Digital government affair service-oriented adaptive agent modeling method, system and product

Abstract

The invention belongs to the field of digital government affair service system modeling, and provides a digital government affair service-oriented adaptive agent modeling method, system and product, and the technical scheme is as follows: obtaining business processing data of each government affair department agent; constructing a digital government affair service model based on the business processing data of each government affair department agent; and according to different response variables, corresponding modeling features of the digital government affair service model are matched, and according to the incidence relation between the response variables and the corresponding modeling features, events causing significant changes of the response variables are determined. The framework captures and models microscopic individual features and an emergence mechanism thereof in a digital government affair service system, which not only facilitates standardization of a modeling process, but also eliminates a gap between complex feature modeling of a government affair department intelligent agent and system and AI technology application.

Description

Technical Field

[0001] The present invention belongs to the field of digital government service system modeling, and in particular to an adaptive intelligent agent modeling method, system and product for digital government services. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Digital government is a new form of government service that has emerged with the support of artificial intelligence technology. Entities with different intelligence (such as government departments, business personnel, and software robots) participate in co-evolution and gradually form a complex social system, namely the digital government service system. In these systems, adaptive individuals and groups can spontaneously form organized structures and behavior patterns through interactions and feedback mechanisms to provide efficient services. This self-organizing ability enables the system to self-regulate and adapt to changes in the demand environment. The study of digital government service systems helps to design and improve social policies and organizational management, and helps to gain insight into the role of various factors and relationships in the system. Therefore, it has attracted more and more attention from researchers.

[0004] The complexity of modeling digital government service systems stems from the diversity of their businesses and needs, the multi-link nature of business processes, and the uncertainty and dynamism of the system. Its operational architecture can be modeled in three layers: (1) Social layer: The adaptive service subject (i.e., individual agent of government departments) that provides services achieves sustainable development through autonomous decision-making and regulatory measures; (2) Physical layer: The functions based on physical devices are encapsulated into services and uploaded to the cloud, and diversified intelligent devices achieve crowdsourcing and crowdfunding through collaboration; (3) Information layer: Emphasis on the complex connections and interactions between adaptive service subjects. Since complex adaptive systems involve human and social factors (such as changes in demand, competition and collaboration between departments), accurately modeling the complex characteristics of adaptive government department agents and artificial intelligence society is crucial for the effective analysis and governance of digital government service systems.

[0005] Existing methods of modeling and analyzing digital government service systems using complex networks and activity-based models (ABM) often focus on specific technical implementations or isolated features. However, as social theory and computer technology are further integrated into ABM research, and digital government service systems become increasingly complex, the modeling process often involves various features at the individual, social, and system levels. However, existing modeling methods are difficult to accurately represent these complex features, and there is a gap between existing technologies and complex feature modeling. Summary of the invention

[0006] In order to solve at least one of the technical problems existing in the above-mentioned background technology, the present invention provides an adaptive intelligent agent modeling method, system and product for digital government services. In order to capture the characteristics of micro-entities (such as decision-making and interaction) in the digital government service system and describe their emergence mechanism, the autonomy, evolution, interactivity and emergence characteristics of the adaptive departmental individual agent to the artificial intelligence society are modeled respectively, and the corresponding characteristics are matched according to the actual degree of intelligence of digital government affairs, thereby improving the efficiency of government service governance.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A first aspect of the present invention provides an adaptive agent modeling method for digital government services, comprising the following steps:

[0009] Obtain business processing data of intelligent entities in various government departments;

[0010] Based on the business processing data of the intelligent agents of each government department, a digital government service model is constructed; wherein the digital government service model includes multiple layers, each layer models the subject and system characteristics of different complexity; wherein the L1 layer models the basic characteristics of the intelligent agents of the government departments, the L2 layer models the evolutionary characteristics of the intelligent agents of the government departments based on the modeling characteristics of the L1 layer, the L3 layer models the interaction characteristics between the intelligent agents of each government department based on the modeling characteristics of the L2 layer, and the L4 layer models the emergent characteristics of the AI ​​society based on the modeling characteristics of the L3 layer;

[0011] Determine the factors that affect government services, match the corresponding modeling features of the digital government service model according to different influencing factors, and determine the events that cause significant changes in the influencing factors based on the correlation between different influencing factors and corresponding modeling features.

[0012] Furthermore, the L1 layer models the basic characteristics of the government department agent, including:

[0013] Obtain the state information and environmental information list of the government department agent itself;

[0014] Determine the information type and memory requirements that the government department agent needs to store and retrieve, and save the government department agent's own state information and environmental information list information as "state-behavior" pairs;

[0015] Based on the current “state-action” pair, the agent takes corresponding actions to complete the task or adjust its own state and make decisions;

[0016] According to the decision, the state information and environmental information list data of the government department agent itself are updated to obtain a structured representation of autonomous features.

[0017] Furthermore, the process of modeling the evolutionary characteristics of the government department agent in the L2 layer includes:

[0018] Based on the basic characteristics of a single government department agent, the genetic evolution of government department agents is modeled;

[0019] Obtain information about neighboring government department agents, take the capability attributes of each government department agent as a knowledge point, represent each knowledge point as multiple sectors, determine the best sector based on the agent's attributes, and determine the learning reference target for imitation learning based on the combination of the best sectors;

[0020] Identify study areas;

[0021] Calculate the survival capabilities of all departmental agents, calculate the fitness values ​​of all departmental agents based on their survival capabilities, select the agents with the highest fitness values ​​in the first N cycles in the learning area, and broadcast the knowledge points of these agents for other agents to learn.

[0022] Furthermore, the process of modeling the interaction characteristics between government department agents at L3 layer includes:

[0023] Determine the initial communication network topology between the intelligent agents of each government department;

[0024] If it is collaboration between individuals in government departments, the weights between nodes in the communication network topology structure are updated by recording the relationship list of the department agents that have established contact;

[0025] If it is the collaboration between individual government departments and the collaborative alliance, determine the collaboration intention of the government department agent and choose whether to join the collaborative alliance;

[0026] Calculate the profit distribution during the collaboration process and decide whether to adopt a negotiation mechanism based on your own status.

[0027] Furthermore, the profit distribution calculation formula during the collaboration process is:

[0028]

[0029] Where Profit(i) is the agent i The income obtained after participating in the cooperation; Cost(i) is the income of Agent i The total cost of participating in the collaboration; Cost total is the total cost of processing an order; Value(i) is the i The normalized effective value created by participating in the collaboration; Value total is the total effective value created during order processing; a is the profit distribution coefficient;total is the total profit gained when the order is completed.

[0030] Furthermore, the process of modeling the emergent characteristics of the AI ​​society at L4 includes:

[0031] Define the impact of the environment on government agency agents;

[0032] The government department agent selects actions based on the current state, interacts with the environment, and obtains immediate rewards and feedback for the next state;

[0033] Combined with rewards and feedback, the constraints built into the constraints considered before the agent makes a decision are continuously adjusted according to the purpose and status of the system operation, that is, the intervention strategy.

[0034] Furthermore, the autonomous features are structurally represented as:

[0035] L1(Agent)= <R,S t ,E t ,V t ,M t ,D t >,

[0036] The evolutionary characteristics of the government department agent are structurally represented as follows:

[0037] L2(Agent)= <L1(Agent),F,Y t >,

[0038] The interaction characteristics of government department agents are structurally represented as follows:

[0039] L3(Society)= <L2(Agent),C t ,G t ,P t ,TS>,

[0040] The emergent characteristics of AI society are structurally represented as follows:

[0041] L4(System)= <L3(Society),Env.,Q t ,N t >,

[0042] Among them, R is the property that the Agent maintains stability, S t is the dynamic capability attribute of the agent that changes over time, E t is the agent’s perception ability, V t is the Agent’s responsiveness, M t is the memory capacity of the Agent, D t is the decision-making ability of the agent, F is the prior condition for the agent to learn and evolve, and Yt is the learning ability of the Agent, C t is the communication rule between agents, G t is the cooperation rule between agents, P t is the competition rule between agents, TS represents the system topology, Env. is the interaction between the environment and department agents; Q t represents the feedback mechanism from the system to the Agent, N t System intervention strategies adopted for the stable development of the system.

[0043] Furthermore, factors affecting government services include system performance indicators and customer satisfaction.

[0044] A second aspect of the present invention provides an adaptive agent modeling system for digital government services, comprising:

[0045] A data acquisition module, which is used to obtain business processing data of each government department intelligent body;

[0046] A digital government service modeling module, which is used to construct a digital government service model based on the business processing data of each government department agent; wherein the digital government service model includes multiple layers, each layer models subjects and system characteristics of different complexity; wherein the L1 layer models the basic characteristics of the government department agent, the L2 layer models the evolutionary characteristics of the government department agent based on the modeling characteristics of the L1 layer, the L3 layer models the interaction characteristics between the government department agents based on the modeling characteristics of the L2 layer, and the L4 layer models the emergent characteristics of the AI ​​society based on the modeling characteristics of the L3 layer;

[0047] The governance module is used to determine the factors that affect government services, match the corresponding modeling features of the digital government service model according to different influencing factors, and determine the events that cause significant changes in the influencing factors based on the correlation between different influencing factors and corresponding modeling features.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] According to the improvement of the complexity of the subject and the system, the model of the present invention describes in detail the behavior pattern and decision-making process of the adaptive government department agent from four levels (i.e., L1, L2, L3 and L4), namely, autonomous characteristics, evolutionary characteristics, interactive characteristics and emergent characteristics. Among them, the L1 layer models the perception, memory, behavior and decision-making ability of the government department agent; the L2 layer models the learning mechanism of the government department agent based on heterogeneity and limited rationality; the L3 layer models the communication, collaboration, competition and network topology between the government department agents; and the L4 layer models the environmental impact, feedback loop and intervention mechanism of the system from a macro perspective. This framework captures and models the micro-individual characteristics and their emergent mechanisms in the digital government service system, which not only helps to standardize the modeling process, but also eliminates the gap between the modeling of complex characteristics of government department agents and systems and the application of AI technology.

[0050] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0052] Figure 1 It is a general structural diagram of the adaptive intelligent agent modeling method for digital government services provided by an embodiment of the present invention;

[0053] Figure 2 It is a flow chart of an adaptive agent modeling method for digital government services provided by an embodiment of the present invention;

[0054] Figure 3 It is a modeling logic diagram of individual autonomous features provided by an embodiment of the present invention;

[0055] Figure 4 It is a modeling logic diagram of individual evolution characteristics provided by an embodiment of the present invention;

[0056] Figure 5 It is a modeling logic diagram of the interaction feature between subjects provided by an embodiment of the present invention;

[0057] Figure 6 It is a modeling logic diagram of the system emergence characteristics provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0059] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0060] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0061] As mentioned in the background technology, the existing digital government service system modeling process often involves various characteristics at the individual, social, and system levels. However, existing modeling methods are difficult to accurately represent these complex characteristics, and there is a gap between existing technologies and complex feature modeling.

[0062] The method for aligning the characteristics of a digital government service system with AI technology based on adaptive agent modeling provided by the present invention is based on collecting log data of the digital government service system. The method can be divided into four layers (i.e., L1, L2, L3, and L4) for modeling:

[0063] (1) L1: Statistics on the characteristics, state changes, and parameter distribution of government department agents, and modeling the autonomous characteristics of department agents from an individual perspective, including perception, memory, behavior, and decision-making.

[0064] (2) L2: Analyze the heterogeneous characteristics and learning evolution mechanism of government department agents, and model their evolutionary characteristics from an individual perspective, including modeling agent learning mechanisms based on heterogeneity and bounded rationality.

[0065] (3) L3: Collect statistics on the interaction data between agents in government departments and model the interaction characteristics between agents from a social perspective, including communication, collaboration, competition, and topology.

[0066] (4) L4: Model the emergent characteristics of the AI ​​society from a system perspective, including environmental impacts within the system, feedback loops between departmental agents and the system, and intervention mechanisms. When modeling a digital government service system, some of these characteristics can be modeled based on the research question.

[0067] The AI ​​society can be seen as a virtual system built based on ABM technology for analyzing digital government service systems. It includes intelligent subjects, environment and system operation rules. It is a new social form spawned by artificial intelligence technology, which is characterized by interactions between subjects and associations between subjects and the environment. As the subject of system modeling, the service individual agent can represent a real individual or entity, a specific robot or an entity completely simulated by software. In the digital government service system, the service individual agent is a department agent with adaptive capabilities. These department agents include similar departments with similar functions and different departments with different functions, and there is cooperation and competition. They are endowed with different complex characteristics and behaviors, and can autonomously adjust their behaviors, strategies and decisions according to environmental changes and the information obtained to achieve better performance and adaptability. Figure 1 In the above, the interaction between the hierarchical AI features and their intermediate parts constitutes a relatively complete and abstract structure of the evolution cycle. The basic theory provides basic modeling techniques for the features of each layer. The model library encapsulates the models corresponding to various features in the object-oriented component structure, which is easy to manage and can be expanded as needed. The input of this method is the information list of dynamic features stored in the government department agent and service system at time t; the output is the information list of dynamic features stored in the government department agent and service system at time t+1. That is, the system takes period t as the evolution unit, and the system runs a complete cycle in each period, and the information list of dynamic features stored in the government department agent and service system is updated once; assuming that the system ends operation after T periods, the system's operating data within T periods (including the influencing factors and response variables of the reaction system characteristics) is statistically deduced to analyze the system's evolution process and assist system governance.

[0068] Embodiment 1

[0069] like Figure 2 As shown, this embodiment provides an adaptive agent modeling method for digital government services, including the following steps:

[0070] Step 1: Obtain the business processing data of each government department agent;

[0071] In this embodiment, the business processing data of each government department intelligent body includes data such as changes in the business processing capabilities of each government department intelligent body, changes in business backlogs, and the frequency of collaboration between departments, reflecting the operating status of government departments in government services; for example, the time when the user submits the application, the type and progress of the business handled, and records the API calls between different institutions, including request parameters, response time and results, etc.

[0072] Step 2: Based on the business processing data of each government department’s intelligent body, a digital government service model is constructed;

[0073] In this embodiment, the digital government service model includes multiple layers, each layer models subjects and system characteristics of different complexity; the L1 layer models the basic characteristics of the government department agent, and the L2 to L4 layers respectively model supplementary characteristics based on the modeling characteristics of the previous layer; the intelligence of the department agents modeled from L1 to L4 becomes higher and higher, and the system becomes more and more complex.

[0074] The specific steps include:

[0075] Step 201, L1 layer models the basic features of the government department Agent;

[0076] Adaptive agents simulate real human or human group behavior, which is reflected in their ability to reason, plan, and act on themselves, other intelligent agents, and the environment. Figure 2 As shown in Figure 1, the perception (sensors) and memory of the scene by the government department agent provide key information about the environment and experience. The collaboration of perception, memory, and effectors enables the government department agent to make intelligent decisions and take appropriate actions.

[0077] The specific steps include:

[0078] Step 2011: Information perception and storage

[0079] Obtain the current state information of the government department agent itself (including assets, location) and the list of environmental information (such as other agents and social environment information that the government department agent can perceive);

[0080] Department Agents perceive their own and the environment's status by reading log data and system status information. For example, the business processing module can perceive the current request load, resource usage, and error status. The perceived content includes its own performance indicators, resource usage, business status, etc., as well as the status of other Agents in the environment and the overall operation of the system. For example, a server node can perceive the load of other server nodes to make decisions when load balancing.

[0081] Step 2012: determine the information type and memory requirements that the government department Agent needs to store and retrieve, and save the information in step 2011 as a "state-behavior" pair;

[0082] Department Agents can store perceived information and historical experience in a database, file system, or memory. For example, the results and timestamps of business processing are stored in a database for subsequent analysis and query. The memory content includes historical data, empirical rules, decision results, etc. For example, the user authentication module can remember common error types and solutions so that similar problems can be quickly handled next time.

[0083] The generated historical data is stored in the memory and continuously updated. As time evolves, the government department agent can selectively retain, update and output the memory, and realize the modeling of long-term and short-term memory by controlling the forget gate, input gate and output gate. This memory mechanism allows the agent to capture key information and long-term dependencies when processing sequence data, thereby promoting better decision-making and prediction.

[0084] The memory mechanism of the government agency agent can be expressed as follows:

[0085] M t =M t-1 ⊙ f t +A t ⊙ i t (1)

[0086] Where M t is the memory of the Agent; M t-1 is the early memory of the agent; f is the forgetting vector, which determines the features retained in the memory and their weights; A t is the new memory obtained based on the input; i t is the update vector, which determines the weight of the features in the new memory; ⊙ denotes element-wise multiplication.

[0087] Step 2013: Based on the current “state-behavior”, the Agent takes corresponding actions to complete the task or adjust its own state and make a decision;

[0088] Based on the perceived information and the experience in memory, the department agent takes corresponding actions to complete the task or adjust its own status. For example, when the business processing module perceives that the request load is too high, it can start more threads to improve the processing capacity; when the resource usage is close to the limit, it can take resource optimization measures, such as releasing unnecessary memory. The agent's behavior rules can guide the agent's behavior through predefined rules or policies. For example, a load balancing strategy is formulated to distribute requests to other nodes with lower loads when a server node is overloaded.

[0089] Department Agents make decisions based on perceived information, remembered experience, and predefined goals. For example, when processing user requests, they decide whether to approve the request based on the user's identity, request type, and system resource availability. At the same time, Agents can use different decision algorithms to implement the Agent's decision-making process. For example, machine learning algorithms can be used to predict future request loads based on historical data in order to adjust resource allocation in advance. Finally, department Agents can evaluate the results of decisions in order to continuously optimize the decision-making process. For example, by comparing the effects of different decision plans, the best decision plan can be selected.

[0090] The decision-making mechanism of the government department agent refers to the logic and algorithm inside the agent, which determines the agent's intelligence level and behavior. According to the intelligence level of the government department agent, the decision-making is divided into three levels:

[0091] 1) “Zero Intelligence” Mode: Low-intelligence agents make random decisions from a set of actions.

[0092] 2) "Observation-Action" mode: The medium-intelligent agent makes decisions based on the current state, and the decision-making mechanism consists of a set of rules in the form of "if...then..." statements.

[0093] The medium and high intelligence government department agents evaluate the current state and behavior based on the information data perceived in step 2011 and the memory data stored in step 2012, and make the most favorable decision for themselves. The decision-making process of the medium and high intelligence department agents is shown in formulas (2) to (3):

[0094] E t *S t *M t →D t .Rules*V t →S (t+1) (2)

[0095] π(v|s)→Q(s,v),Q(s,v)→π(v|s) (3),

[0096] In the formula, E t is the information perceived in step 2011, S t A list of information reflecting the current status of the department agent; M t Memory of the department Agent in step 2012; D t .Rules are the rules set in the decision-making mechanism; π(v|s) represents the policy function, which represents the probability of selecting action v under a given state s; Q(s,v) represents the expected cumulative reward given a specific state and action. V tIt is the agent's responsiveness, including its spontaneous behavior and all behaviors triggered by external events; t It is the decision-making ability of the agent, including the rules of behavior of the agent in various situations;

[0097] 3) "Observation-Prediction" mode: highly intelligent department agents make decisions based on reasoning, using loss functions to represent the effectiveness of previous decisions. The smaller the loss function value, the greater the weight given to the excellent strategy. This decision is represented by the following formula:

[0098] D t =W h *[D t-1 ,S t ]+b h (4)

[0099] Where D t and D t-1 is the weight of the decision information at t and t-1; W h is the decision weight vector; b h is the bias vector;

[0100] Step 2014: Update the Agent information list of the government department and perform the next round of iteration until the operation data of the system within the set period is completed and the autonomous feature structured representation is obtained;

[0101] The final structured representation of the department agent's autonomous feature L1(Agent) is as follows:

[0102] L1(Agent)= <R,S t ,E t ,V t ,M t ,D t > (5),

[0103] Where R is the stable attribute of the Agent, such as the type of government department; S t It is the dynamic capability attribute of the agent that changes over time, such as the assets of government departments; E t is the agent’s perception capability, such as the department’s ability to obtain information; V t It is the agent's responsiveness, including its spontaneous behavior and all behaviors triggered by external events; M t The memory ability of the agent, including the duration of long-term and short-term memory, etc.; D t It is the decision-making ability of the agent, including the agent's behavioral rules in various situations.

[0104] Step 202, L2 layer models the evolution characteristics of the government department Agent;

[0105] Different departmental agents may undertake different government service functions. For example, some departments are responsible for handling citizens' household registration business, while others may focus on tax declaration services. This difference in function will cause them to exhibit different characteristics in terms of processing procedures, required data, and interactive objects. Even if they perform the same function, different agents may have different performance. This includes response time, processing power, reliability, etc. For example, some agents may be able to process requests faster due to higher hardware configuration or better algorithm optimization, while other agents may be prone to performance degradation under high load. L2 models departmental agents with higher intelligence based on L1. The L2 layer introduces diversity by giving departmental agents distinct personalities, goals, and value orientations, gradually revealing the differences and uniqueness of agents.

[0106] The evolutionary characteristics of government department agents are mainly reflected in their learning ability. Figure 3 As shown in the figure, the limited rationality and heterogeneity in the digital government service system are the prerequisites for the learning of government department agents, which enables government department agents to make approximately optimal decisions within limited resources and time without comprehensive search and analysis. On this basis, government department agents continuously improve their decisions through self-reflection, imitating other government departments, and absorbing experience from scenarios.

[0107] Bounded rationality includes incomplete information and incomplete rationality. However, "bounded rationality" does not mean "irrationality". It is just that under the constraints of information, knowledge and ability, decisions are made according to the "fast-frugal heuristic". The bounded rational decision of the government department agent is expressed as P(a i |s i ), indicating the government department Agent i In status i Take action a i The probability, rather than certainty, provides an interface for introducing the research conclusions of psychology and behavioral economics, such as prospect theory and learned bias model.

[0108] Incorporating heterogeneity into artificial social modeling helps solve complex dynamic game problems. By simulating multi-agent, multi-period dynamic game processes, agents from various government departments constantly adjust their strategies throughout the game process, and jointly push the overall situation toward a specific "equilibrium". It includes two aspects:

[0109] i) Attribute heterogeneity: usually manifested as differences in specific parameter values, such as traders’ risk preferences, energy constraints, beliefs, etc. Among them, the heterogeneous goals of agents in different departments determine the motivation and direction of the agents.

[0110] ii) Behavior heterogeneity: It can be divided into two categories: a. N-type model: the strategy set is constant; b. Autonomous model: the strategies of agents adopting this model are heterogeneous. The difference from the N-type model is that agents can create new strategies through learning. Agents with different intelligence levels have different cognitive and behavioral modes, and their strategy sets are updated in different ways.

[0111] In the computational model, the transition from optimization based on complete rationality to simulation based on limited rationality improves the flexibility of modeling and reduces the difficulty of solving the system. The government department agent continuously improves its behavior and performance through technologies such as genetic learning. If the evolutionary characteristics in the digital government service system are to be considered, after completing the modeling of step 201 in the L1 layer, the modeling process of the evolutionary characteristics is as follows:

[0112] It should be noted that, depending on the modeling scenario and research question, some or all of the following learning features can be modeled;

[0113] Step 2021: Genetic evolution modeling of government department agents

[0114] Genetic evolution simulates inheritance between departments and sub-departments. The characteristics of a single department agent are identified and represented as a matrix. During the evolution process, a random value between 0 and 1 is generated. If the generated random value is less than the mutation threshold, the agent mutates. In the weight matrix, a weight variable is randomly selected and replaced with a random value (with a fluctuation range within 10% of the initial value). This will cause a small change in the agent, which may produce a healthier agent. A smaller fluctuation range can avoid catastrophic failures of neural networks.

[0115] When the energy of an agent drops to 0, it will die. When the energy of an agent reaches the reproduction threshold, it will produce offspring. The offspring agent will inherit some properties from its parents, as shown in formula (6):

[0116] Offspring=parent1*a+parent2*(1-a) (6),

[0117] Where Offspring is the attribute vector of the offspring object; a is a randomly generated value between 0 and 1, and parent1 and parent2 represent the weight matrices of the attributes.

[0118] Step 222: Imitation learning modeling of government department agent

[0119] Imitation learning is used to model the mechanism of mutual learning between neighboring departments. Department Agent uses the information obtained from neighboring department Agents, and the capability attributes of each department Agent are used as a knowledge point. ij is the knowledge point of the jth Agent, S r1 ,S r2 ,...,S rk Represents the knowledge points of other agents in the organization. Each knowledge point is then represented as multiple sectors (e.g., its location, number of stored orders). After comparing the standardized attribute values ​​of all agents, the best sectors in the organization are selected. By combining these best sectors, the final learning reference target can be formed. The agent compares one of its own sectors with the sectors of the virtual learning object to retain the better point.

[0120] Step 2023: Social learning modeling of government department agents

[0121] The social learning mechanism of the department is used to simulate the impact of corporate culture or social culture on department individuals. Department agents judge their own game strategies based on the social culture they accept and their historical strategies in the game process. The social learning modeling of department agents is as follows:

[0122] Identify all departmental agents in the entire region or part of the region as a learning society. The learning region is represented by the following formula:

[0123] If|X d -X1|=Rand()*(X2-X1),X d ∈this society (7),

[0124] Among them, X d Represents a point in the area; X1 represents the reference point; X2 represents the center point; Rand() represents a random value in the range [0,1].

[0125] Then, the survivability of all department agents is calculated as follows:

[0126]

[0127] Among them, Viability i represents the survival value of the ith agent; w j Indicates the weight value of the jth attribute; Attribute j Represents the value of j attributes.

[0128] After that, the standardized fitness value of all agents is calculated by combining the survival capabilities of all agents. i :

[0129]

[0130] Among them, Fitness i Represents the standardized fitness value of the ith Agent; viability i Represents the survival ability of the ith Agent.

[0131] Finally, the agents with the highest fitness values ​​in the first N cycles in the area are selected, and the knowledge points of these elite agents are broadcasted for other agents to observe and learn. After receiving the broadcast information, other agents compare the recommended knowledge points with their own knowledge points, switch rules according to their own strategies, and decide whether to perform imitation learning and change their own knowledge.

[0132] Step 2024: Update the information list of the department agent and the service system, and perform the next cycle iteration until the operation data of the system within the set cycle is completed, and the structured representation of the evolutionary characteristics of the department agent is obtained;

[0133] L2(Agent)= <L1(Agent),F,Y t > (10),

[0134] Among them, F is the prior condition for agent learning and evolution, including heterogeneity and bounded rationality; Y t It is the learning ability of the agent, which improves its own learning ability through learning environment and other agents.

[0135] Step 203: L3 layer models the interaction characteristics between government department agents

[0136] The interaction modeling of departmental agents based on social networks is directly related to the structural characteristics and internal evolution mechanism of the social system. Due to the diversity and interaction of agents, quantitative changes will lead to qualitative changes, thus forming a complex and dynamic AI society. L3 is modeled on the basis of L2. The departmental agents in L3 not only have basic adaptive characteristics and learning mechanisms, but also have mutual communication and competition and cooperation mechanisms, which constitute the organizational structure of the system.

[0137] The interactivity of departmental agents is mainly reflected in the collaboration between agents. Collaboration is a combination of individual task-solving ability and communication ability. In complex coordination tasks, there may be differences in goals or intentions between departmental agents, which brings difficulties to collaboration. Figure 4As shown in Figure 1, in the agent interaction mechanism based on social networks, communication is the basis of collaboration and competition. In the fierce market competition, departmental agents may form collaborative groups with different topological structures. Departmental agents make decisions and take appropriate actions based on their own cognition and the information received from the scene.

[0138] In the computational model, communication between departmental agents can be achieved through complex networks, shared data structures, etc. Departmental agents share important data, insights, and knowledge through communication to increase mutual understanding and decision-making capabilities. This includes direct point-to-point communication, as well as indirect broadcasting or mediated transmission. When modeling, various techniques and methods such as game theory and social network analysis can be used to capture the characteristics of communication, competition, and cooperation. Agents can share the same goals and reasonably distribute tasks based on personal skills and resource availability. Through effective task division and cooperation, agents can improve work efficiency. If the interactive features in the digital government service system are to be considered, after completing the modeling in the L1 layer and the modeling in the L2 layer, the modeling process of the interactive features specifically includes the following steps:

[0139] Step 2031, designing the communication network topology structure of the initial government department Agent in the system;

[0140] The initial contact of the government department agent can be represented by a network structure, such as a small-world network. In addition to the fixed topology in the previous system or the topology switched according to certain rules, the modeling process of passively changing the network topology through operations such as node failure, edge failure, and adding edges can also be used to study some emergencies in society. This type of work, combined with control design, will eventually be classified as an optimal topology design problem.

[0141] Step 2032: Modeling the collaboration process between individuals in government departments:

[0142] By recording the subjects that establish contact, the relationship list of government department agents is obtained, and the weights between nodes in the communication network topology are updated;

[0143] The government department agent builds its own relationship network through the number of collaborations, which can be expressed as the following formula:

[0144]

[0145] Where P ij Agent i and Agent j The strength of the relationship between i and N j Agent i and Agent jThe number of contact objects in the strong connection relationship list; N is the total number of Agents in the network; n ij Agent i and Agent j The actual number of encounters between them; T is the total number of repeated runs.

[0146] Step 2033: Modeling the collaboration process between individual government departments and the collaboration alliance;

[0147] The adjustment and update of the collaboration intention of the government department agent depends on the following formula:

[0148] (v i_co ≥v i_in )? Evole(no):Evole(yes) (12),

[0149] Where V i_co and V i_in They represent the benefits obtained by the ith agent when choosing the cooperation strategy and the independent operation strategy. Only when the above formula is not satisfied, the agent will tend to join a new collaborative alliance.

[0150] During the collaboration between steps 2032 and 2033, the profit distribution calculation formula is:

[0151]

[0152] Where Profit(i) is the agent i The income obtained after participating in the cooperation; Cost(i) is the income of Agent i The total cost of participating in the collaboration; Cost total is the total cost of processing an order; Value(i) is the i The normalized effective value created by participating in the collaboration; Value total is the total effective value created during order processing; a is the profit distribution coefficient; Profit total is the total profit gained when the order is completed.

[0153] Negotiations between government department agents can often achieve a win-win situation, leading to a Nash equilibrium in the system. The negotiation mechanism is represented by the following formula:

[0154] C i =f(H i ) (14),

[0155] In the formula, C iis the collaborative strategy, which is the ratio of the expected profit Profit(i) of the Agent; f() represents the coordination function; H i Represents Agent i experience.

[0156] Step 2034: Update the information list of the department agent and the service system, perform the next cycle iteration, and obtain the structured representation of the interaction characteristics of the government department agent;

[0157] L3(Society)= <L2(Agent),C t ,G t ,P t ,TS> (15),

[0158] In the formula, C t G is the communication rules between agents, including the communication range, etc. t is the cooperation rules between agents, including cooperation conditions, etc.; t is the competition rules between agents, including resource constraints, etc.; TS represents the system topology, such as tree structure, star structure and grid structure.

[0159] Step 204: L4 layer models the emergent characteristics of the AI ​​society

[0160] In the digital government system, there are many environmental factors. From a social perspective, the public's requirements for the convenience and transparency of government services are constantly increasing, which has prompted the continuous optimization of the digital government system. When people submit business applications on the system, the system can provide real-time feedback on the acceptance status, processing progress and other information of the application. The intervention mechanism of the digital government system is reflected in the active regulation of government processes and service quality. When emergencies occur, such as natural disasters that limit the offline processing of certain government services, the system can intervene quickly, guide the relevant business to online processing, and issue emergency processing guidelines. For some risky government decisions, the system can intervene through data analysis and model prediction.

[0161] The digital government service system shows strong intelligence in three aspects: environmental impact, system feedback and intervention mechanism. In social systems, there is not only competition and cooperation between agents, but also time-varying correlations and nonlinear interactions between internal agents or groups and between agents and the environment, which are the basic driving factors for the emergence of the system.

[0162] In the digital government service system, the scenario is a system composed of government department agents and the environment. The environment can be a natural environment or a social environment. The environment in the digital government service system is the external conditions and influences of the service individual agent, which determines the agent's perception ability and action space, and is mainly reflected in the demand orders in the society;

[0163] External intervention in the system mainly includes two aspects:

[0164] i) In an experiment, variables or parameters in a system are changed through human intervention to observe how the system responds;

[0165] ii) Consider different types of human intervention, such as policy changes, technology upgrades, etc., and test the evolution of the system under different intervention strategies.

[0166] like Figure 5 As shown in Figure 1, the government department agent can send requests for information about the state of the environment. At the same time, the behavior of the government department agent may cause changes in the state of the environment and the behavior of other agents. In addition, the feedback of the government department agent is simulated through the reward signal or evaluation indicator of the system. These signals can be used to indicate whether the agent's behavior is correct or close to the goal, and to update the learning algorithm or decision-making mechanism of the government department agent. The system or environment continuously optimizes the strategy set by receiving feedback signals from the agent, and induces or forces intervention in the agent's decision.

[0167] In the computational model, the environmental model acts as a container that connects the agent to the geographic scene based on domain knowledge, including spatial distribution and spatiotemporal associations. When the research goal is to understand the mechanism, the abstract environmental model is sufficient as the background of the agent without extensive environmental details. However, when the goal is policy optimization to ensure a high degree of consistency between the artificial society and the real system, a more specific environmental model is required. Agents use appropriate interfaces, APIs, or virtual environments to simulate their interactions with the environment. If the interactive features in the digital government service system are to be considered, after completing the modeling of the L1 layer, the L2 layer, and the L3 layer, the modeling process of the emergent features specifically includes:

[0168] Step 2041, define the impact of the environment on the government department Agent;

[0169] The environmental information obtained by government department agents from social demand orders can be described according to the following dimensions: 1) Completeness: whether the environment provides all the information required by the agent; 2) Observability: whether the agent can observe the state of the environment in whole or in part; 3) Determinism: whether the environment has a unique result on the agent's behavior; 4) Staticity: whether the environment remains unchanged before and after the agent's behavior; 5) Discreteness: whether the environment consists of finite states and actions, or is it continuous and infinite; 6) Unity: whether there is only one agent in the environment, or whether there is competition or cooperation between multiple agents.

[0170] The environmental impact perceived by the government department agent is expressed as follows:

[0171] E= e ,X,δ e >,S e *X→δ e (16)

[0172] In the formula, S e is the state set of the environment; X is the set of external events, and δ e Represents a new environment state based on the current environment state and events.

[0173] Step 2042: Modeling system feedback mechanism

[0174] The government department agent selects actions based on the current state, interacts with the environment, and obtains immediate rewards and feedback for the next state.

[0175] Based on this feedback, the government agency agent can update its value function and strategy to make better decisions in future interactions.

[0176] Specific algorithms and methods can vary according to the characteristics of the problem and research needs, such as Q learning, deep Q network (DQN), policy gradient, etc. The feedback information received by the government department agent from the environment is expressed as the following formula using the reward function:

[0177] R(t) = r( S t ,a(t)) (17),

[0178] In the formula, R(t) represents the immediate reward obtained by the agent at time t based on the selected action and the current environment state; R() represents the reward function; S t is the state of the environment at time t; a(t) represents the action chosen by the Agent at time t.

[0179] ​Based on the feedback from the environment, the government department agent can update the value function to more accurately evaluate the value of the state and action. The specific formula for updating the value function can vary depending on the specific algorithm and method. Based on the obtained rewards and the estimate of the value function, the updated value function formula can be expressed as follows:

[0180] V(s(t))=V(s(t))+α*(R(t)+γ*V(s(t+1))-V(s(t)))(18), Q(s(t),a(t) )=Q(s(t),a(t))+α*(R(t)+γ*Q(s(t+1),a(t+1))-Q(s(t),a(t)))(19),

[0181] Where V(s(t)) represents the estimated state value at time t, that is, the expected value of the cumulative reward that the agent can obtain in state s; Q(s(t),a(t)) represents the estimated action value at time t, that is, the expected value of the cumulative reward that the agent can obtain after selecting action a in state s; s(t+1) represents the next state that the agent enters after selecting action a(t) at time t; α is the learning rate, and γ is the discount factor used to measure the importance of future returns.

[0182] Based on environmental feedback and strategy evaluation, the agent can update its strategy to obtain better rewards in future interactions. The updated strategy formula based on value function estimation can be expressed as follows:

[0183] π(t+1)=argmaxQ(s(t),a(t)) (20),

[0184] Among them, π(t+1) represents the strategy at time t+1, and the argmax operation represents the selection of the action that maximizes Q(s(t), a(t)).

[0185] Step 2043: Modeling the intervention mechanism of the system operator

[0186] Under the induction strategy, the agent makes decisions based on its own state, but has no obligation to execute them; the intervention strategy imposes constraints on the agent that must be considered before making a decision. The system operator continuously adjusts the strategy according to the system's goals and state, which can be expressed as follows:

[0187] Intervention t ,J t )= Syatem ,S t ,Goal System > (21),

[0188] Among them, Intervention (R t ​,J t ) represents the intervention mechanism; R t and J t Respectively represent the incentive strategy and intervention strategy of the system; S Syatem Indicates the system state under the action of Agent; S t represents the environmental state at time t; Goal System Represents the goal of the system.

[0189] Step 2044: Update the information list of the department agent and the service system, perform the next cycle iteration, and obtain the emergent characteristics of the AI ​​society;

[0190] The structured representation L4 (System) of the emergent features of the department agent is as follows:

[0191] L4(System)= <L3(Society),Env.,Q t ,N t > (22),

[0192] Where Env. is the interaction between the environment and the department agent; Q t Represents a feedback mechanism from the system to the agent. The agent can extract knowledge and improve decision making; t System intervention strategies adopted for the stable development of the system.

[0193] Step 3: Determine the factors that affect government services, match the corresponding modeling features of the digital government service model according to different influencing factors, and determine the events that cause significant changes in the influencing factors based on the correlation between different influencing factors and corresponding modeling features.

[0194] The specific steps include:

[0195] Step 301, determining the response variables that affect government services;

[0196] In this embodiment, system effectiveness and customer satisfaction can be used;

[0197] System performance is used to evaluate the overall operating performance of the system. It can be obtained by collecting and calculating system performance indicator data monitored by the system (such as server load average, response time average, business processing success rate, etc.). Customer satisfaction summarizes the satisfaction evaluation results of the intelligent agents of the public, calculates the average satisfaction score in different time periods, and understands the customer's satisfaction with government services.

[0198] Step 302: Obtain relevant data of response variables affecting government services;

[0199] Start the multi-agent model, and in each time step, the agents interact according to the behavioral rules. At the same time, data related to influencing factors (such as the number of applications for different types of business services related to social needs, the distribution of application time, and department-related changes in the length of business queues of government department agents, fluctuations in business processing time, and the frequency of collaboration between departments, etc.) and data related to response variables (such as business processing success rate, average processing time, system resource utilization indicators related to system performance, and customer satisfaction-related satisfaction score data of service-oriented agents) are collected.

[0200] Step 303: Perform time series analysis on the acquired data related to the response variables affecting the government services to obtain their evolution process;

[0201] Step 3031: When analyzing the system evolution process, trend analysis can be used to perform time series analysis (such as smoothing data using a moving average method) on system performance indicators (such as business processing success rate and average processing time) and customer satisfaction data to observe their changing trends within the evolution cycle and determine whether they are improving or deteriorating.

[0202] Step 3032: Study the correlation between changes in social demand (such as a substantial increase in the number of business applications), changes in government behavior (such as adjustments to business processing rules), and system performance and customer satisfaction through correlation analysis;

[0203] In this embodiment, correlation analysis may be performed by calculating a correlation coefficient or constructing a regression model.

[0204] Step 3033: Find key events that lead to significant changes in system performance or customer satisfaction (such as a new policy causing a sharp increase in business applications) through key event and turning point identification;

[0205] Step 3034: Analyze the reasons for changes in system performance or satisfaction, and identify turning points in system evolution (such as performance improvement after system upgrade) and related factors and behavioral changes.

[0206] Step 304: Perform auxiliary governance of government services based on the evolution analysis results;

[0207] By performing data analysis on the system evolution results, we can obtain suggestions on performance optimization, functional improvement, risk warning and prevention, etc.

[0208] In terms of performance optimization suggestions, based on the results of system performance analysis, if the business processing time is too long, it can be suggested to optimize the business processing process of government departments, increase personnel or improve system resource performance, and propose dynamic resource allocation plans for unreasonable system resource utilization (such as periodic overload or idleness of the server);

[0209] In terms of functional improvement, based on customer satisfaction analysis, if the public is dissatisfied with the quality of a certain type of service, suggestions are made to improve the business handling process or service method (such as increasing the clarity of the service guide and optimizing the online handling interface);

[0210] In terms of risk warning and prevention, a risk warning indicator system is established based on the analysis of the system evolution process. When the business processing success rate continues to decline or customer satisfaction is below the critical value, timely warnings are issued, prompting relevant departments to take measures (such as personnel training, system function optimization) to prevent serious system problems.

[0211] Embodiment 2

[0212] This embodiment provides an adaptive agent modeling system for digital government services, including:

[0213] A data acquisition module, which is used to obtain business processing data of each government department intelligent body;

[0214] A digital government service modeling module, which is used to construct a digital government service model based on the business processing data of each government department agent; wherein the digital government service model includes multiple layers, each layer models subjects and system characteristics of different complexity; wherein the L1 layer models the basic characteristics of the government department agent, the L2 layer models the evolutionary characteristics of the government department agent based on the modeling characteristics of the L1 layer, the L3 layer models the interaction characteristics between the government department agents based on the modeling characteristics of the L2 layer, and the L4 layer models the emergent characteristics of the AI ​​society based on the modeling characteristics of the L3 layer;

[0215] The governance module is used to determine the factors that affect government services, match the corresponding modeling features of the digital government service model according to different influencing factors, and determine the events that cause significant changes in the influencing factors based on the correlation between different influencing factors and corresponding modeling features.

[0216] Embodiment 3

[0217] This embodiment provides a program product, which is a computer program product, including a computer program. When the computer program is executed by a processor, the steps in the adaptive intelligent agent modeling method for digital government services as described in Example 1 are implemented.

[0218] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive agent modeling method for digital government services, characterized in that: The steps include: Obtain business processing data of intelligent entities in various government departments; Based on the business processing data of the intelligent agents of each government department, a digital government service model is constructed; wherein the digital government service model includes multiple layers, each layer models the subject and system characteristics of different complexity; wherein the L1 layer models the basic characteristics of the intelligent agents of the government departments, the L2 layer models the evolutionary characteristics of the intelligent agents of the government departments based on the modeling characteristics of the L1 layer, the L3 layer models the interaction characteristics between the intelligent agents of each government department based on the modeling characteristics of the L2 layer, and the L4 layer models the emergent characteristics of the AI ​​society based on the modeling characteristics of the L3 layer; Determine the factors that affect government services, match the corresponding modeling features of the digital government service model according to different influencing factors, and determine the events that cause significant changes in the influencing factors based on the correlation between different influencing factors and corresponding modeling features.

2. The adaptive agent modeling method for digital government services according to claim 1, characterized in that: The L1 layer models the basic features of government agency agents, including: Obtain the state information and environmental information list of the government department agent itself; Determine the information type and memory requirements that the government department agent needs to store and retrieve, and save the government department agent's own state information and environmental information list information as "state-behavior" pairs; According to the current "state-behavior" pair, the agent takes corresponding actions to complete the task or adjust its own state and make decisions; According to the decision, the state information and environmental information list data of the government department agent itself are updated to obtain a structured representation of autonomous features.

3. The adaptive agent modeling method for digital government services according to claim 1, characterized in that: The process of modeling the evolutionary characteristics of government agency agents at L2 includes: Based on the basic characteristics of a single government department agent, the genetic evolution of government department agents is modeled; Obtain information about neighboring government department agents, take the capability attributes of each government department agent as a knowledge point, represent each knowledge point as multiple sectors, determine the best sector based on the agent's attributes, and determine the learning reference target for imitation learning based on the combination of the best sectors; Identify study areas; Calculate the survival capabilities of all departmental agents, calculate the fitness values ​​of all departmental agents based on their survival capabilities, select the agents with the highest fitness values ​​in the first N cycles in the learning area, and broadcast the knowledge points of these agents for other agents to learn.

4. The method for modeling an adaptive agent for digital government services according to claim 1, characterized in that: The process of modeling the interaction characteristics between government department agents at L3 includes: Determine the initial communication network topology between the intelligent agents of each government department; If it is collaboration between individuals in government departments, the weights between nodes in the communication network topology structure are updated by recording the relationship list of the department agents that have established contact; If it is the collaboration between individual government departments and the collaborative alliance, determine the collaboration intention of the government department agent and choose whether to join the collaborative alliance; Calculate the profit distribution during the collaboration process and decide whether to adopt a negotiation mechanism based on your own status.

5. The adaptive agent modeling method for digital government services according to claim 4, characterized in that: The profit distribution calculation formula during the collaboration process is: Where Profit(i) is the agent i The income obtained after participating in the cooperation; Cost(i) is the income of Agent i The total cost of participating in the collaboration; Cost total is the total cost of processing an order; Value(i) is the i The normalized effective value created by participating in the collaboration; Value total is the total effective value created during order processing; a is the profit distribution coefficient; Profit total is the total profit gained when the order is completed.

6. The method for modeling an adaptive agent for digital government services according to claim 1, characterized in that: The L4 process of modeling the emergent characteristics of an AI society includes: Define the impact of the environment on government agency agents; The government department agent selects actions based on the current state, interacts with the environment, and obtains immediate rewards and feedback for the next state; Combined with rewards and feedback, the constraints built into the constraints considered before the agent makes a decision are continuously adjusted according to the purpose and status of the system operation, that is, the intervention strategy.

7. The method for modeling an adaptive agent for digital government services according to claim 1, characterized in that: The autonomous feature structure is represented as: L1(Agent)=<R,S t ,E t ,V t ,M t ,D t >, The evolutionary characteristics of the government department agent are structurally represented as follows: L2(Agent)=<L1(Agent),F,Y t >, The interaction characteristics of government department agents are structurally represented as follows: L3(Society)=<L2(Agent),C t ,G t ,P t ,TS>, The emergent characteristics of AI society are structurally represented as follows: L4(System)=<L3(Society),Env.,Q t ,N t >, Among them, R is the property that the Agent maintains stability, S t is the dynamic capability attribute of the agent that changes over time, E t is the agent’s perception ability, V t is the Agent’s responsiveness, M t is the memory capacity of the Agent, D t is the decision-making ability of the agent, F is the prior condition for the agent to learn and evolve, and Y t is the learning ability of the Agent, C t is the communication rule between agents, G t is the cooperation rule between agents, P t is the competition rule between agents, TS represents the system topology, Env. is the interaction between the environment and department agents; Q t represents the feedback mechanism from the system to the Agent, N t System intervention strategies adopted for the stable development of the system.

8. The method for modeling an adaptive agent for digital government services according to claim 1, characterized in that: Factors that affect government services include system performance indicators and customer satisfaction.

9. Adaptive agent modeling system for digital government services, characterized by: include: A data acquisition module, which is used to obtain business processing data of each government department intelligent body; A digital government service modeling module, which is used to construct a digital government service model based on the business processing data of each government department intelligent body; wherein the digital government service model includes multiple layers, each layer models subjects and system characteristics of different complexity; wherein the L1 layer models the basic characteristics of the government department intelligent body, the L2 layer models the evolutionary characteristics of the government department intelligent body based on the modeling characteristics of the L1 layer, the L3 layer models the interaction characteristics between the government department intelligent bodies based on the modeling characteristics of the L2 layer, and the L4 layer models the emergent characteristics of the AI ​​society based on the modeling characteristics of the L3 layer; The governance module is used to determine the factors that affect government services, match the corresponding modeling features of the digital government service model according to different influencing factors, and determine the events that cause significant changes in the influencing factors based on the correlation between different influencing factors and corresponding modeling features.

10. A program product, the program product being a computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps in the adaptive agent modeling method for digital government services as described in any one of claims 1 to 8 are implemented.

Images