System, presentation method, and presentation program

Abstract

An agent system according to the present disclosure comprises a control unit that performs a presentation corresponding to a specified target on the basis of information pertaining to the sensed state of a user. The control unit performs a plurality of presentations corresponding to the specified target in ascending order of fluctuations in the state of the user.

Description

System, presentation method and presentation program

[0001] The present disclosure relates to a system, a presentation method, and a presentation program.

[0002] Conventionally, there are agent systems that make various suggestions to users from terminal devices such as AI speakers. A known prior art for this agent system is one that automatically generates predetermined behavioral norms (means for solving problems within a community, predetermined value standards (i.e., values), predetermined lifestyle rhythms, etc.) and indirectly encourages behavioral changes based on the behavioral norms to solve community problems.

[0003] Japanese Patent Application Laid-Open No. 2021-182170

[0004] However, the above-mentioned conventional technology has a problem in that there are cases where suggestions that are unacceptable to the user continue, which may increase distrust and discomfort towards the agent system.

[0005] Therefore, the present disclosure provides a system, a presentation method, and a presentation program that can prevent users from growing distrustful or uncomfortable about the agent system.

[0006] It should be noted that the above problem or object is merely one of multiple problems or objects that can be solved or achieved by multiple embodiments disclosed in this specification.

[0007] The system of the present disclosure includes a control unit that provides a presentation corresponding to a target identified based on information about the sensed state of the user, and the control unit presents a plurality of presentations corresponding to the identified target in descending order of the degree of change relative to the state of the user.

[0008] FIG. 1 is a block diagram illustrating an example of a configuration of an agent system according to an embodiment. FIG. 2 is a block diagram illustrating an example of a functional configuration of the agent system according to an embodiment. FIG. 3 is an explanatory diagram illustrating an example of definition information (solution). FIG. 4 is an explanatory diagram illustrating an example of definition information (measure). FIG. 5 is a flowchart illustrating an example of an operation of the agent system according to an embodiment. FIG. 6 is a flowchart illustrating an example of an operation of a process for making another proposal. FIG. 7 is a flowchart illustrating an example of an operation of a process for encouraging the creation of a new request. FIG. 8 is an explanatory diagram illustrating an example of definition information (solution) according to Example 1. FIG. 9 is an explanatory diagram illustrating an example of definition information (solution) according to Example 2. FIG. 10 is an explanatory diagram illustrating an example of a proposal according to Example 3. FIG. 11 is an explanatory diagram illustrating an example of a proposal according to Example 4. FIG. 12 is an explanatory diagram illustrating an example of definition information (measure) according to Example 4. FIG. 13 is an explanatory diagram illustrating an example of definition information (measure) according to Example 5. FIG. 14 is an explanatory diagram illustrating an example of definition information (measure) according to Example 5. FIG. 15 is an explanatory diagram illustrating an example of definition information (measure) according to Example 6. FIG. 16 is an explanatory diagram illustrating an example of an option according to Example 7. FIG. 17 is a hardware configuration diagram illustrating an example of a computer.

[0009] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant description will be omitted.

[0010] Furthermore, in this specification and drawings, similar components of the embodiments may be distinguished by adding at least one different alphabet and / or number after the same reference numeral. However, if there is no need to particularly distinguish between similar components, the same reference numeral will be used. For example, multiple configurations having substantially the same functional configurations may be distinguished as necessary, such as definition information (solution) 132a and definition information (measure) 132b (see FIGS. 3 and 4). For example, if there is no need to particularly distinguish between definition information (solution) 132a and definition information (measure) 132b, they will simply be referred to as definition information 132 (see FIG. 2).

[0011] One or more embodiments (including examples, modifications, and application examples) described below can be implemented independently. However, at least a portion of the embodiments described below may be implemented in appropriate combination with at least a portion of another embodiment. These embodiments may include novel features that are different from each other. Therefore, these embodiments may contribute to solving different purposes or problems and may produce different effects from each other.

[0012] (System Configuration) Fig. 1 is a block diagram showing an example of the configuration of an agent system according to an embodiment. As shown in Fig. 1, one example of the configuration of an agent system 100 is a configuration in which an information processing device 1 such as a server device and a terminal device 2 used by a user are connected via a network 3 such as the Internet or a LAN (Local Area Network).

[0013] The information processing device 1 controls the presentation of information to the terminal device 2 connected via the network 3, such as specifying the content that the terminal device 2 presents to the user.

[0014] The terminal device 2 can be applied to various devices used by users, such as AI speakers, tablet terminals, smartphones, PCs (personal computers), televisions, air conditioners, and in-vehicle devices (e.g., navigation devices) installed in vehicles used by users.

[0015] In the above-described example of the configuration of the agent system 100, control over presentation, such as specifying the content to be presented to the user, is performed by an information processing device 1 separate from the terminal device 2, but the configuration is not limited to this. For example, the agent system 100 may be configured as a single terminal device 2, in which control over presentation is performed by the terminal device 2.

[0016] 2 is a block diagram showing an example of the functional configuration of the agent system 100 according to the embodiment. As shown in FIG. 2, the agent system 100 includes an input unit 10, a processing unit 11, an output unit 12, and a storage unit 13.

[0017] The input unit 10 is a processing unit that receives as input the state of the user acquired from various sensors such as a microphone, camera, acceleration sensor, biosensor, and temperature sensor of the terminal device 2. Specifically, the input unit 10 receives input of sensed data via the network 3 from devices such as a webcam, microphone, acceleration sensor / gyro sensor, heart rate monitor / electroencephalograph, and digital thermometer installed on the terminal device 2 or separately from the terminal device 2.

[0018] The processing unit 11 receives information from the input unit 10 and determines feedback (presentation) to the user. For example, the processing unit 11 can apply a control layer of a general OS (Operating System) that controls a window that displays an application, drawing of multiple content, and delivers events such as touches to each content. The processing unit 11 is an example of a control unit.

[0019] The processing unit 11 includes a user information sensing unit 111 , an expectation value grasping unit 112 , a problem grasping unit 113 , a solution definition unit 114 , a policy definition unit 115 , a simulation unit 116 , and a feedback unit 117 .

[0020] The user information sensing unit 111 is a processing unit that determines the user's state based on information sensed by various sensors, such as a microphone, camera, acceleration sensor, gyro sensor, biometric sensor, and temperature sensor, received by the processing unit 11. Specifically, the user information sensing unit 111 recognizes the user's movements and facial expressions based on the user's body or face information recognized from camera footage. The user information sensing unit 111 also recognizes the user's speech from audio input through a microphone. The user information sensing unit 111 also recognizes the user's state from input signals from various biometric sensors (such as an electroencephalogram sensor, pulse sensor, body temperature sensor, and blood pressure sensor). The user information sensing unit 111 also recognizes the user's surrounding environment (e.g., temperature and humidity) from measurements such as a digital thermometer and digital humidity sensor. The user's state determined by the user information sensing unit 111 is, for example, a numerical value representing emotions such as joy, anger, sadness, and happiness, temperature, etc., expressed as a score or the like. As an example, user states with similar values ​​are considered to have low fluctuations, while user states with widely differing values ​​are considered to have high fluctuations.

[0021] The expectation value grasping unit 112 is a processing unit that grasps the desired state of the user to be expected based on the state of the user determined by the user information sensing unit 111. Specifically, if the user's facial expression determined by the user information sensing unit 111 indicates an angry or sad state, the expectation value grasping unit 112 grasps the opposite state, that is, a state of enjoyment or happiness, as the desired state. Furthermore, if the user information sensing unit 111 detects that the user is asleep or about to fall asleep (looking sleepy) from the user's facial expression determined by the user information sensing unit 111, the expectation value grasping unit 112 grasps a state of sound sleep as the desired state.

[0022] Furthermore, when the user information sensing unit 111 determines that the user's movement is while driving (riding) a car, the expected value understanding unit 112 understands that the user's wakefulness (a state without car sickness) is the desired state. Furthermore, when the user information sensing unit 111 determines that the temperature around the user is not within a predetermined temperature range (for example, low or high temperature), the expected value understanding unit 112 understands that the temperature falls within the predetermined temperature range as the desired state. Note that the above is just an example of how the desired state is understood based on the user's state, and is not limited to the above.

[0023] The problem grasping unit 113 is a processing unit that identifies problems that hinder the user's desirable state and suggested options for achieving the desirable state grasped by the expected value grasping unit 112. Specifically, the problem grasping unit 113 identifies problems that hinder the desirable state and suggested options by referring to a table in which problems and suggested options for each desirable state are set.

[0024] The solution definition unit 114 is a processing unit that defines a solution (a solution method) for the problem identified by the problem understanding unit 113. Specifically, the solution definition unit 114 defines a solution for the identified problem based on definition information 132 that is stored in advance in the storage unit 13.

[0025] 3 is an explanatory diagram showing an example of the definition information (solution) 132a. As shown in FIG. 3, the definition information (solution) 132a defines, for each problem, the solution, category, benefits, disadvantages, etc. corresponding to the problem. The solution indicates the content to be presented to the user as a solution to the problem.

[0026] The category indicates the category to which the solution belongs. For example, the category indicates modals such as "sight, smell, taste" or environmental indicators such as "temperature, humidity."

[0027] The effect indicates the magnitude of the effect (the magnitude of the change in the user's state) when the solution is presented to the user. For example, the effect may be indicated as a value of "large, medium, or small."

[0028] The demerit indicates the magnitude of the demerit (the magnitude of the change in the user's state) if the solution is not effective when presented to the user. For example, the demerit can be displayed as a value of "large, medium, or small."

[0029] The policy definition unit 115 is a processing unit that defines policies for the proposal of the option identified by the problem understanding unit 113. Specifically, the policy definition unit 115 defines policies for the proposal of the identified option based on definition information 132 that is stored in advance in the storage unit 13.

[0030] 4 is an explanatory diagram showing an example of the definition information (measures) 132b. As shown in FIG. 4, the definition information (measures) 132b defines, for each option proposal, the corresponding measures, categories, targets, etc. The measures indicate the content of the measures to be presented to the user to propose options. The implementation order of these measures is preset in the definition information (measures) 132b (e.g., from top to bottom). Specifically, the implementation order is set so that measures that will have the least effect on the user's state when implemented are ranked higher.

[0031] The category indicates the category to which the measure belongs. For example, the category indicates environment if the measure is to change the temperature environment, content if the measure is to present content, etc.

[0032] The target indicates a specific target of the measure. For example, the target indicates temperature when the measure is to change the temperature environment, or commercials when the measure is to present content.

[0033] Returning to Fig. 2, the simulation unit 116 is a processing unit that simulates the user's reaction when a solution to the problem identified by the problem understanding unit 113 or a proposed option identified by the problem understanding unit 113 is presented to the user. Specifically, the simulation unit 116 uses a known simulation technique to simulate the user's reaction (changes in the user's state) when a solution or option is presented to the user in the current user state determined by the user information sensing unit 111. Based on the simulation results, the simulation unit 116 calculates the probability that the user will accept the solution or option.

[0034] The feedback unit 117 is a processing unit that, when a solution to a problem identified by the problem identification unit 113 or a measure corresponding to an option identified by the problem identification unit 113 is presented to the user, provides feedback regarding the solution or the measure corresponding to the option based on the user's state determined by the user information sensing unit 111.

[0035] Specifically, the feedback unit 117 determines the content of the feedback based on whether the user's state when the solution or measure was presented approached the desired state ascertained by the expected value ascertainment unit 112, and updates the definition information 132 with the determined content.

[0036] For example, if the user's state when a predetermined solution is presented approaches the desired state grasped by the expected value grasping unit 112, the feedback unit 117 changes the value of the effect in the definition information (solution) 132a to a larger value. Also, if the user's state when a predetermined solution is presented deviates from the desired state grasped by the expected value grasping unit 112, the feedback unit 117 changes the value of the demerit in the definition information (solution) 132a to a larger value. Also, if the user's state when a predetermined measure is presented approaches the desired state grasped by the expected value grasping unit 112, the feedback unit 117 moves the implementation order of the measure in the definition information (measure) 132b up. Also, if the user's state when a predetermined measure is presented deviates from the desired state grasped by the expected value grasping unit 112, the feedback unit 117 moves the implementation order of the measure in the definition information (measure) 132b down.

[0037] The output unit 12 is a processing unit that presents the solution or measure defined by the processing unit 11 to the user. Specifically, the output unit 12 outputs the solution or measure to the terminal device 2 via the network 3. The terminal device 2 presents the solution or measure output by the output unit 12 to the user.

[0038] For example, if the solution or measure is a voice output or a screen display, the terminal device 2 outputs a voice or displays a screen based on the content of the solution. Note that the presentation of the solution or measure described above is just one example, and the terminal device 2 may output a scent using an aroma diffuser, for example. Furthermore, the terminal device 2 may operate a home appliance such as an air conditioner in response to the presentation of the solution or measure.

[0039] The storage unit 13 is a storage device that stores various types of information in a manner that allows the information processing device 1, the terminal device 2, or the network 3 to read and write the information. Specifically, the storage unit 13 stores user information 131 related to users, and definition information 132 including the above-mentioned definition information (solution) 132a and definition information (measure) 132b.

[0040] The user information 131 includes, for example, information received by the processing unit 11 and obtained by sensing the user using a microphone, camera, or the like. The user information 131 also includes attribute information related to the user's attributes (e.g., including at least one attribute such as gender, age, nationality, religion, or race). The user information 131 also includes setting information previously set by the user regarding the presentation of solutions or measures (details will be described later). This attribute information and setting information are previously set by the user via the terminal device 2, etc.

[0041] 5 is a flowchart showing an example of the operation of the agent system 100 according to the embodiment. As shown in FIG. 5, when the process starts, the processing unit 11 performs a loop process (S1 to S10) until the system is terminated.

[0042] Specifically, the user information sensing unit 111 senses the user's state and acquires (determines) the user's state (S2).

[0043] Next, the expected value grasping unit 112 grasps the desired state of the user that should be expected based on the state of the user determined by the user information sensing unit 111 (S3).

[0044] Next, the problem grasping unit 113 identifies problems that hinder the user's desirable state grasped by the expectation value grasping unit 112, and suggestions of options that will bring about the desirable state.

[0045] Next, the solution definition unit 114 refers to the definition information (solution) 132a and defines one or more solutions (solution methods) corresponding to the problem identified by the problem understanding unit 113. Here, the solution definition unit 114 may narrow down the identified solutions based on attribute information included in the user information. Specifically, the solution definition unit 114 narrows down the identified solutions to those whose content matches the attribute information.

[0046] Furthermore, the policy definition unit 115 refers to the definition information (policy) 132b and defines one or more policies corresponding to the proposed options identified by the issue understanding unit 113. Here, the policy definition unit 115 may narrow down the identified multiple policies based on attribute information included in the user information. Specifically, the policy definition unit 115 narrows down the identified multiple policies to those whose content matches the attribute information.

[0047] Next, the processing unit 11 determines whether there is any content to be proposed (presented) (solution or option proposal) (S4). If there is no content to be proposed (S4: No), the processing unit 11 skips the process to S10.

[0048] If there is content to be proposed (S4: Yes), the processing unit 11 determines whether the content to be proposed is a solution proposal for the problem (S5). If it is a solution proposal for the problem (S5: Yes), the processing unit 11 executes processing to make another proposal to confirm the problem (S6), and proceeds to S10.

[0049] 6 is a flowchart showing an example of an operation of the process of making another proposal. As shown in FIG. 6, when the process starts, the problem grasping unit 113 identifies a problem, and the solution definition unit 114 identifies a solution corresponding to the problem identified by the problem grasping unit 113 by referring to the definition information (solution) 132a (S20).

[0050] Next, the simulation unit 116 performs a simulation in which the identified solution is presented to the user, and acquires the state of the user after the presentation (S21).

[0051] Next, the processing unit 11 determines, based on the simulation results, whether or not a new problem will arise as a result of the solution if the proposal fails (S22).

[0052] Specifically, the expected value grasping unit 112 grasps the user's desired state after the solution is presented to the user based on the user's state after the presentation. Next, the problem grasping unit 113 determines whether there is a new problem that hinders the user's desired state after the presentation grasped by the expected value grasping unit 112.

[0053] If no new problem arises (S22: No), the processing unit 11 proceeds to S29.

[0054] If a new problem arises (S22: Yes), the processing unit 11 refers to the definition information (solution) 132a to identify solutions corresponding to the problem (S23), and executes a loop process (S24 to S28) to present solutions in order of least change to the user's state, that is, solutions with least effect but least disadvantage. This loop process is performed a number of times (the number of solutions - 1) for the solutions corresponding to the problem obtained by referring to the definition information (solution) 132a.

[0055] Specifically, when the loop processing (S24 to S28) starts, the processing unit 11 presents the solution with the lowest effect among the identified solutions that have not yet been implemented, since this solution is the solution with the lowest change in the user's condition (S25). Specifically, the processing unit 11 presents solutions with low effect and low disadvantages. For example, if two solutions have the same effect, a solution with a low disadvantage is the solution with the lowest change in the user's condition. Therefore, by presenting a solution with a low disadvantage, the processing unit 11 can further reduce the change in the user's condition.

[0056] Next, the user information sensing unit 111 senses the state of the user after the solution is presented, and acquires (determines) the state of the user (S26).

[0057] Next, the processing unit 11 determines whether or not there are signs of problem resolution based on the user's state acquired in S26 (S27). Specifically, the processing unit 11 determines whether or not the user's state acquired in S26 approaches the user's desired state ascertained by the expectation value ascertainment unit 112. For example, if the user's state approaches the user's desired state, the processing unit 11 determines that there are signs of problem resolution. On the other hand, if the user's state is far from the user's desired state, the processing unit 11 determines that there are no signs of problem resolution.

[0058] If no sign of problem solution is found (S27: No), the processing unit 11 proceeds to S28 and proceeds to the next loop. This allows the agent system 100 to present solutions to the user in order of least effective.

[0059] If there are signs of problem solution (S27: Yes), the processing unit 11 presents the most effective solution among the identified solutions (S29), and ends the process.

[0060] When the loop process (S24 to S28) is completed, the processing unit 11 redefines the request (task) (S30) and terminates the process.

[0061] Returning to FIG. 5, if the content to be proposed is not a proposal for a solution to a problem (S5: No), the processing unit 11 determines whether the content to be proposed is a proposal for an option (S7).

[0062] If the content to be proposed is not a proposal of an option (S7: No), the processing unit 11 directly presents the content of the proposal to the terminal device 2 (S9), and the process proceeds to S10.

[0063] If the content to be proposed is a proposal of an option (S7: Yes), the processing unit 11 executes a process to encourage the user to make a new request (acceptance of the option) (S8).

[0064] 7 is a flowchart showing an example of an operation of a process for encouraging the user to make a new request. As shown in FIG. 7, when the process starts, the processing unit 11 defines options for achieving a desired state (satisfying the user's request) (S40), and executes a loop process (S41 to S47) for a predetermined number of attempts (N). The number of attempts (N) is set in advance by the user via the terminal device 2 or the like.

[0065] When the loop process (S41 to S47) starts, the simulation unit 116 simulates a case where the defined options are presented to the user (S42).

[0066] Next, the simulation unit 116 calculates the probability that the option will be accepted based on the simulation results, and determines whether the calculated probability is equal to or greater than a predetermined value (R [%]) (S43).

[0067] If the probability that the option will be accepted is equal to or greater than a predetermined value (S43: Yes), the processing unit 11 presents the option (S46) and ends the process.

[0068] If the probability that the option will be accepted is not equal to or greater than a predetermined value (S43: No), the processing unit 11 refers to the definition information (measures) 132b, identifies measures corresponding to the option in accordance with the implementation order, and outputs the measures to the terminal device 2. The terminal device 2 implements (presents) the output measures (S44). Next, the user information sensing unit 111 senses the user's state to acquire (determine) the user's state (S45), and the process proceeds to S47.

[0069] In S47, if the number of attempts is less than the predetermined number (N), the process returns to S41. If the number of attempts is equal to or greater than the predetermined number (N), the processing unit 11 does not present the option (rejects the option) and ends the process.

[0070] Examples 1 to 8 of the agent system 100 according to the above embodiment will be described below.

[0071] Example 1 In Example 1, "reducing car sickness during automatic driving" is shown as an example in which another proposal is made to confirm the user's problem.

[0072] Fig. 8 is an explanatory diagram illustrating an example of definition information (solution) 132a according to Example 1. As shown in the definition information (solution) 132a in Fig. 8, solutions to the problem of "car sickness" include, for example, "reducing speed," "presenting an odor," and "opening a window."

[0073] Among these solutions, the most effective solution is "reducing vibration by reducing speed," but this has the disadvantage of delaying the arrival time if the user is not carsick. Therefore, based on the definition information (solution) 132a, the agent system 100 executes less effective solutions such as "opening a window" and "presenting a scent (e.g., mint scent)." Next, if the agent system 100 observes a reduction in the user's car sickness, it determines that the user is experiencing car sickness and implements "reducing speed." If the user does not observe a reduction in the car sickness, it determines that the problem is not car sickness and stops presenting solutions for car sickness. In this way, the agent system 100 can prevent the user from growing distrust and discomfort toward the system.

[0074] (Example 2) In Example 2, "adjusting light to fall asleep" is shown as an example in which another suggestion is made to confirm the user's problem.

[0075] 9 is an explanatory diagram illustrating an example of definition information (solution) 132a according to Example 2. As shown in the definition information (solution) 132a in Fig. 9, solutions to the problem of "sleeping with the lights on" include "light adjustments to help fall asleep," such as "turning off the lights in the room," "dimming the lights in the room," "turning off indirect lighting," and "closing the curtains."

[0076] For example, suppose the agent system 100 detects that the user is reading a book late at night, yawns, and becomes sleepy. In this case, the agent system 100 presents a solution to the problem of "falling asleep with the lights on." Here, the agent system 100 determines whether the user has the intention to sleep by presenting step-by-step solutions.

[0077] In this case, all of the solutions will be in the "lighting" category, so a sub-parameter "distance from user" is set in the definition information (solution) 132a. Based on this sub-parameter, the agent system 100 presents solutions that have the least impact on the user, starting with those that are farther away. If the agent system 100 detects that the user is trying to turn up the light during the process, it determines that the user is not interested in sleeping and stops adjusting the light.

[0078] (Example 3) For example, when recommending tourist spots to a user who is planning a trip, there is a problem that the user feels uncomfortable if the suggested candidate spots do not match the user's preferences. Therefore, this problem is solved by encouraging the user to create a new request.

[0079] In the third embodiment, the agent system 100 displays, for example, things reminiscent of tourist spots in the car in stages as a presentation, and determines the content of the suggestion depending on whether the user shows interest.

[0080] Fig. 10 is an explanatory diagram illustrating an example of a proposal according to Example 3. Specifically, Fig. 10 illustrates images to be presented to the user as proposal contents P1 to P9 that evoke tourist destinations.

[0081] 10, the agent system 100 presents a suggestion P1 showing an animal that is reminiscent of a character from a popular theme park, and determines whether the user shows interest in the animal by engaging in a conversation, pointing, gazing, etc. If the user shows no interest, the agent system 100 presents a suggestion P2 that is reminiscent of a character from another theme park, or a suggestion P7 that is reminiscent of a smell.

[0082] Next, if the user shows interest in proposals P1, P4, and P7, the agent system 100 sequentially presents more specific proposals. For example, if the user shows interest in proposal P1, the agent system 100 presents proposal P2, and if the acceptance probability of the destination (option) is equal to or greater than a predetermined value, presents proposal P3 related to the destination (option).

[0083] Similarly, if the user shows interest in proposal P4, the agent system 100 presents proposal P5, and if the acceptance probability of the destination (option) is equal to or greater than a predetermined value, presents proposal P6 related to the destination. Also, if the user shows interest in proposal P7, the agent system 100 presents proposal P8, and if the acceptance probability of the destination (option) is equal to or greater than a predetermined value, presents proposal P9 related to the destination.

[0084] Example 4 In Example 4, a "recipe suggestion" is shown as an example of encouraging the user to make a new request.

[0085] Fig. 11 is an explanatory diagram illustrating an example of a proposal according to Example 4. Fig. 12 is an explanatory diagram illustrating an example of definition information (measures) 132b according to Example 4.

[0086] As shown in the definition information (measure) 132b in FIG. 12 , when a user is enjoying a travel guide using an AR-HUD (Head-Up Display) or an AR / VR-HMD (Head-Mounted Display), an advertisement suggests the option of eating Chinese food. In this case, as shown in FIG. 11 , the agent system 100 presents a Chinese-style advertisement image G11, such as a dragon, on an AR-HUD screen G1 in a city, and recommends Chinese food as an option. In this way, the agent system 100 can increase the probability of the user selecting Chinese food by evoking the image of Chinese food in the user's mind. Here, a HUD is a display device that projects information directly into the user's field of vision. An HMD is a display device worn on the user's head. For example, in HUDs and HMDs, a translucent display is placed in front of the user's eyes, overlaying information on the user's normal field of vision. The advertisement image G11 is a virtual object that is displayed superimposed on real space. In the above example, a Chinese-style virtual advertisement, such as a dragon, is used to remind the user of Chinese food, but the virtual object is not limited to this and may be any type. Furthermore, the virtual object may be one that allows the user to arbitrarily set in advance what type of virtual object to display. The virtual object may be a static virtual object that does not move by itself, or a dynamic virtual object that moves by itself.

[0087] Fifth Embodiment In a fifth embodiment, a case is shown in which the indoor environment, such as temperature and humidity, is changed to make it easier for the user to perform the suggested actions (drink carbonated water, sleep). Figures 13 and 14 are explanatory diagrams showing an example of definition information (measures) 132b according to the fifth embodiment.

[0088] 13, when suggesting drinking carbonated water for health reasons, the agent system 100 increases the temperature and humidity to make the user want to drink carbonated water, thereby increasing the probability that the suggestion (drink carbonated water) will be accepted.

[0089] Similarly, when suggesting sleep as a break, as shown in the definition information (measure) 132b of FIG. 14, the agent system 100 increases the temperature to create an environment that makes the user sleepy.

[0090] (Example 6) Example 6 shows a case where commercials are inserted before, after, or at key points in a video to make it easier for the user to follow a suggestion (e.g., eat salad for dinner). Fig. 15 is an explanatory diagram showing an example of definition information (measure) 132b according to Example 6.

[0091] 15, when suggesting that a person who is lacking in vegetables eat salad, the agent system 100 inserts a commercial for a vitamin supplement before or after or at a turning point in a video that the user watches on a daily basis. In this way, the agent system 100 does not directly suggest eating vegetables, but makes the user aware of the importance of vitamins, making them want to eat vegetables, and thus increasing the probability that the suggestion will be accepted.

[0092] Seventh Embodiment In a seventh embodiment, a case where options available to a user are narrowed down in order to guide the user to a desired action that is ultimately proposed is shown. Fig. 16 is an explanatory diagram showing an example of options according to the seventh embodiment.

[0093] 16, when suggesting to a seated user that they go for a walk, the agent system 100 may present suggestions (options) P10 and P11 that are easier than going for a walk, such as "recommend going to the kitchen to get a drink of water" or "check the contents of the refrigerator." In this way, the agent system 100 can ultimately encourage the user to go for a walk (go out to do some shopping).

[0094] Eighth Embodiment In an eighth embodiment, the processing unit 11 of the agent system 100 improves usability by optimizing (updating) the predefined definition information 132 according to the user.

[0095] The processing unit 11 of the agent system 100 may use reinforcement learning, which senses the user's reaction after making a suggestion and evaluates and learns from the user's satisfaction, as a method of optimizing the definition information 132. In this case, there is a risk that the agent system may provide the user with a low-accuracy suggestion during the search stage, which could damage the user's trust. Therefore, the agent system 100 performs search (low-accuracy suggestions) in the morning and makes high-accuracy suggestions in the afternoon. This results in high-accuracy, high-quality suggestions in the latter half of the day, allowing the user to feel the improvement in accuracy. In this way, the agent system 100 is able to perform reinforcement learning without reducing the user's overall satisfaction for the day.

[0096] (Effects) As described above, the agent system 100 includes a processing unit 11 that makes presentations corresponding to identified goals based on the sensed state of the user. The processing unit 11 presents multiple presentations corresponding to the identified goals in descending order of their effect on the user's state. In this way, the agent system 100 makes presentations that have little effect on the user's state, thereby preventing the user from receiving a series of presentations that are unacceptable to the user. In other words, the agent system 100 can prevent the user from feeling distrust or discomfort toward the system.

[0097] Furthermore, when the goal is to solve a predetermined problem, if the presentation of a problem other than the predetermined problem occurs, the agent system 100 presents multiple suggestions in descending order of their effect on the user's state. This allows the agent system 100 to present suggestions that have the least effect on the user's state, i.e., suggestions that are less likely to cause a different problem, thereby preventing the user from feeling distrustful or uncomfortable about the system.

[0098] Furthermore, when the goal is to propose a predetermined option, the agent system 100 presents multiple options corresponding to the option proposal until the probability that the option proposal will be accepted reaches a predetermined value or more. This allows the agent system 100 to present the option proposal only after making it more likely to be accepted, thereby preventing the user's distrust or discomfort towards the system from increasing due to the option proposal.

[0099] Furthermore, if the probability of the proposed option being accepted does not reach a predetermined value or more when the agent system 100 has repeated the presentation of multiple options corresponding to the proposed option a predetermined number of times, the agent system 100 will not present the option and will reject it. This prevents the agent system 100 from increasing the user's distrust or discomfort towards the system due to repeated presentations.

[0100] Furthermore, the agent system 100 presents a plurality of suggestions for the identified goal based on definition information 132 that defines, for each goal, a plurality of suggestions for the goal and the effect of the suggestions on the user's state. This allows the agent system 100 to present a plurality of suggestions for the goal based on the predefined definition information 132.

[0101] Furthermore, the agent system 100 updates the definition information 132 based on the state of the user sensed when the proposal content is presented. This allows the agent system 100 to feed back to the definition information 132 the state of the user when the proposal content is presented based on the definition information 132.

[0102] Furthermore, the agent system 100 narrows down the number of suggestions corresponding to the identified goal based on attribute information indicating the user's attributes, thereby enabling the agent system 100 to provide suggestions corresponding to the user's attributes (e.g., gender, age, religion, race, etc.).

[0103] (Hardware Configuration Example) Information devices such as the information processing device 1 and the terminal device 2 according to the above-described embodiments are realized by a computer 1000 having a configuration as shown in Fig. 17, for example. Fig. 10 is a hardware configuration diagram showing an example of the computer 1000. The computer 1000 has a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an SSD (Solid State Drive) 1400, a communication interface 1500, and an input / output interface 1600. The components of the computer 1000 are connected by a bus 1050.

[0104] The CPU 1100 operates and controls each component based on programs stored in the ROM 1300 or the SSD 1400. For example, the CPU 1100 loads the programs stored in the ROM 1300 or the SSD 1400 into the RAM 1200 and executes processing corresponding to the various programs.

[0105] The ROM 1300 stores boot programs such as a Basic Input Output System (BIOS) that is executed by the CPU 1100 when the computer 1000 is started, and programs that depend on the hardware of the computer 1000 .

[0106] The SSD 1400 is a computer-readable recording medium that non-temporarily records programs executed by the CPU 1100 and data used by such programs. Specifically, the SSD 1400 is a recording medium that records a communication program according to the present disclosure, which is an example of the program data 1450. The SSD 1400 may be another non-temporary recording medium, such as a hard disk drive (HDD).

[0107] The communication interface 1500 is an interface for connecting the computer 1000 to an external network 1550 (e.g., the Internet). For example, the CPU 1100 receives data from other devices and transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

[0108] The input / output interface 1600 is an interface for connecting the input / output device 1650 and the computer 1000. For example, the CPU 1100 receives data from input devices such as a touch panel, keyboard, mouse, microphone, and camera via the input / output interface 1600. The CPU 1100 also transmits data to output devices such as a display, speaker, and printer via the input / output interface 1600. The input / output interface 1600 may also function as a media interface for reading programs and the like recorded on a predetermined recording medium. Examples of media include optical recording media such as DVDs (Digital Versatile Discs) and PDs (Phase Change Rewritable Discs), magneto-optical recording media such as MOs (Magneto-Optical Disks), tape media, magnetic recording media, and semiconductor memories.

[0109] For example, when the computer 1000 functions as the information processing device 1 or the terminal device 2 according to the embodiment, the CPU 1100 of the computer 1000 executes a presentation program loaded onto the RAM 1200 to realize the functions of the input unit 10, the processing unit 11, the output unit 12, etc. The presentation program according to the present disclosure and data in the RAM 1200 are stored in the SSD 1400. The CPU 1100 reads and executes the program data 1450 from the SSD 1400, but as another example, the CPU 1100 may obtain these programs from another device via an external network 1550.

[0110] The present technology can also be configured as follows. (1) A system including a control unit that makes a presentation corresponding to a goal identified based on information related to a sensed user's state, wherein the control unit presents multiple presentations corresponding to the identified goal in descending order of their effect on the user's state. (2) The system described in (1), wherein the information related to the user's state is acquired by at least one of a microphone, a camera, an acceleration sensor, a gyro sensor, a biometric sensor, a temperature sensor, and a humidity sensor. (3) The system described in (1) or (2), wherein, when the goal is to solve a predetermined problem, the control unit makes multiple presentations in descending order of their effect on the user's state when making the presentations will result in a problem different from the predetermined problem. (4) The system described in (3), wherein the control unit makes the multiple presentations a predetermined number of times. (5) The system described in (3) or (4), wherein the control unit determines whether or not there are signs of solving the predetermined problem based on the information related to the user's state, and makes presentations based on the determination result. (6) The system according to any one of (1) to (5), wherein, when the goal is a proposal of a predetermined option, the control unit presents a plurality of options corresponding to the proposal of the option until a probability that the proposal of the option will be accepted reaches a predetermined value or more. (7) The system according to (6), wherein, when the probability that the proposal of the option will be accepted does not reach a predetermined value or more after repeating a plurality of options corresponding to the proposal of the option a predetermined number of times, the control unit discards the proposal of the option without presenting it. (8) The system according to any one of (1) to (7), wherein the control unit presents a plurality of options for the identified goal based on definition information that defines, for each goal, a plurality of options to be presented for the goal and the impact of the presented options on the user's state. (9) The system according to (8), wherein the definition information defines the magnitude of a change in the user's state when the presented options are presented to the user. (10) The system according to (9), wherein the definition information sets a subparameter indicating the magnitude of the impact on the user's state.(11) The system described in (8), wherein the control unit updates the definition information based on the user's state sensed when the content to be presented is presented. (12) The system described in any one of (1) to (11), wherein the control unit narrows down multiple presentations corresponding to the identified goal based on attribute information indicating attributes of the user. (13) The system described in (11) or (12), wherein the definition information defines a magnitude of a change in the user's state when the content to be presented is presented to the user, and the control unit updates the magnitude of the change in the user's state in the definition information based on whether the user's state sensed when the content to be presented is close to a predetermined state. (14) The system described in (12), wherein the attribute information includes at least one attribute of the user's gender, age, nationality, religion, and race. (15) The system described in (11), wherein the control unit updates the definition information using reinforcement learning that evaluates and learns from the user's state sensed when the content to be presented is presented. (16) A presentation method that executes a process in which a computer makes a presentation corresponding to a specified target based on information related to a sensed state of a user, and presents a plurality of presentations corresponding to the specified target in descending order of variation with respect to the state of the user. (17) A presentation program that causes a computer to execute a process in which a computer makes a presentation corresponding to a specified target based on information related to a sensed state of a user, and presents a plurality of presentations corresponding to the specified target in descending order of variation with respect to the state of the user.

[0111] 1...information processing device 2...terminal device 3...network 10...input unit 11...processing unit 12...output unit 13...storage unit 100...agent system 111...user information sensing unit 112...expectation value grasping unit 113...problem grasping unit 114...solution definition unit 115...measure definition unit 116...simulation unit 117...feedback unit 131...user information 132...definition information 132a...definition information (solution) 132b...definition information (measure) 1000...computer 1050...bus 1100...CPU 1200...RAM 1300...ROM 1400...SSD 1450...program data 1500...communication interface 1550...external network 1600...input / output interface 1650...input / output device G1...AR-HUD screen G11...advertising image P1, P2, P4, P5, P7, P8...Proposal content P3, P6, P9, P10, P11...Proposal content (options)

Claims

1. A system comprising a control unit that provides presentations corresponding to identified targets based on information relating to the sensed state of a user, wherein the control unit presents a plurality of presentations corresponding to the identified targets in descending order of their variability relative to the user's state.

2. The system according to claim 1, wherein the information about the user's state is acquired by at least one of a microphone, a camera, an acceleration sensor, a gyro sensor, a biometric sensor, a temperature sensor, and a humidity sensor.

3. The system described in claim 1, wherein, when the goal is to solve a specified problem, the control unit makes multiple presentations in order of least change to the user's state when making the presentation results in a problem other than the specified problem.

4. The system according to claim 3, wherein the control unit performs the plurality of presentations a predetermined number of times.

5. The system according to claim 3, wherein the control unit determines whether there are signs of a solution to the specified problem based on information about the user's condition, and makes a presentation based on the determination result.

6. The system according to claim 1, wherein, when the goal is a proposal of a predetermined option, the control unit presents a plurality of options corresponding to the proposal of the option until the probability that the proposal of the option will be accepted reaches or exceeds a predetermined value.

7. The system described in claim 6, wherein the control unit rejects the option proposal without making it if the probability that the option proposal will be accepted does not reach a predetermined value or higher when multiple presentations corresponding to the option proposal are repeated a predetermined number of times.

8. The system described in claim 1, wherein the control unit makes multiple presentations for the identified goal based on definition information that defines, for each goal, multiple presentation contents for the goal and the effect of the presentation contents on the user's state.

9. The system according to claim 8, wherein the definition information defines the magnitude of the state change of the user when the presentation content is presented to the user.

10. The system according to claim 9, wherein the definition information includes a subparameter set regarding the magnitude of the effect on the user's condition.

11. The system according to claim 8, wherein the control unit updates the definition information based on the state of the user sensed when the presentation content is presented.

12. The system according to claim 1, wherein the control unit narrows down the plurality of suggestions corresponding to the identified goal based on attribute information indicating attributes of the user.

13. The system described in claim 11, wherein the definition information defines the magnitude of the user's state change when the presentation content is presented to the user, and the control unit updates the magnitude of the user's state change in the definition information based on whether the user's state sensed when the presentation content is presented approaches a predetermined state.

14. The system according to claim 12, wherein the attribute information includes at least one attribute of the user's gender, age, nationality, religion, or race.

15. The system according to claim 11, wherein the control unit updates the definition information using reinforcement learning, which evaluates and learns from the sensed state of the user when the presentation content is presented.

16. A presentation method in which a computer performs a process in which it makes a presentation corresponding to a target identified based on information related to the sensed state of a user, and presents multiple presentations corresponding to the identified target in order of least change relative to the state of the user.

17. A presentation program that causes a computer to execute a process of making a presentation corresponding to a target identified based on information regarding the sensed state of a user, and presenting multiple presentations corresponding to the identified target in order of least change relative to the state of the user.

Images