording device 92 to execute a recording reservation process for the program in question. In this case, the terminal device 5 generates operation information indicating the operation for making the recording request (step S21), and the generated operation information is transmitted from the terminal device 5 to the cloud server 1 (step S22). Meanwhile, as shown in FIG. 10, upon acquiring the operation information, the cloud server 1 generates control information for causing the recording device 92 to execute the recording reservation process based on the acquired operation information (step S23). The generated control information is then transmitted from the cloud server 1 to the recording device 92 (step S24). Meanwhile, upon acquiring the control information, the recording device 92 executes the recording reservation process using the acquired control information (step S25). Thereafter, when the program start time of the program for which recording has been reserved arrives, the recording device 92 starts recording (step S26). When the end time of the scheduled program arrives, the recording device 92 ends the recording (step S27) and generates viewing history information including the program identification information, day of the week information, start time information, end time information, and program type information of the recorded program (step S28). The generated viewing history information is then transmitted from the recording device 92 to the cloud server 1 (step S29). Meanwhile, upon acquiring the viewing history information, the cloud server 1 associates the program identification information, day of the week information, start time information, end time information, and program type information contained in the acquired viewing history information with each other and stores them in the viewing history storage unit 134 (step S30).

Furthermore, after the aforementioned time to send location information arrives, and the series of processes in steps S7 and S8 are executed, the cloud server 1 determines that the user has returned home (step S31). In this case, the aforementioned homecoming notification information is sent from the cloud server 1 to the location management server 2 (step S32). Here, upon receiving the homecoming notification information, the location management server 2 stops the periodic transmission of the terminal device 5's location information to the cloud server 1.

Next, as shown in FIG. 11, the cloud server 1 generates route estimation model information indicating a route estimation model using location information indicating the user's stopover locations, stay period information, and day of the week information, and updates the route estimation model information already stored in the model storage unit 135 with the generated route estimation model information (step S33). After that, the cloud server 1 generates home-coming time estimation model information indicating a home-coming time estimation model using the user's most recent location information, stay period information, day of the week information, and home-coming time information indicating the user's actual home-coming time stored in the movement status storage unit 133, and updates the home-coming time estimation model information already stored in the model storage unit 135 with the generated home-coming time estimation model information (step S34).

When the user manually performs a viewing start operation to start viewing, the television receiver 91 starts displaying video (step S35). Then, when the user manually performs a viewing end operation to end viewing, the television receiver 91 ends video display (step S36). The television receiver 91 then performs a viewing time counting process to count the viewing time of at least one program viewed by the user (step S37) and identifies programs that the user continued watching for a predetermined reference time or longer (step S38). Next, the television receiver 91 generates viewing history information for the identified programs, including program identification information, day of the week information, start time information, end time information, and program type information (step S39), and transmits the generated viewing history information from the television receiver 91 to the cloud server 1 (step S40). Meanwhile, upon acquiring the viewing history information, the cloud server 1 associates the program identification information, day of the week information, start time information, end time information, and program type information contained in the acquired viewing history information with each other and stores them in the viewing history storage unit 134 (step S41).

Furthermore, when a preset stop-off place identification period arrives, the cloud server 1 identifies as a stop-off place a location where the user's location information during the aforementioned location identification period and the user's stay time ΔTs at the location indicated by the location information are equal to or greater than a preset reference time ΔTsth (step S42). Next, the cloud server 1 updates the location information already stored in the location memory unit 132 with the location information indicating the identified stop-off place of the user (step S43). After that, the cloud server 1 generates route estimation model information indicating a route estimation model using the updated location information, stay period information, and day of the week information, and updates the route estimation model information already stored in the model memory unit 135 with the generated route estimation model information (step S44).

Next, the information provision process executed by the cloud server 1 according to this embodiment will be described with reference to Figures 12 and 13. This information provision process is initiated, for example, when a program for executing the information provision process is started in the cloud server 1. First, the location information acquisition unit 111 determines whether or not it has acquired location information and time information transmitted from the location management server 2 (step S101). If the location information acquisition unit 111 determines that it has not yet acquired location information and time information (step S101: No), the process of step S103, described below, is executed. On the other hand, if the location information acquisition unit 111 determines that it has acquired location information and time information (step S101: Yes), it associates the location information and time information with each other and stores them in the location storage unit 131. The travel status determination unit 113 then determines the user's travel status based on the location information stored in the location memory unit 131 and the location information stored in the location memory unit 132. If the travel status determination unit 113 determines that the user has arrived at or departed from a stop-off location, it generates travel status information consisting of location information indicating the stop-off location, arrival time information indicating the arrival time, departure time information, and departure time information. The travel status determination unit 113 then stores the generated travel status information in the travel status memory unit 133 (step S102). Next, the travel status determination unit 113 determines whether the user has arrived at the stop-off location based on the generated travel status information (step S103). If the travel status determination unit 113 determines that the user has not yet arrived at the stop-off location (step S103: No), the process of step S113, described below, is executed.

On the other hand, if the travel status determination unit 113 determines that the user has arrived at a stopover location (step S103: Yes), the estimation unit 115 uses the above-mentioned route estimation model to estimate the user's travel route, i.e., a combination of stopover locations that the user will stop at, based on location information for the stopover locations where the user has stopped and day-of-week information indicating the days of the week on which the user stopped at the stopover locations (step S104). Next, the estimation unit 115 uses the above-mentioned return-home time estimation model to estimate the user's return-home time based on the combination of location information indicating the stopover locations where the user will stop, indicated by the estimated travel route, stay period information indicating the stay period at each stopover location indicated by the determined travel route, and day-of-week information indicating the days of the week on which the user stopped at the stopover locations (step S105). Thereafter, the program selection unit 117 selects programs that belong to the same program type as at least one program that the user has viewed in the past and that is preferred by the user (step S106).

Next, the notification determination unit 116 determines whether the user's arrival time Tre is before the program start time Tst and whether the time difference ΔT between the user's arrival time Tre and the program start time Tst is less than or equal to the first time difference threshold ΔTth1 and greater than the second time difference threshold ΔTth2 (step S107). If the notification determination unit 116 determines that the arrival time Tre is before the program start time Tst and the time difference ΔT is less than or equal to the first time difference threshold ΔTth1 and greater than the second time difference threshold ΔTth2 (step S107: Yes), it determines to transmit program information to the terminal device 5 possessed by the user. Then, the program notification unit 118 generates program information for the program identified by the program identification information selected by the program selection unit 117 and transmits it to the terminal device 5 (step S108), after which the processing of step S111 described below is executed.

On the other hand, suppose the notification determination unit 116 determines that the arrival time Tre of the user home is before the program start time Tst and the time difference ΔT is greater than the first time difference threshold ΔTth1, or that the time difference ΔT is less than or equal to the second time difference threshold ΔTth1, or that the arrival time Tre of the user home is after the program start time Tst (step S107: No). In this case, the notification determination unit 116 determines whether the arrival time Tre of the user home is before the program start time Tst and the time difference ΔT from the arrival time Tre of the user home to the program start time Tst is less than or equal to the second time difference threshold ΔTth2, or whether the arrival time Tre of the user home is after the program start time Tst (step S109). Here, suppose the notification determination unit 116 determines that the arrival time Tre of the user home is before the program start time Tst and the time difference ΔT from the arrival time Tre of the user home to the program start time Tst is greater than the first time difference threshold ΔTth1 (step S109: No). In this case, the program notification unit 118 avoids sending the program information to the terminal device 5, and the processing of step S113 described below is executed. Meanwhile, the notification determination unit 116 determines that the arrival time Tre is before the program start time Tst and the time difference ΔT between the user's arrival time Tre and the program start time Tst is less than or equal to the second time difference threshold ΔTth2 described above, or that the arrival time Tre is after the program start time Tst (step S109: Yes). In this case, the program notification unit 118 generates recording necessity inquiry information to inquire about the need to record the program identified by the program identification information selected by the program selection unit 117, and transmits this information to the terminal device 5 (step S110).

Next, the device control unit 120 determines whether or not it has acquired operation information transmitted from the terminal device 5 (step S111). If the device control unit 120 determines that it has acquired operation information transmitted from the terminal device 5 (step S111: Yes), it generates control information for causing the recording device 92 to execute a recording reservation process based on the acquired operation information, and transmits the generated control information to the recording device 92 (step S112).

Then, the movement status determination unit 113 determines whether the user has returned home based on the generated movement status information (step S113). If the movement status determination unit 113 determines that the user has not yet returned home (step S113: No), the processing of step S117 described below is executed. On the other hand, if the movement status determination unit 113 determines that the user has returned home (step S113: Yes), the return home notification unit 114 sends return home notification information to the location management server 2 (step S114). Next, the model generation unit 121 generates route estimation model information indicating a route estimation model using the location information, stay period information, and day of the week information indicating the above-mentioned user's stopover locations, and updates the route estimation model information already stored in the model storage unit 135 with the generated route estimation model information (step S115). Next, the model generation unit 121 generates home-coming time estimation model information that indicates a home-coming time estimation model, using the user's most recent location information, stay period information, day of the week information, and home-coming time information that indicates the user's actual home-coming time stored in the movement status storage unit 133. The model generation unit 121 then updates the home-coming time estimation model information already stored in the model storage unit 135 with the generated home-coming time estimation model information (step S116).

Next, as shown in FIG. 13, the viewing history acquisition unit 119 determines whether or not viewing history information transmitted from the television receiver 91 or the recording device 92 has been acquired (step S117). If the viewing history acquisition unit 119 determines that viewing history information has not been acquired (step S117: No), the processing of step S119, described below, is executed. On the other hand, if the viewing history acquisition unit 119 determines that viewing history information has been acquired (step S117: Yes), it associates the program identification information, day of the week information, start time information, end time information, and program type information contained in the acquired viewing history information with each other and stores them in the viewing history storage unit 134 (step S118).

Next, the location identification unit 112 determines whether the aforementioned stop-off place identification period has arrived (step S119). If the location identification unit 112 determines that the stop-off place identification period has not yet arrived (step S119: No), the process of step S101 is executed again. On the other hand, if the location identification unit 112 determines that the stop-off place identification period has arrived (step S119: Yes), the location identification unit 112 references the location information stored in the location memory unit 131 and identifies as a stop-off place a location where the user's location information during the aforementioned location identification period and the user's stay time ΔTs at the location indicated by the location information are equal to or greater than a predetermined reference time ΔTsth (step S120). Then, the location identification unit 112 updates the location information already stored in the location memory unit 132 with the location information indicating the identified user's stop-off place (step S121). Next, the model generation unit 121 generates route estimation model information indicating a route estimation model using the updated location information, stay period information, and day of the week information, and updates the route estimation model information already stored in the model storage unit 135 with the generated route estimation model information (step S122). Then, the processing of step S101 is executed again.

As described above, according to the cloud server 1 of this embodiment, the estimation unit 115 estimates the user's travel route using a route estimation model, and estimates the user's time of return home from the estimated travel route using a return home time estimation model. Furthermore, the program selection unit 117 selects programs that belong to the same program type as the program type of at least one program that the user has previously viewed and that the user prefers. Then, when the notification determination unit 116 determines that program information for programs of the program type should be sent to the terminal device 5 carried by the user, the program notification unit 118 sends the program information to the terminal device 5 carried by the user. This makes it possible to provide the user with program information for the user's preferred programs according to the user's time of return home, thereby making it possible to guide the user to programs that the user prefers according to the user's location and behavioral patterns.

However, if a user living in building H does not know in advance the broadcast date and time of a program of their choice, for example, they may be out during the broadcast time and be unable to watch their favorite program. In contrast, the information provision system of this embodiment can guide users to their favorite programs based on their location and behavioral patterns. Therefore, even if a user goes out without knowing in advance the broadcast date and time of a program of their choice, they can find out the program's broadcast time while they are out and act accordingly.

Furthermore, the notification determination unit 116 according to this embodiment determines to transmit program information to the terminal device 5 if the user's arrival time is before the start time of the selected program and the time difference between the user's arrival time and the program start time is equal to or less than a preset first time difference threshold and greater than a preset second time difference threshold. As a result, the user is notified of program information if the time difference between the user's arrival time and the program start time is an appropriate length, allowing the user to be notified of appropriate program information.

Furthermore, in this embodiment, the notification determination unit 116 determines to send recording necessity inquiry information to the terminal device to inquire about whether the user needs to record the program if the user's arrival time is before the start time of the selected program and the time difference between the arrival time and the program start time is equal to or less than the second time difference threshold, or if the user's arrival time is after the program start time. The program notification unit 118 then sends the recording necessity inquiry information to the terminal device 5. Furthermore, upon acquiring operation information, the device control unit 120 generates control information for causing the recording device 92 to record the selected program based on the operation information and transmits it to the recording device 92. This allows the user to inquire about whether the program needs to be recorded if there is a possibility that the user will not be able to return home by the program start time, and the user can have the recording device 92 record the program via the terminal device 5. In other words, if the user learns the start time of their favorite program while on the way home, they can record the program on the spot if they will not be able to return home by the program start time. This prevents the user from missing a program they want to watch.

(Embodiment 2)
The information providing device of this embodiment differs from the information providing device of embodiment 1 in that the estimation unit estimates the user's time of return home and the program that the user will watch using a return home time program estimation model that estimates the user's time of return home and the program type of at least one program that the user prefers based on the stay period at at least one stop-off point included in the estimated travel route, and the program that belongs to the same program type.

The hardware configuration of the cloud server according to this embodiment is the same as the hardware configuration of the cloud server 1 according to embodiment 1 shown in FIG. 2. Hereinafter, the hardware configuration according to this embodiment will be described using the same reference numerals as those used in the description of embodiment 1. As shown in FIG. 14, the CPU 101 of the cloud server 2001 reads programs stored in the auxiliary storage unit 103 into the main storage unit 102 and executes them, thereby functioning as a position information acquisition unit 111, a location identification unit 112, a movement status determination unit 113, a homecoming notification unit 114, an estimation unit 2115, a notification determination unit 2116, a program notification unit 118, a viewing history acquisition unit 2119, a device control unit 120, and a model generation unit 2121. Note that in FIG. 14, components similar to those in embodiment 1 are denoted by the same reference numerals as in FIG. 4. Furthermore, the auxiliary storage unit 103 has a position memory unit 131, a location memory unit 132, a movement status memory unit 133, a viewing history memory unit 2134, and a model memory unit 2135.

The viewing history storage unit 2134 stores information indicating the viewing history of programs viewed by the user on the television receiver 91, in association with travel situation identification information that identifies the user's travel situation immediately before the user viewed the program or the user's travel situation when the program was scheduled for recording. As shown in FIG. 15 , for example, the viewing history storage unit 2134 stores, in chronological order, the program identification information of the program viewed by the user, day of the week information indicating the day on which the program was aired, start time information and end time information indicating the start and end times of the program, and program type information indicating the type of the program, in association with the travel situation identification information. The example shown in FIG. 15 indicates that the user's travel situation on Monday was identified by travel situation identification information "a ₀ ," and that the user watched a news program that aired from 7:00 to 8:00 that day.

Returning to FIG. 14, the model storage unit 2135, similar to the model storage unit 135 described in embodiment 1, stores route estimation model information indicating a route estimation model for estimating a travel route from location information of stop-off locations visited by the user and day-of-week information indicating the day of the week on which the user stopped at the stop-off locations. The model storage unit 2135 also stores home-time program estimation model information indicating a home-time program estimation model for estimating the user's home-time and a program belonging to the same program type as the program type of at least one program preferred by the user, based on location information included in the estimated user's travel route, stay period information indicating the time the user will stay at at least one stop-off location included in the travel route, and weekday information indicating the day of the week on which the user will travel along the travel route. The home-time program estimation model is, for example, a forward propagation neural network and has a structure similar to the home-time estimation model described in embodiment 1. Here, the output layer outputs the combination of home-time and program with the largest expected value based on the output from the final hidden layer. The model storage unit 2135 also stores at least one combination of route estimation model information and home time program estimation model information in association with terminal device identification information that identifies the corresponding terminal device 5.

Each time it is determined that the user has arrived at a stop-off location, the estimation unit 2115 selects a combination corresponding to the terminal identification information of the terminal device 5 possessed by the user from among at least one combination of route estimation model information and home time program estimation model information stored in the model storage unit 2135. The estimation unit 2115 then estimates the user's travel route using the selected route estimation model based on location information of the stop-off locations visited by the user and day of the week information indicating the day of the week on which the user stopped at the stop-off locations. The estimation unit 2115 also estimates a combination of the user's home time and program using the selected home time program estimation model based on location information corresponding to the estimated travel route, stay period information indicating the stay period at each stop-off location, and day of the week information indicating the day of the week on which the user stopped at the stop-off locations. Specifically, the estimation unit 2115 uses the location information corresponding to the determined travel route, information on the stay period at each stop-off location indicated by the determined travel route, and information on the day of the week on which the user stopped at each stop-off location to calculate the expected value for each combination of times and programs before and after each time in the time period after the time the user arrives at or departs from the stop-off location, using the aforementioned home-coming time program estimation model stored in the model storage unit 2135. The estimation unit 2115 then determines the combination of time and program with the largest calculated expected value as the combination of the user's home-coming time and the user's preferred program, and notifies the notification determination unit 2116 of the determined home-coming time, home-coming time information indicating the program, and program identification information.

The notification determination unit 2116 identifies the start time information corresponding to the program identification information notified by the estimation unit 2115 from the start time information stored in the viewing history storage unit 2134. The notification determination unit 2116 then compares the homecoming time indicated by the homecoming time information notified by the estimation unit 2115 with the program start time indicated by the identified start time information. If the user's homecoming time is before the program start time and the time difference between the user's homecoming time and the program start time is less than or equal to a predetermined first time difference threshold and greater than a predetermined second time difference threshold, the notification determination unit 2116 determines to transmit program information to the terminal device 5 possessed by the user. Furthermore, if the user's homecoming time is before the program start time and the time between the user's homecoming time and the program start time is less than the predetermined second time difference threshold or the user's homecoming time is after the program start time, the notification determination unit 2116 determines to transmit recording necessity inquiry information to the terminal device 5 to inquire about the user's need to record the program. On the other hand, if the user's return home time is before the program start time and the time between the user's return home time and the program start time is greater than a preset first time difference threshold, the notification determination unit 2116 determines to avoid sending program information and recording necessity inquiry information to the terminal device 5.

When the viewing history acquisition unit 2119 acquires viewing history information transmitted from the television receiver 91 or recording device 92, it identifies the most recent movement status information at the time the viewing history information was acquired from the movement status information stored in the movement status memory unit 133. The viewing history acquisition unit 2119 then associates the program identification information, day of the week information, start time information, end time information, and program type information contained in the acquired viewing history information with the movement status identification information that identifies the identified movement status information, and stores them in the viewing history memory unit 2134.

Similar to the model generation unit 121 described in embodiment 1, each time it is determined that the user has returned home, the model generation unit 2121 generates route estimation model information indicating a route estimation model using location information indicating the user's stopover locations, stay period information, and day of the week information. The model generation unit 2121 then stores the generated route estimation model information in the model storage unit 2135. Furthermore, each time it is determined that the user has returned home, the model generation unit 2121 generates home time estimation model information indicating a home time program estimation model using the user's most recent location information, stay period information, and day of the week information stored in the movement status storage unit 133, home time information indicating the user's actual home time, and program identification information. Specifically, the model generation unit 2121 first calculates the expected value for each combination of time and program from the user's most recent location information, stay period information, and day of the week information, using the home time program estimation model indicated by the home time program estimation model information stored in the model storage unit 2135. Next, the model generation unit 2121 sets the expected value of the combination of the time of arrival home indicated by the most recent information about the time of arrival home stored in the travel status storage unit 2133 and the program actually viewed by the user after arriving home stored in the viewing history storage unit 2134 to be higher than the expected values of combinations of other times and programs. For example, the model generation unit 2121 sets the expected value of the most recent time of arrival home stored in the travel status storage unit 2133 and the program viewed by the user after arriving home to a number greater than 0, and sets the expected values of other times and programs to "0." Then, the model generation unit 2121 calculates the error between the expected value calculated using the home time program estimation model and the expected value set for the combination of the time of arrival home indicated by the most recent information about the time of arrival home stored in the travel status storage unit 2133 and the program actually viewed by the user after arriving home stored in the viewing history storage unit 2134. The model generation unit 2121 then determines the weighting coefficients for the home-coming time program estimation model using backpropagation based on the calculated errors, and updates the home-coming time program estimation model information stored in the model storage unit 2135 with the home-coming time program estimation model information including information indicating the determined weighting coefficients.

Next, the information provision processing executed by the cloud server 2001 according to this embodiment will be described with reference to Figures 16 and 17. Note that in Figures 16 and 17, processing similar to that in embodiment 1 is assigned the same reference numerals as in Figures 12 and 13. First, after a series of processing steps S101 and S102 are executed, the travel status determination unit 113 determines whether the user has arrived at the stop-off location as described above (step S103). Here, if the travel status determination unit 113 determines that the user has not yet arrived at the stop-off location (step S103: No), the processing of step S113 described below is executed. On the other hand, if the travel status determination unit 113 determines that the user has arrived at the stop-off location (step S103: Yes), the estimation unit 115 estimates the user's travel route (step S104). Next, the estimation unit 115 estimates a combination of the user's home time and program from the combination of location information corresponding to the estimated travel route, stay period information indicating the time of stay at each stop-off location, and day of the week information indicating the day of the week on which the user stopped off at each stop-off location, using the above-mentioned home time program estimation model (step S2101). Subsequently, a series of processes from step S107 to step S112 are executed.

Thereafter, the travel status determination unit 113 determines whether the user has returned home (step S113). If the travel status determination unit 113 determines that the user has not yet returned home (step S113: No), the process of step S117 described below is executed. On the other hand, if the travel status determination unit 113 determines that the user has returned home (step S113: Yes), the return home notification unit 114 transmits return home notification information to the location management server 2 (step S114). Next, the model generation unit 2121 generates route estimation model information indicating a route estimation model and updates the route estimation model information already stored in the model storage unit 2135 with the generated route estimation model information (step S115). Next, the model generation unit 2121 generates return home program estimation model information indicating a return home program estimation model using the most recent user location information, stay period information, day of the week information, return home time information indicating the user's actual return home time, and program identification information stored in the travel status storage unit 133. Then, the model generation unit 2121 updates the home time program estimation model information already stored in the model storage unit 2135 with the generated home time program estimation model information (step S2102).

Next, as shown in FIG. 17, the viewing history acquisition unit 119 determines whether it has acquired viewing history information transmitted from the television receiver 91 or the recording device 92 (step S117). If the viewing history acquisition unit 119 determines that it has not acquired viewing history information (step S117: No), it executes the processing of step S119, which will be described later. On the other hand, if the viewing history acquisition unit 119 determines that it has acquired viewing history information (step S117: Yes), it acquires the viewing history information transmitted from the television receiver 91 or the recording device 92 and identifies the most recent movement status information at the time the viewing history information was acquired from the movement status information stored in the movement status storage unit 133. The viewing history acquisition unit 2119 then associates the program identification information, day of the week information, start time information, end time information, and program type information contained in the acquired viewing history information with the movement status identification information that identifies the identified movement status information, and stores them in the viewing history storage unit 2134 (step S2103). Next, the model generation unit 2121 generates home-coming time estimation model information indicating a home-coming time program estimation model using the user's most recent location information, stay period information, day of the week information, home-coming time information indicating the user's actual home-coming time, and program identification information stored in the movement status storage unit 133. The model generation unit 2121 then updates the home-coming time program estimation model information already stored in the model storage unit 2135 with the generated home-coming time program estimation model information (step S2104). Then, the processing from step S119 onwards is executed.

As described above, in the cloud server 2001 according to this embodiment, the estimation unit 2115 estimates the user's time of return home and the programs the user will watch using a home-time program estimation model that estimates the user's preferred programs along with the user's time of return home from the period of stay at each stop-off point included in the estimated travel route. This makes it possible to estimate the combination of home-time and program for each user, for example, when multiple users live together in building H, and therefore to select and present program information that appropriately reflects each user's preferences as program information to the users.

(Embodiment 3)
The information providing device of this embodiment differs from the information providing device of embodiment 1 in that it includes an inventory status notification unit that transmits inventory status information indicating the inventory status in the refrigerator to the terminal device when the time difference between the time the user returns home and the start time of the program selected by program selection unit 117 is greater than the above-mentioned first time difference threshold and equal to or less than a preset third time difference threshold.

As shown in FIG. 18, the information provision system according to this embodiment includes a television receiver 91, a recording device 92, and a refrigerator 93 installed in building H, a cloud server 3001, a location management server 2, a relay server 3, and terminal devices 3005A and 3005B. In FIG. 18, the same components as those in Embodiment 1 are designated by the same reference numerals as in FIG. 1. The television receiver 91, the recording device 92, and the refrigerator 93 can communicate with the cloud server 3001 via local network NW2 and wide area network NW1, respectively. The refrigerator 93 has an imaging unit (not shown) that captures images of the interior of the refrigerator, and upon receiving inventory status request information from the cloud server 3001 requesting the transmission of inventory status information indicating the inventory status inside the refrigerator, the imaging unit captures an image of the interior. The refrigerator 93 then generates inventory status information including image information indicating the image captured by the imaging unit and transmits it to the cloud server.

The hardware configuration of terminal devices 3005A and 3005B according to this embodiment is the same as the hardware configuration of terminal device 5 according to embodiment 1 shown in FIG. 2. Furthermore, the hardware configuration of cloud server 3001 is the same as the hardware configuration of cloud server 1 according to embodiment 1 shown in FIG. 2. Hereinafter, the hardware configuration of terminal devices 3005A and 3005B and cloud server 3001 according to this embodiment will be described using the same reference numerals as those used in the description of embodiment 1. The CPU 501 of terminal devices 3005A and 3005B reads a program stored in auxiliary memory unit 503 into main memory unit 502 and executes it, thereby functioning as a reception unit 511, display control unit 3512, positioning unit 513, location information notification unit 514, program information acquisition unit 515, operation information generation unit 516, operation information transmission unit 517, and inventory status acquisition unit 3518, as shown in FIG. 19. Note that components in FIG. 19 that are the same as those in embodiment 1 are designated by the same reference numerals as those in FIG. 3. In addition, auxiliary memory unit 503 has an image memory unit 531, and main memory unit 502 has a position memory unit 521 and a captured image memory unit 522 that stores image information included in inventory status information (described below) transmitted from cloud server 3001. When inventory status acquisition unit 3518 acquires inventory status information transmitted from cloud server 3001, it extracts image information included in the acquired inventory status information and stores it in captured image memory unit 522. Display control unit 3512 generates an inventory status notification image showing the inventory status of refrigerator 93 using the image information stored in captured image memory unit 522, and displays the generated inventory status notification image on display unit 504.

The CPU 101 of the cloud server 3001 in this embodiment reads out the programs stored in the auxiliary memory unit 103 into the main memory unit 102 and executes them, thereby functioning as a location information acquisition unit 111, a location identification unit 112, a movement status determination unit 113, a homecoming notification unit 114, an estimation unit 115, a notification determination unit 3116, a program selection unit 117, a program notification unit 118, a viewing history acquisition unit 119, a device control unit 120, a model generation unit 121, and an inventory status notification unit 3122, as shown in FIG. 20. Note that in FIG. 20, components similar to those in embodiment 1 are assigned the same reference numerals as in FIG. 4. The auxiliary memory unit 103 also has a location memory unit 131, a location memory unit 132, a movement status memory unit 133, a viewing history memory unit 134, and a model memory unit 135. If the user's arrival time is before the program start time and the time difference between the user's arrival time and the program start time is equal to or less than the first time difference threshold and greater than the second time difference threshold, notification determination unit 3116 determines to transmit program information to terminal device 3005A, 3005B carried by the user. Also, if the user's arrival time is before the program start time and the time between the user's arrival time and the program start time is less than the second time difference threshold, or if the user's arrival time is after the program start time, notification determination unit 3116 determines to transmit recording necessity inquiry information to terminal device 3005A, 3005B to inquire about the user's need to record the program. Furthermore, if the user's arrival time is before the program start time and the time difference between the user's arrival time and the program start time is greater than the first time difference threshold and less than the preset third time difference threshold, notification determination unit 3116 determines to transmit inventory status information indicating the inventory status of refrigerator 93 to terminal device 3005A, 3005B. Here, the third time difference threshold can be set, for example, based on the time it takes for the user to shop at a nearby supermarket, commercial facility, etc., and is set to, for example, two hours. On the other hand, if the time the user arrives home is before the start time of the program and the time between the time the user arrives home and the start time of the program is greater than the aforementioned third time difference threshold, the notification determination unit 3116 determines to avoid sending program information, recording necessity inquiry information, and inventory status information to terminal devices 3005A and 3005B.

When the notification determination unit 3116 determines that inventory status information indicating the inventory status of refrigerator 93 should be sent to terminal devices 3005A and 3005B, the inventory status notification unit 3122 sends inventory status information indicating the inventory status inside the refrigerator to terminal devices 3005A and 3005B. Here, the inventory status notification unit 3122 generates inventory status request information that requests refrigerator 93 to send the aforementioned inventory status information and sends it to refrigerator 93, thereby acquiring the inventory status information sent from refrigerator 93 and sending the acquired inventory status information to terminal devices 3005A and 3005B. Here, the inventory status notification unit 3122 sends the inventory status information to terminal devices 3005A and 3005B, which are preset destinations.

Next, the operation of the information provision system according to this embodiment will be described with reference to FIG. 21. In FIG. 21, the relay process at the relay server 3 is omitted for communications between terminal devices 3005A, 3005B and cloud server 3001 via the relay server 3. The same processes as those described in embodiment 1 are denoted by the same reference numerals. First, assume that the series of processes from steps S1 to S6 described in embodiment 1 are executed, and then the aforementioned time to transmit location information arrives, as shown in FIG. 21. In this case, the series of processes from steps S7 to S12 are executed. Next, assume that cloud server 3001 determines that the user's return home time is before the start time of the program, and that the time difference ΔT between the user's return home time and the start time of the program is greater than the aforementioned first time difference threshold ΔTth1 and less than or equal to the aforementioned third time difference threshold ΔTth3 (step S3001). In this case, cloud server 3001 generates the aforementioned inventory status request information (step S3002), and the generated inventory status request information is sent from cloud server 3001 to refrigerator 93 (step S3003). Meanwhile, upon receiving the inventory status request information, refrigerator 93 captures an image of the interior of the refrigerator using the imaging unit and generates inventory status information including image information showing the image captured by the imaging unit (step S3004). Next, the generated inventory status information is sent from refrigerator 93 to cloud server 3001 (step S3005).

On the other hand, when cloud server 3001 acquires inventory status information, the acquired inventory status information is transmitted from cloud server 3001 to terminal devices 3005A and 3005B (step S3006). On the other hand, when terminal devices 3005A and 3005B acquire inventory status information, they each extract image information included in the acquired inventory status information and store it in captured image storage unit 522. Then, terminal devices 3005A and 3005B each generate an inventory status notification image representing the inventory status of refrigerator 93 using the image information stored in captured image storage unit 522, and display the generated inventory status notification image on display unit 504 (step S3007).

Next, the information provision processing executed by the cloud server 3001 according to this embodiment will be described with reference to FIG. 22. Note that in FIG. 22, processing similar to that of embodiment 1 is assigned the same reference numerals as in FIGS. 12 and 13. First, after the series of processing steps S101 and S106 are executed, the notification determination unit 3116 determines whether the user's homecoming time Tre is before the program start time Tst and whether the time difference ΔT from the user's homecoming time Tre to the program start time Tst is equal to or less than the first time difference threshold ΔTth1 and greater than the second time difference threshold ΔTth2 (step S107). Here, assume that the notification determination unit 3116 determines that the homecoming time Tre is before the program start time Tst and the time difference ΔT is greater than the first time difference threshold ΔTth1 (step S107: No). In this case, the notification determination unit 3116 determines whether the time Tre of returning home is before the program start time Tst and whether the time difference ΔT is greater than the first time difference threshold ΔTth1 and less than or equal to the third time difference threshold ΔTth3 (step S3101). Here, if the notification determination unit 3116 determines that the time difference ΔT is greater than the third time difference threshold ΔTth3 (step S3101: No), the processing from step S113 onwards is executed.

On the other hand, suppose the notification determination unit 3116 determines that the time difference ΔT is greater than the first time difference threshold ΔTth1 and less than or equal to the third time difference threshold ΔTth3 (step S3101: Yes). In this case, the inventory status notification unit 3122 generates inventory status request information requesting the refrigerator 93 to transmit the inventory status information and transmits it to the refrigerator 93 (step S3102), thereby acquiring the inventory status information transmitted from the refrigerator 93 (step S3103). Next, the inventory status notification unit 3122 transmits the acquired inventory status information to the preset destination terminal devices 3005A and 3005B (step S3104). Subsequently, the processing from step S113 onwards is executed.

As described above, in the cloud server 3001 according to this embodiment, the notification determination unit 3116 determines to send inventory status information indicating the inventory status of the refrigerator 93 to the terminal devices 3005A and 3005B if the user's return home time is before the start time of the program and the time difference between the return home time and the start time of the program is greater than the first time difference threshold and less than or equal to the third time difference threshold. The inventory status notification unit 3122 then sends inventory status information indicating the inventory status inside the refrigerator to the terminal devices 3005A and 3005B. This allows the user to check the inventory status of the refrigerator 93 when there is still time before the start time of the program and the user stops by a nearby supermarket to do some shopping, for example, and thus prevents the user from making unnecessary purchases.

(Embodiment 4)
The information providing device of this embodiment is different from the information providing device of embodiment 1 in that it includes a home-coming time notification unit that transmits home-coming time information indicating the user's home-coming time estimated by the estimation unit to a terminal device carried by the user, and does not include a program notification unit.

As shown in FIG. 23, the information provision system according to this embodiment includes a television receiver 91, a recording device 92, a refrigerator 93, a rice cooker 94, and a water heater 95 installed in building H, a cloud server 4001, a location management server 2, a relay server 3, and a terminal device 5. Note that in FIG. 23, components similar to those in embodiment 1 are assigned the same reference numerals as in FIG. 1. The television receiver 91, the recording device 92, the refrigerator 93, the rice cooker 94, and the water heater 95 can communicate with the cloud server 4001 via the local network NW2 and the wide area network NW1, respectively. The recording device 92, the refrigerator 93, the rice cooker 94, and the water heater 95 each operate based on control information transmitted from the cloud server 4001.

The hardware configuration of the terminal device 4005 according to this embodiment is the same as the hardware configuration of the terminal device 5 according to embodiment 1 shown in FIG. 2. The hardware configuration of the cloud server 4001 is the same as the hardware configuration of the cloud server 1 according to embodiment 1 shown in FIG. 2. Hereinafter, the hardware configurations of the terminal device 4005 and cloud server 4001 according to this embodiment will be described using the same reference numerals as those used in the description of embodiment 1. The CPU 501 of the terminal device 4005 reads a program stored in the auxiliary storage unit 503 into the main storage unit 502 and executes it, thereby functioning as a reception unit 511, a display control unit 4512, a positioning unit 513, a location information notification unit 514, a home time acquisition unit 4518, an operation information generation unit 4516, and an operation information transmission unit 517, as shown in FIG. 24. Note that components in FIG. 24 that are the same as those in embodiment 1 are denoted by the same reference numerals as those in FIG. 3. The auxiliary storage unit 503 includes an image storage unit 531, and the main storage unit 502 includes a location storage unit 521.

When the operation information generation unit 4516 receives from the reception unit 511 information indicating the operation details for operating the recording device 92, refrigerator 93, rice cooker 94, and water heater 95 from the cloud server 1, the operation information generation unit 4516 generates operation information indicating the operation details for operating the recording device 92, refrigerator 93, rice cooker 94, and water heater 95. The operation information generation unit 4516 then notifies the generated operation information to the operation information transmission unit 517, which then transmits the notified operation information to the cloud server 1 via the relay server 3. When the arrival-home time acquisition unit 4518 acquires the arrival-home time information (described below) transmitted from the cloud server 4001, the operation information generation unit 4516 notifies the display control unit 4512 of the acquired arrival-home time information. When the display control unit 4512 receives the arrival-home time information from the arrival-home time acquisition unit 4518, the display control unit 4512 generates a arrival-home time notification image indicating the arrival-home time indicated by the notified arrival-home time information, and displays the generated arrival-home time notification image on the display unit 504.

The CPU 101 of the cloud server 4001 reads out the program stored in the auxiliary memory unit 103 into the main memory unit 102 and executes it, thereby functioning as a location information acquisition unit 111, a location identification unit 112, a movement status determination unit 113, a homecoming notification unit 114, an estimation unit 115, a homecoming time notification unit 4118, and a device control unit 4120, as shown in FIG. 25. Note that in FIG. 25, components similar to those in embodiment 1 are assigned the same reference numerals as in FIG. 4. The auxiliary memory unit 103 also has a location memory unit 131, a location memory unit 132, a movement status memory unit 133, and a model memory unit 135. The homecoming time notification unit 4118 generates homecoming time information indicating the user's homecoming time estimated by the estimation unit 115, and transmits the generated homecoming time information to the terminal device 5.

When the device control unit 4120 acquires the operation information transmitted from the terminal device 5, it generates control information for operating the recording device 92, refrigerator 93, rice cooker 94, or water heater 95 based on the acquired operation information. The device control unit 4120 then transmits the generated control information to the recording device 92, refrigerator 93, rice cooker 94, or water heater 95.

Next, the information provision process executed by the cloud server 4001 according to this embodiment will be described with reference to FIG. 26. Note that in FIG. 26, the same processes as those in embodiment 1 are denoted by the same reference numerals as those in FIGS. 12 and 13. First, after the series of processes in steps S101 and S102 are executed, the travel status determination unit 113 determines whether the user has arrived at the stop-off location based on the generated travel status information (step S103). Here, if the travel status determination unit 113 determines that the user has arrived at the stop-off location (step S103: Yes), the estimation unit 115 estimates the user's travel route using a route estimation model, as described in embodiment 1 (step S104). Next, the estimation unit 115 estimates the user's return home time using a return home time estimation model, as described in embodiment 1 (step S105). Next, the arrival-home time notification unit 4118 generates arrival-home time information indicating the user's arrival-home time estimated by the estimation unit 115 and transmits the generated arrival-home time information to the terminal device 4005 (step S4101). The device control unit 4120 then determines whether operation information transmitted from the terminal device 4005 has been acquired (step S4102). If the device control unit 4120 determines that operation information transmitted from the terminal device 4005 has been acquired (step S4102: Yes), it generates control information for operating the recording device 92, refrigerator 93, rice cooker 94, or water heater 95 based on the acquired operation information and transmits the generated control information to the recording device 92, refrigerator 93, rice cooker 94, or water heater 95 (step S4103). Then, a series of processes from steps S113 to S116 are executed. Next, a series of processes from steps S119 to S122 are executed.

As described above, in the cloud server 4001 according to this embodiment, the arrival-home time notification unit 4118 generates arrival-home time information indicating the user's arrival-home time estimated by the estimation unit 115 and transmits the generated arrival-home time information to the terminal device 4005. Furthermore, upon receiving operation information transmitted from the terminal device 4005, the device control unit 4120 generates control information for operating the recording device 92, refrigerator 93, rice cooker 94, or water heater 95 based on the received operation information and transmits the control information to the recording device 92, refrigerator 93, rice cooker 94, or water heater 95. This allows the user to refer to the arrival-home time indicated in the arrival-home time information received by the terminal device 5 and operate the recording device 92, refrigerator 93, rice cooker 94, or water heater 95 according to the arrival-home time. Therefore, for example, the recording device 92, refrigerator 93, rice cooker 94, or water heater 95 can be operated in an optimal state for the user when the user returns home.

The above describes various embodiments of the present disclosure, but the present disclosure is not limited to the aforementioned embodiments. For example, the route estimation model may estimate a travel route from location information of stop-off locations visited by the user, day-of-the-week information indicating the day of the week on which the user stopped at the stop-off locations, and weather conditions on the day on which the user stopped at the stop-off locations. Furthermore, the home-time estimation model may estimate a user's home time from location information included in the estimated user's travel route, stay period information indicating the time the user stayed at at least one stop-off location included in the travel route, day-of-the-week information indicating the day on which the user travels along the travel route, and weather conditions on the day on which the user stopped at the stop-off locations. Furthermore, the home time program estimation model may estimate the user's home time and a program that belongs to the same program type as at least one program preferred by the user, based on location information included in the estimated user's travel route, stay period information indicating the time the user will stay at at least one stop-off location included in the travel route, weekday information indicating the day of the week on which the user will travel along the travel route, and weather conditions on the day the user stops at the stop-off location.

With this configuration, the travel route, return time, and combinations of the user's preferred programs are estimated taking into account the weather conditions on the day the user stopped off at the stop-off location. This improves the accuracy of estimating the user's travel route, return time, and combinations of the user's preferred programs.

In each embodiment, the model generation unit 121, 2121 may exclude some of the past location information, stay period information, and past home time information from the training data used to generate the home time estimation model or home time program estimation model, or may add past location information, stay period information, and past home time information that was not used as training data to the training data. Furthermore, the model generation unit 121, 2121 may generate a new home time estimation model or home time program estimation model through reinforcement learning each time the user returns home.

In each embodiment, an example has been described in which the estimation unit 115, 2115, model generation unit 121, 2121, and model storage unit 135, 2135 are realized on the same cloud server 1, 2001, 3001, 4001, but this is not limited to this. For example, the model generation unit 121, 2121 and model storage unit 135, 2135 may be realized on a device separate from the estimation unit 115, 2115.

In each embodiment, examples have been described in which the home-coming time estimation model and home-coming time program estimation model are forward-propagation neural networks, but this is not limited to this and they may also be, for example, multi-class classification support vector machines.

Furthermore, the various functions of the cloud servers 1, 2001, 3001, 4001 and terminal devices 5, 3005A, 3005B, 4005 according to the present disclosure may be realized by software, firmware, or a combination of software and firmware. In this case, the software or firmware may be written as a program, and the program may be stored and distributed on a computer-readable recording medium such as a flexible disk, CD-ROM (Compact Disc Read Only Memory), DVD (Digital Versatile Disc), or MO (Magneto-Optical Disc). By loading and installing the program on a computer, a computer capable of realizing each of the aforementioned functions may be configured. Furthermore, in cases where each function is realized by sharing the work between an OS (Operating System) and an application, or by cooperation between the OS and an application, only the parts other than the OS may be stored on the recording medium.

Furthermore, each program can be superimposed on a carrier wave and distributed over a network. For example, the program can be posted on a bulletin board system (BBS) on the network and distributed over the network. These programs can then be launched and run under the control of the OS in the same way as other application programs, thereby enabling the above-mentioned processing to be performed.

This disclosure is suitable as an information provision system that provides information about programs according to the user's arrival time.

1, 2001, 3001, 4001 Cloud server, 2 Location management server, 3 Relay server, 5, 3005A, 3005B, 4005 Terminal device, 91 Television receiver, 92 Recording device, 93 Refrigerator, 94 Rice cooker, 95 Water heater, 101, 501 CPU, 102, 502 Main memory unit, 103, 503 Auxiliary memory unit, 106, 506 Wide area communication unit, 107 Timekeeping unit, 109, 509 Bus, 111 Location information acquisition unit, 112 Location identification unit, 113 Travel status determination unit, 114 Return home notification unit, 115, 2115 Estimation unit, 116, 2116, 3116 Notification determination unit, 117 Program selection unit, 118 Program notification unit, 119, 2119 Viewing history acquisition unit, 120, 4120: Device control unit, 121, 2121: Model generation unit, 131: Position memory unit, 132: Location memory unit, 133, 2133: Movement status memory unit, 134, 2134: Viewing history memory unit, 135, 2135: Model memory unit, 504: Display unit, 505: Input unit, 508: GNSS receiver, 511: Reception unit, 512, 3512, 4512: Display control unit, 513: Positioning unit, 514: Location information notification unit, 515: Program information acquisition unit, 516: Operation information generation unit, 517: Operation information transmission unit, 521: Position memory unit, 531: Image memory unit, 3122: Inventory status notification unit, 3518: Inventory status acquisition unit, 3522: Captured image memory unit, NW1: Wide area network, NW2: Local network

Claims (10)

a location information acquisition unit that acquires location information indicating the location of a user;
a location identification unit that identifies at least one stop-off location that the user will stop off at based on the location information of the user and the stay time of the user at the location indicated by the location information within a predetermined period of time;
a travel status determination unit that determines a travel status of the user based on a stay time of the user at each of the at least one stop-off places;
an estimation unit that estimates the travel route using a route estimation model that estimates the travel route of the user from the travel status, and estimates the user's return home time using a return home time estimation model that estimates the user's return home time from a stay period at each of the at least one stop-off places included in the estimated travel route;
a program selection unit that selects a program that belongs to the same program type as the program type of at least one broadcast program that the user has viewed in the past and that the user likes;
a notification determination unit that determines whether or not to transmit program information of the selected program to the terminal device carried by the user based on the start time of the selected program and the time of returning home;
a program notification unit that, when it is determined that the program information should be transmitted to the terminal device carried by the user, transmits the program information to the terminal device.
Information provision device. the notification determination unit determines to transmit the program information to the terminal device when the time of coming home is before the start time of the selected program and the time difference between the time of coming home and the start time of the program is equal to or less than a predetermined first time difference threshold and is greater than a predetermined second time difference threshold.
The information providing device according to claim 1 . the notification determination unit determines to transmit to the terminal device recording necessity inquiry information for inquiring of the user about whether or not to record the program if the time of coming home is before the start time of the selected program and the time difference between the time of coming home and the start time of the program is equal to or less than the second time difference threshold, or if the time of coming home is after the start time of the program;
When the notification determination unit determines that the recording necessity inquiry information should be transmitted to the terminal device, the program notification unit transmits the recording necessity inquiry information to the terminal device.
The information providing device according to claim 2 . a device control unit that generates control information for causing a recording device to record the selected program and transmits the control information to the recording device when the time of coming home is before the start time of the selected program and the time difference between the time of coming home and the start time of the program is equal to or less than the second time difference threshold, or when the time of coming home is after the start time of the program.
4. The information providing device according to claim 2 or 3. the notification determination unit determines to transmit inventory status information indicating an inventory status in the refrigerator to the terminal device when the time of coming home is before the start time of the selected program and a time difference between the time of coming home and the start time of the program is equal to or less than a preset third time difference threshold and is greater than the first time difference threshold;
and a stock status notification unit that transmits the stock status information to the terminal device when the notification determination unit determines that the stock status information should be transmitted to the terminal device.
The information providing device according to any one of claims 2 to 4. the stock status notification unit transmits the stock status information to a plurality of terminal devices including the terminal device;
The information providing device according to claim 5 . a location information acquisition unit that acquires location information indicating the location of a user;
a location identification unit that identifies at least one stop-off location that the user will stop off at based on the location information of the user and the stay time of the user at the location indicated by the location information within a predetermined period of time;
a travel status determination unit that determines a travel status of the user based on a stay time of the user at each of the at least one stop-off places;
an estimation unit that estimates the user's travel route using a route estimation model that estimates the user's travel route from the travel status, and that estimates the user's return home time and a program that the user will watch using a return home time program estimation model that estimates the user's return home time and a program that belongs to the same program type as the program type of at least one program that the user likes from a stay period at each of the at least one stop-off places included in the estimated travel route;
a notification determination unit that determines whether or not to transmit program information of the estimated program to a terminal device carried by the user based on the estimated start time of the program and the time of returning home;
a program notification unit that, when it is determined that the program information should be transmitted to the terminal device carried by the user, transmits the program information to the terminal device.
Information provision device. A terminal device owned by a user;
a location information acquisition unit that acquires location information indicating the location of the user identified based on the location of the terminal device;
a location identification unit that identifies at least one stop-off location that the user will stop off at based on the location information of the user and the stay time of the user at the location indicated by the location information within a predetermined period of time;
a travel status determination unit that determines a travel status of the user based on a stay time of the user at each of the at least one stop-off places;
an estimation unit that estimates the travel route using a route estimation model that estimates the travel route of the user from the travel status, and estimates the user's return home time using a return home time estimation model that estimates the user's return home time from a stay period at each of the at least one stop-off places included in the estimated travel route;
a program selection unit that selects a broadcast program that belongs to the same program type as the program type of at least one broadcast program that the user has viewed in the past and that the user likes;
a notification determination unit that determines whether or not to transmit program information of the program of the program type to the terminal device carried by the user based on the start time of the selected program and the time of returning home;
a program notification unit that transmits the program information to the terminal device when it is determined that the program information should be transmitted to the terminal device.
Information provision system. an information providing device acquiring location information indicating a location of a user;
a step in which the information providing device identifies at least one stop-off place to be visited by the user based on the location information of the user and the stay time of the user at the location indicated by the location information within a predetermined period of time;
The information providing device determines a movement status of the user based on a stay time of the user at each of the at least one stop-off places;
the information providing device estimating the travel route using a route estimation model that estimates the travel route of the user from the travel status, and estimating the return home time of the user using a return home time estimation model that estimates the return home time of the user from a stay period at each of the at least one stop-off places included in the estimated travel route;
a step of the information providing device selecting a broadcast program that belongs to the same program type as the program type of at least one broadcast program that the user has viewed in the past and that the user likes;
a step of determining whether or not the information providing device should transmit program information of the selected program to a terminal device carried by the user based on the start time of the selected program and the time of returning home;
and when it is determined that the program information should be transmitted to the terminal device carried by the user, the information providing device transmits the program information to the terminal device.
Information provision method. Computer,
a location information acquisition unit that acquires location information indicating the location of a user;
a location identification unit that identifies at least one stop-off location that the user will stop off at based on the location information of the user and the stay time of the user at the location indicated by the location information within a predetermined period of time;
a movement status determination unit that determines a movement status of the user based on a stay time of the user at each of the at least one stop-off places;
an estimation unit that estimates the travel route using a route estimation model that estimates the travel route of the user from the travel status, and estimates the user's return home time using a return home time estimation model that estimates the user's return home time from a stay period at each of the at least one stop-off places included in the estimated travel route;
a program selection unit that selects a broadcast program that belongs to the same program type as the program type of at least one broadcast program that the user has viewed in the past and that the user likes;
a notification determination unit that determines whether or not to transmit program information of the selected program to a terminal device carried by the user based on the start time of the selected program and the time of returning home;
a program notification unit that, when it is determined that the program information should be transmitted to the terminal device carried by the user, transmits the program information to the terminal device;
A program to function as a