Method and system for society simulation by generative agent-based modeling

Abstract

A social simulation method and system through generative agent-based modeling are disclosed. A social simulation method according to one embodiment may include the steps of: providing a user interface to a user that includes a setting function for an environment and an agent for social simulation; executing a social simulation using generative agent-based modeling (GABM) based on the environment and agent set through the user interface; and providing the execution result of the social simulation to the user through the user interface.

Description

Technology Field

[0001] The following description concerns a social simulation method and system through generative agent-based modeling. Background Technology

[0002] Predicting individual behavior is very difficult, and predicting the reactions of groups of people is even more challenging. However, humans are inherently social animals, and their behavior influences one another. If it were possible to effectively predict public reactions to specific events, methods of information dissemination, and interaction behaviors, it could be of great help in various fields, such as supporting corporate decision-making, forecasting and optimizing marketing campaigns, and planning election activities.

[0003] [Prior Art No.]

[0004] Korean Registered Patent No. 10-1889655 The problem to be solved

[0005] We provide a social simulation method and system through generative agent-based modeling. means of solving the problem

[0006] A social simulation method of a social simulation system implemented by at least one computer device, wherein the at least one computer device includes at least one processor, and the social simulation method comprises: a step of providing a user interface to a user that includes a setting function for an environment and an agent for social simulation by the at least one processor; a step of executing a social simulation by the at least one processor using Generative Agent-Based Modeling (GABM) based on the environment and agent set through the user interface; and a step of providing the execution result of the social simulation to the user through the user interface by the at least one processor.

[0007] According to one aspect, the step of providing the user interface to a user may be characterized by comprising: receiving data including an explanation of the social simulation through the user interface; analyzing the received data through a Large Language Model to generate configuration data for at least one of the environment and the agent; and recommending the configuration data through the user interface.

[0008] According to another aspect, the environment set above includes text-based data describing the environment of the social simulation, and the step of executing the social simulation may be characterized by including the step of implementing a virtual space of the social simulation using the text-based data describing the environment of the social simulation.

[0009] According to another aspect, the agent is implemented to interact with other agents in the set environment according to conversations and behaviors generated based on a large language model as an individual entity having unique attributes placed in the set environment, and the step of executing the social simulation may be characterized by including the step of observing and recording the manner of interaction between agents placed in the set environment.

[0010] According to another aspect, the unique attribute may be characterized by being set based on data input or selected by the user through the user interface.

[0011] According to another aspect, the social simulation method may further include the step of generating at least one agent having preset basic attributes by the at least one processor; and the step of presenting the generated at least one agent to the user through the user interface.

[0012] According to another aspect, the step of executing the social simulation may be characterized by including the step of setting unique attributes of each of the at least one agent by reflecting data input or selected by the user for the at least one agent through the user interface to the basic attributes of the at least one agent.

[0013] According to another aspect, the user interface further includes a function for receiving data to control the process of the social simulation, and the step of executing the social simulation may be characterized by executing the social simulation using the data to control the process of the social simulation further.

[0014] According to another aspect, the step of providing the execution results of the social simulation may be characterized by including the step of displaying, through the user interface, at least one of information regarding whether a simulation goal has been achieved for each iteration of the social simulation, information regarding the process of achieving the simulation goal if the simulation goal has been achieved, and information explaining the possible reasons if the simulation goal has not been achieved.

[0015] According to another aspect, the information regarding the process of achieving the simulation goal may be characterized by including information regarding the process of interaction between agents deployed in the set environment.

[0016] According to another aspect, the step of providing the execution results of the social simulation may be characterized by including the step of providing information on the ratio of agents classified into pre-set items for the social simulation.

[0017] According to another aspect, the step of executing the social simulation may be characterized by repeating the social simulation as many times as the number of social simulations set through the user interface, and the step of providing the execution results of the social simulation may be characterized by providing the results for each iteration of the social simulation and the overall conclusion of the repeated social simulations, respectively.

[0018] According to another aspect, the social simulation method may further include the step of providing a function for a conversation between the agent and the user through the user interface by the at least one processor.

[0019] According to another aspect, the step of providing a function for the conversation may be characterized by providing the function for the conversation in conjunction with an area in the user interface where the social simulation execution result is displayed, so that the user can converse with the agent by referring to the social simulation execution result.

[0020] A computer program stored on a computer-readable recording medium is provided to be combined with a computer device to execute the above method on the computer device.

[0021] A computer-readable recording medium is provided on which a computer program for executing the above method is recorded on a computer device.

[0022] A social simulation system implemented by at least one computer device, wherein the at least one computer device includes at least one processor, and the at least one processor provides a user interface to a user that includes a setting function for an environment and an agent for social simulation, executes a social simulation using Generative Agent-Based Modeling (GABM) based on the environment and agent set through the user interface, and provides the execution result of the social simulation to the user through the user interface. Effects of the invention

[0023] It is possible to provide a social simulation method and system through generative agent-based modeling. Brief explanation of the drawing

[0024] FIG. 1 is a drawing illustrating an example of a network environment according to an embodiment of the present invention. FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. FIG. 3 is a diagram illustrating an example of a general view of a social simulation system in one embodiment of the present invention. FIG. 4 is a diagram illustrating an example of a user interface for inputting or selecting data for setting up a social simulation in an embodiment of the present invention. FIG. 5 is a diagram illustrating an example of a user interface for editing input or selected data for setting up a social simulation in one embodiment of the present invention. FIG. 6 is a diagram illustrating an example of a user interface that provides information about an agent in one embodiment of the present invention. FIG. 7 is a diagram illustrating an example of a user interface that provides the execution results of a social simulation in one embodiment of the present invention. FIG. 8 is a drawing illustrating an example of a user interface for displaying the conclusion of a simulation in one embodiment of the present invention. FIG. 9 is a flowchart illustrating an example of a social simulation method in one embodiment of the present invention. Specific details for implementing the invention

[0025] Hereinafter, embodiments will be described in detail with reference to the attached drawings.

[0026] A social simulation system according to embodiments of the present invention may be implemented by at least one computer device. In this case, a computer program according to an embodiment of the present invention may be installed and run on at least one computer device, and at least one computer device may perform a social simulation method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium to be combined with at least one computer device and to execute a social simulation method on at least one computer device.

[0027] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment of FIG. 1 illustrates an example including a plurality of electronic devices (110, 120, 130, 140), a plurality of servers (150, 160), and a network (170). FIG. 1 is an example for explaining the invention, and the number of electronic devices or servers is not limited to that shown in FIG. 1. Furthermore, the network environment of FIG. 1 is merely an example of one of the environments applicable to the present embodiments, and the environments applicable to the present embodiments are not limited to the network environment of FIG. 1.

[0028] Multiple electronic devices (110, 120, 130, 140) may be fixed terminals or mobile terminals implemented as computer devices. Examples of multiple electronic devices (110, 120, 130, 140) include smartphones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, etc. For example, FIG. 1 shows the shape of a smartphone as an example of an electronic device (110), but in embodiments of the present invention, the electronic device (110) may substantially refer to one of various physical computer devices capable of communicating with other electronic devices (120, 130, 140) and / or servers (150, 160) via a network (170) using a wireless or wired communication method.

[0029] The communication method is not limited and may include not only communication methods utilizing communication networks (e.g., mobile communication networks, wired internet, wireless internet, broadcasting networks) that the network (170) may include, but also short-range wireless communication between devices. For example, the network (170) may include any one or more networks such as a PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Additionally, the network (170) may include any one or more network topologies such as a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, but is not limited thereto.

[0030] Each of the servers (150, 160) may be implemented as a computer device or multiple computer devices that communicate with multiple electronic devices (110, 120, 130, 140) through a network (170) to provide commands, code, files, content, services, etc. For example, the server (150) may be a system that provides services to multiple electronic devices (110, 120, 130, 140) connected through the network (170).

[0031] FIG. 2 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. Each of the plurality of electronic devices (110, 120, 130, 140) or servers (150, 160) described above can be implemented by the computer device (200) illustrated in FIG. 2.

[0032] As illustrated in FIG. 2, such a computer device (200) may include memory (210), a processor (220), a communication interface (230), and an input / output interface (240). The memory (210) is a computer-readable recording medium and may include a non-perishable mass storage device such as RAM (random access memory), ROM (read only memory), and a disk drive. Here, a non-perishable mass storage device such as a ROM and a disk drive may be included in the computer device (200) as a separate permanent storage device distinct from the memory (210). Additionally, an operating system and at least one program code may be stored in the memory (210). These software components may be loaded into the memory (210) from a computer-readable recording medium separate from the memory (210). This separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. In another embodiment, software components may be loaded into memory (210) via a communication interface (230) rather than a computer-readable recording medium. For example, software components may be loaded into memory (210) of a computer device (200) based on a computer program installed by files received through a network (170).

[0033] The processor (220) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (220) via memory (210) or a communication interface (230). For example, the processor (220) may be configured to execute instructions received according to program code stored in a recording device such as memory (210).

[0034] The communication interface (230) may provide a function for the computer device (200) to communicate with other devices (e.g., storage devices described above) through the network (170). For example, requests, commands, data, files, etc. generated by the processor (220) of the computer device (200) according to program code stored in a recording device such as memory (210) may be transmitted to other devices through the network (170) under the control of the communication interface (230). Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device (200) through the communication interface (230) of the computer device (200) via the network (170). Signals, commands, data, etc. received through the communication interface (230) may be transmitted to the processor (220) or memory (210), and files, etc. may be stored in a storage medium (the permanent storage device described above) that the computer device (200) may further include.

[0035] The input / output interface (240) may be a means for interfacing with an input / output device (250). For example, the input device may include a device such as a microphone, keyboard, or mouse, and the output device may include a device such as a display or speaker. As another example, the input / output interface (240) may be a means for interfacing with a device in which the functions for input and output are integrated into one, such as a touchscreen. At least one of the input / output devices (250) may be configured as a single device with the computer device (200). For example, it may be implemented in a form in which a touchscreen, microphone, speaker, etc., are included in the computer device (200), such as in a smartphone.

[0036] Additionally, in other embodiments, the computer device (200) may include fewer or more components than the components of FIG. 2. However, it is not necessary to clearly illustrate most of the prior art components. For example, the computer device (200) may be implemented to include at least some of the input / output devices (250) described above, or may include other components such as a transceiver, a database, etc.

[0037] FIG. 3 is a diagram illustrating an example of a general view of a social simulation system in an embodiment of the present invention. It is almost impossible to achieve to conduct social experiments and observe the results in actual human society because it is extremely costly and time-consuming. Accordingly, the social simulation system (300) according to the present embodiment can simulate the reaction of a crowd facing a specific event by constructing an interaction mechanism between several intelligent agents based on a Large Language Model (LLM) and Generative Agent-Based Modeling (GABM). In addition, the social simulation system (300) can perform repetitive experiments and observations through environmental settings using this simulation.

[0038] GABM is a powerful tool used to understand and simulate complex systems, enabling the modeling of social systems centered around individual agents (i.e., entities acting independently). Each agent can possess unique attributes, behavioral rules, and decision-making processes, allowing for the study of dynamic changes within the entire system. For example, GABM can be utilized in the social sciences to simulate social interactions, network formation, and collective behavior; in economics to model market trends, consumer behavior, and corporate competition; in environmental sciences to study ecosystem interactions, climate change, and resource management; or in the medical field to model infectious disease spread and medical resource allocation. As components, GABM can include elements such as agents, environments, rules, and interactions. Agents are individual entities that may possess unique attributes (e.g., age, gender, location), while the environment is a virtual space where agents interact; this space can be a virtual physical space or a network structure. Rules are regulations that determine how agents behave; for instance, an infection spread model might include the probability of infection and propagation rules. Interaction refers to interactions between agents, and such interactions can lead to dynamic changes in social systems. For example, interactions may include transactions occurring between buyers and sellers in a marketing model. This GABM is useful for policy decision-making and strategy formulation because it allows for the understanding of the behavior of complex systems through simple rules of individual agents, enables the model to be expanded by easily adding new agents and rules, and allows for simulations that reflect real-world situations.

[0039] In addition, LLMs, such as models like GPT-3, GPT-4, or GPT-5, can generate agent behaviors or conversations through natural language processing. This allows agents to perform situation-appropriate behaviors more naturally and human-like. The social simulation system (300) can generate conversations or behaviors of each agent through LLMs and, based on this, control agents to interact with each other in a GABM-based social simulation environment. By combining GABM and LLMs in this way, more complex and realistic simulations become possible. For example, conversations between agents and decision-making processes can be generated through LLMs and integrated into agent-based modeling.

[0040] The social simulation system (300) may include an environment (310), an agent (320), a game master (330), time (340), and an LLM (350) as major components to construct a social simulation based on such GABM.

[0041] The simulation environment (310) can correspond to the environment described as a component of GABM. This simulation environment (310) can be constructed using text describing a virtual society to limit the initial statement.

[0042] The agent (320) can correspond to the agent described as a component of GABM. In this case, the agent (320) can be configured using various personas to configure various LLM-based intelligent agents, including various attributes such as name, gender, age, occupation, family, personal characteristics, goals, etc. Additionally, the agent (320) may be selected from among existing registered agents, including various attributes.

[0043] The game master (330) may be the entity controlling the entire simulation process, but this game master (330) may be given as various states expressed in text to control the simulation environment (310) and the agent (320).

[0044] Time (340) may include the start time of the simulation and / or time steps. For example, a time step may refer to the time taken for an interaction between agents in the simulation. As a more specific example, a time step may refer to a time cycle in which an interaction between agents occurs within the simulation. In this case, if the time step is set to one hour, it may simulate what Role A will say to Role B after one hour, or how Role A will react to Role C, etc. Since the simulation proceeds in a turn-based manner, a time step may refer to the time elapsed in one turn of the simulation (one interaction between agents) (e.g., one minute, one hour, two hours, etc.).

[0045] LLM (350) may adopt a Strategic Technology and Operations Analysis (STOA) LLM to simulate crowd reactions. STOA is an academic field that primarily focuses on technology and operations analysis, and studies how companies or organizations can enhance their competitiveness through technological change and operational optimization. The STOA LLM can be used to analyze data collected from STOA using an LLM capable of processing and analyzing vast amounts of data to derive hidden patterns and insights for strategic decision-making, or to generate predictive models for market trends, technological advancements, and operational efficiency.

[0046] The social simulation system (300) can provide a user interface (380) to a user (370) accessing it using a user terminal (360). The user interface (380) can provide a function for the social simulation system (300) to input or select data for setting up the social simulation from the user (370), such as the environment (310), agent (320), state of the game master (330), time (340), etc. This user interface (380) can provide the aforementioned function to the user (370) through a web page-based or app-based interface.

[0047] When a user (370) inputs or selects data for setting up a social simulation through a user interface (380), the social simulation system (300) can set up a simulation environment (310) according to the input or selected data, place agents (320) in the set simulation environment (310), and start the simulation according to the time (340) and the state of the game master (330). In this case, interaction begins between the agents (320) according to given attributes (character, goal, etc.), and the social simulation system (300) can observe how the agents (320) interact with each other until the simulation ends.

[0048] Afterward, when the simulation is completed, the social simulation system (300) may generate and provide a simulation report. The simulation report may include data explaining whether the goal of the simulation was achieved, information on the process of achieving the goal if the goal was achieved, and, if the goal was not achieved, possible reasons. For example, the social simulation system (300) may provide the generated simulation report to the user (370) through the user interface (380).

[0049] Additionally, the social simulation system (300) may further provide the ability for the user (370) to converse with each of the agents (320) through the user interface (380). Conversations with these agents (320) may help the user (370) to understand the simulation results more deeply.

[0050] Such social simulations can be utilized in various areas, including marketing strategy decision-making, user targeting, and corporate management. For example, social simulations can be used to predict possible outcomes, such as user feedback and projected revenue, before launching a marketing campaign, or to identify potential target users for a new product or service prior to its release. Furthermore, for internal corporate policies, satisfaction levels can be assessed through prior simulations and used as a reference for adjustment.

[0051] FIG. 4 is a diagram illustrating an example of a user interface for inputting or selecting data for setting up a social simulation in an embodiment of the present invention. The embodiment of FIG. 4 shows an example of a user interface that can be provided to a user. The user interface of FIG. 4 may correspond to the user interface (380) described above.

[0052] In the user interface of FIG. 4, the area (411) for entering a description can provide a function for the user to enter information to explain the social simulation. The embodiment of FIG. 4 shows an example in which only a part of the text entered in the area (411) is displayed.

[0053] In the user interface of FIG. 4, the Setting tab shown in the first dotted box (412) may include functions for displaying and editing various data that are input or selected for setting up the social simulation. With the Setting tab currently selected, the user can input or select various data. The Run Result tab shown in the second dotted box (413) may include functions for displaying the results of running the simulation and allowing the user to converse with each of the agents. As previously explained, conversing with the agents can help the user gain a deeper understanding of the simulation results. This Run Result tab will be explained in more detail later.

[0054] The area (414) for inputting the initial state can provide a function for receiving information from the user to describe the initial state of each agent. The information regarding the initial state of the agent input through the area (414) can subsequently be used to implement the agent using an LLM model.

[0055] The area (415) for selecting an LLM model may provide a function to receive a selection of a model for implementing an agent from the user. Through this function, a list of selectable models may be provided, and the user may select a desired model from the list. In this case, the agent may be implemented through the selected model. At this time, as previously explained, each agent may be implemented by reflecting information about the initial state entered by the user.

[0056] The area (416) for setting the Total Run may provide a function to receive the number of times the simulation is repeated from the user. The user can set how many times the simulation will be repeated through the area (416), and the results of the simulation execution may be provided for each run of the simulation.

[0057] The area (417) for setting the start time can provide a function to receive the start time of the simulation from the user. This function can be linked with a function for the user to input or select a date, time, etc.

[0058] The agent area (418) may provide a function to receive at least one agent to be placed in the simulation from the user and to display information about the selected agent. An example is shown in the embodiment of FIG. 4 where an image showing the appearance of the agent and the name of the agent are displayed. Additionally, a function may be further provided to check detailed information about the selected agent by selecting information about the displayed individual agent.

[0059] The area (419) for inputting initial environments may provide a function for receiving data describing the environment from the user to set up the environment for simulation (e.g., environment (310)). An example of text data describing the environment is shown in the embodiment of FIG. 4.

[0060] The area (420) for inputting GM states (GM (Game Master) States) can provide a function for receiving data from the user to control the entire simulation process. The embodiment of FIG. 4 shows an example of text data for controlling the simulation process.

[0061] The components area (421) may provide functions for setting the goals of the simulation. Through this components area (421), functions may be provided for selecting whether to summarize and display observation results or output common sense morality indicators or other people's opinion indicators, and functions for setting various simulation goals such as immutable components, self-awareness, situation awareness, checking the response of agents for each situation, and simulation execution time.

[0062] The Run button (422) can provide a function to receive a signal from the user indicating the start of the simulation. For example, if the user selects the Run button (422), the social simulation system (300) can run the simulation from the start time set by the user in the area (417). If no start time is set separately through the area (417), the social simulation system (300) can run the social simulation from the moment the user selects the Run button (422).

[0063] The Edit button (423) can provide a function for editing input or selected data for the settings of the social simulation.

[0064] FIG. 5 is a diagram illustrating an example of a user interface for editing input or selected data for setting up a social simulation in an embodiment of the present invention. In the embodiment of FIG. 4, when a user selects an edit button (423) (for example, in a PC (Personal Computer) environment, the user clicks the area corresponding to the edit button (423) with a mouse), functions may be provided for the user to input, modify, delete, and select data for each item, as in the embodiment of FIG. 5.

[0065] For example, in the embodiment of FIG. 5, the first dotted box (510) represents an example of a function that can receive additional agents to be placed in the environment from a user. It is very difficult for a user who intends to build a social simulation in relation to a specific domain to directly set all components for building the social system. For example, it is very difficult for a user to directly set multiple attributes for each of the multiple agents to be placed in the environment for the social simulation, and usability may be poor. Accordingly, the social simulation system (300) preconfigures agents with various attributes (e.g., name, age, occupation, family, etc.) pre-set, and can determine an agent selected by the user as an agent to be placed in the environment. At this time, the user can input an initial state for the selected agent to further specify the agent's attributes.

[0066] Additionally, when a user inputs a description, the social simulation system (300) may analyze the description to generate data (e.g., text data) to be reflected in the initial state, initial environment, GM state, components, etc., and recommend it to the user. In this case, the user may use the recommended data as is or at least modify some of it to set up the social simulation. For example, the social simulation system (300) may input a description into an LLM model to generate and recommend data to be reflected in various settings such as the initial state, initial environment, GM state, components, etc. Later, if the user inputs additional data regarding the initial state, initial environment, GM state, and / or components, the system may further reflect the additionally input data to generate new data and recommend it to the user. According to the embodiment, the attributes of the agent may also be pre-set based on the LLM model.

[0067] FIG. 6 is a diagram illustrating an example of a user interface that provides information about an agent in an embodiment of the present invention. In the embodiment of FIG. 4, when a user selects an agent displayed through the agent area (418) of the user interface (for example, by hovering the mouse over an area where information about a specific agent is displayed), the social simulation system (300) may provide detailed information about the selected agent. The embodiment of FIG. 6 illustrates an example in which detailed information about the selected agent is displayed through a pop-up window (610). The detailed information about the agent may include the attributes of the agent described above, and may include attributes pre-set based on an LLM model and / or attributes set by reflecting user input.

[0068] FIG. 7 illustrates an example of a user interface that provides the results of a social simulation in an embodiment of the present invention. In the embodiment of FIG. 4, it was previously explained that the execution result tab shown in the second dotted box (413) of FIG. 4 may include a function that displays the results of the simulation and allows the user to converse with each of the agents. When the user selects the execution result tab, a user interface such as FIG. 7 may be provided. The first dotted box (710) of FIG. 7 illustrates an example of a user interface for selecting the number of times a simulation has been repeatedly executed. In the embodiment of FIG. 7, an example is shown where the user selects the third simulation out of five times the simulation has been repeatedly executed. Additionally, the first dotted box (710) further illustrates an example of an interface (720) for displaying the conclusion of the simulation.

[0069] As the third simulation is selected, the simulation result display area (730) may display the simulation execution results according to the execution of the social simulation. The simulation execution results may include information on how each agent acted, how they reacted to a specific event, or how they thought about a specific event.

[0070] According to an embodiment, the social simulation system (300) may display information such as the ratio of agents by item, which is pre-set in the simulation execution results, using text or graphs. For example, the ratio of agents who support a company's remote work policy and the ratio of agents who oppose it may be displayed using text or graphs. If the social simulation examines the reactions of agents to a new product / service, the social simulation system (300) may calculate and display satisfaction levels by age group or gender regarding the new product / service using text or graphs.

[0071] The conversation area (740) can provide a function that allows the user to converse with each of the agents. As previously explained, each agent can be implemented based on an LLM, and thus the social simulation system (300) can handle conversations between the user and these LLM-based agents. For example, the user can select a specific agent in the conversation area (740) and input a message, and the social simulation system (300) inputs the input message into the LLM implementing the agent and displays the response generated by the LLM through the conversation area (740), thereby allowing conversations between the user and the agent to proceed. As previously explained, conversations between the user and the agents can help the user understand the simulation results more deeply.

[0072] FIG. 8 is a diagram illustrating an example of a user interface for displaying the conclusion of a simulation in an embodiment of the present invention. In the embodiment of FIG. 7, the conclusion of the simulation can be displayed in the simulation result display area (730) as the interface (720) for displaying the conclusion of the simulation is selected. FIG. 7 illustrates an example in which only a portion of the simulation conclusion is displayed. Even in this case, according to the embodiment, the social simulation system (300) can display information such as the ratio of agents by item, which is pre-set in the overall simulation execution result, using text or graphs, etc.

[0073] The above embodiments described examples of conducting social simulations regarding situations where a company implements a new policy, primarily focusing on inferring how interactions occur between agents; however, it can be easily understood through the above description that a wider variety of social simulations are possible. For instance, a company providing shopping services can utilize agents categorized by various categories (e.g., gender, age group, hobbies, preferences, etc.) to conduct social simulations regarding potential fluctuations in sales revenue when a 10% discount is applied uniformly to all products, and to conduct social simulations regarding potential fluctuations in sales revenue when a 10% discount is applied only to specific items, and utilize this information for the company's decision-making. In this process, the agents by category may provide information such as the purchase rate and non-purchase rate of products. Furthermore, various additional information can be obtained through conversations with the agents, where users ask why the 10% discounted products were not purchased or if the items were not to their liking.

[0074] FIG. 9 is a flowchart illustrating an example of a social simulation method in an embodiment of the present invention. The social simulation method according to the present embodiment may be performed by a social simulation system (300) implemented through at least one computer device. At this time, each of the at least one computer device may correspond to the computer device (200) described above through FIG. 2. At least one processor included in the at least one computer device may be implemented to execute a control instruction according to the code of an operating system included in memory or the code of at least one computer program. Here, the at least one processor may operate according to the control instruction provided by the code to control the social simulation system (300) so that the social simulation system (300) performs steps (910 to 940) included in the method of FIG. 9.

[0075] In step (910), the social simulation system (300) may provide the user with a user interface that includes a setting function for the environment and agents for the social simulation. For example, the set environment may include text-based data describing the environment of the social simulation. Additionally, the agents may be individual entities placed in the set environment that have unique attributes and may be implemented to interact with other agents in the set environment according to conversations and behaviors generated based on a large language model. Here, the unique attributes may be set based on data input or selected by the user through the user interface.

[0076] According to an embodiment, the social simulation system (300) may receive data including a description of the social simulation through a user interface. In this case, the social simulation system (300) may analyze the received data through a large language model to generate configuration data for the environment and at least one of the agents, and may recommend the configuration data through the user interface. Through this configuration data, the user can easily configure the environment and agents of the social simulation through simple selection and modification as needed, without having to input all data for configuring the environment and agents of the social simulation.

[0077] In step (920), the social simulation system (300) can execute a social simulation using a generated agent-based modeling based on an environment and agents set through a user interface. For example, the social simulation system (300) can implement a virtual space of the social simulation using text-based data describing the environment of the social simulation. Additionally, the social simulation system (300) can observe and record the manner of interaction between agents placed in the set environment, for example, the virtual space described above.

[0078] According to an embodiment, the social simulation system (300) can generate at least one agent having preset basic attributes and can present the generated at least one agent to a user through a user interface. In this case, at step (920), the social simulation system (300) can set unique attributes for each of the at least one agent by reflecting data input or selected by the user for the at least one agent through the user interface to the basic attributes of the at least one agent.

[0079] Additionally, according to an embodiment, the user interface may further include a function for receiving data to control the process of the social simulation. In this case, the social simulation system (300) may execute the social simulation by further utilizing the data to control the process of the social simulation. This data may differ in that it is applied to the execution of the social simulation, unlike data for setting up an environment or agent.

[0080] In step (930), the social simulation system (300) may provide the results of the social simulation execution to the user through a user interface. For example, the social simulation system (300) may display through the user interface at least one of the following: information regarding whether a simulation goal has been achieved for each iteration of the social simulation, information regarding the process of achieving the simulation goal if the simulation goal has been achieved, and information explaining the possible reasons if the simulation goal has not been achieved. Here, the information regarding the process of achieving the simulation goal may include information regarding the process of interaction between agents deployed in a set environment. Additionally, the social simulation system (300) may provide information regarding the ratio of agents classified into pre-set items for the social simulation. Information regarding this ratio may be provided in the form of a graph or the like.

[0081] Additionally, the social simulation system (300) may repeat the social simulation as many times as the number of social simulations set through the user interface in step (920). In this case, in step (930), the social simulation system (300) may provide the results for each iteration of the social simulation and the overall conclusion of the repeated social simulations, respectively.

[0082] In step (940), the social simulation system (300) may provide a function for conversation between an agent and a user through a user interface. For example, the social simulation system (300) may provide a function for conversation in conjunction with an area in the user interface where the results of the social simulation execution are displayed, so that the user can converse with the agent by referring to the results of the social simulation execution.

[0083] As such, according to the embodiments of the present invention, a social simulation method and system through generation agent-based modeling can be provided.

[0084] The system or device described above may be implemented as a hardware component, or a combination of a hardware component and a software component. For example, the device and component described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0085] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, virtual equipment, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0086] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or multiple hardware components, and is not limited to a medium directly connected to a computer system, but may also exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0087] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0088] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A social simulation method of a social simulation system implemented by at least one computer device, wherein the at least one computer device includes at least one processor, and the social simulation method comprises: a step of providing a user interface to a user by the at least one processor, the user interface including a setting function for an environment and an agent for social simulation; a step of executing a social simulation by the at least one processor using Generative Agent-Based Modeling (GABM) based on the environment and agent set through the user interface; and a step of providing the execution result of the social simulation to the user through the user interface by the at least one processor. Claim 2 A social simulation method according to claim 1, wherein the step of providing the user interface to a user comprises: receiving data including an explanation of the social simulation through the user interface; analyzing the received data through a Large Language Model to generate setting data for at least one of the environment and the agent; and recommending the setting data through the user interface. Claim 3 A social simulation method according to claim 1, wherein the set environment includes text-based data describing the environment of the social simulation, and the step of executing the social simulation includes the step of implementing a virtual space of the social simulation using the text-based data describing the environment of the social simulation. Claim 4 A social simulation method according to claim 1, wherein the agent is implemented to interact with other agents in the set environment according to conversations and behaviors generated based on a large language model as an individual entity having unique attributes placed in the set environment, and the step of executing the social simulation includes the step of observing and recording the manner of interaction between agents placed in the set environment. Claim 5 A social simulation method according to claim 4, characterized in that the unique attribute is set based on data input or selected by the user through the user interface. Claim 6 A social simulation method according to claim 1, further comprising: a step of generating at least one agent having preset basic attributes by the at least one processor; and a step of presenting the generated at least one agent to the user through the user interface. Claim 7 A social simulation method according to claim 6, wherein the step of executing the social simulation includes the step of setting unique attributes of each of the at least one agent by reflecting data input or selected by the user for the at least one agent through the user interface into the basic attributes of the at least one agent. Claim 8 A social simulation method according to claim 1, wherein the user interface further includes a function for receiving data to control the process of the social simulation, and the step of executing the social simulation is characterized by executing the social simulation using the data to control the process of the social simulation. Claim 9 A social simulation method according to claim 1, wherein the step of providing the execution result of the social simulation comprises the step of displaying, through the user interface, at least one of information regarding whether a simulation goal has been achieved for each iteration of the social simulation, information regarding the process of achieving the simulation goal if the simulation goal has been achieved, and information explaining the possible reasons if the simulation goal has not been achieved. Claim 10 A social simulation method according to claim 9, characterized in that the information regarding the process of achieving the simulation goal includes information regarding the process of interaction between agents placed in the set environment. Claim 11 A social simulation method according to claim 1, wherein the step of providing the execution result of the social simulation includes the step of providing information on the ratio of agents classified into pre-set items for the social simulation. Claim 12 A social simulation method according to claim 1, wherein the step of executing the social simulation involves repeating the social simulation as many times as the number of social simulations set through the user interface, and the step of providing the execution results of the social simulation involves providing the results for each repetition of the social simulation and the overall conclusion of the repeated social simulations, respectively. Claim 13 A social simulation method according to claim 1, further comprising the step of providing a function for a conversation between the agent and the user through the user interface by the at least one processor. Claim 14 A social simulation method according to claim 13, wherein the step of providing a function for the above conversation is characterized by providing the function for the conversation in conjunction with an area in the user interface where the social simulation execution result is displayed, so that the user can converse with the agent by referring to the social simulation execution result. Claim 15 A computer program stored on a computer-readable recording medium to execute the method of any one of claims 1 to 14 on a computer device in combination with a computer device. Claim 16 A computer-readable recording medium having a computer program recorded thereon for executing the method of any one of paragraphs 1 through 14 on a computer device. Claim 17 A social simulation system implemented by at least one computer device, wherein the at least one computer device includes at least one processor, and the at least one processor provides a user interface to a user that includes a setting function for an environment and an agent for social simulation, executes a social simulation using Generative Agent-Based Modeling (GABM) based on the environment and agent set through the user interface, and provides the execution result of the social simulation to the user through the user interface. Claim 18 A social simulation system according to claim 17, characterized in that, in order to provide the above-mentioned user interface to a user, the above-mentioned at least one processor receives data including a description of the social simulation through the above-mentioned user interface, analyzes the received data through a Large Language Model to generate configuration data for at least one of the environment and the above-mentioned agent, and recommends the configuration data through the above-mentioned user interface. Claim 19 A social simulation system according to claim 17, wherein the environment set above includes text-based data describing the environment of the social simulation, and, in order to execute the social simulation, implements a virtual space of the social simulation using the text-based data describing the environment of the social simulation by at least one processor. Claim 20 A social simulation system according to claim 17, wherein the agent is implemented to interact with other agents in the set environment according to conversations and behaviors generated based on a large language model as an individual entity having unique attributes placed in the set environment, and wherein, in order to execute the social simulation, the method of interaction between agents placed in the set environment is observed and recorded by the at least one processor.

Images