Information processing device, information processing method, and information processing program

Abstract

An information processing device according to the present invention comprises: an acquisition unit that acquires a user instruction which is input by a user in order to obtain an optimized plan; a condition configuration unit that configures a prescribed condition on the basis of the user instruction; a plan determination unit that determines a plan on the basis of the condition; and a presentation unit that presents the condition and the plan to the user. Thus, the burden on a user associated with setting of a condition for obtaining a plan is reduced, thereby assisting the user in more easily obtaining a desired plan.

Description

Information Processing Apparatus, Information Processing Method, and Information Processing Program

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

[0002] There is known a technique for obtaining a plan desired by a user by causing the user to input quantitative conditions to be provided to an optimization solver. For example, Patent Document 1 discloses a technique that accepts input of data necessary for creating a delivery plan, and creates a delivery plan for delivering packages to a plurality of delivery destinations at specified dates and times from a plurality of delivery bases using a plurality of transportation means.

[0003] Japanese Unexamined Patent Application Publication No. 2013-136421

[0004] In the technique described in Patent Document 1, an administrator who formulates a delivery plan is not necessarily familiar with a delivery planning system that calculates a delivery plan or an optimization solver inside the delivery planning system, and therefore may not be able to set appropriate delivery conditions to obtain a desired delivery plan. In such a case, for example, the user contacts the maintenance support of the delivery planning system, and the maintenance support sets the delivery conditions on behalf of the user or instructs the user how to set the delivery conditions. Accordingly, there is a demand for reducing the burden on the user related to setting conditions for obtaining a plan, so that the user can more easily obtain the plan desired by the user.

[0005] The present disclosure has been made in view of the above problem, and an exemplary object thereof is to provide a technique that supports reducing the burden on a user related to setting conditions for obtaining a plan, so that the user can more easily obtain the plan desired by the user.

[0006] An information processing apparatus according to an exemplary aspect of the present disclosure includes: an acquisition unit that acquires a user instruction input by a user to obtain an optimized plan; a condition configuration unit that configures predetermined conditions based on the user instruction; a plan determination unit that determines the plan based on the conditions; and a presentation unit that presents the conditions and the plan to the user.

[0007] An information processing method relating to an exemplary aspect of this disclosure includes: an acquisition process in which at least one processor acquires user instructions input by a user in order to obtain an optimized plan; a condition configuration process in which the at least one processor configures predetermined conditions based on the user instructions; a plan determination process in which the at least one processor determines the plan based on the conditions; and a presentation process in which the at least one processor presents the conditions and the plan to the user.

[0008] An illustrative aspect of the present disclosure is an information processing program that causes a computer to function as an information processing device, wherein the computer functions as: an acquisition means for acquiring user instructions input by a user to obtain an optimized plan; a condition configuration means for configuring predetermined conditions based on the user instructions; a plan determination means for determining the plan based on the conditions; and a presentation means for presenting the conditions and the plan to the user.

[0009] One exemplary effect of this disclosure is that it can provide technology that reduces the burden on users in setting conditions for obtaining a plan, thereby helping users more easily obtain the plan they desire.

[0010] This is a block diagram showing the configuration of the information processing device related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a block diagram showing the configuration of the information processing system related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a diagram schematically illustrating a specific example of the condition configuration processing related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a diagram schematically illustrating a specific example of the condition configuration processing related to this disclosure. This is a diagram schematically illustrating a specific example of a modified version of the condition configuration processing related to this disclosure. This is a diagram showing an example of a screen displayed in the presentation processing related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a diagram schematically illustrating a specific example of the first determination condition related to this disclosure. This is a diagram showing an example of a screen displayed in the presentation processing related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a diagram showing an example of a screen displayed in the presentation processing related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a diagram schematically illustrating a specific example of the condition configuration processing related to this disclosure. This is a diagram showing an example of a screen displayed in the presentation processing related to this disclosure. This is a block diagram showing the configuration of the information processing system related to this disclosure. This is a flowchart showing the flow of the information processing method related to this disclosure. This is a diagram schematically illustrating a specific example of the preprocessing related to this disclosure. This is a diagram schematically illustrating a specific example of the handling method related to this disclosure. This is a block diagram showing the hardware configuration of a computer that functions as each of the above-mentioned devices related to this disclosure.

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining some or all of the technologies (things or methods) employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in each of the exemplary embodiments shown below may also be included in the scope of the present invention. In addition, the effects mentioned in each of the exemplary embodiments shown below are examples of effects that can be expected in that exemplary embodiment and do not define the scope of the present invention. That is, embodiments that do not produce the effects mentioned in each of the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] [First Exemplary Embodiment] A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form for each of the exemplary embodiments described later. The scope of application of each technology adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology adopted in this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems occur. Furthermore, each technology shown in the drawings referenced to explain this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems occur.

[0013] (Overview of Information Processing Device 1) Information Processing Device 1 is a device that calculates an optimized plan desired by the user using its built-in optimization solver and presents the calculated plan to the user. Examples of optimization solvers include, but are not limited to, solvers based on mathematical optimization techniques such as Grobi, and solvers based on generative optimization techniques. For example, examples of plans targeted by Information Processing Device 1 include delivery plans for delivery companies, railway timetable scheduling, departure and arrival scheduling at airports, shift scheduling for part-time workers, and route guidance combining public transportation. However, the target plans are not limited to these, and any plan that can be calculated by providing quantitative conditions to the built-in optimization solver is acceptable, and is not limited to the examples mentioned above. Quantitative conditions may be, for example, conditions that can be set by selecting one of several options, conditions that can be set by specifying a numerical value or a range of numerical values, etc., but are not limited to these.

[0014] (Configuration of Information Processing Device 1) The configuration of the information processing device 1 will be described with reference to Figure 1. Figure 1 is a block diagram showing the configuration of the information processing device 1 according to this disclosure. As shown in Figure 1, the information processing device 1 includes an acquisition unit 11, a condition configuration unit 12, a plan determination unit 13, and a presentation unit 14. The acquisition unit 11 is an example of a configuration that realizes the acquisition means. The condition configuration unit 12 is an example of a configuration that realizes the condition configuration means. The plan determination unit 13 is an example of a configuration that realizes the plan determination means. The presentation unit 14 is an example of a configuration that realizes the presentation means.

[0015] The acquisition unit 11 acquires user instructions entered by the user in order to obtain an optimized plan. Here, the user instructions include natural language sentences. These natural language sentences may be entered by voice or as text. The user instructions may also be entered by, for example, a mouse, keyboard, touchpad, touch panel, microphone, or a combination thereof. Furthermore, the user instructions may include natural language sentences instead of setting quantitative conditions by manual input, or they may include a combination of quantitative conditions set by manual input and natural language sentences.

[0016] The condition configuration unit 12 configures predetermined conditions based on user instructions. For example, "predetermined conditions" are conditions set in advance as quantitative conditions that can be given to the optimization solver. "Configuring conditions" means, for example, setting one of several options as the condition, or setting a numerical value or a range of numerical values. For example, the condition configuration unit 12 may configure the conditions based on the output information by inputting an instruction statement that instructs the generating AI (Artificial Intelligence) model to configure predetermined conditions based on user instructions. Alternatively, the condition configuration unit 12 may configure predetermined conditions based on user instructions using other methods (for example, rule-based methods) rather than just using a generating AI model.

[0017] The plan determination unit 13 determines a plan based on the configured conditions. For example, the plan determination unit 13 may obtain a plan output from the optimization solver by providing the conditions configured by the condition configuration unit 12 to the optimization solver.

[0018] The presentation unit 14 presents the configured conditions and the determined plan to the user. For example, the presentation unit 14 may present the conditions and plan to the user by outputting them to an output device such as a display, printer, or speaker. This allows the user to know what conditions have been configured based on the user instructions they have entered, and what plan has been determined based on those conditions.

[0019] (Effects of the Information Processing Device 1) As described above, the Information Processing Device 1 employs a configuration that includes an acquisition unit 11 for acquiring user instructions input by the user in order to obtain an optimized plan, a condition configuration unit 12 for configuring predetermined conditions based on the user instructions, a plan determination unit 13 for determining a plan based on the configured conditions, and a presentation unit 14 for presenting the configured conditions and the determined plan to the user. Therefore, the Information Processing Device 1 has the effect of reducing the burden on the user in setting conditions for obtaining a plan and making it easier for the user to obtain the plan they desire.

[0020] (Flow of Information Processing Method S1) The flow of information processing method S1 will be explained with reference to Figure 2. For example, if the information processing device 1 is equipped with at least one processor, the information processing device 1 executes information processing method S1. Figure 2 is a flowchart showing the flow of information processing method S1 according to this disclosure. As shown in Figure 2, information processing method S1 includes an acquisition process S11, a condition configuration process S12, a plan determination process S13, and a presentation process S14.

[0021] In acquisition process S11, at least one processor (for example, acquisition unit 11) acquires user instructions input by the user in order to obtain an optimized plan. Since acquisition process S11 will be described in the same way as acquisition unit 11, a detailed explanation will not be repeated.

[0022] In the condition configuration process S12, at least one processor (for example, the condition configuration unit 12) configures predetermined conditions based on user instructions. The condition configuration process S12 will be described in the same way as the condition configuration unit 12, so a detailed explanation will not be repeated.

[0023] In the plan determination process S13, at least one processor (for example, the plan determination unit 13) determines a plan based on the configured conditions. The plan determination process S13 will be described in the same way as the plan determination unit 13, so a detailed explanation will not be repeated.

[0024] In presentation processing S14, at least one processor (for example, presentation unit 14) presents the configured conditions and the determined plan to the user. Presentation processing S14 will be described in the same way as presentation unit 14, so a detailed explanation will not be repeated.

[0025] (Effects of Information Processing Method S1) As described above, the Information Processing Method S1 employs a configuration that includes: an acquisition process S11 in which at least one processor acquires user instructions input by the user in order to obtain an optimized plan; a condition configuration process S12 in which at least one processor configures predetermined conditions based on the user instructions; a plan determination process S13 in which at least one processor determines a plan based on the configured conditions; and a presentation process S14 in which at least one processor presents the configured conditions and the determined plan to the user. For this reason, the Information Processing Method S1 provides the same effects as the Information Processing Device 1.

[0026] [Second Exemplary Embodiment] A second exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same function as those described in the above-described exemplary embodiment are denoted by the same reference numerals, and their descriptions are omitted as appropriate. The scope of application of each technology adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology adopted in this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise. Furthermore, each technology shown in the drawings referenced to describe this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise.

[0027] (Overview of Information Processing System 10A) Information processing system 10A is a system that calculates an optimized plan desired by the user using an integrated optimization solver and presents the calculated plan to the user. In the following description, an embodiment of information processing system 10A that includes a server 1A providing a cloud-type service that presents the plan, and a user terminal 2 used by a user utilizing the service will be described. However, information processing system 10A may also be configured as a single information processing device that encompasses the functions of server 1A and user terminal 2.

[0028] (Configuration of Information Processing System 10A) The configuration of the information processing system 10A will be described with reference to Figure 3. Figure 3 is a block diagram showing the configuration of the information processing system 10A according to this disclosure. As shown in Figure 3, the information processing system 10A includes a server 1A, a user terminal 2, and a target data storage device 3. Although Figure 3 shows one user terminal 2 and one target data storage device 3, the number of at least one of the user terminals 2 and target data storage devices 3 included in the information processing system 10A may be multiple. The server 1A is connected to each of the user terminals 2 and the target data storage devices 3 via a network NW so as to be able to communicate. The network NW is configured to include, for example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public telephone network, a mobile data communication network, or a combination of some or all of these. However, the configuration of the network NW is not limited to the example described above.

[0029] (Target Data Storage Device 3) As shown in Figure 3, the target data storage device 3 stores the target data. The target data is data that is referenced in order to calculate an optimized plan desired by the user. For example, if the plan is a delivery plan, the target data may include, but is not limited to, delivery information such as the delivery address, the origin address, the time window (date and time, time window width), the type of package, information on weight and capacity such as the number of packages, driver / vehicle information, and past usage history. Furthermore, the target data stored in the target data storage device 3 may be managed by a linked system that manages the target data.

[0030] (User terminal 2) As shown in Figure 3, the user terminal 2 includes a control unit 210, a storage unit 220, a communication unit 230, an input unit 240, and a display unit 250.

[0031] (Input Unit 240 and Display Unit 250) The input unit 240 is configured to include input devices such as a keyboard, mouse, microphone, and touchpad. The display unit 250 is configured to include a display device. The input unit 240 and the display unit 250 may also be configured to include an input / output device integrally formed as a touch panel or the like. In addition, at least a part of one or both of the input unit 240 and the display unit 250 may be connected to the user terminal 2 as a peripheral device instead of being built into the user terminal 2, or may be built into or connected to a terminal (not shown) that is communicatively connected to the user terminal 2.

[0032] (Communication Unit 230) The communication unit 230 communicates with devices outside the user terminal 2. The communication unit 230 transmits data supplied from the control unit 210 to external devices and supplies data received from external devices to the control unit 210. For example, the communication unit 230 communicates with the server 1A. The data that the communication unit 230 transmits to the server 1A may include user instructions entered by the user to obtain an optimized plan. The data that the communication unit 230 receives from the server 1A may include information indicating the conditions used to determine the plan and the determined plan.

[0033] (Storage Unit 220) The storage unit 220 stores various data referenced by the control unit 210, and various data generated by the control unit 210. At least a portion of the storage unit 220 may be connected to the user terminal 2 as a peripheral device, or it may be included in a device (not shown) that is communicatively connected to the user terminal 2, instead of being built into the user terminal 2.

[0034] (Control Unit 210) The control unit 210 controls all parts of the user terminal 2. For example, the control unit 210 includes the dialogue unit 21. For example, the dialogue unit 21 displays information to be presented to the user on the display unit 250 under the control of the server 1A, and acquires information entered by the user via the input unit 240. The dialogue unit 21 also receives information to be presented to the user from the server 1A via the communication unit 230, and transmits information entered by the user to the server 1A.

[0035] (Server 1A) Server 1A is an example of an information processing device. As shown in Figure 3, Server 1A includes a control unit 110, a storage unit 120, and a communication unit 130.

[0036] (Communication Unit 130) The communication unit 130 communicates with external devices of the server 1A. The communication unit 130 transmits data supplied from the control unit 110 to external devices and supplies data received from external devices to the control unit 110. As an example, the communication unit 130 communicates with the user terminal 2. The data that the communication unit 130 receives from the user terminal 2 may include user instructions entered by the user to obtain an optimized plan. The data that the communication unit 130 transmits to the user terminal 2 may include information indicating the conditions used to determine the plan and the determined plan.

[0037] As an example, the communication unit 130 communicates with the target data storage device 3. The data that the communication unit 130 transmits to the target data storage device 3 may include information requesting the target data. The data that the communication unit 130 receives from the target data storage device 3 may include the target data.

[0038] (Storage Unit 120) The storage unit 120 stores various data referenced by the control unit 110, and various data generated by the control unit 110. At least a part of the storage unit 120 may be connected to the server 1A as a peripheral device instead of being built into the server 1A, or it may be included in a device (not shown) that is communicatively connected to the server 1A. For example, the server 1A stores a plurality of conditions T1, T2, ..., usage history H, and model AI. The usage history H may be stored in the target data storage device 3. The model AI may also be stored in an external device. The model AI is not mandatory, and it does not necessarily have to be stored in the storage unit 120.

[0039] (Conditions T1, T2, ...) Multiple conditions T1, T2, ... are included in the predetermined conditions that the planning decision unit 13, described later, refers to when determining a plan. Multiple conditions T1, T2, ... are conditions that do not depend on each other. Hereafter, unless it is necessary to explain each of the conditions T1, T2, ... separately, each will be referred to as condition T. Condition T indicates quantitative conditions that can be given to the optimization solver embedded in the planning decision unit 13, described later, and includes information indicating the settable values ​​(multiple options, numerical ranges, etc.). For example, examples of quantitative conditions that can be given to the optimization solver that calculates a delivery plan include condition T1 regarding optimization indicators, condition T2 regarding highways, etc. Condition T1 regarding optimization indicators may include multiple options such as minimizing the number of vehicles, minimizing travel time, minimizing the load factor, etc. Condition T1 regarding optimization indicators is configured by selecting one of the multiple options as the settable value. The condition T2 regarding the expressway may include multiple options, such as "pass through," "do not pass through," or "leave it to the map." The condition T2 regarding the expressway is configured by selecting one of these multiple options as the set value. However, the condition T is not limited to the example described above.

[0040] Specific examples of conditions that can be given to the optimization solver when the plan is a delivery plan include, but are not limited to, the following: load factor (any unit such as weight, quantity, or volume), maximum number of trips (number of rotations), average maximum number of deliveries per day per truck, specified delivery time at the destination, specified subcontractor, specified vehicle by product type, specified vehicle by delivery destination, specified yard conditions (maximum vehicle type that can park alongside), mixed load conditions by cargo type, consideration of driver rest time during operation, arrangement of route carrier, working time at the delivery destination, vehicle type (passenger car, small / large truck, etc.), driver skills, driver's assigned area, driver's working hours, and specified driver or vehicle for each delivery destination. Among these specific examples of conditions, conditions that have dependencies on each other may be combined to form a single condition T. This allows multiple conditions T to be configured so that they do not have dependencies on each other.

[0041] (Usage History H) Usage History H indicates information related to plans that have been used in the past by the user of the user terminal 2. Usage History H may include, for example, conditions used when calculating said plan. In addition, Usage History H may include information indicating the date and time when said plan was used, the user's ID, and the like.

[0042] (Model AI) Model AI is a generative AI model that has been machine-learned to generate information based on input instructions. Model AI may be, for example, a large language model capable of executing various natural language processing tasks, but is not limited thereto. As Model AI, a general-purpose generative AI model may be applied, or a generative AI model fine-tuned using knowledge related to the field of the target plan may be applied. In addition, Model AI is not limited to being stored in the storage unit 120, and may be stored in an external device that provides a generation service using a generative AI model. Further, an example where Model AI is used as one type of generative AI model will be described below, but different generative AI models may be used to realize each function. In addition, a generative AI model is not necessarily required to be used to realize each function.

[0043] (Control Unit 110) Control Unit 110 comprehensively controls each unit of the user terminal 2. For example, Control Unit 110 includes an acquisition unit 11, a condition constructing unit 12, a plan determining unit 13, and a presenting unit 14.

[0044] The acquisition unit 11 is configured in the same manner as each unit included in the information processing apparatus 1, and is further configured as follows. The acquisition unit 11 acquires a user instruction input by the user to obtain an optimized plan by receiving the instruction from the user terminal 2. Since the details of the user instruction are as described above, repeated detailed description will be omitted.

[0045] The condition configuration unit 12 is configured in the same way as the other parts of the information processing device 1, and is configured as follows. For example, the condition configuration unit 12 may configure multiple conditions based on the response from the model AI by inputting an instruction statement to the model AI that instructs the model AI to respond to a user instruction about which setting value (option, numerical value, numerical range, etc.) is appropriate for multiple conditions T. "Configuring condition T" means determining the setting value to be given as a constraint to the optimization solver for condition T. Hereinafter, "configuring condition T" may also be written as "setting condition T". Furthermore, the condition configuration unit 12 does not necessarily have to use a model AI. For example, the condition configuration unit 12 may use a rule-based method to determine the options according to a given word list, such as selecting "minimize the number of drivers" if the user instruction for determining the optimization indicator includes words such as "number of drivers", selecting "reduce travel time" if it includes words such as "time", and selecting "maximize the load factor" if it includes words such as "load factor".

[0046] Alternatively, the condition configuration unit 12 may configure each of the multiple conditions using a model AI. For example, the condition configuration unit 12 may configure each condition T individually by inputting an instruction statement to the model AI instructing it to respond to a user instruction by indicating which setting value is appropriate for that condition T, and then configuring the condition T based on the response from the model AI.

[0047] Alternatively, the condition configuring unit 12 may acquire a plurality of answers by calling one or more model AIs, which are not necessarily the same model AI, a plurality of times, and then configure the condition T based on the proportions of the answers. For example, the condition configuring unit 12 may determine the most frequently selected option as the appropriate option as a result of calling the model AI a plurality of times. For example, when calling the model AI 100 times results in 20 selections of option A, 30 selections of option B, and 50 selections of option C, the most frequently answered option C may be selected. Alternatively, the condition configuring unit 12 may randomly determine a final option as the appropriate option based on the proportions obtained as a result of calling the model AI a plurality of times. For example, when calling the model AI 100 times results in 20 selections of option A, 30 selections of option B, and 50 selections of option C, a random number may be generated at a ratio of 20:30:50, and the resulting option may be selected.

[0048] Furthermore, if a first determination condition for determining that a configured condition matches a user instruction is not satisfied, the condition configuring unit 12 may configure the condition based on a new user instruction input in response to presentation of a question sentence related to the condition.

[0049] For example, the first determination condition may be a condition based on whether or not an answer that no setting value for any condition T applies (hereinafter referred to as "not applicable") is obtained from the model AI. For example, the condition configuring unit 12 may add the option "not applicable" to settable setting values for the condition T, and then input an instruction to the model AI that instructs the model AI to answer which setting value is appropriate based on the user instruction. Hereinafter, obtaining an answer of "not applicable" (or other than "not applicable") for a condition T is described as "the condition T is 'not applicable' (or other than 'not applicable')" or the like. This allows the first determination condition to be configured as follows, for example. For example, the first determination condition may be a condition that at least one condition T is other than "not applicable". Further, for example, the first determination condition may be a condition that all conditions T are other than "not applicable". Furthermore, for example, the first determination condition may be a condition that a specific condition T among a plurality of conditions T is other than "not applicable".

[0050] Furthermore, if, for example, the model AI can provide information indicating the probability of a condition T along with appropriate setting values, the first judgment condition may be a condition based on the probability obtained for each condition T. For example, the first judgment condition may be a condition in which the statistical values ​​of the probability obtained for multiple conditions T (e.g., mean, minimum, maximum, etc.) are greater than or equal to a threshold. An example of obtaining information indicating the probability is a method in which one or more model AIs, not necessarily the same model AI, are called multiple times, multiple responses are obtained, and then a condition T is constructed and the probability is obtained based on the proportion of those responses. For example, when randomly selecting the final option based on that proportion, the proportion (for example, if the model AI is called 100 times and the result is option A 20 times, option B 30 times, and option C 50 times, the ratio 20:30:50) may be used as the probability.

[0051] However, the first determination criterion only needs to be a condition for determining whether the configured conditions match the user instructions, and is not limited to the examples described above.

[0052] Furthermore, if the first determination condition for determining whether the configured conditions match the user's instructions is not met, the condition configuration unit 12 may configure the conditions by referring to the usage history H of plans previously used by the user. Specific examples of the first determination condition are as described above. For example, if a condition T that is deemed "not applicable" is used when calculating a plan indicated by the past usage history H, the condition configuration unit 12 may configure the condition T using the setting value of that previously used condition T. Also, for example, if the condition T is used in multiple plans indicated by the past usage history H, and the setting values ​​are different, the condition configuration unit 12 may configure the condition T based on statistical information of the setting value of that condition T (for example, the setting value with the most frequent use).

[0053] Furthermore, the condition configuration unit 12 may generate justification information that shows the basis for the configuration of condition T. For example, the condition configuration unit 12 may input an instruction sentence to the model AI instructing it to respond to a user instruction by indicating which setting value is appropriate for condition T and the part of the user instruction that serves as the basis for that. This enables the condition configuration unit 12 to generate justification information based on the information output from the model AI. Alternatively, the condition configuration unit 12 may generate justification information without using the model AI. For example, if condition T is configured using a rule-based method with a word list as described above, the words detected at that time may be used as justification information.

[0054] The planning unit 13 is configured in the same way as the planning unit 13 included in the information processing device 1, and is configured as follows: The planning unit 13 acquires target data from the target data storage device 3. The planning unit 13 also refers to the acquired target data and calculates a plan using an optimization solver based on a plurality of conditions T configured by the condition configuration unit 12.

[0055] The presentation unit 14 is configured in the same way as the presentation unit 14 included in the information processing device 1, and is configured as follows: The presentation unit 14 presents the conditions T configured by the condition configuration unit 12 and the plan calculated by the plan determination unit 13 to the user terminal 2 by transmitting them. Furthermore, if the condition configuration unit 12 has generated supporting information, the presentation unit 14 presents the supporting information to the user terminal 2 along with the configured conditions T by transmitting it to the user terminal 2.

[0056] (Method executed by the information processing system 10A) The information processing system 10A configured as described above executes the information processing methods S1A to S5. Below, an example is given in which the plan targeted by the information processing methods S1A to S5 is a delivery plan. The conditions T1 and T2 stored in the memory unit 120 are to be included in the delivery conditions (an example of predetermined conditions) that can be given to the optimization solver that calculates the delivery plan. However, the plan targeted is not limited to a delivery plan, but may be any other type of plan.

[0057] (Flow of Information Processing Method S1A) The information processing system 10A configured as described above executes the information processing method S1A. Figure 4 is a flowchart showing the flow of the information processing method S1A according to this disclosure. As shown in Figure 4, the information processing method S1A includes steps S101 to S105.

[0058] Step S101 is an example of the acquisition process. In step S101, the acquisition unit 11 of the server 1A acquires user instructions, including natural language sentences, that have been entered by the user from the dialogue unit 21 of the user terminal 2 in order to obtain an optimized delivery plan.

[0059] In step S102, the planning unit 13 obtains the delivery information, which is the target data, from the target data storage device 3. Specific examples of the delivery information are as described above.

[0060] Step S103 is an example of a condition configuration process. In step S103, the condition configuration unit 12 sets delivery conditions based on user instructions. Figure 5 is a diagram that schematically illustrates a specific example of using the model AI of step S103 according to this disclosure. In Figure 5, the callout mark type figure attached to the figure containing "condition configuration unit" indicates information input to the model AI by the condition configuration unit 12. Also, the callout mark type figure attached to the figure containing "AI" indicates information output from the model AI. The same applies to other drawings.

[0061] As shown in Figure 5, the user instruction R1 input by user U includes the natural language sentence "Minimize the driver's driving time as much as possible, and it's okay to use the highway, but..." The condition configuration unit 12 inputs the instruction IN1 to the model AI: "For the input natural language, what are the most appropriate optimization indicators, highway conditions, etc." This causes the model AI to output the answer OUT1: "Optimization indicator: Minimize travel time, highway conditions: Leave it to the map,..." Based on the answer OUT1, the condition configuration unit 12 sets "Minimize travel time" as the condition T1 related to the optimization indicator and "Leave it to the map" as the condition T2 related to the highway.

[0062] Step S104 in Figure 4 is an example of the plan determination process. In step S104, the plan determination unit 13 calculates a delivery plan for the delivery information acquired as target data by providing the delivery conditions to the optimization solver.

[0063] Step S105 is an example of the presentation process. In step S105, the presentation unit 14 presents the configured delivery conditions and the determined delivery plan to the user via the dialogue unit 21 of the user terminal 2. Note that the configured delivery conditions are not limited to being presented together with the delivery plan in step S105; they may also be transmitted to the user terminal 2 following step S103 and presented to the user. With this, the information processing system 10A terminates the information processing method S1A.

[0064] (Flow of Information Processing Method S2) The information processing system 10A may also execute an information processing method S2 which is a modified version of information processing method S1A. Figure 6 is a flowchart showing the flow of information processing method S2 according to this disclosure. As shown in Figure 6, information processing method S2 differs from information processing method S1A in that it includes S203 instead of S103. Other aspects are the same as information processing method S1, so a detailed explanation will not be repeated.

[0065] Step S203 is an example of a condition configuration process. In S203, the condition configuration unit 12 sets each condition T that is not dependent on one another and is included in the delivery conditions, based on the user instruction R1.

[0066] Figure 7 is a schematic diagram illustrating a specific example of using the Model AI in step S203 of this disclosure. As shown in Figure 7, the user instruction R1 input by user U includes the natural language sentence "Minimize the driver's driving time as much as possible, and it's okay to use the highway, but..." The condition configuration unit 12 inputs instruction IN2 "What is the most appropriate optimization indicator for the input natural language?" to the Model AI. As a result, the Model AI outputs answer OUT2 "Minimize travel time". Based on answer OUT2, the condition configuration unit 12 sets "Minimize travel time" as the condition T1 related to the optimization indicator. The condition configuration unit 12 also inputs instruction IN3 "What is the most appropriate highway condition for the input natural language?" to the Model AI. As a result, the Model AI outputs answer OUT3 "Leave it to the map". Based on answer OUT3, the condition configuration unit 12 sets "Leave it to the map" as the condition T2 related to the highway.

[0067] (Modifications of steps S203 and S104) Step S203 can be modified as follows. In step S203, the condition configuration unit 12 may determine whether the condition T configured based on the user instruction is a hard constraint that must be followed by the optimization solver, or a soft constraint that should be followed as much as possible.

[0068] In this case, step S104 is modified as follows. In step S104, the plan determination unit 13 calculates a delivery plan by providing each of the multiple conditions T to the optimization solver as a hard constraint or a soft constraint according to the judgment result of the condition configuration unit 12. With this modification, a plan that is accurately tailored to the user's instructions can be presented to the user.

[0069] Figure 8 schematically illustrates a specific example of a modified step S203 in this disclosure in which a model AI is used. In this modified example, the delivery conditions include a condition T3 relating to a time window constraint, and the condition T3 is configured based on a user instruction R1. Furthermore, as shown in Figure 8, the user instruction R1 also includes the natural language sentence "The time constraint must be satisfied." The condition configuration unit 12 inputs the instruction IN4 to the model AI: "Determine whether the following sentence is a hard constraint or a soft constraint in a mathematical optimization delivery planning problem: 'The time constraint must be satisfied'." As a result, the model AI outputs the answer OUT4: "The sentence 'The time constraint must be satisfied' indicates that it is a 'hard constraint' in a mathematical optimization delivery planning problem...." Therefore, the condition configuration unit 12 determines that condition T3 is a hard constraint. As a result, in step S104, condition T3 is given to the optimization solver as a hard constraint, and the delivery plan is calculated.

[0070] (Screen Example G1) Figure 9 is a diagram showing an example of a screen displayed on the display unit 250 of the user terminal 2 in step S105 of the information processing methods S1 and S2 according to this disclosure. In Figure 9, the speech bubble-shaped figure attached to the figure containing "U" indicates information input by user U. Also, the speech bubble-shaped figure attached to the figure containing "Delivery Planning Agent" indicates information received from server 1A. The same applies to the other figures.

[0071] As shown in Figure 9, the example screen G1 includes user instructions R1 entered by user U, information A1 indicating delivery conditions, and information A2 indicating the delivery plan.

[0072] In the example screen G1, first, user U inputs user instruction R1, and this user instruction R1 is sent to server 1A (S101). Also, delivery information is acquired by server 1A (S102). Next, server 1A configures the delivery conditions based on user instruction R1, and information A1 indicating these delivery conditions is sent to user terminal 2 (S103 or S203). As a result, the received information A1, "We will plan the delivery under the following conditions. Optimization index: Minimize travel time. Highway conditions: Automatic, ...", is added and displayed on the example screen G1.

[0073] Next, server 1A determines a delivery plan based on the configured delivery conditions, and information A1 indicating the delivery plan is transmitted to user terminal 2 (S104). As a result, the received information A2, "How is this delivery plan? Vehicle 1: A→B, Vehicle 2: C→D→E→F, Vehicle 3: G→H→I→J, ...", is added and displayed on screen example G1 (S105). Information A2 may also include an image showing the delivery plan (for example, an image IMG in which the route showing the delivery plan is superimposed on a map), as shown in Figure 9.

[0074] (Flow of Information Processing Method S3) The information processing system 10A may also execute an information processing method S3 which is a modified version of information processing method S1A. Figure 10 is a flowchart showing the flow of information processing method S3 according to this disclosure. As shown in Figure 10, information processing method S3 includes S303, S306, and S308 in addition to S101 to S105 included in information processing method S1A. Other points are the same as those of information processing method S1, so a detailed explanation will not be repeated.

[0075] Step S303 is executed following step S103. In step S303, the condition configuration unit 12 determines whether a first determination condition for determining whether the configured condition matches the user instruction is met. A specific example of the first determination condition is as described above. If it is determined to be Yes in step S303, steps S104 and S105 are executed next. If it is determined to be No in step S303, steps S306 to S308 are executed. Steps S306 to S308 may be executed multiple times, not just once. By executing steps S306 to S308 multiple times, it is expected that new user instructions will be obtained, which may have the same meaning but slightly different wording. As a result, the likelihood of configuring a condition that matches the user instruction increases.

[0076] In step S306, the presentation unit 14 presents the user, via the dialogue unit 21, with a question regarding the condition T for which the first determination condition is not met (for example, the condition T for which the result is "not applicable").

[0077] In step S307, the acquisition unit 11 acquires new user instructions entered by the user in response to the presentation of the question.

[0078] In step S308, the condition configuration unit 12 sets conditions T that do not satisfy the first judgment condition based on new user instructions. It may also review and reset conditions T that previously satisfied the first judgment condition based on the context including the user instructions received so far. Subsequently, steps S104 and S105 are executed. This increases the likelihood that conditions T that do not match the original user instructions can be set based on new user instructions.

[0079] Figure 11 is a diagram that schematically illustrates a specific example of using the model AI in step S303 of this disclosure. As shown in Figure 11, the user instruction R1 input by user U includes the natural language sentence "Minimize the driver's driving time as much as possible, and it's okay to use the highway,..." The condition configuration unit 12 inputs the instruction IN1 to the model AI, "For the input natural language, what are the most appropriate optimization indicators, highway conditions, etc." As a result, the model AI outputs the answer OUT1-a "Optimization indicator: Minimize travel time, Highway conditions: Not applicable,..." Based on the answer OUT1-a, the condition configuration unit 12 can set "Minimize travel time" as the condition T1 related to the optimization indicator, but it cannot set the condition T2 related to the highway because it is "Not applicable". Therefore, in this example, it is determined to be No in step S303.

[0080] (Screen Example G2) Figure 12 is a diagram showing an example of a screen displayed on the display unit 250 of the user terminal 2 in steps S306 to S307 and S105 of the information processing method S3 according to the present disclosure. As shown in Figure 12, screen example G2 includes user instruction R1 input by user U, information A3 indicating delivery conditions, user instruction R2, information A4 indicating delivery conditions, and information A5 indicating a delivery plan.

[0081] First, the input of user instruction R1 in screen example G2 (S101) and the acquisition of delivery information by server 1A (S102) will be explained in the same way as in screen example G1. Next, server 1A sets the delivery conditions based on user instruction R1, and information A3 indicating the delivery conditions is transmitted to user terminal 2 (S103). As a result, the received information A3 is added and displayed on screen example G2.

[0082] Here, as shown in Information A3, "Minimize travel time" was set as the condition T1 for the optimization indicator based on user instruction R1, but the condition T2 for highways, and the other conditions T3, T4, etc. were not set. In other words, since it was determined to be No in step S303, Information A3 includes the question, "The following delivery conditions have not been set. Please set them..." The question includes a simple explanation of each of the unset conditions T2, T3, and T4 (S306).

[0083] Next, in example screen G2, user U inputs a new user instruction R2 regarding condition T3, "Condition T3 should be xxx...", and this user instruction R2 is sent to server 1A (S307). Server 1A then sets condition T3 based on the new user instruction R2, and information A4 indicating the delivery conditions, including condition T3, is sent to user terminal 2 (S308). As a result, the received information A4 is added to and displayed on example screen G2.

[0084] Next, server 1A determines a delivery plan based on the delivery conditions including the set conditions T1 and T3, and information A5 indicating the delivery plan is transmitted to user terminal 2 (S104). As a result, the received information A5 is added to the display on screen example G2 (S105).

[0085] (Flow of Information Processing Method S4) The information processing system 10A may also execute an information processing method S4 which is a modified version of information processing method S3. Figure 13 is a flowchart showing the flow of information processing method S4 according to this disclosure. As shown in Figure 13, information processing method S4 differs from information processing method S3 in that it includes S406 instead of S306 to S307. Other aspects are the same as information processing method S3, so a detailed explanation will not be repeated.

[0086] Step S406 is executed if it is determined to be No in step S303. In step S406, the condition configuration unit 12 refers to past conditions indicated by the usage history H and sets conditions T for which the first determination condition is not met (for example, conditions T for which the result is "not applicable"). Subsequently, steps S104 to S105 are executed. This allows conditions T that do not match the user's instructions to be set based on the user's usage history H.

[0087] (Screen example G3) Figure 14 is a diagram showing an example of a screen displayed on the display unit 250 of the user terminal 2 in step S105 of the information processing method S4 according to the present disclosure. As shown in Figure 14, screen example G3 includes a user instruction R1 entered by user U, information A6 indicating delivery conditions, and information A7 indicating a delivery plan.

[0088] First, the input of user instruction R1 in screen example G3 (S101) and the acquisition of delivery information by server 1A (S102) will be explained in the same way as in screen example G1. Next, server 1A sets the delivery conditions based on user instruction R1 (S103). Here, although condition T1 regarding the optimization indicator and condition T2 regarding the highway were set based on user instruction R1, conditions T3 and T4 were not set as "not applicable" (No in step S303). Therefore, based on the usage history H, "aaa" is set for condition T3 and "bbb" is set for condition T4 (S406). Information A6 indicating the delivery conditions including the set conditions T1 to T4 is also sent to user terminal 2. As a result, the received information A6 is added to and displayed on screen example G3. Note that information A6 includes information indicating that "conditions T3 and T4 were set based on the usage history."

[0089] Next, server 1A determines a delivery plan based on the delivery conditions including the set conditions T1 to T4, and information A7 indicating the delivery plan is transmitted to user terminal 2 (S104). As a result, the received information A7 is added to the display on screen example G4 (S105).

[0090] (Screen example G4) The information processing method S3 can be further modified to include step S406 in the information processing method S4. In this case, the modified information processing method S3 can present the user with the result of setting a condition T that cannot be set solely based on user instructions by referring to the usage history H (S406), and can also obtain new user instructions regarding the condition T (S306 to S308).

[0091] Figure 15 is a diagram showing an example of a screen displayed on the display unit 250 of the user terminal 2 in step S105 of the modified information processing method S3 according to the present disclosure. As shown in Figure 15, the example screen G4 includes a user instruction R1 input by user U, information A8 indicating delivery conditions, a user instruction R3, information A9 indicating delivery conditions, and information A10 indicating a delivery plan.

[0092] First, the input of user instruction R1 in screen example G4 (S101) and the acquisition of delivery information by server 1A (S102) will be explained in the same way as in screen example G1. Next, server 1A sets the delivery conditions based on user instruction R1. Here, although condition T1 regarding the optimization indicator and condition T2 regarding the highway are set based on user instruction R1, conditions T3 and T4 are not set as "not applicable" (No in step S303). Therefore, based on the usage history H, "aaa" is set for condition T3 and "bbb" is set for condition T4 (S406). Information A8 indicating the delivery conditions including the set conditions T1 to T4 is also sent to user terminal 2. As a result, the received information A8 is added and displayed on screen example G4. Information A8 also includes a question asking for the appropriateness of conditions T3 and T4 set based on the usage history H, such as "The following delivery conditions are not set, is this OK?" (S306).

[0093] Next, in the example screen G4, user U inputs a new user instruction R3 regarding condition T3, "Set condition T3 to xxx instead of aaa...", and this user instruction R3 is sent to server 1A (S307). Server 1A then sets condition T3 based on the new user instruction R3, and information A9 indicating the delivery conditions including condition T3 is sent to user terminal 2 (S308). As a result, the received information A9 is added and displayed on the example screen G4.

[0094] Next, server 1A determines a delivery plan based on the delivery conditions including the set conditions T1 to T4, and information A10 indicating the delivery plan is transmitted to user terminal 2 (S104). As a result, the received information A10 is added to the display on screen example G4 (S105).

[0095] (Flow of Information Processing Method S5) The information processing system 10A may also execute an information processing method S5 which is a modified version of information processing method S2. Figure 16 is a flowchart showing the flow of information processing method S5 according to this disclosure. As shown in Figure 16, information processing method S5 differs from information processing method S2 in that it includes S503 instead of S203. Other aspects are the same as information processing method S1, so a detailed explanation will not be repeated.

[0096] Step S503 is an example of a condition configuration process. In step S503, the condition configuration unit 12 sets each of the multiple conditions T based on the user instruction R1 and generates the basis information for that condition.

[0097] Figure 17 is a diagram that schematically illustrates a specific example of using the model AI in step S503 of this disclosure. As shown in Figure 17, the user instruction R1 input by user U includes the natural language sentence "Minimize the driver's driving time as much as possible, and it is okay to use the highway, but..." The condition configuration unit 12 inputs the instruction IN5 to the model AI "Determine whether the following statement indicates whether or not to use the highway when planning the delivery, or whether to leave it to the map, and specify the sentence that serves as the basis:..." As a result, the model AI outputs the answer OUT5 "Regarding the decision of whether or not to use the highway in the provided statement, it can be determined that the setting is 'leave it to the map' based on part of the following. The sentence that serves as the basis: 'It is okay to use the highway'" Based on the answer OUT5, the condition configuration unit 12 sets the condition T2 regarding the highway to "leave it to the map" and generates the basis information indicating "It is okay to use the highway" included in the user instruction R1.

[0098] In step S503, instead of inputting an instruction statement for each condition T, an instruction statement may be input that collectively instructs the model AI to select appropriate setting values ​​and generate supporting information for each of the multiple conditions T.

[0099] (Screen example G5) Figure 18 is a diagram showing an example of a screen displayed on the display unit 250 of the user terminal 2 in step S105 of the information processing method S5 according to the present disclosure. As shown in Figure 18, screen example G5 includes a user instruction R1 entered by user U, information A11 indicating delivery conditions, and information A12 indicating a delivery plan.

[0100] First, the input of user instruction R1 in screen example G5 (S101) and the acquisition of delivery information by server 1A (S102) will be explained in the same way as in screen example G1. Next, in server 1A, delivery conditions are set based on user instruction R1, and the basis information is generated, and information A11, which includes the delivery conditions and the basis information, is transmitted to user terminal 2 (S503). As a result, the received information A11 is added to and displayed on screen example G1. Information A11 includes information indicating that the condition T2 regarding expressways is set to "Leave it to the map," and the basis information that the reason for this is "It is OK to use expressways."

[0101] Next, server 1A determines a delivery plan based on the configured delivery conditions, and information A12 indicating the delivery plan is transmitted to user terminal 2 (S104). As a result, the received information A12 is added to the display on screen example G5 (S105).

[0102] (Effects of Information Processing System 10A) As described above, in the information processing system 10A, the predetermined conditions include multiple conditions that are not dependent on each other, and the condition configuration unit 12 is configured to configure each of the multiple conditions. Therefore, with the information processing system 10A, in addition to the effects of the information processing device 1, it is expected that the accuracy of configuring the predetermined conditions based on user instructions will be increased, and the ease of implementation when increasing or decreasing the conditions to be considered will be increased.

[0103] Furthermore, in the information processing system 10A, the condition configuration unit 12 is configured to configure the condition based on new user instructions input in response to the presentation of a question about the condition if the first determination condition for determining whether the configured condition matches the user instruction is not met. Therefore, according to the information processing system 10A, in addition to the effects performed by the information processing device 1, the user's "thoughts" that they want to convey to the system are clarified by asking for confirmation of conditions that the user has forgotten to specify or is otherwise unable to set, thereby improving the accuracy of the plan from the user's perspective and increasing the user's sense of satisfaction.

[0104] Furthermore, in the information processing system 10A, the condition configuration unit 12 is configured such that, if the first determination condition for determining whether the configured conditions match user instructions is not met, it refers to the usage history of plans previously used by the user to configure the conditions. Therefore, according to the information processing system 10A, in addition to the effects of the information processing device 1, the user can expect an improvement in user experience because conditions T that the user did not specifically instruct are also set based on their usage history.

[0105] Furthermore, in the information processing system 10A, the condition configuration unit 12 generates justification information indicating the basis for the conditions using a generation AI model, and the presentation unit 14 presents the conditions to the user along with the justification information. Therefore, with the information processing system 10A, in addition to the effects achieved by the information processing device 1, the user can obtain the effect of knowing which part of their instructions was the basis for setting the conditions.

[0106] [Third Exemplary Embodiment] A third exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same function as those described in the above-described exemplary embodiment are denoted by the same reference numerals, and their descriptions are omitted as appropriate. The scope of application of each technology adopted in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology adopted in this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise. Furthermore, each technology shown in the drawings referenced to describe this exemplary embodiment can also be adopted in other exemplary embodiments included in this disclosure, to the extent that no particular technical problems arise.

[0107] (Configuration of Information Processing System 10B) Information processing system 10B is a modified version of information processing system 10A. Below, we will focus on explaining the differences between information processing system 10B and information processing system 10A, and will not repeat detailed explanations of similar points.

[0108] The configuration of the information processing system 10B will be described with reference to Figure 19. Figure 19 is a block diagram showing the configuration of the information processing system 10B according to this disclosure. As shown in Figure 19, the information processing system 10B is configured in the same way as the information processing system 10A, except that it includes Server 1B instead of Server 1A.

[0109] (Server 1B) In Server 1B, the control unit 110 includes, in addition to the acquisition unit 11, condition configuration unit 12, plan determination unit 13, and presentation unit 14 provided in Server 1A, a data processing unit 15 and an alternative condition generation unit 16. The configuration of Server 1B other than the control unit 110 is the same as that of Server 1A. The data processing unit 15 is an example of a configuration that realizes data processing means. The alternative condition generation unit 16 is an example of a configuration that realizes alternative condition generation means.

[0110] The acquisition unit 11, the condition configuration unit 12, and the presentation unit 14 are configured in the same way as the functional blocks of the same name included in the server 1A. The plan determination unit 13 is configured in the same way as the plan determination unit 13 included in the server 1A, and is configured as follows. If the first determination condition for determining whether the configured conditions match the user instruction is not met, the plan determination unit 13 generates countermeasure information using a model AI that indicates a countermeasure to obtain a plan corresponding to the user instruction. The plan determination unit 13 also determines the plan by executing the countermeasure indicated by the generated countermeasure information. As for specific examples of the first determination condition, as described above, a condition based on whether each of the multiple conditions T included in the predetermined conditions is "not applicable" may be applied.

[0111] For example, the planning unit 13 may input an instruction to the model AI that instructs it to respond with a method of action to obtain a plan in accordance with the user's instructions if the first determination condition is not met. This generates method of action information based on the output from the model AI. Alternatively, the planning unit 13 may input an instruction to the model AI that instructs it to execute the method of action indicated by the generated method of action information. This executes the method of action. The method of action may be, for example, a program that can be executed by a computer, and the method of action information may include information written in a programming language.

[0112] The data processing unit 15 performs at least one of the following: (1) generating preprocessing information using a model AI that indicates preprocessing that can be performed on target data referenced by the plan determination unit 13 to determine a plan, and executing preprocessing based on the generated preprocessing information; and (2) generating postprocessing information using a model AI that indicates postprocessing that can be performed on the determined plan, and executing postprocessing based on the generated postprocessing information. Examples of preprocessing include, but are not limited to, processing to reduce processing costs such as the execution time by the plan determination unit 13, and processing to improve the accuracy of the plan determined by the plan determination unit 13.

[0113] For example, the data processing unit 15 may input an instruction statement to the model AI instructing it to respond with preprocessing that can be performed to obtain a plan based on the target data. This generates preprocessing information. Alternatively, for example, the data processing unit 15 may input an instruction statement to the model AI instructing it to execute the preprocessing indicated in the preprocessing information. This executes the preprocessing. The preprocessing may be, for example, a program that can be executed by a computer, and the preprocessing information may include information written in a programming language.

[0114] Furthermore, post-processing could include, but is not limited to, processing to present the plan determined by the plan determination unit 13 to the user in an easy-to-understand manner.

[0115] For example, the data processing unit 15 may input an instruction statement to the model AI instructing it to respond with executable post-processing steps in order to present the determined plan to the user in an easily understandable manner. This generates post-processing information. Alternatively, for example, the data processing unit 15 may input an instruction statement to the model AI instructing it to execute the post-processing steps indicated by the post-processing information. This executes the post-processing steps. The post-processing steps may be, for example, a program executable by a computer, and the post-processing information may include information written in a programming language.

[0116] If the second determination condition for determining the completion of the process for determining the plan is not met, the alternative condition generation unit 16 uses model AI to construct alternative conditions that are more appropriate than the conditions configured based on user instructions. For example, the second determination condition may be that the conditions configured based on user instructions are not solvable. In this case, for example, an alternative condition may be generated that relaxes the configured conditions. Alternatively, for example, the second determination condition may be that, when comparing the plan calculated based on the conditions configured based on user instructions with the plan calculated based on the alternative conditions that relax the configured conditions, the latter plan yields a higher efficiency index. Relaxing the conditions may include, but are not limited to, increasing the number of options set as the conditions, changing the numerical value or range of numerical values, or deleting one of the multiple set conditions.

[0117] (Flow of Information Processing Method S6) The information processing system 10B configured as described above executes the information processing method S1B. Figure 20 is a flowchart showing the flow of the information processing method S1B according to this disclosure. As shown in Figure 20, the information processing method S1B includes steps S601 to S615.

[0118] Step S601 is an example of an acquisition process and will be explained in the same way as step S101.

[0119] In step S602, the data processing unit 15 acquires delivery information as target data from the target data storage device 3.

[0120] In step S603, the data processing unit 15 uses model AI to generate executable pre-processing information for the delivery information.

[0121] In step S604, the data processing unit 15 executes the preprocessing indicated by the preprocessing information. However, if no useful preprocessing information is generated in step S603, the preprocessing in step S604 does not necessarily have to be executed.

[0122] Figure 21 is a diagram that schematically illustrates a specific example of steps S603 to S604 in this disclosure. As shown in Figure 21, the delivery information D1 as the target data is assumed to contain 1500 delivery cases to be planned in the Kanto region. In this case, the data processing unit 15 inputs the instruction IN6, "How to obtain a delivery plan based on the given delivery information?" to the model AI. As a result, the model AI outputs the answer OUT6-1, "Solution: Kanto consists of multiple regions (Tokyo, Kanagawa, Saitama, ...), so it is sufficient to divide it by region. Example program: hogehoge..." Then, the model AI outputs the answer OUT6-2, "Execute the above program," and the program is executed. As a result, the Kanto delivery information D1 is divided into Tokyo delivery information D2, Kanagawa delivery information D3, Saitama delivery information D4, ... Subsequent processing is performed based on the divided delivery information D2, D3, and D4. For example, the process of calculating the delivery plan (S608 or S609, described later) is executed for each of the delivery information items D2, D3, and D4.

[0123] Step S605 in Figure 20 is an example of a condition configuration process and will be described in the same way as step S103 or S203.

[0124] In step S606, the plan determination unit 13 determines whether the first determination condition for determining whether the configured conditions match the user instructions is met. A specific example of the first determination condition is as described above. The case where Yes is determined in step S606 will be described later. If No is determined in step S606, the next steps S607 to S608 are executed.

[0125] In step S607, the plan determination unit 13 generates action method information using model AI that indicates how to take action to obtain a plan in accordance with the user's instructions.

[0126] Step S608 is an example of the plan determination process. In step S608, the plan determination unit 13 determines the plan by executing the countermeasure indicated by the generated countermeasure information. Subsequently, step S610, which will be described later, is executed.

[0127] Figure 22 is a diagram that schematically illustrates a specific example of steps S607 to S608 in this disclosure. As shown in Figure 22, the user instruction R4 input by user U contains the natural language sentence "Minimize the driver's driving time as much as possible, and you can use the highway, but h(x)...". Here, h(x) represents a natural language sentence indicating an ambiguous expression, an unmanageable user instruction, etc., and does not necessarily indicate that it is expressed mathematically. The planning unit 13 inputs the instruction IN7 "How to obtain a delivery plan based on the given user instruction and data?" to the model AI in response to the user instruction R4. As a result, the model AI outputs the answer OUT7-1 "Handling method: Calculate several delivery plans based on the conditions excluding the unknown instruction h(x), and arrange the calculated delivery plans that seem to satisfy h(x) in order of recommendation. Program example: hogehoge". Subsequently, the model AI outputs the answer OUT7-2 "Execute the above program", and the program is executed. This allows for the calculation of multiple delivery plans based on conditions configured from user instructions, excluding the unknown instruction h(x). Furthermore, from these calculated delivery plans, delivery plans P1, P2, P3, ... are obtained in descending order of their degree to which h(x) is satisfied. Known techniques can be applied to calculate the degree to which h(x) is satisfied.

[0128] Step S609 in Figure 20 is executed if the answer in step S606 is determined to be Yes. Step S609 is an example of a plan decision process and will be explained in the same way as step S104.

[0129] In step S610, the alternative condition generation unit 16 determines whether the second determination condition for determining the completion of the process for determining the plan is met. A specific example of the second determination condition is as described above. The case where Yes is determined in step S610 will be described later. If No is determined in step S610, step S611 is executed.

[0130] Step S611 is an example of the alternative condition generation process. In step S611, the alternative condition generation unit 16 generates alternative conditions. Specific examples of alternative conditions are as described above. Subsequently, the process from step S609 is repeated based on the new delivery conditions including the alternative conditions.

[0131] If the answer is Yes in step S610, steps S612 and subsequent steps are executed. In step S612, the data processing unit 15 generates post-processing information that can be executed for the plan calculated by the plan determination unit 13, using model AI.

[0132] In step S613, the data processing unit 15 executes the post-processing indicated by the post-processing information. However, if no useful post-processing information is generated in step S612, the post-processing in step S613 does not necessarily have to be executed.

[0133] Step S614 is an example of a presentation process and will be described in the same way as step S105.

[0134] In step S615, the control unit 110 determines whether the user has approved the presented delivery plan. For example, information indicating whether the user has approved or not may be obtained by the dialogue unit 21 of the user terminal 2 and transmitted to the server 1B. If it is determined to be No in step S615, the information processing system 10B repeats the processing from step S601. If it is determined to be Yes in step S615, the information processing method S1B terminates.

[0135] (Effects of Information Processing System 10B) As described above, Information Processing System 10B further includes a data processing unit 15 that performs at least one of the following: (1) generating pre-processing information that can be executed on target data referenced by the plan determination unit 13 to determine a plan using a generation AI model, and executing pre-processing based on the generated pre-processing information; and (2) generating post-processing information that can be executed on the determined plan using a generation AI model, and executing post-processing based on the generated post-processing information. Therefore, with Information Processing System 10B, in addition to the effects achieved by Information Processing System 10A, it is expected that processing costs such as execution time when determining a plan can be reduced and the accuracy of the determined plan can be improved by performing pre-processing on the target data. Furthermore, it is expected that the plan can be presented in an easy-to-understand manner for the user by performing post-processing on the determined plan.

[0136] Furthermore, in the information processing system 10B, if the first determination condition for determining whether the configured conditions match the user's instructions is not met, the plan determination unit 13 generates countermeasure information indicating countermeasures to obtain a plan corresponding to the user's instructions using a generation AI model, and determines the plan by executing the countermeasures indicated by the countermeasure information. Therefore, in addition to the effects achieved by the information processing system 10A, the information processing system 10B also has the effect of being able to determine a plan corresponding to the user's instructions even when it is not possible to configure conditions that match the user's instructions.

[0137] Furthermore, the information processing system 10B is configured to include an alternative condition generation unit 16 that, if the second determination condition for determining the completion of the process for determining the plan is not met, generates alternative conditions with a higher degree of appropriateness than the configured conditions using an AI model. Therefore, in addition to the effects achieved by the information processing system 10A, the information processing system 10B can provide the user with a plan that is superior to the plan that would be created if user instructions were followed.

[0138] [Example of implementation by software] Some or all of the functions of each device constituting the information processing device 1 and the information processing systems 10A and 10B (hereinafter also referred to as "each of the above devices") may be implemented by hardware such as integrated circuits (IC chips) or by software.

[0139] In the latter case, each of the above devices is implemented, for example, by a computer that executes instructions for a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 23. Figure 23 is a block diagram showing the hardware configuration of computer C, which functions as one of the above devices according to this disclosure.

[0140] Computer C comprises at least one processor C1 and at least one memory C2. Memory C2 stores a program P for operating Computer C as each of the above-mentioned devices. In Computer C, the processor C1 reads and executes the program P from memory C2, thereby realizing each of the above-mentioned devices.

[0141] For processor C1, for example, a CPU (Central Processing Unit), GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating Point Number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof can be used. For memory C2, for example, flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof can be used.

[0142] Computer C may also be equipped with RAM (Random Access Memory) for loading program P at runtime and for temporarily storing various data. Furthermore, computer C may be equipped with a communication interface for sending and receiving data with other devices. Additionally, computer C may be equipped with an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0143] Furthermore, program P can be recorded on a non-temporary, tangible recording medium M that is readable by computer C. Such recording medium M can include, for example, tape, disk, card, semiconductor memory, or programmable logic circuitry. Computer C can acquire program P via such recording medium M. Program P can also be transmitted via a transmission medium. Such transmission mediums can include, for example, a communication network or broadcast waves. Computer C can also acquire program P via such transmission medium.

[0144] Furthermore, each of the above functions of each of the above devices may be implemented by a single processor in a single computer, by multiple processors in a single computer working together, or by multiple processors in each of multiple computers working together. In addition, the programs for implementing each of the above functions in each of the above devices may be stored in a single memory in a single computer, distributed and stored in multiple memories in a single computer, or distributed and stored in multiple memories in each of multiple computers.

[0145] [Addendum A] This disclosure includes the technologies described in the following addendums. However, the present invention is not limited to the technologies described in the following addendums, and various modifications are possible within the scope of the claims.

[0146] (Appendix A1) An information processing device comprising: an acquisition means for acquiring user instructions input by a user in order to obtain an optimized plan; a condition configuration means for configuring predetermined conditions based on the user instructions; a plan determination means for determining the plan based on the conditions; and a presentation means for presenting the conditions and the plan to the user.

[0147] (Appendix A2) The information processing apparatus according to Appendix A1, further comprising: (1) generating preprocessing information by a generating AI model that indicates preprocessing that can be performed on target data referenced by the plan determination means for determining the plan, and performing preprocessing based on the generated preprocessing information; and (2) generating post-processing information by a generating AI model that indicates post-processing that can be performed on the determined plan, and performing post-processing based on the generated post-processing information.

[0148] (Note A3) The information processing apparatus described in Note A1 or A2, wherein if the first determination condition for determining whether the configured conditions match the user instruction is not met, the plan determination means generates countermeasure information indicating a countermeasure to obtain a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information.

[0149] (Appendix A4) If the second determination condition for determining the completion of the process for determining the plan is not met, the information processing device according to any one of Appendix A1 to A3 further comprises: an alternative condition generation means for constructing alternative conditions with a higher degree of appropriateness than the configured conditions using an AI model.

[0150] (Appendix A5) The information processing apparatus according to any one of Appendices A1 to A4, wherein the predetermined conditions include a plurality of conditions that are not dependent on each other, and the condition configuring means constitutes each of the plurality of conditions.

[0151] (Note A6) The information processing device according to any one of Notes A1 to A5, wherein the condition setting means sets the condition based on a new user instruction input in response to the presentation of a question about the condition if the first determination condition for determining whether the set condition matches the user instruction is not met.

[0152] (Note A7) The information processing device according to any one of Notes A1 to A6, wherein the condition setting means, when the first determination condition for determining whether the set conditions match the user instruction is not met, refers to the usage history of plans previously used by the user to set the conditions.

[0153] (Appendix A8) The information processing apparatus according to any one of Appendix A1 to A7, wherein the condition setting means generates basis information indicating the basis for setting the condition, and the presentation means presents the condition together with the basis information to the user.

[0154] [Addendum B] This disclosure includes the technologies described in the following addendums. However, the present invention is not limited to the technologies described in the following addendums, and various modifications are possible within the scope of the claims.

[0155] (Appendix B1) An information processing method comprising: an acquisition process in which at least one processor acquires user instructions input by a user in order to obtain an optimized plan; a condition configuration process in which the at least one processor configures predetermined conditions based on the user instructions; a plan determination process in which the at least one processor determines the plan based on the conditions; and a presentation process in which the at least one processor presents the conditions and the plan to the user.

[0156] (Appendix B2) The information processing method according to Appendix B1, further comprising data processing in which at least one processor performs at least one of the following: (1) generating preprocessing information by a generating AI model that indicates preprocessing that can be performed on target data referenced by the plan determination process to determine the plan, and executing preprocessing based on the generated preprocessing information; and (2) generating post-processing information by a generating AI model that indicates post-processing that can be performed on the determined plan, and executing post-processing based on the generated post-processing information.

[0157] (Appendix B3) The information processing method according to Appendix B1 or B2, wherein in the plan determination process, if the first determination condition for determining whether the configured conditions match the user instruction is not met, the at least one processor generates countermeasure information indicating a countermeasure to obtain a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information.

[0158] (Appendix B4) The information processing method according to any one of Appendix B1 to B3, further comprising: an alternative condition generation process in which, if the second determination condition for determining the end of the process for determining the plan is not met by the at least one processor, an alternative condition with a higher degree of appropriateness than the configured condition is constructed by an AI model.

[0159] (Appendix B5) The information processing method according to any one of Appendices B1 to B4, wherein the predetermined conditions include a plurality of conditions that are not dependent on each other, and in the condition configuration process, the at least one processor constitutes each of the plurality of conditions.

[0160] (Appendix B6) The information processing method according to any one of Appendices B1 to B5, wherein in the condition configuration process, if the first determination condition for determining whether the configured condition matches the user instruction is not met, the processor configures the condition based on a new user instruction input in response to the presentation of a question about the condition.

[0161] (Note B7) The information processing method according to any one of Notes B1 to B6, wherein in the condition configuration process, if the first determination condition for determining whether the configured conditions match the user instructions is not met, the at least one processor configures the conditions by referring to the usage history of plans previously used by the user.

[0162] (Appendix B8) The information processing method according to any one of Appendix B1 to B7, wherein in the condition configuration process, the at least one processor generates justification information indicating the basis for configuring the condition, and in the presentation process, the at least one processor presents the condition together with the justification information to the user.

[0163] [Addendum C] This disclosure includes the technologies described in the following addendums. However, the present invention is not limited to the technologies described in the following addendums, and various modifications are possible within the scope of the claims.

[0164] (Appendix C1) A program for causing a computer to function as an information processing device, wherein the computer functions as: an acquisition means for acquiring user instructions input by a user to obtain an optimized plan; a condition configuration means for configuring predetermined conditions based on the user instructions; a plan determination means for determining the plan based on the conditions; and a presentation means for presenting the conditions and the plan to the user.

[0165] (Appendix C2) The information processing program described in Appendix C1, which further causes the computer to function as a data processing means that performs at least one of the following: (1) generating preprocessing information indicating preprocessing that can be performed on target data referenced by the plan determination means to determine the plan using a generation AI model, and performing preprocessing based on the generated preprocessing information; and (2) generating post-processing information indicating post-processing that can be performed on the determined plan using a generation AI model, and performing post-processing based on the generated post-processing information.

[0166] (Note C3) The plan determination means, if the first determination condition for determining whether the configured conditions match the user instruction is not met, generates countermeasure information indicating a countermeasure to obtain a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information, as described in Note C1 or C2.

[0167] (Appendix C4) An information processing program according to any one of Appendices C1 to C3, which further causes the computer to function as an alternative condition generation means that, if the second determination condition for determining the completion of the process for determining the plan is not met, generates alternative conditions using an AI model that have a higher degree of appropriateness than the configured conditions.

[0168] (Appendix C5) The predetermined conditions include a plurality of conditions that are not dependent on each other, and the condition configuration means constitutes each of the plurality of conditions, the information processing program described in any one of Appendices C1 to C4.

[0169] (Note C6) The condition-configuring means is an information processing program according to any one of Notes C1 to C5, which configures the conditions based on new user instructions input in response to the presentation of a question about the conditions if the first determination condition for determining whether the configured conditions match the user instructions is not met.

[0170] (Note C7) The condition-configuring means is an information processing program according to any one of Notes C1 to C6, which, if the first determination condition for determining whether the configured conditions match the user instructions is not met, configures the conditions by referring to the usage history of plans previously used by the user.

[0171] (Appendix C8) The information processing program according to any one of Appendices C1 to C7, wherein the condition setting means generates basis information indicating the basis for setting the condition, and the presentation means presents the condition together with the basis information to the user.

[0172] [Addendum D] This disclosure includes the technologies described in the following addendums. However, the present invention is not limited to the technologies described in the following addendums, and various modifications are possible within the scope of the claims.

[0173] (Appendix D1) An information processing device comprising at least one processor, the at least one processor performing: an acquisition process for acquiring user instructions input by a user to obtain an optimized plan; a condition configuration process for configuring predetermined conditions based on the user instructions; a plan determination process for determining the plan based on the conditions; and a presentation process for presenting the conditions and the plan to the user.

[0174] The information processing device may further include memory. The memory may also store a program for causing at least one processor to perform each of the aforementioned processes.

[0175] (Appendix D2) The information processing apparatus according to Appendix D1, wherein the at least one processor further performs data processing, which includes: (1) generating preprocessing information by a generating AI model that indicates preprocessing that can be performed on target data referenced by the plan determination process to determine the plan, and executing preprocessing based on the generated preprocessing information; and (2) generating post-processing information by a generating AI model that indicates post-processing that can be performed on the determined plan, and executing post-processing based on the generated post-processing information.

[0176] (Note D3) In the plan determination process, if the first determination condition for determining whether the configured conditions match the user instruction is not met, the information processing apparatus according to Note D1 or D2 generates countermeasure information indicating a countermeasure to obtain a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information.

[0177] (Appendix D4) The information processing apparatus according to any one of Appendix D1 to D3, wherein if the at least one processor does not satisfy the second determination condition for determining the end of the process for determining the plan, it further executes an alternative condition generation process which generates alternative conditions with a higher degree of appropriateness than the configured conditions using an AI model.

[0178] (Note D5) The information processing apparatus according to any one of Notes D1 to D4, wherein the predetermined conditions include a plurality of conditions that are not dependent on each other, and in the condition configuration process, the at least one processor constitutes each of the plurality of conditions.

[0179] (Note D6) In the condition configuration process, if the first determination condition for determining whether the configured condition matches the user instruction is not met, the information processing device according to any one of Notes D1 to D5, wherein the first determination condition for determining whether the configured condition matches the user instruction is not met, the condition is configured based on a new user instruction input in response to the presentation of a question about the condition.

[0180] (Note D7) In the condition configuration process, if the first determination condition for determining whether the configured conditions match the user instruction is not met, the information processing device according to any one of Notes D1 to D6, wherein the at least one processor configures the conditions by referring to the usage history of plans previously used by the user.

[0181] (Note D8) In the condition configuration process, the at least one processor generates justification information indicating the basis for the condition configuration, and in the presentation process, the at least one processor presents the condition to the user together with the justification information, as described in any one of Notes D1 to D7.

[0182] [Addendum E] This disclosure includes the technologies described in the following addendums. However, the present invention is not limited to the technologies described in the following addendums, and various modifications are possible within the scope of the claims.

[0183] (Appendix E1) A non-temporary recording medium on which a program for causing a computer to function as an information processing device is recorded, the program causing the computer to execute: an acquisition process for acquiring user instructions input by a user to obtain an optimized plan; a condition configuration process for configuring predetermined conditions based on the user instructions; a plan determination process for determining the plan based on the conditions; and a presentation process for presenting the conditions and the plan to the user.

[0184] Some or all of the elements (e.g., configuration and function) described as subscripts to subscript A1 may also be subordinate to subscripts B1, C1, D1, and E1 in a similar manner. Some or all of the elements described in any subscript may apply to various hardware, software, recording means, systems, and methods for recording software.

[0185] Although the present invention has been described above with reference to embodiments, the present invention is not limited thereto. Various modifications to the structure and details of the present invention can be made that are understandable to those skilled in the art within the scope of the invention.

[0186] This application claims priority based on Japanese Patent Application No. 2025-056852, filed on 28 March 2025, and incorporates all of its disclosures herein.

[0187] 1 Information Processing Device 1A, 1B Server 2 User Terminal 3 Target Data Storage Device 10A, 10B Information Processing System 11 Acquisition Unit 12 Condition Configuration Unit 13 Plan Decision Unit 14 Presentation Unit 15 Data Processing Unit 16 Alternative Condition Generation Unit 21 Dialogue Unit 110, 210 Control Unit 120, 220 Storage Unit 130, 230 Communication Unit 240 Input Unit 250 Display Unit C1 Processor C2 Memory

Claims

1. An information processing device comprising: acquisition means for acquiring user instructions input by a user to obtain an optimized plan; condition configuration means for configuring predetermined conditions based on the user instructions; plan determination means for determining the plan based on the conditions; and presentation means for presenting the conditions and the plan to the user.

2. The information processing apparatus according to claim 1, further comprising: (1) generating preprocessing information by a generating AI model that indicates preprocessing that can be performed on target data referenced by the plan determination means for determining the plan, and performing preprocessing based on the generated preprocessing information; and (2) generating post-processing information by a generating AI model that indicates post-processing that can be performed on the determined plan, and performing post-processing based on the generated post-processing information.

3. The information processing apparatus according to claim 1 or 2, wherein if the first determination condition for determining whether the configured conditions match the user instruction is not met, the plan determination means generates countermeasure information indicating a countermeasure to obtain a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information.

4. If a second determination condition for determining the completion of the process for determining the plan is not met, the information processing apparatus according to claim 1 or 2 further comprises: an alternative condition generation means for generating alternative conditions with a higher degree of appropriateness than the configured conditions using an AI model.

5. The information processing apparatus according to claim 1 or 2, wherein the predetermined conditions include a plurality of conditions that are not dependent on each other, and the condition configuring means constitutes each of the plurality of conditions.

6. The information processing apparatus according to claim 1 or 2, wherein the condition setting means sets the condition based on a new user instruction input in response to the presentation of a question about the condition, if the first determination condition for determining whether the set condition matches the user instruction is not met.

7. The information processing apparatus according to claim 1 or 2, wherein the condition-configuring means configures the conditions by referring to the usage history of plans previously used by the user if the first determination condition for determining whether the configured conditions match the user instructions is not met.

8. The information processing apparatus according to claim 1 or 2, wherein the condition setting means generates basis information indicating the basis for setting the condition, and the presentation means presents the condition together with the basis information to the user.

9. An information processing method comprising: an acquisition process in which at least one processor acquires user instructions input by a user to obtain an optimized plan; a condition configuration process in which the at least one processor configures predetermined conditions based on the user instructions; a plan determination process in which the at least one processor determines the plan based on the conditions; and a presentation process in which the at least one processor presents the conditions and the plan to the user.

10. The information processing method according to claim 9, further comprising data processing in which at least one processor performs at least one of the following: (1) generating preprocessing information by a generating AI model that indicates preprocessing that can be performed on target data referenced by the plan determination process to determine the plan, and executing preprocessing based on the generated preprocessing information; and (2) generating post-processing information by a generating AI model that indicates post-processing that can be performed on the determined plan, and executing post-processing based on the generated post-processing information.

11. The information processing method according to claim 9 or 10, wherein, in the plan determination process, if the first determination condition for determining whether the configured conditions match the user instruction is not met, the at least one processor generates countermeasure information indicating a countermeasure for obtaining a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information.

12. The information processing method according to claim 9 or 10, further comprising: if the at least one processor does not satisfy a second determination condition for determining the end of the process for determining the plan, an alternative condition generation process which generates alternative conditions with a higher degree of appropriateness than the configured conditions using an AI model for generating alternative conditions.

13. The information processing method according to claim 9 or 10, wherein the predetermined conditions include a plurality of conditions that are not dependent on each other, and in the condition configuration process, the at least one processor constitutes each of the plurality of conditions.

14. The information processing method according to claim 9 or 10, wherein, in the condition configuration process, if the first determination condition for determining whether the configured condition matches the user instruction is not met, the at least one processor configures the condition based on a new user instruction input in response to the presentation of a question statement regarding the condition.

15. The information processing method according to claim 9 or 10, wherein, in the condition configuration process, if the first determination condition for determining whether the configured condition matches the user instruction is not met, the at least one processor configures the condition by referring to the usage history of plans previously used by the user.

16. The information processing method according to claim 9 or 10, wherein in the condition configuration process, the at least one processor generates justification information indicating the basis for configuring the condition, and in the presentation process, the at least one processor presents the condition together with the justification information to the user.

17. A program for causing a computer to function as an information processing device, wherein the computer functions as: an acquisition means for acquiring user instructions input by a user to obtain an optimized plan; a condition configuration means for configuring predetermined conditions based on the user instructions; a plan determination means for determining the plan based on the conditions; and a presentation means for presenting the conditions and the plan to the user.

18. The information processing program according to claim 17, wherein the computer is further configured to function as a data processing means that performs at least one of the following: (1) generating preprocessing information by a generation AI model that indicates preprocessing that can be performed on target data referenced by the plan determination means to determine the plan, and executing preprocessing based on the generated preprocessing information; and (2) generating post-processing information by a generation AI model that indicates post-processing that can be performed on the determined plan, and executing post-processing based on the generated post-processing information.

19. The information processing program according to claim 17 or 18, wherein the plan determination means, if the first determination condition for determining whether the configured conditions match the user instruction is not met, generates countermeasure information indicating a countermeasure to obtain a plan corresponding to the user instruction using a generating AI model, and determines the plan by executing the countermeasure indicated by the countermeasure information.

20. The information processing program according to claim 17 or 18, wherein the computer is further configured to function as an alternative condition generation means that, if a second determination condition for determining the completion of the process for determining the plan is not met, generates alternative conditions using an AI model that have a higher degree of appropriateness than the configured conditions.

Images