Information processing device and information processing method

Abstract

To be able to evaluate the content of event planning. [Solution] The information processing device 1 has a first acquisition unit 131 that acquires planning information including information about the location of the event, and a generation unit 132 that generates a prompt that prompts the user to propose a venue layout for the event location indicated by the planning information based on evaluation axes received from the user, and the large-scale language model 2 is a large-scale language model that is configured to be able to refer to performance information of past events that includes the venue layout and people flow information indicating the flow of people at the venue of a past event that was held in the past, and evaluation results of the past event based on one or more evaluation axes, or a large-scale language model that has learned the performance information and the evaluation results as training data, and has a second acquisition unit 133 that inputs a prompt to the large-scale language model 2 and acquires information indicating the venue layout from the large-scale language model 2, and an output unit 134 that outputs the information indicating the layout.

Description

[Technical Field]

[0001] The present invention relates to an information processing device and an information processing method. [Background technology]

[0002] Conventionally, there are known techniques for supporting event planners. For example, Patent Document 1 discloses a device for evaluating whether a target facility is suitable for holding an event. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7504276 Summary of the Invention [Problem to be solved by the invention]

[0004] Event planners need to consider not only the selection of a facility to hold the event, but also the content of the event plan. However, conventional technologies have had the problem of being unable to evaluate the content of the event plan.

[0005] The present invention has been made in consideration of these points, and aims to make it possible to evaluate the contents of an event plan. [Means for solving the problem]

[0006] An information processing device according to a first aspect of the present invention comprises a first acquisition unit that acquires planning information for an event, including information regarding the location of the event; and a generation unit that generates a prompt that causes a large-scale language model to propose a venue layout for the event location indicated by the planning information, based on evaluation axes received from a user, for evaluating the event. The large-scale language model is a large-scale language model that is configured to be able to refer to performance information of past events, including people flow information indicating the venue layout and people flow at the location of a past event that was held in the past, and evaluation results of the past event based on one or more evaluation axes, or a large-scale language model that has been trained using the performance information and the evaluation results as training data. The information processing device comprises: a first acquisition unit that inputs the prompt into the large-scale language model and acquires information indicating the venue layout from the large-scale language model corresponding to the evaluation axes received from the user; and an output unit that outputs the information indicating the layout.

[0007] The generation unit may generate a prompt that proposes multiple venue layouts at the location where the event is to be held, the second acquisition unit may input the prompt into the large-scale language model to acquire multiple pieces of information indicating the venue layouts, and the output unit may output information indicating the multiple layouts.

[0008] The generation unit may generate the prompt to suggest examples of booth setups at the venue where the event is held as a layout of the venue at the venue where the event is held, the second acquisition unit may input the prompt to the large-scale language model and acquire information indicating examples of booth setups as information indicating the layout of the venue, and the output unit may output the information indicating the examples of booth setups.

[0009] The generation unit may generate the prompt that anticipates the flow of people at the location where the event is being held, the second acquisition unit may input the prompt into the large-scale language model to acquire information indicating the expected flow of people at the location where the event is being held, and the output unit may output the information indicating the flow of people.

[0010]

[0011]

[0012]

[0013]

[0014]

[0015]

[0016]

[0017] An information processing method according to a second aspect of the present invention includes the steps of: acquiring event planning information, including information about the location of the event, executed by a computer; and generating a prompt that causes a large-scale language model to propose a venue layout for the event location indicated by the planning information based on evaluation axes received from a user for evaluating the event, wherein the large-scale language model is a large-scale language model configured to be able to refer to performance information of past events, including people flow information indicating the venue layout and people flow at the location of a past event that was held in the past, and evaluation results of the past event based on one or more evaluation axes, or a large-scale language model that has been trained using the performance information and the evaluation results as training data, and includes the steps of inputting the prompt into the large-scale language model, acquiring information from the large-scale language model indicating the layout of the venue corresponding to the evaluation axes received from the user, and outputting the information indicating the layout. [Effects of the Invention]

[0018] According to the present invention, it is possible to provide an effect that it is possible to evaluate the contents of an event plan. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a diagram illustrating an overview of an information processing device. [Figure 2]FIG. 2 is a diagram illustrating a functional configuration of an information processing device. [Figure 3] FIG. 10 is a diagram illustrating an example of a prompt. [Figure 4] FIG. 10 is a diagram showing an example of evaluation information displayed on a user terminal. [Figure 5] FIG. 1 is a sequence diagram showing the flow of processing in an information processing device, a large-scale language model, and a user terminal. [Figure 6] FIG. 10 is a diagram showing an example of a map displayed on a user terminal, showing examples of booths and people flow at an event venue. DETAILED DESCRIPTION OF THE INVENTION

[0020] [Overview of information processing device 1] 1 is a diagram showing an overview of an information processing device 1. The information processing device 1 is communicably connected to a large-scale language model (LLM) 2 and a user terminal 3 used by a user who is a planner who plans and designs an event, and is a computer for supporting the user in planning and designing an event.

[0021] The large-scale language model 2 is, for example, a generative AI (Artificial Intelligence) such as ChatGPT (registered trademark) or Claude (registered trademark), and outputs an answer corresponding to the instruction indicated by the prompt in response to receiving a prompt as instruction information. The user terminal 3 is, for example, a computer such as a personal computer or a tablet.

[0022] The information processing device 1 acquires from a user plan information indicating the details of an event plan ((1) in FIG. 1). In response to acquiring the plan information, the information processing device 1 generates a prompt to have the large-scale language model 2 evaluate the event indicated by the plan information based on one or more evaluation axes for evaluating the event ((2) in FIG. 1).

[0023] The information processing device 1 inputs the generated prompt to the large-scale language model 2 ((3) in FIG. 1), and acquires evaluation information indicating the evaluation results of the event indicated by the project information, generated by the large-scale language model 2 ((4) in FIG. 1). In response to acquiring the evaluation information, the information processing device 1 outputs the acquired evaluation information to the user terminal 3 ((5) in FIG. 1).

[0024] Here, the large-scale language model 2 is a model that incorporates, for example, a search expansion and generation (RAG) function and is configured to be able to refer to past event result information that indicates the details of past events that were held in the past, the results of the past events, and evaluation results based on one or more evaluation axes for the past events. This allows the large-scale language model 2 to appropriately evaluate the plan details indicated by the plan information based on the results of the past events and the evaluation results.

[0025] In this way, a user of the user terminal 3 can obtain an evaluation result for the event indicated by the plan information by inputting plan information indicating the plan content of an event that the user has planned and designed into the information processing device 1. This allows the user to check the evaluation result and evaluate the plan content. Therefore, the information processing device 1 can enable the user to evaluate the plan content of the event.

[0026] [Functional configuration of information processing device 1] Next, a description will be given of the functional configuration of the information processing device 1. Fig. 2 is a diagram showing the functional configuration of the information processing device 1. The information processing device 1 has a communication unit 11, a storage unit 12, and a control unit 13.

[0027] The communication unit 11 is a communication interface for transmitting and receiving data to and from the large-scale language model 2, the user terminal 3, etc. via a communication network such as a mobile phone line or the Internet. The storage unit 12 is a storage medium that stores various types of data, and includes a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk, an SSD (Solid State Drive), etc. The storage unit 12 stores a program executed by the control unit 13. For example, the storage unit 12 stores a program that causes the control unit 13 to function as a first acquisition unit 131, a generation unit 132, a second acquisition unit 133, and an output unit 134.

[0028] The control unit 13 is, for example, a CPU (Central Processing Unit). The control unit 13 executes a program stored in the storage unit 12, thereby functioning as a first acquisition unit 131, a generation unit 132, a second acquisition unit 133, and an output unit 134.

[0029] The first acquisition unit 131 acquires plan information indicating the planned content of an event. For example, in response to receiving a request to acquire an analysis page from the user terminal 3, the first acquisition unit 131 transmits the analysis page to the user terminal 3 and displays the analysis page on the user terminal 3. The first acquisition unit 131 then accepts the plan information from the user terminal 3. The first acquisition unit 131 acquires, via the analysis page, information indicating the planned content of the event, such as the date and time of the event, the venue, the type, scale, purpose, target demographic, advertising media, advertising frequency, and the quality of the services to be provided, from the user terminal 3. The first acquisition unit 131 may acquire, from the user terminal 3, a file containing multiple pieces of information indicating the planned content of the event, such as an overview document including at least one of text information and images indicating the planned content of the event, and analyze the file to acquire the plan information of the event.

[0030] The generation unit 132 generates a prompt to have the large-scale language model 2 evaluate the event indicated by the planning information acquired by the first acquisition unit 131 based on one or more evaluation axes for evaluating the event. Here, the one or more evaluation axes are predetermined, such as economic effect, ability to attract customers, uniqueness, suitability for the target, suitability of the timing of the event, and geographical suitability. In addition to the above, the evaluation axes may also include cooperation with exhibitors and sponsors and social significance. Furthermore, the one or more evaluation axes are considered to be predetermined, but are not limited thereto. Before generating the prompt, the generation unit 132 may accept the setting of one or more evaluation axes from the user terminal 3, or may present one or more evaluation axes to the user terminal 3 and accept the selection of the evaluation axis to be evaluated or the editing of the evaluation axes.

[0031] The generation unit 132 generates a prompt that includes the project information acquired by the first acquisition unit 131 and generates evaluation information that indicates an evaluation corresponding to each of one or more evaluation axes of the project information and an overall evaluation of the project information based on the evaluation of each of the one or more evaluation axes.

[0032] Fig. 3 is a diagram showing an example of a prompt generated by the generation unit 132. As shown in Fig. 3, it can be seen that the prompt includes the content of the event indicated by the project information, multiple evaluation axes, and an instruction to evaluate the event along the multiple evaluation axes and comprehensively. Also, Fig. 3 shows that the large-scale language model 2 includes an instruction to indicate the evaluation along each of the multiple evaluation axes by a score.

[0033] The generation unit 132 may generate a prompt that clearly indicates external factors to be taken into consideration when evaluating an event for the large-scale language model 2. For example, when evaluating an event for the large-scale language model 2, the generation unit 132 may generate a prompt that indicates that the event should be evaluated taking into consideration weather information corresponding to the date on which the event is held or the expected congestion of public transportation on the date on which the event is held. The generation unit 132 may also receive information indicating external factors to be taken into consideration when evaluating an event from the user terminal 3, and generate a prompt that instructs the user to evaluate the event taking into consideration the received external factors. In this way, the information processing device 1 can cause the large-scale language model 2 to evaluate the event while reliably taking into consideration the clearly indicated external factors.

[0034] Furthermore, depending on the project information acquired by the first acquisition unit 131, there may be evaluation axes along which an event cannot be evaluated. For this reason, the generation unit 132 may cause the large-scale language model 2 to identify one or more evaluation axes to be evaluated based on the project information acquired by the first acquisition unit 131, and may generate a prompt that causes the large-scale language model 2 to evaluate the event indicated by the project information based on the evaluation axes. For example, the generation unit 132 may cause the large-scale language model 2 to identify one or more evaluation axes along which an event can be evaluated based on the project content indicated by the project information, and may generate a prompt that causes the event indicated by the project information to be evaluated based on the identified evaluation axes.

[0035] Furthermore, the generation unit 132 may generate a prompt that causes a relatively important evaluation axis among one or more evaluation axes to be identified based on the project information acquired by the first acquisition unit 131, and causes the user to evaluate the event indicated by the project information based on the identified evaluation axis. For example, when the first acquisition unit 131 acquires an outline document or the like that indicates the planned content of an event as project information, the generation unit 132 may extract characteristics of the event based on an explanatory text of the event or a schematic diagram of the event included in the outline document, and generate a prompt that causes a relatively important evaluation axis of the event to be identified based on the characteristics.

[0036] Furthermore, the generation unit 132 may generate a prompt that causes a determination as to whether it is appropriate to hold an event based on an evaluation result of the event indicated by the plan information acquired by the first acquisition unit 131, and generates evaluation information that includes the evaluation result and a comment indicating whether it is appropriate to hold the event. In this way, the information processing device 1 can provide the user of the user terminal 3 with information to help them decide whether to hold the event.

[0037] Furthermore, the generation unit 132 may identify an evaluation to be improved among the evaluations on one or more evaluation axes based on the evaluation result of the event indicated by the planning information acquired by the first acquisition unit 131, and may generate a prompt to generate a change proposal for the event planning content to improve the identified evaluation. In this case, for example, the generation unit 132 generates a prompt to identify an evaluation axis with a relatively low evaluation among one or more evaluation axes as an evaluation to be improved based on the evaluation result of the event indicated by the planning information acquired by the first acquisition unit 131.

[0038] Here, the generation unit 132 may generate a prompt to identify an evaluation corresponding to an evaluation axis with a relatively high influence on the overall evaluation as an evaluation that needs to be improved, on the condition that the evaluation corresponding to the evaluation axis with a relatively high influence on the overall evaluation is less than a predetermined score. In this way, the information processing device 1 can prompt the user of the user terminal 3 to consider ways to improve the content of the event plan.

[0039] Furthermore, the generation unit 132 may generate a prompt that specifies, as an evaluation axis that has a high evaluation in a past event with a relatively good performance content among past events similar to the event indicated by the project information acquired by the first acquisition unit 131, as an evaluation axis that has a high influence on the overall evaluation. In this case, the generation unit 132 includes in the prompt an instruction statement that specifies, as an evaluation axis that has a high influence on the overall evaluation, a past event with a relatively good performance content among past events similar to the event indicated by the project information acquired by the first acquisition unit 131, evaluates the specified past event on multiple evaluation axes, and specifies the evaluation axis with a relatively high evaluation as an evaluation axis that has a high influence on the overall evaluation.

[0040] In addition, the generation unit 132 may generate a prompt that causes the large-scale language model 2 to evaluate the event indicated by the project information and other events, and generates a comparison result between the evaluation result of the event and the evaluation result of the other events.

[0041] In this case, the first acquisition unit 131 acquires other event information indicating the planned content of another event that is different from the event indicated by the plan information and is scheduled to be held within a predetermined range from the location of the event and within a predetermined period from the scheduled date of the event. For example, the first acquisition unit 131 may acquire the other event information from the user terminal 3, or may acquire the other event information by accessing a webpage that provides event information for the other event.

[0042] The generation unit 132 then generates a prompt that includes the plan information acquired by the first acquisition unit 131 and the other event information acquired by the first acquisition unit 131, causes the user to evaluate the event indicated by the plan information and the other events indicated by the other event information, and generates a comparison result between the evaluation result of the event and the evaluation result of the other events. In this way, the information processing device 1 causes the user of the user terminal 3 to compare the evaluation results of the event planned by the user with other events that may compete with the event, and allows the user to consider the merits of the plan content.

[0043] Furthermore, if there is an event component not included in the project information, the generation unit 132 may generate a prompt to suggest the content of the component that would cause the event to exceed a predetermined standard if the component were included in the event. In this case, the generation unit 132 may generate a prompt including an instruction to create the content of the event component not included in the project information based on the project content of the event included in the project information. For example, if the project content of the event included in the project information includes the location or time of the event, the generation unit 132 may generate a prompt including an instruction to create the content of the event component that will give the event an advantage over other events that correspond to the location or time. In this way, the information processing device 1 can support the user of the user terminal 3 in considering the event component not included in the project information.

[0044] The second acquisition unit 133 inputs the prompt generated by the generation unit 132 into the large-scale language model 2, and acquires evaluation information indicating the evaluation results of the event indicated by the planning information acquired by the first acquisition unit 131 from the large-scale language model 2.

[0045] The output unit 134 outputs the evaluation information acquired by the second acquisition unit 133 from the large-scale language model 2 to the user terminal 3. Fig. 4 is a diagram showing an example of evaluation information displayed on the user terminal 3. As shown in Fig. 4, for the content of the event indicated by the plan information acquired by the first acquisition unit 131, a score and evaluation comments are displayed as evaluation information of the event corresponding to each of one or more evaluation axes, and it can be seen that an overall evaluation based on one or more evaluation axes is also displayed.

[0046] [Processing flow in information processing device 1] Next, a description will be given of the flow of processing in the information processing device 1. Fig. 5 is a sequence diagram showing the flow of processing in the information processing device 1, the large-scale language model 2, and the user terminal 3.

[0047] For example, in response to receiving a request to acquire an analysis page from the user terminal 3, the first acquisition unit 131 transmits the analysis page to the user terminal 3 (S1, S2) and displays the analysis page on the user terminal 3. Then, the first acquisition unit 131 acquires project information from the user terminal 3 via the analysis page (S3).

[0048] Next, the generation unit 132 generates a prompt that causes the large-scale language model 2 to evaluate the event indicated by the acquired project information based on one or more evaluation axes (S4). The second acquisition unit 133 inputs the generated prompt to the large-scale language model 2 (S5) and acquires the evaluation information generated by the large-scale language model 2 (S6). The output unit 134 transmits the acquired evaluation information to the user terminal 3 (S7) to display the evaluation information on the analysis page.

[0049] [Variation 1] In the above-described embodiment, the large-scale language model 2 is, for example, a model that incorporates a search expansion and generation function and is configured to be able to refer to performance information indicating the performance details of past events and evaluation results of past events based on one or more evaluation axes, but this is not limited to this.

[0050] The large-scale language model 2 may be a model that has been trained in advance using performance information indicating the performance details of past events, which are events that have been held in the past, and evaluation results of the past events based on one or more evaluation axes as training data.

[0051] By doing this, the information processing device 1 can evaluate the planned content of the event indicated by the planned information acquired by the first acquisition unit 131, in the same way as when using a large-scale language model 2 that is configured to be able to refer to performance information indicating the actual performance content of past events and evaluation results of past events based on one or more evaluation axes using the RAG function.

[0052] [Variation 2] In the above-described embodiment, the large-scale language model 2 evaluates the event indicated by the plan information, but this is not limiting and the large-scale language model 2 may also propose the layout of the event venue for the event indicated by the plan information. In this case, the large-scale language model 2 may be a large-scale language model configured to be able to refer to performance information indicating performance details including the layout of booths and the like set up at past event venues and the flow of people at the venues and surrounding areas, or a large-scale language model trained using the performance information as training data.

[0053] The first acquisition unit 131 may acquire planning information indicating a map of the location where the event will be held, and the generation unit 132 may generate a prompt that causes the large-scale language model 2 to propose a layout for the event at the location where the event will be held, which layout will result in a high evaluation of the event. In this case, the generation unit 132 may receive from the user terminal 3 a selection of an evaluation axis for which the evaluation content is to be improved, out of one or more evaluation axes, and generate a prompt that causes the user terminal 3 to propose a layout that will result in a high evaluation corresponding to the received evaluation axis.

[0054] For example, when the generation unit 132 receives a selection of customer attraction as an evaluation axis for which the user wants to improve the evaluation content from the user terminal 3, the generation unit 132 generates a prompt to suggest a layout that will have a high evaluation corresponding to customer attraction. Furthermore, the generation unit 132 may generate a prompt to instruct the map of the event venue included in the planning information to show examples of booths or the like that will have a high evaluation and the expected flow of people around those examples of installation.

[0055] Fig. 6 is a diagram showing an example of a map displayed on a user terminal 3, showing examples of booth installations and people flow at an event venue. Two examples of booth installations are shown in Fig. 6, and it can be seen that arrows indicating people flow are displayed corresponding to each installation example. By checking the examples of booth installations and people flow, the user of the user terminal 3 can consider the official layout of the event venue.

[0056] [Effects of this embodiment] As described above, the information processing device 1 acquires planning information indicating the planned content of an event, generates a prompt to have the large-scale language model 2 evaluate the event indicated by the planning information based on one or more evaluation axes for evaluating the event, the large-scale language model 2 being configured to be able to refer to performance information indicating the performance content of past events and evaluation results of past events based on one or more evaluation axes, or a large-scale language model that has learned the performance information and the evaluation results as training data, and inputs the prompt into the large-scale language model 2, and outputs evaluation information indicating the evaluation results of the event acquired from the large-scale language model 2. In this way, the information processing device 1 can evaluate events from various perspectives.

[0057] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations' Sustainable Development Goals (SDGs), which is "Build resilient infrastructure, promote inclusive and sustainable industrialization, and promote innovation and resilience."

[0058] The present invention has been described above using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by functionally or physically distributing or integrating any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combination also have the effects of the original embodiments. [Explanation of symbols]

[0059] 1. Information processing equipment 2 Large-scale language models 3. User terminal 11 Communications Department 12 Storage section 13 Control Unit 131 First acquisition part 132 Generation part 133 Second Acquisition Department 134 Output section

Claims

1. a first acquisition unit that acquires event planning information including information about a venue for the event; a generation unit that generates a prompt for causing a large-scale language model to propose a venue layout for the event location indicated by the planning information based on an evaluation axis received from a user for evaluating the event, the large-scale language model is a large-scale language model configured to be able to refer to performance information of past events, which are events held in the past, including people flow information indicating the layout of the venue and the flow of people at the venue of the past event, and evaluation results of the past event based on one or more evaluation axes, or a large-scale language model trained using the performance information and the evaluation results as training data; a second acquisition unit that inputs the prompt into the large-scale language model and acquires, from the large-scale language model, information indicating a layout of the venue corresponding to the evaluation axis received from the user; an output unit that outputs information indicating the layout, Information processing device.

2. the generation unit generates a prompt that allows the user to propose multiple venue layouts for the event location; the second acquisition unit inputs the prompt into the large-scale language model to acquire a plurality of pieces of information indicating the layout of the venue; the output unit outputs information indicating the plurality of layouts. The information processing device according to claim 1 .

3. the generation unit generates the prompt to suggest an example of booth installation at the venue of the event as a layout of a venue at the venue of the event; the second acquisition unit inputs the prompt into the large-scale language model and acquires information indicating an example of booth installation as information indicating the layout of the venue; the output unit outputs information indicating an example of installation of the booth. The information processing device according to claim 1 .

4. the generation unit generates the prompt by imagining a flow of people at a venue where the event is held; the second acquisition unit inputs the prompt into the large-scale language model to acquire information indicating an expected flow of people at a location where the event is to be held; The output unit outputs information indicating the people flow. The information processing device according to claim 1 .

5. The computer executes obtaining planning information for the event, including information regarding the location of the event; generating a prompt for prompting a large-scale language model to propose a venue layout for the event location indicated by the planning information based on evaluation criteria received from the user for evaluating the event; the large-scale language model is a large-scale language model configured to be able to refer to performance information of past events, which are events held in the past, including people flow information indicating the layout of the venue and the flow of people at the venue of the past event, and evaluation results of the past event based on one or more evaluation axes, or a large-scale language model trained using the performance information and the evaluation results as training data; inputting the prompt into the large-scale language model and obtaining, from the large-scale language model, information indicating the layout of the venue corresponding to the evaluation axis received from the user; and outputting information indicating the layout. Information processing methods.

Images