Information processing device, control method, and program
Patent Information
- Application Number
- PCT/JP2025/012014
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-03-26
- Publication Date
- 2026-10-01
Smart Images
Figure JP2025012014_01102026_PF_FP_ABST
Abstract
Description
Information Processing Apparatus, Control Method and Program
[0001] The present disclosure relates to an information processing apparatus, a control method, and a program.
[0002] Technologies for controlling a controlled object are known. For example, Patent Document 1 discloses a control device that controls a controlled object using a machine learning model.
[0003] Japanese Unexamined Patent Application Publication No. 2020-057238
[0004] By the way, in recent years, the use of generative artificial intelligence (generative AI) has become widespread. Although generative AI is highly convenient, it often produces unexpected outputs. Therefore, when generative AI is used to control a controlled object, there is a risk that inappropriate control may be performed. Patent Document 1 does not disclose control using generative AI. For this reason, there is a demand for a proposal of a technology that prevents inappropriate control from being performed in control using generative AI.
[0005] Accordingly, one of the objects to be achieved by the embodiments disclosed in this specification is to provide an information processing apparatus, a control method, and a program capable of preventing inappropriate control from being performed in control using generative AI.
[0006] The information processing apparatus according to the present disclosure includes: a receiving unit that receives a request regarding an operation of a controlled object from a user; a control instruction acquiring unit that acquires a control instruction for controlling the controlled object from generative AI by inputting an instruction statement created based on the request into the generative AI; a determining unit that determines whether the control instruction conforms to a preset control rule; and a control unit that executes control based on the control instruction when the control instruction conforms to the control rule, and does not execute the control instruction when the control instruction does not conform to the control rule.
[0007] The control method according to this disclosure involves an information processing device receiving a request from a user regarding the operation of a controlled object, inputting an instruction statement created based on the request to a generating AI, obtaining a control command for controlling the controlled object from the generating AI, determining whether the control command conforms to a pre-set control rule, executing control based on the control command if the control command conforms to the control rule, and not executing the control command if the control command does not conform to the control rule.
[0008] The program relating to this disclosure causes a computer to execute the following steps: a receiving step of receiving a request from a user regarding the operation of a controlled object; a control command acquisition step of obtaining a control command for controlling the controlled object from a generating AI by inputting an instruction statement created based on the request into the generating AI; a determination step of determining whether the control command conforms to a pre-set control rule; and a control step of executing control based on the control command if the control command conforms to the control rule, and not executing the control command if the control command does not conform to the control rule.
[0009] According to this disclosure, it is possible to provide an information processing device, a control method, and a program that can prevent inappropriate control from being performed in control using generated AI.
[0010] This is a block diagram showing an example of the configuration of the information processing device related to this disclosure. This is a block diagram showing an example of the configuration of the information processing system related to this disclosure. This is a flowchart showing an example of the operation hardware configuration of a computer that implements the processing unit related to this disclosure.
[0011] For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same or corresponding elements are denoted by the same reference numeral, and redundant explanations have been omitted as necessary for clarity of explanation. Furthermore, each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated not only with one specific embodiment but also with one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create embodiments that are not explicitly illustrated or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps described in any of the drawings may be changed as appropriate.
[0012] <Embodiment 1> The configuration example of the information processing device 1 will be described below with reference to Figure 1. Figure 1 is a block diagram showing an example of the configuration of the information processing device 1. The information processing device 1 has a reception unit 2, a control command acquisition unit 3, a determination unit 4, and a control unit 5. The information processing device 1 is any device equipped with computer resources, for example. The information processing device 1 is a device that controls a controlled object. Here, the controlled object is, for example, a vehicle, but is not limited to this, and can be any predetermined device.
[0013] The reception unit 2 receives requests from the user regarding the operation of the controlled object. The reception unit 2 may also receive requests made by the user by voice. However, the reception unit 2 may also receive requests entered by the user into the information processing device 1 by any input method, such as text input, not limited to voice input.
[0014] The control command acquisition unit 3 acquires control commands for controlling the controlled object from the generating AI by inputting an instruction statement created based on the request received by the receiving unit 2 to the generating AI. More specifically, the control command acquisition unit 3 acquires control commands for controlling the controlled object, which are commands that cause the controlled object to execute controls that satisfy the request, by using the generating AI. The control command may also be called a control signal. The generating AI is specifically, for example, a large language model (LLM (Large language Model)) learned by machine learning. The generating AI takes an instruction statement written in natural language that instructs the generation of information such as text data as input, and generates and outputs information by performing predetermined calculations based on the instruction statement. The instruction statement may also be called a prompt. In this way, the control command acquisition unit 3 acquires the control commands (control commands output by the generating AI) generated by the generating AI based on the request received by the receiving unit 2. The generating AI may be owned by the information processing device 1, or it may be owned by another device that is communicably connected to the information processing device 1. In other words, the model of the generated AI may be stored in the information processing device 1, or it may be stored in another device that is communicatively connected to the information processing device 1.
[0015] The determination unit 4 determines whether the control command acquired by the control command acquisition unit 3 conforms to a pre-set control rule. Here, the control rule is a rule that defines an appropriate control for the controlled object, that is, a rule that defines a correct control for the controlled object. In other words, the control rule is a rule that defines a control that is not inappropriate among the controls for the controlled object, or a rule that defines a control that is not incorrect among the controls for the controlled object.
[0016] The control unit 5 executes control based on a control command if the control command acquired by the control command acquisition unit 3 conforms to the control rules. Conversely, the control unit 5 does not execute a control command if the control command acquired by the control command acquisition unit 3 does not conform to the control rules.
[0017] According to the information processing device 1, among the control instructions generated by the generating AI, those determined to conform to the control rules are executed, while those determined not to conform to the control rules are not executed. Therefore, it is possible to prevent inappropriate control from being implemented in control using the generating AI. This effect can also be obtained in the control method including the above-described process of the information processing device 1, the program that performs the above-described process of the information processing device 1, or a non-temporary computer-readable medium on which the program is stored.
[0018] The following describes an embodiment that is a more specific version of Embodiment 1. <Embodiment 2> The following describes an example of the configuration of the information processing device 100 using Figure 2. Figure 2 is a block diagram showing an example of the configuration of the information processing system 10. The information processing system 10 is a system that includes the information processing device 100 and the controlled object 200. The information processing device 100 is the device corresponding to the information processing device 1 described above and controls the controlled object 200. In this embodiment, the controlled object 200 is given as an example when it is a vehicle in which a user is riding, but the controlled object 200 is not limited to this. The information processing device 100 may also be mounted on the controlled object 200.
[0019] As shown in Figure 2, the information processing device 100 includes a UI unit 110, a communication unit 120, and a processing unit 150.
[0020] The UI unit 110 is a user interface device that includes an input device for receiving input from the user and an output device for outputting information to the user. For example, if the user gives instructions to the information processing device 100 by voice, the input device may be a microphone that receives the user's voice input. If the user gives instructions to the information processing device 100 by text, the input device may be a keyboard or a pointing device. If the information processing device 100 outputs information to the user as an image, the output device may be a display, for example. If the information processing device 100 outputs information to the user by voice, the output device may be a speaker. In this embodiment, the UI unit 110 only needs to have an input device and does not necessarily need to have an output device. Also, instead of the information processing device 100 itself having the UI unit 110, the information processing device 100 may be connected to a UI unit 110 that exists as an external device to the information processing device 100 in a communicable manner.
[0021] The communication unit 120 is a hardware circuit that communicates with other devices such as the controlled object 200, and may include software such as firmware.
[0022] Next, the processing unit 150 of the information processing device 100 will be described. The processing unit 150 executes any processing of the information processing device 100. In this embodiment, the processing unit 150 has a receiving unit 151, a control command acquisition unit 152, a determination unit 153, and a control unit 154.
[0023] The reception unit 151 corresponds to the reception unit 2 described above. The reception unit 151 receives requests from the user regarding the operation of the controlled object 200. These requests instruct the controlled object 200 to perform an action to fulfill the user's wishes. For example, the reception unit 151 receives requests spoken by the user via the UI unit 110 (input device). Requests from the user can also be called instructions or commands from the user. Requests from the user may instruct specific actions of the controlled object 200 (vehicle), such as "open the windows," or they may instruct the effect to be obtained as a result of performing an action, such as "cool the inside of the car." If the reception unit 151 receives a request by voice, it may perform a process to convert the voice data into text data.
[0024] The control command acquisition unit 152 corresponds to the control command acquisition unit 3 described above. Based on the request received by the reception unit 151, the control command acquisition unit 152 creates an instruction statement for input to the generating AI. The instruction statement is a statement that instructs the generation of a control command for the controlled object 200. More specifically, the control command acquisition unit 152 creates an instruction statement that instructs the generating AI to generate a control command for an action that satisfies the request received by the reception unit 151. Then, the control command acquisition unit 152 inputs the created instruction statement to the generating AI. That is, the control command acquisition unit 152 inputs the instruction statement to the generating AI model that has been pre-trained. Note that part of the instruction statement for the generating AI may be input to the generating AI model before the reception unit 151 receives the request. For example, a statement instructing the role to be given to the generating AI may be input to the generating AI when the information processing device 100 is started up. For example, the generating AI may have an instruction statement pre-entered, such as, "Act as a control system for the controlled object 200 and output a control command that satisfies the request that will be entered later." In this case, when the receiving unit 151 receives a request, the control command acquisition unit 152 inputs the text data of the received request (for example, "Cool down the inside of the car") as an instruction statement into the generating AI.
[0025] The control command acquisition unit 152 then acquires control commands from the generating AI that satisfy the request received by the receiving unit 151. In other words, the control command acquisition unit 152 acquires the control commands output by the generating AI in response to the input instruction statement containing the request received by the receiving unit 151. In this embodiment, the model constituting the generating AI is stored in a storage device provided by the information processing device 100, such as the memory 502 described later, but the model may also be stored in a server or the like that is connected to the information processing device 100 in a manner that allows communication.
[0026] The determination unit 153 corresponds to the determination unit 4 described above. The determination unit 153 determines whether the control command acquired by the control command acquisition unit 152 from the generated AI conforms to a pre-set control rule. As described above, a control rule is a rule that defines appropriate control for the controlled object. If the controlled object 200 is a vehicle, for example, rules such as "do not open the vehicle doors" and "do not violate the prescribed laws that stipulate the rules that vehicles driving on public roads must comply with (for example, the Road Traffic Act enacted in Japan)" are pre-defined as control rules. Note that there may be one or more rules defined as control rules. If there are multiple rules defined as control rules, the determination unit 153 determines whether the control command acquired by the control command acquisition unit 152 conforms to each rule.
[0027] The control unit 154 corresponds to the control unit 5 described above. The control unit 154 executes a control command if the determination unit 153 determines that the acquired control command conforms to the control rule. In this way, the control unit 154 controls the controlled object 200. Conversely, the control unit 154 does not execute a control command if the acquired control command does not conform to the control rule. For example, in response to a user request to "cool down the car," the generating AI might output a control command to open the vehicle doors. Opening the vehicle doors might cool down the car, but this control rule does not conform to the control rule "do not open the vehicle doors." Therefore, the control unit 154 does not execute this control rule. This avoids the control to open the vehicle doors. This prevents events such as doors opening while the vehicle is in motion. If the control rule includes multiple rules, the control unit 154 executes control according to the control command if the control command conforms to all of those rules, and does not execute control if it does not conform to any of the rules.
[0028] Furthermore, when the control unit 154 executes a control command, it may notify the user of the control result via the UI unit 110. Also, when the control unit 154 does not execute a control command, it may notify the user via the UI unit 110 that the generated control command will not be executed because it does not conform to the control rules.
[0029] Next, the operation flow of the information processing device 100 will be explained with reference to the flowchart in Figure 3. Figure 3 is a flowchart showing an example of the operation of the information processing device 100.
[0030] In step S100, the reception unit 151 receives a request from the user regarding the operation of the controlled object 200. Next, in step S101, the control command acquisition unit 152 uses the generated AI to acquire a control command corresponding to the request received in step S100. Next, in step S102, the determination unit 153 determines whether the control command acquired in step S101 conforms to a predetermined control rule. If the acquired control command conforms to the predetermined control rule, the process proceeds to step S103. On the other hand, if the acquired control command does not conform to the control rule, the process proceeds to step S104. In step S103, the control unit 154 controls the controlled object 200 by executing the control command acquired in step S101. On the other hand, in step S104, the control unit 154 does not execute the control command acquired in step S101.
[0031] Embodiment 2 has been described above. According to the information processing device 100, among the control commands generated by the generating AI, control commands that are determined to conform to the control rules are executed, and control commands that are determined not to conform to the control rules are not executed. Therefore, it is possible to prevent inappropriate control from being implemented in control using the generating AI.
[0032] <Embodiment 3> This embodiment differs from Embodiment 2 described above in that, if the control command output by the generating AI does not conform to the control rules, the information processing device proposes an alternative.
[0033] Figure 4 is a block diagram showing an example of the configuration of the information processing system 10a. The information processing system 10a differs from the configuration shown in Figure 2 in that the information processing device 100 is replaced by the information processing device 100a. The information processing device 100a may be mounted on the controlled object 200. Below, the configuration and processing of the information processing device 100a that differ from those of the information processing device 100 will be described, and the configuration and processing that are the same as those of the information processing device 100 will be omitted as appropriate.
[0034] The information processing device 100a differs from the information processing device 100 in that the processing unit 150 is replaced by the processing unit 150a. Furthermore, the processing unit 150a differs from the processing unit 150 in that it further has a replacement unit 155.
[0035] The alternative unit 155 proposes an alternative control to the user if it determines that the control command acquired by the control command acquisition unit 152 does not conform to the control rules. A generation AI may be used to acquire the alternative proposed by the alternative unit 155. In this case, for example, the control command acquisition unit 152 acquires an alternative control command from the generation AI by inputting an instruction statement to the generation AI instructing it to provide an alternative control to the control command that was determined to be incompatible. The alternative unit 155 then proposes the alternative represented by the control command acquired from the generation AI to the user. By using a generation AI to acquire alternatives in this way, it becomes possible to propose alternatives without having to prepare alternatives in advance for each control command that does not conform to the control rules.
[0036] Furthermore, if the acquired control command does not conform to the control rules, the alternative unit 155 may propose a predetermined alternative to the control performed by that control command to the user. In this case, since an appropriate alternative that conforms to the control rules can be prepared in advance, it is possible to prevent the generated AI from proposing another unsuitable control.
[0037] The alternative unit 155 proposes an alternative (control content of the alternative) to the user, for example, using the UI unit 110 (output device). Specifically, the alternative unit 155 may display an image showing the content of the alternative on a display, or it may output audio explaining the content of the alternative from a speaker.
[0038] The control unit 154 executes the control of an alternative when the user instructs it to do so. The user instructs the execution of an alternative, for example, via the UI unit 110. This instruction may also be received by the reception unit 151. The reception unit 151 may receive instructions spoken by the user, or instructions entered via text input, etc. If the user refuses to execute an alternative proposed by the alternative unit 155, the alternative unit 155 may propose yet another alternative.
[0039] Next, the operation flow of the information processing device 100a will be explained with reference to the flowchart in Figure 5. Figure 5 is a flowchart showing an example of the operation of the information processing device 100a.
[0040] In step S200, the reception unit 151 receives a request from the user regarding the operation of the controlled object 200. Next, in step S201, the control command acquisition unit 152 uses the generated AI to acquire a control command corresponding to the request received in step S200. Next, in step S202, the determination unit 153 determines whether the control command acquired in step S201 conforms to a predetermined control rule. If the acquired control command conforms to the predetermined control rule, the process moves to step S203. Then, in step S203, the control unit 154 controls the controlled object 200 by executing the control command acquired in step S201. Conversely, if the acquired control command does not conform to the control rule, the process moves to step S204.
[0041] In step S204, the control unit 154 does not execute the control command acquired in step S201. Then, the process moves to step S205. In step S205, the alternative unit 155 proposes an alternative control method to the user based on the control command acquired in step S201. As mentioned above, the generation AI may be used again to propose the alternative method.
[0042] For example, assume that in step S200, the receiving unit 151 receives a user's request to "cool down the inside of the vehicle". Then, assume that in step S201, a control instruction to open the vehicle door is acquired. In this case, the control instruction does not conform to the control rule "do not open the vehicle door" (NO in step S202), so in step S205, for example, control for activating the air conditioner is proposed as an alternative.
[0043] If the user approves the alternative proposed in step S205 (YES in step S206), the process proceeds to step S207. In contrast, if the user does not approve the alternative (NO in step S206), the process ends. Note that, as described above, proposals of other alternative solutions may be repeated. When the process proceeds to step S207, the control according to the alternative is executed.
[0044] Embodiment 3 has been described above. In the present embodiment, when the control generated by the generative AI is inappropriate, an alternative is proposed, so usability is improved.
[0045] <Embodiment 4> The present embodiment differs from Embodiment 2 described above in that a control rule is set based on the state of the controlled object 200 or the state of the surroundings of the controlled object 200.
[0046] FIG. 6 is a block diagram showing an example configuration of an information processing system 10b. The information processing system 10b differs from the configuration shown in FIG. 2 in that the information processing apparatus 100 is replaced with an information processing apparatus 100b. Note that the information processing apparatus 100b may be mounted on the controlled object 200. Hereinafter, among the configuration and processing of the information processing apparatus 100b, the configuration and processing different from those of the information processing apparatus 100 will be described, and descriptions of the configuration and processing that are the same as those of the information processing apparatus 100 will be omitted as appropriate.
[0047] The information processing apparatus 100b differs from the information processing apparatus 100 in that the processing unit 150 is replaced with a processing unit 150b. Further, the processing unit 150b differs from the processing unit 150 in that it further includes a state acquisition unit 156.
[0048] The state acquisition unit 156 acquires at least one of a state of the controlled object 200 and a state surrounding the controlled object 200. The state acquisition unit 156 may acquire both the state of the controlled object 200 and the state surrounding the controlled object 200. More specifically, the state acquisition unit 156 acquires information indicating a state (hereinafter also referred to as state information). The state acquisition unit 156 may acquire the state information by receiving an output from a sensor that detects the state, or may acquire the state information transmitted from another device that manages the state of the controlled object 200 or the surrounding environment thereof. In addition, the state acquisition unit 156 may acquire state information input by a user via the UI unit 110 (input device). As described above, the state acquisition unit 156 only needs to acquire the state information by any method. For example, when the controlled object 200 is a vehicle, the state acquisition unit 156 acquires state information indicating at least one of a state of the vehicle and a state surrounding the vehicle. In this case, the state acquired by the state acquisition unit 156 may be a vehicle state such as, for example, a driving state of the vehicle (e.g., whether the vehicle is being driven) or an operating state of a device constituting the vehicle (e.g., a failure state). In particular, the state acquired by the state acquisition unit 156 may be an in-vehicle state of the vehicle such as a state of an in-vehicle environment (e.g., temperature, humidity, etc.) or whether there is a child in the vehicle. In addition, the state acquired by the state acquisition unit 156 may be a surrounding state of the vehicle such as, for example, whether an object such as a person exists in the surroundings, what the season, weather, temperature, or humidity is at a location where the vehicle is present, or whether the location where the vehicle is present is on a public road or a private land.
[0049] In the present embodiment, the determination unit 153 sets a control rule based on the state of the controlled object 200 or the state surrounding the controlled object 200 acquired by the state acquisition unit 156. Specifically, the determination unit 153 determines which of predetermined rules as control rule candidates is to be enabled according to the state acquired by the state acquisition unit 156. Note that the determination unit 153 may enable a plurality of rules. Then, the determination unit 153 performs determination processing on a control command generated by generative AI using a control rule set based on the state of the controlled object 200 or the state surrounding the controlled object 200. That is, the determination unit 153 performs the determination processing using the enabled control rule.
[0050] Specific examples of rules set according to the acquired state, that is, rules that are enabled according to the acquired state, will be explained. When the controlled object 200 is a vehicle, the determination unit 153 sets the control rules as follows, for example.
[0051] For example, if the state acquisition unit 156 acquires state information indicating that the vehicle is in motion or state information indicating that there is an object (e.g., a person) around the vehicle, it sets the rule "Do not open the vehicle door" as a control rule. In other words, in such a case, the determination unit 153 determines that the control command to open the vehicle door does not conform to the control rule.
[0052] Furthermore, for example, if the status acquisition unit 156 acquires status information indicating that the season at the location where the vehicle is located is summer, or status information indicating that the temperature inside the vehicle is above a predetermined temperature (for example, 30 degrees Celsius), it sets the rule "Do not activate the heater" as a control rule. In other words, in such cases, the determination unit 153 determines that the control command to activate the heater does not conform to the control rule.
[0053] Furthermore, for example, if the status acquisition unit 156 acquires status information indicating that there is a child inside the vehicle, it sets the rule "Do not open the vehicle windows" as a control rule. In other words, in such a case, the determination unit 153 determines that the control command to open the windows does not conform to the control rule.
[0054] Furthermore, for example, if the status acquisition unit 156 acquires status information indicating that the location of the vehicle is on a public road, it sets a control rule that states, "Do not violate the prescribed laws that define the rules that vehicles traveling on public roads must comply with." In other words, in such a case, the determination unit 153 determines that a control command to perform a prescribed driving action that violates the said law (for example, driving the wrong way on a road) does not conform to the control rule.
[0055] Next, the operation flow of the information processing device 100b will be explained with reference to the flowchart in Figure 7. Figure 7 is a flowchart showing an example of the operation of the information processing device 100b.
[0056] In step S300, the reception unit 151 receives a request from the user regarding the operation of the controlled object 200. Next, in step S301, the control command acquisition unit 152 uses the generated AI to acquire a control command corresponding to the request received in step S300. Next, in step S302, the state acquisition unit 156 acquires the state of the controlled object 200. Next, in step S303, the determination unit 153 determines whether the control command acquired in step S301 conforms to the control rule set according to the state acquired in step S302. If the acquired control command conforms to the set control rule, the process moves to step S304. Then, in step S304, the control unit 154 controls the controlled object 200 by executing the control command acquired in step S301. Conversely, if the acquired control command does not conform to the control rule, the process moves to step S305. In step S305, the control unit 154 does not execute the control command acquired in step S301.
[0057] Embodiment 4 has been described above. In this embodiment, the determination process of the determination unit 153 is performed using control rules set based on the state of the controlled object 200 or the state of the surroundings of the controlled object 200. Therefore, appropriate control can be performed according to the state.
[0058] The processing units 150, 150a, and 150b described above may be implemented by a computer as shown in Figure 8. Hereinafter, when processing units 150, 150a, and 150b are referred to without particular distinction, they will be referred to as processing unit 150, etc. Figure 8 is a block diagram showing an example of the hardware configuration of a computer that implements processing unit 150, etc. As shown in Figure 8, the computer 500 includes an input / output interface 501, memory 502, and a processor 503.
[0059] The input / output interface 501 is used to communicate with components other than the processing unit 150, etc., as needed. The memory 502 is composed of, for example, a combination of volatile memory and non-volatile memory. The memory 502 is used to store software (computer programs) containing one or more instructions executed by the processor 503, and data used for various processes.
[0060] The processor 503 reads and executes software (computer programs) from the memory 502, thereby performing processing for each component such as the processing unit 150. The processor 503 may be, for example, a microprocessor, an MPU (Micro Processor Unit), or a CPU (Central Processing Unit). The processor 503 may include multiple processors.
[0061] The program, when loaded into a computer, includes a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include electrical, optical, acoustic or other forms of propagating signals. The program may also be included in a computer program product.
[0062] Furthermore, the functions of the processing unit 150 and the like described above do not necessarily have to be implemented by a single device. That is, the functions of the processing unit 150 and the like described above may be distributed across two or more devices. For example, the functions of the processing unit 150 and the like described above may be implemented by an information processing system composed of multiple information processing devices that can communicate via a network. Also, some or all of the information processing devices 100, 100a, and 100b, or the multiple information processing devices that perform distributed processing, may be servers. In addition, some or all of the functions of the processing unit 150 and the like described above may be implemented by electronic circuits.
[0063] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.
[0064] Some or all of the embodiments described above may also be described as follows, but are not limited to the following: Some or all of the elements (e.g., configurations and functions) described in Appendices 2 to 6 that are dependent on Appendice 1 may also be dependent on Appendices 7 to 8 in the same way as in Appendices 2 to 6. Furthermore, some or all of the elements described in any of the Appendices may be applied to various hardware, software, recording means, systems, and methods for recording software.
[0065] (Note 1) An information processing device comprising: a receiving means for receiving requests from a user regarding the operation of a controlled object; a control command acquisition means for obtaining a control command for controlling the controlled object from a generating AI by inputting an instruction statement created based on the request to the generating AI; a determination means for determining whether the control command conforms to a pre-set control rule; and a control means for executing control based on the control command when the control command conforms to the control rule, and not executing the control command when the control command does not conform to the control rule. (Note 2) The information processing device according to Note 1, further comprising an alternative means for proposing an alternative control to the control command to the user when the control command does not conform to the control rule, wherein the control means executes the control of the alternative when the user instructs the execution of the control of the alternative. (Note 3) The information processing device according to Note 2, wherein the control command acquisition means inputs an instruction statement to the generating AI instructing the generating AI to provide an alternative control command when the control command does not conform to the control rule, and the alternative means proposes the alternative represented by the control command acquired from the generating AI to the user. (Note 4) The information processing device according to Note 2, wherein the alternative means proposes a predetermined alternative to the control command to the user when the control command does not conform to the control rule. (Note 5) The information processing device according to any one of Notes 1 to 4, wherein the determination means uses the control rule set based on the state of the controlled object or the state of the surroundings of the controlled object. (Note 6) The information processing device according to Note 5, wherein the controlled object is a vehicle, and the determination means uses the control rule set based on the state inside the vehicle.(Note 7) A control method comprising: an information processing device receiving a request from a user regarding the operation of a controlled object; inputting an instruction statement created based on the request into a generating AI to obtain a control command for controlling the controlled object from the generating AI; determining whether the control command conforms to a pre-set control rule; executing control based on the control command if the control command conforms to the control rule; and not executing the control command if the control command does not conform to the control rule. (Note 8) A program that causes a computer to execute: a receiving step of receiving a request from a user regarding the operation of a controlled object; a control command acquisition step of inputting an instruction statement created based on the request into a generating AI to obtain a control command for controlling the controlled object from the generating AI; a determination step of determining whether the control command conforms to a pre-set control rule; and a control step of executing control based on the control command if the control command conforms to the control rule; and not executing the control command if the control command does not conform to the control rule.
[0066] 1 Information Processing Unit 2 Reception Unit 3 Control Command Acquisition Unit 4 Determination Unit 5 Control Unit 10 Information Processing System 10a Information Processing System 10b Information Processing System 100 Information Processing Unit 100a Information Processing Unit 100b Information Processing Unit 110 UI Unit 120 Communication Unit 150 Processing Unit 150a Processing Unit 150b Processing Unit 151 Reception Unit 152 Control Command Acquisition Unit 153 Determination Unit 154 Control Unit 155 Substitution Unit 156 Status Acquisition Unit 200 Control Target 500 Computer 501 Input / Output Interface 502 Memory 503 Processor
Claims
1. An information processing device comprising: a receiving means for receiving requests from a user regarding the operation of a controlled object; a control command acquisition means for obtaining a control command for controlling the controlled object from a generating AI by inputting an instruction statement created based on the request into the generating AI; a determination means for determining whether the control command conforms to a pre-set control rule; and a control means for executing control based on the control command if the control command conforms to the control rule, and not executing the control command if the control command does not conform to the control rule.
2. The information processing apparatus according to claim 1, further comprising an alternative means for proposing to the user an alternative control method for the control command if the control command does not conform to the control rules, wherein the control means executes the alternative control method when the user instructs the execution of the alternative control method.
3. The information processing apparatus according to claim 2, wherein the control command acquisition means inputs an instruction statement to the generating AI instructing the generating AI to provide an alternative control method when the control command does not conform to the control rule, thereby acquiring the alternative control command from the generating AI, and the alternative means proposes the alternative method represented by the control command acquired from the generating AI to the user.
4. The information processing apparatus according to claim 2, wherein the alternative means proposes to the user a predetermined alternative to the control by the control command when the control command does not conform to the control rule.
5. The information processing apparatus according to any one of claims 1 to 4, wherein the determination means uses the control rule set based on the state of the controlled object or the state of the surroundings of the controlled object.
6. The information processing apparatus according to claim 5, wherein the controlled object is a vehicle, and the determination means uses the control rule set based on the state inside the vehicle.
7. A control method comprising: an information processing device receiving a request from a user regarding the operation of a controlled object; inputting an instruction statement created based on the request to a generating AI, thereby obtaining a control command for controlling the controlled object from the generating AI; determining whether the control command conforms to a pre-set control rule; executing control based on the control command if the control command conforms to the control rule; and not executing the control command if the control command does not conform to the control rule.
8. A program that causes a computer to execute the following steps: a reception step of receiving a request from a user regarding the operation of a controlled object; a control command acquisition step of obtaining a control command for controlling the controlled object from a generating AI by inputting an instruction statement created based on the request into the generating AI; a determination step of determining whether the control command conforms to a pre-set control rule; and a control step of executing control based on the control command if the control command conforms to the control rule, and not executing the control command if the control command does not conform to the control rule.