JP7466088B2 - Behavior Prediction System - Google Patents

Description

The present invention relates to a behavior estimation system that estimates the behavior in which a user is interested.

Patent Document 1 describes an audio output device that is attached to a child's desk and includes a switch attached to the top board, an audio output control unit with a memory that stores a series of words encouraging a specific behavior, and a speaker. When the switch is pressed on this child's desk, the audio output control unit sequentially outputs a series of words encouraging a specific behavior from the speaker.

Patent Document 1 also describes how, for each time period, a series of words encouraging a specific behavior corresponding to that time period are associated, and the series of words encouraging the specific behavior associated with the time period when the switch is pressed are output in sequence by voice. As a result, each time the child presses the switch, a series of words encouraging the specific behavior is output in sequence from the voice output device, allowing the child to perform the specific behavior through conversation with the child's desk.

JP 2013-287 A

By the way, it is difficult to know what actions a user might be potentially interested in.

The present invention provides a behavior estimation system that can estimate the behavior of a user that is of interest.

The behavior estimation system according to one embodiment of the present invention includes an acquisition unit that acquires at least one of schedule information indicating a schedule of behavior of the first user for a predetermined period planned by the first user and result information indicating the actual behavior of the first user for the predetermined period, a generation unit that generates first interest level information indicating the first user's degree of interest in each of a plurality of behaviors based on the acquired at least one of the information, and an estimation unit that estimates a first behavior in which the first user is interested other than the plurality of behaviors by comparing the generated first interest level information with a plurality of second interest level information each generated for another user.

The behavior estimation system according to one aspect of the present invention includes an acquisition unit that acquires schedule information indicating a schedule of a user's behavior for a predetermined period of time planned by the user, and a generation unit that generates interest level information indicating the user's degree of interest in each of a plurality of behaviors based on the acquired schedule information.

A program according to one aspect of the present invention is a program for causing a computer to execute an information processing method including a first receiving step of receiving arrangement information indicating an arrangement of the plurality of blocks in the case from a toy having a plurality of blocks and a case for storing the plurality of blocks, the toy allowing a user to rearrange the arrangement of the plurality of blocks in the case, a generating step of generating schedule information indicating a schedule of the user's actions for a predetermined period of time based on the received arrangement information, and a transmitting step of transmitting the generated schedule information to a server device.

The behavior estimation system of the present invention can estimate the behaviors that interest a user.

FIG. 1 is a block diagram illustrating a functional configuration of a behavior inference system according to an embodiment. FIG. 2 is a perspective view of the appearance of the toy according to the embodiment. FIG. 3 is a diagram illustrating an example of a screen displayed on a display unit of an information terminal according to an embodiment. FIG. 4 is a flowchart of a first operation example of the behavior inference system according to the embodiment. FIG. 5 is a diagram showing an example of the schedule information and the result information. FIG. 6 is a diagram showing an example of the first interest level information and the second interest level information. FIG. 7 is a diagram conceptually illustrating the processing performed by the machine learning model. FIG. 8 is a diagram showing an example of an image showing a first action. FIG. 9 is a flowchart of an operation example 2 of the behavior inference system according to the embodiment. FIG. 10 is a diagram showing an example of an image indicating a first interest level. FIG. 11 is a flowchart showing the processing steps of a program for operating a computer as an information terminal according to the embodiment.

The following describes the embodiments in detail with reference to the drawings. Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection forms, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the present invention. Furthermore, among the components in the following embodiments, components that are not described in an independent claim are described as optional components.

Note that each figure is a schematic diagram and is not necessarily a precise illustration. In addition, in each figure, the same reference numerals are used for substantially the same configurations, and duplicate explanations may be omitted or simplified.

In addition, terms used in the following embodiments that indicate timing, such as "immediately after" and "instantly," should not be interpreted in a strict sense.

(Embodiment)
[composition]
First, a configuration of a behavior inference system according to an embodiment will be described. Fig. 1 is a block diagram showing a functional configuration of the behavior inference system according to an embodiment.

The behavior estimation system 10 according to the embodiment is a system for estimating behaviors that an infant is interested in. Specifically, the behavior estimation system 10 estimates behaviors that an infant is interested in based on an action plan that the infant makes together with a guardian or a childcare worker (hereinafter referred to as a guardian, etc.) and the actions that the infant actually performs.

As shown in FIG. 1, the behavior estimation system 10 includes a toy 20, an information terminal 30, and a server device 40. The toy 20 and the information terminal 30 are installed, for example, in a building 80. The building 80 is, for example, a residence such as an apartment building or a detached house, but may also be a childcare facility, etc.

[toy]
In the behavior estimation system 10, the toy 20 is used as a user interface for a child to plan behavior together with a guardian, etc. First, the configuration of the toy 20 will be described. FIG.

The toy 20 has a number of blocks 21, each of which is a long, plate-like shape, a case 22 that houses the blocks 21, and a sensor 23 (shown in FIG. 1) built into the case 22.

The blocks 21 are classified into six types according to the color of the block 21. The six types of blocks 21 correspond to six types of behavior. The six types of behavior are actions that the child A can take, such as drawing, making a drawing, going to the park, reading a picture book, playing with trains, and watching DVDs. The guardian P operates the information terminal 30 to register which color block 21 is associated with which behavior in the storage unit 34 of the information terminal 30. In other words, the storage unit 34 stores correspondence information indicating which color block 21 (more specifically, the identification information emitted by the wireless tag described below) is associated with which behavior. For example, about 20 types of behavior candidates are prepared, and the guardian P, etc., in consultation with the child A, selects six types to be associated with the blocks from the 20 types. The number of types of blocks (six in the above example) is not particularly limited.

Placing one block 21 in the case 22 corresponds to planning to perform the action indicated by that block 21 for a certain period of time (e.g., 10 minutes). As shown in FIG. 2, when infant A arranges four blocks 21 of a color corresponding to "drawing" in a row on the left edge of the case 22, this corresponds to planning to "draw" for 40 minutes. Arranging two blocks of a color corresponding to "work" in a row immediately to the right of the four blocks 21 of a color corresponding to "drawing" means planning to "draw" for 40 minutes followed by "work" for 20 minutes.

Each of the multiple blocks 21 has a built-in wireless tag such as an RF tag, and the block 21 emits identification information from the wireless tag built into the block 21. The wireless tag is, for example, a passive type, but may be an active type. The toy 20 senses the identification information emitted by the block 21 using a sensor 23 such as a wireless tag reader, and can transmit arrangement information indicating how the blocks 21 are arranged inside the case 22 to the information terminal 30.

More specifically, the placement information is information that associates storage position information (information indicating the number from the left, etc.) indicating the storage position of the block 21 within the case 22 with the identification information of the block 21 sensed at that storage position. The information terminal 30 can recognize what action has been scheduled by comparing the placement information with the correspondence information stored in the memory unit 34.

In this way, with the toy 20, the infant A can make his/her own schedule in a playful manner, and the information terminal 30 can recognize the schedule made by the infant A. In other words, the infant A can input his/her own schedule into the information terminal 30 in a playful manner.

Furthermore, according to the toy 20, the information terminal 30 can also recognize when the infant A performed each action such as "drawing". In the example of FIG. 2, when infant A actually starts "drawing", he presses one of the push buttons 21a of the blocks 21 of colors corresponding to the four consecutively arranged "drawings", and when he ends "drawing", he presses one of the push buttons 21a of the blocks 21 of colors corresponding to the four "drawings". The toy 20 transmits notification information to the information terminal 30 every time the push button 21a of the block 21 of colors corresponding to "drawing" is pressed. This allows the information terminal 30 to recognize the time when the first notification information is received as the start time of "drawing" and the time when the second notification information is received as the end time of "drawing".

In this way, with toy 20, child A can playfully press push button 21a to input to information terminal 30 what action he or she performed and at what time (hereinafter also referred to as the result of the action).

[Information terminal]
Next, the information terminal 30 will be described. The information terminal 30 is, for example, a general-purpose mobile terminal such as a smartphone or a tablet terminal, but may also be a dedicated terminal for the behavior estimation system 10. The information terminal 30 may also be a home controller such as a HEMS (Home Energy Management System) controller installed in the building 80. Specifically, the information terminal 30 includes an operation receiving unit 31, a display unit 32, a control unit 33, a storage unit 34, a first communication unit 35, and a second communication unit 36.

The operation reception unit 31 receives operations from the guardian P, etc. For example, the operation reception unit 31 receives an operation (registration operation) from the guardian P, etc. to link the color (type) of the block 21 with an action. The operation reception unit 31 is, for example, a capacitive touch panel, but may also be a resistive touch panel.

The display unit 32 displays images. For example, the display unit 32 can display the planned behavior of the infant A and the results of the behavior of the infant A, which are input via the toy 20. FIG. 3 is a diagram showing an example of the display screen of the display unit 32. The display unit 32 is, for example, a display panel such as a liquid crystal panel or an organic EL (Electro Luminescence) panel.

The control unit 33 generates schedule information based on the planned behavior of the infant A input via the toy 20. Specifically, the control unit 33 regards the arrangement of the multiple blocks 21 determined by the arrangement information received by the second communication unit 36 as the planned behavior of the infant A planned by the infant A, and generates the schedule information.

The control unit 33 also generates result information based on the results of the actions of the child A input via the toy 20. Specifically, the control unit 33 generates result information based on notification information received by the second communication unit 36 in response to pressing of the push button 21a provided on the block 21.

In addition, the control unit 33 also controls the display of images on the display unit 32. The control unit 33 is realized, for example, by a microcomputer, but may also be realized by a processor.

The storage unit 34 is a storage device that stores the programs executed by the control unit 33. The storage unit 34 also stores the above-mentioned correspondence information. The storage unit 34 is realized, for example, by a semiconductor memory.

The first communication unit 35 is a communication module (communication circuit) that enables the information terminal 30 to communicate with the server device 40 via a wide area communication network 70 such as the Internet. The first communication unit 35 transmits, for example, schedule information and result information generated by the control unit 33 to the server device 40. The communication performed by the first communication unit 35 is, for example, wireless communication, but may also be wired communication. There is also no particular limitation on the communication standard used for the communication.

The second communication unit 36 is a communication module (communication circuit) that enables the information terminal 30 to communicate with the toy 20 via a local communication network. The second communication unit 36 receives, for example, the above-mentioned placement information and notification information from the toy 20. The communication performed by the second communication unit 36 is, for example, wireless communication, but may also be wired communication. There are no particular limitations on the communication standard used for the communication. Note that the communication between the second communication unit 36 and the toy 20 complies with, for example, BLE (Bluetooth (registered trademark) Low Energy).

[Server device]
Next, the server device 40 will be described. The server device 40 is a cloud server that acquires schedule information and result information from the information terminal 30 and performs information processing to estimate behaviors in which the child A is interested based on the acquired schedule information and result information. The server device 40 includes a communication unit 41, an information processing unit 42, and a storage unit 43.

The communication unit 41 is a communication module (communication circuit) that allows the server device 40 to communicate with the information terminal 30 via the wide area communication network 70. Specifically, the communication unit 41 includes an acquisition unit 44 that acquires schedule information and result information, and a transmission unit 45 that transmits to the information terminal 30 behavioral information indicating behavior that is presumed to interest infant A as a result of the above information processing. The communication performed by the communication unit 41 is, for example, wired communication, but may also be wireless communication. There is also no particular limitation on the communication standard used for the communication.

The information processing unit 42 performs information processing to estimate the behavior in which the child A is interested based on the schedule information and result information acquired by the acquisition unit 44. Specifically, the information processing unit 42 includes a generation unit 46 and an estimation unit 47. The information processing unit 42 is realized, for example, by a microcomputer, but may also be realized by a processor.

The storage unit 43 is a storage device that stores the programs executed by the information processing unit 42 and various information used to perform the above information processing. The storage unit 43 is realized, for example, by a hard disk drive (HDD).

[Operation example 1]
The following describes the first operation example of the behavior estimation system 10. FIG.

First, the acquisition unit 44 of the server device 40 acquires schedule information indicating the planned activities of Infant A for a predetermined period of time planned by Infant A from the information terminal 30 (S11). As shown in FIG. 5, the schedule information is information in which at least some of the approximately 20 types of activities described above are associated with their scheduled times (time periods). FIG. 5 is a diagram showing an example of schedule information.

The specified period is, for example, one month, but is not particularly limited to this. The acquisition unit 44 may acquire schedule information every day to ultimately acquire one month's worth of schedule information, or may acquire one month's worth of schedule information stored in the memory unit 34 of the information terminal 30 all at once.

The acquisition unit 44 also acquires result information indicating the actual behavior of the child A during the above-mentioned predetermined period from the information terminal 30 (S12). FIG. 5 above is also a diagram showing an example of the result information, and as shown in FIG. 5, the result information is information that associates at least some of the approximately 20 types of behaviors described above with the time (time period) at which they were performed.

The acquisition unit 44 may acquire result information every day to ultimately acquire one month's worth of schedule information, or may acquire one month's worth of result information stored in the memory unit 34 of the information terminal 30 all at once.

Next, the generation unit 46 generates first interest level information indicating the degree of interest of the infant A in each of the multiple behaviors based on the acquired schedule information and result information (S13). The first interest level information is, for example, information that ranks the degree of interest of the infant A in the multiple behaviors. FIG. 6 is a diagram showing an example of first interest level information. FIG. 6 also shows second interest level information of infant B, which is different from infant A.

The multiple actions for which the first interest level information indicates the degree of interest of infant A include all actions that were scheduled at least once in one month's worth of schedule information (in other words, actions that were linked to any of the six types of blocks at least once during one month). However, the multiple actions for which the first interest level information indicates the degree of interest of infant A do not include actions that were not scheduled at all in one month's worth of schedule information (in other words, actions that were not linked to any of the six types of blocks at least once during one month).

As mentioned above, six actions can be linked to six types of blocks 21 at a time, but the guardian P or the like can change this linking on a daily basis, so one month's worth of schedule information includes more than six types of actions. In other words, as suggested in FIG. 6, the number of the multiple actions may be greater than six. In this embodiment, about 20 types of action candidates are prepared, and the number of the multiple actions is a maximum of 20, but for the sake of explanation, the number of the multiple actions is assumed to be about 15.

The method of generating the first interest level information by the generation unit 46 will be described in detail below. For example, the generation unit 46 calculates the total scheduled time (i.e., scheduled time), the total scheduled number of times (i.e., scheduled number of times), and the change in scheduled time over time for each of the multiple actions included in one month's worth of schedule information. Note that the change in scheduled time over time is, for example, the difference between the length of time when the action was first scheduled and the length of time when the action was last scheduled.

The generation unit 46 also calculates, for example, for each of the multiple actions included in one month's worth of result information, the total time it was performed (i.e., execution time), the total number of times it was performed (i.e., the number of times it was performed), and the change in execution time over time. Note that the change in execution time over time is, for example, the difference between the length of time when the action was first performed and the length of time when the action was last performed.

Furthermore, the generation unit 46 calculates the total execution time/total planned time and the total number of executions/total number of executions.

Then, the generating unit 46 inputs the calculated information into a machine learning model constructed in advance. The machine learning model is, for example, stored in advance in the storage unit 43. The machine learning model is a discriminator (classifier) constructed to use the calculated information as input information and output the degree of interest of the infant A in the multiple behaviors included in one month's worth of schedule information and result information. FIG. 7 is a diagram conceptually illustrating the processing performed by the machine learning model. The generating unit 46 can generate first interest level information by ranking the degrees of interest in the multiple behaviors output by the machine learning model. Note that the machine learning model is constructed, for example, by supervised learning based on data acquired in advance from multiple subjects (infants).

Note that it is not essential that all of the input information shown in FIG. 7 be used, and it is sufficient that at least one piece of input information be used. For example, if only parameters calculated from the schedule information are used as input information, the process of acquiring result information in step S12 may be omitted. Similarly, for example, if parameters calculated from the execution information (such as the execution time of an action) are used as input information, the process of acquiring schedule information in step S11 may be omitted. In other words, the acquisition unit 44 may acquire at least one piece of information, namely, schedule information and result information.

Here, the generation unit 46 stores the first interest level information in the storage unit 43. The generation unit 46 also stores in the storage unit 43 second interest level information that was previously generated for an infant B other than infant A. In other words, the storage unit 43 stores a plurality of pieces of second interest level information each generated for infant B.

The estimation unit 47 compares the generated first interest level information with multiple pieces of second interest level information to estimate a first behavior that the child A is interested in other than the multiple behaviors included in the one-month schedule information and result information (S14).

Specifically, the estimation unit 47 performs the above comparison to identify second interest level information similar to the first interest level information from among the multiple pieces of second interest level information (S14a). In other words, the estimation unit 47 identifies infant B, who has a similar interest pattern to infant A. The estimation unit 47 compares, for example, 10 types of behaviors that are ranked in the top 10 in the first interest level information with 10 types of behaviors that are ranked in the top 10 in the second interest level information, and determines that the second interest level information with a larger number of common behaviors (up to a maximum of 10) is more similar. In the example of FIG. 6 above, the number of common behaviors is 5.

For example, the estimation unit 47 identifies second interest level information in which the number of common behaviors is a predetermined number (e.g., five) or more as similar second interest level information. In other words, the estimation unit 47 identifies second interest level information in which the ranking is similar to that of the first interest level information. The estimation unit 47 may identify the most similar second interest level information (having the largest number of common behaviors) as similar second interest level information. When there are multiple pieces of identified second interest level information, one may be selected randomly, or further narrowing down may be performed by evaluating the similarity taking into account differences in ranking, etc.

The estimation unit 47 then estimates that among the behaviors included in the identified second interest level information, a behavior that is not included in the first interest level information is the first behavior in which child A is interested. For example, if it is determined that the second interest level information of child B shown in FIG. 6 is most similar, "playing with dolls," which is not included in the first interest level information but is included in the second interest level information, is selected as the first behavior.

When there are multiple actions that satisfy the requirements, all of the multiple actions may be selected as the first action, one may be selected randomly, or the action with the highest ranking may be selected. Furthermore, when there are multiple actions that satisfy the requirements, the estimation unit 47 may store in the memory unit 43 the actions that were not selected as the first action as candidates for the second action described below.

Next, the transmission unit 45 transmits first action information indicating the estimated first action to the information terminal 30 (S15). When the first action information is received by the first communication unit 35, the control unit 33 of the information terminal 30 causes the display unit 32 to display an image indicating the first action based on the received first action information. FIG. 8 is a diagram showing an example of an image indicating the first action. In other words, the image in FIG. 8 is an image that recommends that the guardian P or the like associates the first action, which has not previously been linked to the block 21 of the toy 20, with the block 21 (performs a registration operation).

Furthermore, the estimation unit 47 determines whether or not the acquisition unit 44 has acquired schedule information in which the first action is scheduled within a certain period of time after the transmission unit 45 has transmitted the first action information (S16). The certain period of time is, for example, one month, but is not particularly limited. When it is determined that schedule information in which the first action is scheduled has been acquired within the certain period of time (Yes in S16), this means, in other words, that the guardian P or the like has viewed the image in step FIG. 8 and performed a registration operation to link the first action to one of the six types of blocks 21. In this case, the operation ends.

On the other hand, if it is determined that no schedule information in which a first action is scheduled has been acquired within a certain period of time (No in S16), this means, in other words, that the guardian P, etc. has not performed a registration operation to link the first action to any of the six types of blocks 21. In such a case, the transmission unit 45 transmits second action information indicating a second action different from the first action to the information terminal 30 in order to recommend another action to the guardian P, etc. (S17).

The second behavior may be estimated by performing the processes of steps S11 to S14 again, or may be selected from the second behavior candidates if the second behavior candidates are stored in the memory unit 43 when estimating the first behavior as described above.

As described above, the behavior estimation system 10 can estimate the behaviors that infant A is interested in and present them to the guardian P or the like. As described above, in the behavior estimation system 10, the association between the six types of blocks and the behaviors is performed by the guardian P or the like. In other words, the guardian P or the like selects the behaviors of infant A.

Here, research results show that in order to improve Infant A's self-esteem and to foster Infant A's autonomy, it is important for Infant A to engage in behavior that interests him/her. In order for Infant A to engage in behavior that interests him/her, it would be good if guardians P, etc. could imagine various behaviors of Infant A and make the above-mentioned connections; however, guardians P, etc. tend to unconsciously limit behavior due to the assumption that "my child must be interested in XX." The behavior estimation system 10 can support guardians P, etc., who tend to unconsciously limit behavior in this way, in discovering behaviors that interest Infant A.

[Operation example 2]
The behavior inference system 10 can also provide the first interest level information to the guardian P or the like. Hereinafter, a second operation example of the behavior inference system 10 will be described. Fig. 9 is a flowchart of the second operation example of the behavior inference system 10. Note that the second operation example is an operation example that does not use execution information, but execution information may also be used as in the first operation example.

First, the acquisition unit 44 of the server device 40 acquires schedule information indicating the planned activities of Infant A for a predetermined period of time planned by Infant A from the information terminal 30 (S21). As shown in FIG. 5, the schedule information is information in which at least some of the approximately 20 types of activities described above are associated with their scheduled times (time periods).

Next, the generation unit 46 generates first interest level information indicating the degree of interest of the child A in each of the multiple behaviors based on the acquired schedule information (S22). As shown in FIG. 6 above, the first interest level information is, for example, information that ranks the degree of interest of the child A in the multiple behaviors. The generation unit 46 generates the first interest level information using a machine learning model that uses, as input information, the scheduled time, the scheduled number of times, changes in the scheduled time over time, etc.

Next, the transmitting unit 45 transmits the generated first interest level information to the information terminal 30 (S23). The first communication unit 35 of the information terminal 30 receives the first interest level information, and when the first communication unit 35 receives the first interest level information, the control unit 33 causes the display unit 32 to display an image showing the first interest level information based on the received first interest level information. Figure 10 is a diagram showing an example of an image showing the first interest level information.

As described above, the behavior estimation system 10 can estimate the degree of interest of infant A in each behavior and present the estimation result to the guardian P, etc. In other words, the behavior estimation system 10 can assist the guardian P, etc. in discovering behaviors in which infant A is interested.

[Modification]
In the above embodiment, the toy 20 is used as a user interface. However, the schedule of the behavior of the infant A and the result of the behavior of the infant A may be directly input by operating the operation receiving unit 31 of the information terminal 30. In other words, the behavior estimation system 10 does not need to include the toy 20.

In addition, in the above embodiment, a machine learning model is used to generate the first interest level information, but it is not essential to use a machine learning model. For example, the simplest method of generating the first interest level information may be to calculate the total planned time for one month for each of the multiple activities included in the schedule information, and rank the activities in descending order of the total planned time. The first interest level information can also be generated by a similar method using parameters other than the planned time (such as the planned number of times or the execution time). In this way, a statistical method may be used to generate the first interest level information.

In addition, in the above embodiment, the behavior estimation system 10 targets young children, but it may also target people of other age groups, such as the elderly. The behavior estimation system 10 targets various users and can suggest behaviors that the users were not aware of and that may be of interest to the users.

[Effects, etc.]
In the first operation example, the behavior estimation system 10 includes an acquisition unit 44 that acquires at least one of schedule information indicating a schedule of the behavior of the first user for a predetermined period planned by the first user and result information indicating the actual behavior of the first user for the predetermined period, a generation unit 46 that generates first interest level information indicating the degree of interest of the first user in each of the plurality of behaviors based on the acquired at least one of the information, and an estimation unit 47 that estimates a first behavior in which the first user is interested other than the plurality of behaviors by comparing the generated first interest level information with a plurality of second interest level information each generated for another user. In the above embodiment, the first user is a child A.

When the first user is infant A, such a behavior estimation system 10 can estimate the behaviors that infant A is interested in.

Furthermore, for example, the estimation unit 47 performs the above comparison to identify second interest level information similar to the first interest level information from among the multiple pieces of second interest level information, and estimates the behavior included in the identified second interest level information as the first behavior.

Such a behavior estimation system 10 can estimate a first behavior in which a first user is interested based on second interest level information similar to the first interest level information.

For example, the first interest level information is information that ranks the first user's degree of interest in multiple behaviors. The estimation unit 47 performs a comparison to identify second interest level information that has a similar ranking to the first interest level information from among the multiple second interest level information, and estimates the behavior included in the identified second interest level information as the first behavior.

Such a behavior estimation system 10 can estimate a first behavior in which a first user is interested based on second interest level information that has a ranking similar to that of the first interest level information.

Also, for example, the acquisition unit 44 acquires both the schedule information and the result information. The generation unit 46 generates the first interest level information using one or more of the scheduled time of the action, the scheduled number of times of the action, the change over time of the scheduled time of the action, the execution time of the action, the number of times of the action, the change over time of the execution time of the action, the execution time of the action/scheduled time of the action, and the number of times of the action/scheduled number of times of the action, which are determined based on the acquired schedule information and result information.

Such a behavior estimation system 10 can generate first interest level information using one or more of these parameters.

Also, for example, the acquisition unit 44 acquires at least one of the pieces of information from the information terminal 30. The behavior estimation system 10 further includes a transmission unit 45 that transmits first behavior information indicating the estimated first behavior to the information terminal.

Such a behavior estimation system 10 can generate first interest level information using one or more of these parameters.

Also, for example, when the acquisition unit 44 does not acquire scheduled information in which the first action is scheduled within a certain period of time after the first action information is transmitted, the transmission unit 45 transmits to the information terminal 30 second action information indicating a second action different from the first action, which is presumed to be of interest to the first user other than the multiple actions.

Such a behavior estimation system 10 can assist the owner of the information terminal 30 (e.g., parent P) in discovering behaviors that interest the first user (child A).

For example, the behavior estimation system 10 further includes an information terminal 30, and the information terminal 30 includes a first communication unit 35 that receives the first behavior information, and a display unit 32 that displays an image showing the first behavior based on the received first behavior information.

Such a behavior estimation system 10 can assist the owner of the information terminal 30 (e.g., parent/guardian P) in discovering behaviors that interest the first user (child A) by displaying an image showing the first behavior on the display unit 32.

For example, the first user is infant A, and the behavior estimation system 10 further includes a toy 20 having a plurality of blocks 21 and a case 22 that houses the plurality of blocks 21, where the first user can rearrange the arrangement of the plurality of blocks 21 within the case 22. The information terminal 30 further includes a second communication unit 36 that receives, from the toy 20, arrangement information indicating the arrangement of the plurality of blocks 21 within the case 22, and a control unit 33 that generates schedule information by regarding the arrangement of the plurality of blocks 21 determined by the received arrangement information as the first user's planned behavior for a predetermined period of time proposed by the first user.

Such a behavior estimation system 10 can estimate the behaviors that infant A is interested in based on the scheduled information determined by infant A's placement of blocks 21 in the case 22.

In addition, in the second operational example, the behavior estimation system 10 includes an acquisition unit 44 that acquires schedule information indicating the user's planned behavior for a predetermined period of time planned by the user, and a generation unit 46 that generates first interest level information indicating the user's degree of interest in each of a plurality of behaviors based on the acquired schedule information. In the above embodiment, the first user is infant A.

When the first user is infant A, such a behavior estimation system 10 can estimate the behaviors that infant A is interested in.

Also, for example, the acquisition unit 44 acquires at least one of the pieces of information from the information terminal 30. The behavior estimation system 10 further includes a transmission unit 45 that transmits the first interest level information to the information terminal 30.

Such a behavior estimation system 10 can assist the owner of the information terminal 30 (e.g., parent P) in discovering behaviors that interest the first user (child A).

A program for operating a general-purpose computer as an information terminal 30 performs processing as shown in FIG. 11. FIG. 11 is a flowchart showing the processing procedure of such a program. This program is a program for causing a computer to execute an information processing method including a first receiving step (S31) of receiving arrangement information indicating an arrangement of the plurality of blocks 21 in the case 22 from the toy 20 having a plurality of blocks 21 and a case 22 for storing the plurality of blocks 21, the toy 20 allowing a user to rearrange the arrangement of the plurality of blocks 21 in the case 22, a generating step (S32) of generating schedule information indicating a schedule of the user's actions for a predetermined period based on the received arrangement information, and a transmitting step (S33) of transmitting the generated schedule information to the server device 40. In the above embodiment, the user is a child A.

Such a program can cause the computer to transmit to the server device 40 schedule information that is determined by infant A placing blocks 21 in the case 22. In other words, such a program can assist the server device 40 in estimating the behaviors that infant A is interested in.

Also, for example, the information processing method includes a second receiving step (S34) of receiving from the server device 40 behavioral information indicating a behavior in which the user is interested that is estimated by the server device 40 after the sending step (S33), and a display step (S35) of displaying an image indicating the above behavior based on the received behavioral information.

By displaying images showing the above-mentioned behaviors, such a program can help the computer owner (e.g., parent P) discover behaviors that interest the user (child A).

(Other embodiments)
Although the embodiment has been described above, the present invention is not limited to the above embodiment.

For example, in the above embodiment, the behavior estimation system is realized by multiple devices, but it may be realized as a single device. For example, the behavior estimation system may be realized as a single device equivalent to a server device. When the behavior estimation system is realized by multiple devices, the components of the behavior estimation system may be allocated in any manner to the multiple devices.

For example, the method of communication between the devices in the above embodiment is not particularly limited. In addition, a relay device (not shown) may be used in the communication between the devices.

In addition, in the above embodiment, the processing performed by a specific processing unit may be executed by another processing unit. The order of multiple processes may be changed, or multiple processes may be executed in parallel. Furthermore, operation example 1, operation example 2, and the modified example of the above embodiment may be combined in any manner.

In the above embodiment, each component may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

In addition, each component may be realized by hardware. For example, each component may be a circuit (or an integrated circuit). These circuits may form a single circuit as a whole, or each may be a separate circuit. In addition, each of these circuits may be a general-purpose circuit or a dedicated circuit.

In addition, the general or specific aspects of the present invention may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM. Also, the present invention may be realized as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

For example, the present invention may be realized as a behavior estimation method executed by a computer such as a behavior estimation system, or as a program for causing a computer to execute such a behavior estimation method. The present invention may also be realized as a program for causing a general-purpose computer to operate as the information terminal of the above-mentioned embodiment. The present invention may also be realized as a computer-readable non-transitory recording medium on which these programs are recorded.

In addition, the present invention also includes forms obtained by applying various modifications to each embodiment that a person skilled in the art may conceive, or forms realized by arbitrarily combining the components and functions of each embodiment within the scope of the spirit of the present invention.

REFERENCE SIGNS LIST 10 Behavior estimation system 20 Toy 21 Block 22 Case 30 Information terminal 31 Operation reception unit 32 Display unit 33 Control unit 34 Memory unit 35 First communication unit 36 Second communication unit 40 Server device 41 Communication unit 42 Information processing unit 43 Memory unit 44 Acquisition unit 45 Transmission unit 46 Generation unit 47 Estimation unit A, B Infant P Parent

Claims (10)

an acquisition unit that acquires at least one of schedule information indicating a schedule of an action of the first user during a predetermined period planned by the first user and result information indicating an actual action of the first user during the predetermined period;
a generation unit that calculates parameters related to the time or number of times each of the plurality of behaviors is scheduled or performed based on the at least one of the acquired information, and generates first interest level information indicating the degree of interest of the first user in each of the plurality of behaviors by inputting the calculated parameters into a machine learning model or by statistically processing the calculated parameters;
an estimation unit that estimates a first behavior in which the first user is interested other than the plurality of behaviors by comparing the generated first interest level information with a plurality of second interest level information each generated for another user. The behavior inference system according to claim 1 , wherein the estimation unit identifies second interest level information similar to the first interest level information from among the plurality of second interest level information by performing the comparison, and infers the behavior included in the identified second interest level information as the first behavior. the first interest level information is information that ranks the first user's degree of interest in the plurality of behaviors,
3. The behavior inference system according to claim 2, wherein the estimation unit, by performing the comparison, identifies, from the plurality of pieces of second interest level information, second interest level information having a ranking similar to that of the first interest level information, and infers, as the first behavior, a behavior included in the identified second interest level information. The acquisition unit acquires both the schedule information and the result information,
4. The behavior inference system according to claim 1, wherein the generation unit generates the first interest level information using one or more of a planned time of the behavior, a planned number of times of the behavior, a change over time of the planned time of the behavior, an execution time of the behavior, a number of times of the behavior, a change over time of the execution time of the behavior, an execution time of the behavior/planned time of the behavior, and a number of times of the behavior/planned number of times of the behavior, which are determined based on the acquired schedule information and result information. The acquisition unit acquires the at least one piece of information from an information terminal,
The behavior inference system according to claim 1 , further comprising a transmission unit configured to transmit first behavior information indicating the estimated first behavior to the information terminal. 6. The behavior estimation system according to claim 5, wherein the transmitting unit transmits to the information terminal second behavior information indicating a second behavior different from the first behavior, which is estimated to be of interest to the first user other than the plurality of behaviors, when the acquiring unit does not acquire schedule information in which the first behavior is scheduled within a certain period after the first behavior information is transmitted. The behavior estimation system further includes the information terminal,
The information terminal includes:
A first communication unit that receives the first action information;
The behavior inference system according to claim 5 , further comprising: a display unit configured to display an image indicating the first behavior based on the received first behavior information. the first user is a child,
the behavior estimation system further includes a toy having a plurality of blocks and a case for accommodating the plurality of blocks, the toy allowing the first user to rearrange the arrangement of the plurality of blocks in the case;
The information terminal further includes:
a second communication unit that receives, from the toy, arrangement information indicating an arrangement of the plurality of blocks in the case;
and a control unit that generates the schedule information by regarding the arrangement of the plurality of blocks determined by the received arrangement information as a schedule of the first user's behavior during the specified period planned by the first user. An acquisition unit that acquires schedule information indicating a schedule of an action of a user for a predetermined period of time planned by the user;
a generation unit that calculates parameters related to the scheduled time or number of times for each of a plurality of behaviors based on the acquired schedule information, and generates interest level information indicating the user's degree of interest in each of the plurality of behaviors by inputting the calculated parameters into a machine learning model or by performing statistical processing on the calculated parameters. The acquisition unit acquires the schedule information from an information terminal,
The behavior inference system according to claim 9 , further comprising a transmission unit that transmits the interest level information to the information terminal.

Images