Intelligent Application Method and Device of Organizational Knowledge for Responding to Uncertain Events

Abstract

The embodiment of this application provides an intelligent application method and device for organizational knowledge for coping with uncertain events. This method obtains empirical knowledge for coping with uncertain events from historical cases and simulated cases, constructs a knowledge base system based on this empirical knowledge, transforms the empirical knowledge into nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and empirical knowledge of business experts and employees under uncertain events and integrating them into the AI agent design, this method improves the professionalism and reliability of its decision-making, and further promotes the externalization and intelligent application of empirical knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly to an intelligent application method and device for organizational knowledge for coping with uncertain events. Background Art

[0002] An AI Agent (Artificial Intelligence Agent) is an autonomous artificial intelligence program. It can perceive the environment (collect information through sensors, data input, etc.), and make decisions or take actions based on these perceptions to achieve specific goals or tasks. With the rapid development of artificial intelligence technology, AI agents are playing an increasingly important role in various fields (such as healthcare, finance, manufacturing, etc.).

[0003] However, in the context of coping with uncertain events, the occurrence and outcome of events are uncertain, and the relationships with business activities or other relevant factors are also uncertain. Traditional AI agents usually rely on predefined rules and limited decision trees, and it is difficult to cope with complex and changing environments and tasks. Large Language Models (LLMs), with their powerful natural language understanding and generation capabilities, provide new possibilities for building more intelligent and flexible AI agents. In addition, in such situations, by leveraging the complementary capabilities of artificial intelligence and humans, challenges can be effectively addressed through the collaborative approach of human-intelligence synergy.

[0004] However, how to fully exploit the experience and knowledge of business employees and incorporate them into the design of AI agents to generate AI agents that can make collaborative decisions with business employees, and promote the intelligent application of experiential knowledge, remains an urgent problem to be solved. Summary of the Invention

[0005] Aiming at the problems in the prior art, this application provides an intelligent application method and device for organizational knowledge for coping with uncertain events, to enhance the adaptability of AI agents in dynamic environments, enabling AI agents to make more accurate and timely responses in complex and ever-changing environments.

[0006] To solve at least one of the above problems, this application provides the following technical solutions:

[0007] In a first aspect, this application provides an intelligent application method for organizational knowledge for coping with uncertain events, including:

[0008] Obtain experiential knowledge for coping with uncertain events, and extract key features from the experiential knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision logics;

[0009] Establish a context model based on the collaborative context meta-model, associate the uncertain events, business contexts, collaborative participants with the context model to form decision knowledge nodes; define the relationships between the decision knowledge nodes according to the process steps and the decision logic, and build a knowledge base system based on the decision knowledge nodes and the relationships between the decision knowledge nodes;

[0010] Retrieve the knowledge base system to obtain the decision knowledge nodes for various uncertain events and the relationships between the decision knowledge nodes; generate a task chain and a thinking chain for the AI Agent based on the decision knowledge nodes for various uncertain events and the relationships between the decision knowledge nodes; generate an AI Agent based on the task chain and the thinking chain;

[0011] Receive the input command from the user, and parse the input command through the AI Agent; the AI Agent reasons based on the task chain and the thinking chain to generate decision suggestions for the parsed results, and generates a decision plan for coping with uncertain events based on the task chain.

[0012] Furthermore, the steps of obtaining the empirical knowledge for coping with uncertain events include:

[0013] Obtain a review file through the guidance of the uncertain event response review, and obtain the first empirical knowledge of the uncertain event from the review file;

[0014] Use the large language model to parse the historical data to obtain the second empirical knowledge of the uncertain event; the historical data includes historical cases and meeting minutes.

[0015] Furthermore, the steps of associating the uncertain events, business contexts, collaborative participants with the context model to form decision knowledge nodes include:

[0016] Use the uncertain event as a trigger condition to achieve dynamic response through the event-driven node in the context model;

[0017] Obtain the operation data related to the business context, and convert the operation data into the dynamic constraint variables of the context model;

[0018] Define the collaborative participants as the role nodes in the context model and bind their decision-making authorities.

[0019] Furthermore, the steps of defining the relationships between the decision knowledge nodes according to the process steps and the decision logic include:

[0020] Disassemble the decision logic into a logical chain between decision conditions and execution actions, convert the logical chain into causal rules, establish a deterministic mapping between event trigger conditions and disposal measures, and form an initial causal rule base;

[0021] Establish a variable causal relationship template based on the initial causal rule base, allowing for dynamic adjustment of causal strength according to the business scenario, and support the simulation of possible future causal relationships by embedding a causal inference engine;

[0022] It also includes: disassembling the process steps into independent decision knowledge nodes, analyzing the timing constraints between operations in the process steps, extracting process sequence features, and converting the process sequence features into a timing dependence chain between the decision knowledge nodes to obtain a time dependence relationship.

[0023] Further, the steps of generating a task chain and a thinking chain for an AI Agent based on the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes include:

[0024] Decompose the execution process for uncertain events into a series of subtasks, determine the execution order and dependence relationships between the subtasks, and generate a task chain for the AI Agent;

[0025] Based on the decision logic for uncertain events, combined with the chain-of-thought method, design a perception thinking chain, a memory thinking chain, and a reasoning thinking chain, and construct an inference path for the AI Agent to obtain a thinking chain for the AI Agent;

[0026] Specify an associated set of thinking chain nodes for each subtask in the task chain to form a mapping relationship table.

[0027] Further, the steps of generating an AI Agent based on the task chain and the thinking chain include:

[0028] Define a set of ability dimensions for the AI Agent according to the subtask types in the task chain, and construct an Agent feature vector based on the ability dimensions;

[0029] Adopt the LangChain framework to construct an Agent model architecture, and the Agent model architecture includes a core inference module, a task execution module, a tool invocation module, and a memory management module;

[0030] Compress the Agent model through knowledge distillation technology and dynamically select the model version according to the hardware resources to obtain the final AI Agent.

[0031] Further, the steps of the AI Agent reasoning based on the task chain and the thought chain to generate decision suggestions for the parsed results and generating a decision-making plan for dealing with uncertain events based on the task chain further include: recording the interaction content between the AI Agent and the user, extracting new decision-making experiences from the interaction content, and optimizing the knowledge base system based on the new decision-making experiences.

[0032] In a second aspect, the present application provides an intelligent application device for organizational knowledge for dealing with uncertain events, including:

[0033] A knowledge extraction module, configured to obtain experience knowledge for dealing with uncertain events and extract key features from the experience knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logics;

[0034] A knowledge base system construction module, configured to establish a scenario model based on a collaborative scenario meta-model, associate the uncertain events, business scenarios, and collaborative participants with the scenario model to form decision-making knowledge nodes; define the relationships between the decision-making knowledge nodes according to the process steps and the decision-making logics, and construct a knowledge base system based on the decision-making knowledge nodes and the relationships between the decision-making knowledge nodes;

[0035] An AI Agent generation module, configured to retrieve the knowledge base system to obtain the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate a task chain and a thought chain for the AI Agent based on the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate an AI Agent based on the task chain and the thought chain;

[0036] An interaction module, configured to receive an input command from a user and parse the input command through the AI Agent; the AI Agent reasons based on the task chain and the thought chain to generate decision suggestions for the parsed results and generates a decision-making plan for dealing with uncertain events based on the task chain.

[0037] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the steps of the intelligent application method for organizational knowledge for dealing with uncertain events as described above are implemented.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the intelligent application method for organizational knowledge for dealing with uncertain events as described above are implemented.

[0039] Fifth aspect, the present application provides a computer program product, including a computer program / instructions, which when executed by a processor, implement the steps of the above-mentioned intelligent application method of organizational knowledge for coping with uncertain events.

[0040] As can be seen from the above technical solutions, the present application provides an intelligent application method and device for organizational knowledge for coping with uncertain events. This method obtains empirical knowledge for coping with uncertain events from historical cases and simulated cases, constructs a knowledge base system based on this empirical knowledge, transforms the empirical knowledge into nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and empirical knowledge of business experts and employees under uncertain events and integrating them into the AI agent design, the professionalism and reliability of its decision-making are improved, thereby promoting the externalization and intelligent application of empirical knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is one of the flow diagrams of the intelligent application method of organizational knowledge for coping with uncertain events in the embodiments of the present application;

[0043] Figure 2 It is another flow diagram of the intelligent application method of organizational knowledge for coping with uncertain events in the embodiments of the present application;

[0044] Figure 3 It is yet another flow diagram of the intelligent application method of organizational knowledge for coping with uncertain events in the embodiments of the present application;

[0045] Figure 4 It is the structure diagram of the intelligent application device of organizational knowledge for coping with uncertain events in the embodiments of the present application;

[0046] Figure 5 It is the structure diagram of the electronic device in the embodiments of the present application.

[0047] Reference Signs:

[0048] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. Detailed implementation manners

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0050] In the technical solutions of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant provisions of national laws and regulations.

[0051] Considering the problems existing in the prior art, the present application provides an organizational knowledge intelligent application method and device for coping with uncertain events. The method obtains experience knowledge for coping with uncertain events from historical cases and simulated cases, constructs a knowledge base system based on the experience knowledge, converts the experience knowledge into nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and experience knowledge of business experts and employees in uncertain events and integrating them into the AI agent design, the professionalism and reliability of its decision-making are improved, thereby promoting the externalization and intelligent application of experience knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments.

[0052] To enhance the adaptability of the AI agent in a dynamic environment and enable the AI agent to make more accurate and timely responses in complex and ever-changing environments, the present application provides an embodiment of an organizational knowledge intelligent application method for coping with uncertain events. Refer to Figures 1 - 3 , the organizational knowledge intelligent application method for coping with uncertain events specifically includes the following contents:

[0053] Step S101: Obtain experience knowledge for coping with uncertain events, and extract key features from the experience knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logic.

[0054] Optionally, experiential knowledge is extracted from simulation cases and historical data within the enterprise. Specifically, a review file is obtained through the review guidance of uncertain event response, and the first experiential knowledge of uncertain events is obtained from the review file; the historical data is parsed using a large language model to obtain the second experiential knowledge of uncertain events; the historical data includes historical cases and meeting minutes.

[0055] Exemplary:

[0056] (1) Guidance on reviewing and responding to uncertain events

[0057] Starting from the six dimensions of uncertain events, business scenarios, decision-making objectives, collaborative participants, decision-making basis, and decision-making behavior, offline workshops are organized, integrating brainstorming and scenario simulations to guide sales experts and employees to review and replay the response process of uncertain events, and to create a review document for uncertain event response. In this way, the experience of experts and employees in dealing with similar uncertain events is tapped, and response strategies and decision-making processes are identified and extracted. This experiential knowledge will support the generation of AI agents. This includes:

[0058] (a) Determine the review objectives and framework:

[0059] Goal setting: The main goal of the review is to explore effective response strategies, experiences and decision-making logic by reviewing the response process of uncertain events, so as to provide support for the subsequent generation of AI agents.

[0060] Framework design: Organize the review work according to the following six dimensions:

[0061] Uncertain events: Define the characteristics of events, such as suddenness, complexity, and scope of impact.

[0062] Business context: Identify the business context in which the event occurred.

[0063] Decision-making objectives: Discuss decision-making objectives, such as minimizing losses, improving efficiency, and ensuring rational allocation of resources.

[0064] Collaborative participants: Identify the roles of all parties involved in the incident response process, such as business department heads, management, technical support teams, etc.

[0065] Decision Basis: Identify the data, rules, and criteria used in the decision-making process.

[0066] Decision-making behavior: Review the actual decision-making actions taken during the incident response process and their effects.

[0067] (b) Organising workshops and interactive sessions, which may be carried out through the following means:

[0068] Offline Workshop Organization: Invite business experts, department heads, and relevant employees to participate together to ensure that the review covers all aspects of the business perspective.

[0069] Scenario Simulation: Simulate the scenario of the event occurrence, allowing participants to play different roles and experience the process of coping with uncertain events. Scenario simulation includes online simulation and offline simulation. Through scenario simulation, it helps employees better review and understand the decision-making steps and strategies in actual coping.

[0070] Brainstorming: Guide experts and employees to conduct brainstorming, propose the coping strategies they think are the most effective, and explore potential optimization solutions and improvable decision-making processes.

[0071] (c)Induction and Sorting of Coping Experiences:

[0072] Record the Review Process: During the review process, ensure that all discussions and feedback are recorded in detail, especially the key points regarding the decision-making basis, behaviors, and outcomes.

[0073] Summarize Key Experiences: Integrate the feedback from business experts and employees to summarize the key strategies and best practices for coping with uncertain events. These experiences will support the subsequent generation of AI agents.

[0074] Extraction of Experiential Knowledge: During the review process, clarify which are explicit knowledge (such as established norms, standard operating procedures, etc.) and which are tacit knowledge (such as employees' personal experiences, intuitive judgments, etc.).

[0075] (d)Form a Review Document: Based on the key decision points, experiential strategies, action steps, etc. extracted during the review process, compile a review document for coping with uncertain events.

[0076] (2)Extraction of Experiential Knowledge

[0077] Based on the review document of uncertain events and the explicit knowledge (such as rules and regulations, cases, etc.) and tacit knowledge (such as meeting minutes or recordings, etc.) in the organization, extract knowledge such as the scenarios, personnel, business behaviors, and goals for coping with uncertain events, further including the following steps:

[0078] (a)Explicit Knowledge Extraction: Utilize the natural language processing ability of the LLM to parse the order management rules and regulations within the enterprise, historical order case documents, etc. Through techniques such as text segmentation, entity recognition, and relationship extraction, extract key decision-making events (such as order priority setting, production plan adjustment, financial budget adjustment, etc.), decision-making logics (such as order sorting strategies based on profit margins and delivery times), process steps (such as order reception, review, production scheduling processes), etc. This information is stored in the explicit knowledge base in a structured form for subsequent retrieval and application.

[0079] The specific technical solution includes using pre-trained BERT or large language models for text segmentation and sentence boundary detection to perform high-precision paragraph and sentence segmentation on long documents; using large models for named entity recognition to identify key entities such as people, decision-making situations, behaviors, and goals; identifying the semantic relationships between entities through the semantic understanding ability of large models; and storing the extracted explicit knowledge in a non-relational database such as MongoDB or a graph database like Neo4j to support subsequent queries and analyses.

[0080] (b)Tacit knowledge extraction: Using speech recognition technology to convert order management meeting recordings, employee discussion records, etc. into text, and then using LLM technology for topic modeling and sentiment analysis to extract the experiences, insights, and suggestions of business employees and experts in order selection. For example, from a meeting on order priority adjustment, extract the employees' experiences and suggestions on "flexibly adjusting order priorities to meet sudden demands" and the experts' insights on "optimizing order combinations to maximize profits". These tacit knowledge are stored in the tacit knowledge base in the form of key elements and decision-making logics to supplement and enrich the content of the explicit knowledge base.

[0081] The specific technical solution includes using, for example, Wav2Vec 2.0 for high-precision speech-to-text conversion. Applying large models for word segmentation, part-of-speech tagging, and denoising processing to clean and standardize the transcribed text; identifying the key decision-making elements and logical relationships in the text through dependency syntactic analysis and semantic role annotation supported by large models, and finally storing the extracted tacit knowledge in a non-relational database such as MongoDB or a graph database like Neo4j to support complex queries and correlation analyses.

[0082] Step S102: Establish a context model based on the collaborative context meta-model, associate the uncertain events, business contexts, and collaborative participants with the context model to form decision knowledge nodes; define the relationships between decision knowledge nodes according to the process steps and the decision-making logic, and construct a knowledge base system based on the decision knowledge nodes and the relationships between the decision knowledge nodes.

[0083] Optionally, establishing a context model based on the collaborative context meta-model includes:

[0084] Extract context knowledge based on the review knowledge of uncertain event responses, and define different decision-making context categories and attributes for order selection, such as "high-profit order priority selection context", "urgent order priority selection context", "order adjustment context under resource shortage", etc.

[0085] Based on the collaborative context meta-model, a corresponding context model is established (the elements are as follows) to call the corresponding decision-making knowledge in different uncertain event response scenarios. For example, in the "high-profit order priority selection scenario", the context model will include attributes such as order profit margin, production resource availability, and delivery time to provide decision-making references for AI Agents.

[0086] Elements of the context model:

[0087] Goal: Describe the business goal of this collaborative scenario.

[0088] Collaborative participants: When conducting business in this scenario, internal and external personnel within the department are required to participate. These personnel are closely related to this scenario or need to provide support.

[0089] Business context: Clearly define the business background when the event occurs.

[0090] Goal: Describe the goals that collaborative participants need to achieve in the collaborative context.

[0091] Activities: Some activities that need to be carried out to complete this scenario. These activities may require the joint participation of scenario participants.

[0092] Capabilities: Describe some capabilities or knowledge required for collaborative participants to perform activities.

[0093] Resources: Describe the data required for collaborative participants to perform activities.

[0094] Optionally, in this embodiment, the steps of associating the uncertain event, business context, collaborative participants with the context model to form decision-making knowledge nodes include: using the uncertain event as a trigger condition to achieve dynamic response through the event-driven node in the context model; obtaining operation data related to the business context and converting the operation data into dynamic constraint variables of the context model; defining the collaborative participants as role nodes in the context model and binding their decision-making authorities.

[0095] In this embodiment, key features (such as event types, participants, etc.) are essentially discrete abstractions of real-world elements, but lack the ability to express the following dynamic elements, such as: the real-time state of the business context (such as inventory fluctuations, market changes); the dynamic adjustment of the permissions of collaborative participants (such as temporarily increasing the approval level in crisis mode); the temporal constraints of process steps (such as task A must be started after task B is completed). If nodes are directly formed based on key features, they will become static knowledge fragments and cannot adapt to environmental changes. Therefore, the context model injects context awareness capabilities into decision-making knowledge nodes through the following mechanisms: dynamic constraint variables (such as real-time inventory levels, supplier risk ratings); event-driven responses (such as automatically activating associated nodes when a sensor alarm is triggered); role-permission bindings (such as differences in operation permissions for participants at different ranks). This dynamic association enables nodes to automatically adjust their logical behavior according to changes in the context.

[0096] Exemplarily, uncertain events in the knowledge base system are classified into discrete events and persistent events according to attributes. The CEP (Complex Event Processing) engine is used to define event patterns. When an event is triggered, a preset action interface (such as REST API) is called, and event context parameters are passed; real-time streams such as sensors and trading systems are accessed through Apache Kafka, and batch data such as inventory and orders are synchronized from the ERP system daily, and the JSON Schema is defined to constrain the variable structure to obtain variable generation rules; dynamic permission rules for policy formulation are defined based on the ABAC (Attribute-Based Access Control) model. The binding method is to attach a JWT token to the role node in the context model, which contains encrypted permission declarations. Exemplarily, when an Agent initiates an operation request, the JWT token is decrypted and the permission list is extracted, and the actual available permissions are dynamically calculated according to the current business context parameters (such as risk level, resource type). If the permissions are insufficient, the approval chain route is triggered (such as sending an authorization request to a higher-rank role).

[0097] Optionally, in the mechanism for converting decision logic into causal relationships in this embodiment, it is mainly achieved through structured modeling at the following three levels:

[0098] I. Causal Inference Based on Expert Experience

[0099] 1. Deconstruction of Decision Behavior

[0100] Through the decision-making records of experts in specific situations (such as the selection of emergency response processes, the judgment of resource scheduling priorities), the logical dependence relationship between decision conditions and execution actions is extracted. For example, in emergency response, the disposal steps of the "material shortage" event by experts imply a causal chain of "resource allocation delay → rescue efficiency decline".

[0101] 2. Formal Expression of Rules

[0102] Convert the emergency response plan clauses formulated by experts (such as "initiate a Class B response when the risk indicator of Type A exceeds the threshold") into If-Then causal rules to establish a deterministic mapping between event trigger conditions and disposal measures. This conversion needs to be parameterized and modeled in combination with the spatio-temporal constraints (such as the disaster impact range) in the business scenario.

[0103] II. Data-Driven Causal Discovery

[0104] 1. Analysis of Organizational Operation Data

[0105] Use large language models to analyze unstructured data such as historical event reports and communication records, and identify frequently occurring "event feature - disposal action - result feedback" triples. For example, extract the causal sequence of "equipment failure → production interruption → emergency repair" from accident reports.

[0106] 2. Causal Diagram Construction

[0107] Through Bayesian networks, quantify the probabilistic causal relationships between the behaviors of collaborative participants (such as the response speed of departments), the states of process nodes (such as the completion degree of approvals), and the evolution results of events (such as the degree of risk diffusion). This conversion needs to integrate the multi-source signal correlation features in situation awareness.

[0108] III. Dynamic Adaptation of the Situation Model

[0109] 1. Causal Chain Reconstruction Mechanism

[0110] Establish a variable causal relationship template in the knowledge base system, allowing for dynamic adjustment of causal intensity according to business scenario characteristics (such as disaster types, organizational structures). For example, in different scenarios of the epidemic and earthquake, the causal relationship weights between "information lag" and "decision-making errors" will change.

[0111] 2. Counterfactual Reasoning Support

[0112] By embedding a causal inference engine, support the simulation of causal relationships that have not occurred but may exist (such as "if the evacuation process is initiated 2 hours in advance, the casualty rate will be reduced by X%"). This ability depends on the spatio-temporal deduction module in the situation model.

[0113] In this embodiment, the conversion mechanism realizes the transition from discrete decision-making steps to a continuous causal network by integrating human causal cognition and machine causal discovery, and can improve the predictability and interpretability of emergency decision-making.

[0114] Optionally, in this embodiment, the structured method for time-dependent relationships is as follows:

[0115] (1) Decomposition of Process Steps

[0116] Adopt the atomization method, use the Business Process Model and Notation (BPMN) to parse the flow chart, and extract key nodes (such as "purchase application approval", "logistics scheduling"), node attributes (executing role, input / output data, time-consuming threshold).

[0117] (2) Temporal Constraint Analysis

[0118] Identify the types of dependencies: strong sequential dependency (node B must strictly start after node A is completed, processing strategy: execute serially, set checkpoints), weak parallel dependency (node C and node D can proceed simultaneously, processing strategy: enable multi-threading, resource contention control), conditional trigger dependency (node E is only activated under specific conditions, processing strategy: event listening + callback mechanism)

[0119] (3) Time Dependency Chain Generation

[0120] Adopt the timed Petri net to transform the process sequential characteristics into a state transition model with time constraints.

[0121] In this embodiment, the design of this time dependency relationship realizes the optimality of process executability and efficiency, avoids logical deadlocks through temporal constraints, and helps with accurate resource allocation through critical path analysis.

[0122] Optionally, in addition to the time dependency relationship, this database system also includes data dependency relationships (the input data of node B must come from the output result of node A), which can be realized by defining input / output interfaces through data flow diagrams (DFDs), etc.; resource dependency relationships (multiple nodes compete for the same resource pool (such as equipment, manpower, budget)), which can be realized by means of mutexes and priority scheduling algorithms, etc.; permission dependency relationships (node execution requires authorization by a specific role), which can be realized by means of an RBAC (role-based access control) policy library, etc.; logical dependency relationships (execution condition constraints based on business rules), which can be realized by loading business rules through a Drools rule engine, etc.

[0123] Optionally, this embodiment also includes data service knowledge analysis: sort out the data sources inside the enterprise (such as ERP systems) and outside (such as market demand prediction data, supplier delivery capacity data), and determine the data support required for order selection decisions. Establish a data pragmatic context model to ensure the accuracy and timeliness of data during the decision-making process. For example, in the decision-making process of selecting high-profit orders, the AI Agent needs to access the order profit margin data in the order management system and the resource availability data in the production planning system to make reasonable order selection suggestions.

[0124] Optionally, in this embodiment, the construction of the knowledge base system includes: classifying and tagging the knowledge of dealing with uncertain events according to aspects such as requirements (including the AI agent requirements of business employees), roles (including business employees, tasks, responsibilities, action guidelines, decision-making styles), tasks and goals (including specific task points and goals), scenarios (uncertain event decision scenarios), and behaviors (including decision-making methods, knowledge, and knowledge types involved in specific tasks). Specifically:

[0125] Classification: Classify knowledge according to dimensions such as tasks, roles, scenarios, and goals. For example, tasks can be classified into "order processing", "production scheduling", "financial review", etc., and scenarios can be classified into "order urgency", "resource availability", etc.

[0126] Tagging: Tag each category of knowledge for quick retrieval and search. For example, under the "order processing" category, tags can include "high-profit orders", "order priority", "inventory shortage", etc.

[0127] Step S103: Retrieve the knowledge base system to obtain the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes; generate a task chain and a thinking chain for the AI Agent based on the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes; generate an AI Agent based on the task chain and the thinking chain.

[0128] Optionally, in this embodiment, task chain design: According to a specific decision scenario, retrieve relevant decision nodes and processes from the knowledge base, and design the task chain that the AI Agent needs to execute when dealing with this decision. The task chain includes steps such as planning, decision-making, and action to ensure that the AI Agent can systematically complete the task of dealing with uncertain events. Thinking chain construction: Based on the knowledge base, retrieve key decision scenarios and decision logics, and combine the Chain-of-Thought (CoT) method to design perception, memory, and reasoning thinking chains to construct the reasoning path of the AI Agent. Improve the decision transparency and interpretability of the AI Agent.

[0129] Optionally, in this embodiment, the method for generating the task chain includes:

[0130] (1) Sub-task decomposition method

[0131] Input the process step attributes in the decision knowledge node (such as "purchase approval → risk assessment → plan execution"), each sub-task needs to meet the single responsibility principle (such as "purchase approval" can be split into "form verification" and "budget check"), and mark the dependency relationship, and output the task chain structure represented by a DAG (directed acyclic graph).

[0132] (2) Execution order and dependency definition

[0133] Extract timestamp data (such as the average time taken for historical tasks) from the process sequence features of the knowledge base, calculate the critical path (CPM algorithm), determine the sequence of subtasks that cannot be delayed, and classify the dependencies (strong sequential dependency, resource competition dependency, conditional trigger dependency).

[0134] The generation method of the thought chain includes:

[0135] (1) Implementation of the chain-of-thought method

[0136] Perceptual thought chain design: Define a unified data schema (Apache Avro Schema), including fields: event type, sensor ID, timestamp, value, implement standardized data input, and define anomaly detection rules.

[0137] Memory thought chain design: Adopt hybrid retrieval (vector + keyword) as the knowledge retrieval strategy, and set the knowledge validity period (for example, if a case has not been used for more than 2 years, the similarity weight is reduced by 50%).

[0138] Inference thought chain design: Causal inference engine: Integrate the DoWhy library and perform four-step causal inference: model the causal graph (based on the causal relationships in the knowledge base), identify the estimator (such as ATE average treatment effect), estimate the causal effect, and refute and verify (through sensitivity tests by adding unobserved confounding factors).

[0139] (2) Inference path construction

[0140] Path priority calculation: Dynamically sort based on the confidence of knowledge nodes and causal strength.

[0141] Multi-path parallel exploration: Adopt Monte Carlo Tree Search (MCTS), explore the Top-3 high-weight paths within a limited time, and finally select the one with the highest comprehensive score.

[0142] The binding mechanism between the task chain and the thought chain includes:

[0143] (1) Mapping relationship definition

[0144] Establish the index relationship between the task chain nodes and the thought chain nodes, and convert the logical conditions in the thought chain (such as "inventory safety factor < 0.5") into the execution trigger conditions of the task chain.

[0145] (2) Real-time collaborative control

[0146] When a subtask in the task chain fails, it can trace back to the corresponding reasoning node in the thought chain, initiate an alternative reasoning path (such as downgrading from "causal reasoning" to "rule matching"), generate a new branch of the task chain, and reschedule.

[0147] Optionally, the generation of the task chain and the thought chain also includes: the expert's corrective operations on the AI decision results (such as manually adjusting the priority of the plan) are transmitted back to the knowledge base in real time, triggering incremental learning of the task chain and the thought chain.

[0148] Optionally, the steps of generating an AI Agent based on the task chain and the thought chain include:

[0149] Agent Capability Portrait Modeling: According to the subtask types in the task chain, define the set of ability dimensions of the AI Agent (including: Perception Dimension: data collection frequency (per second / batch processing), multi-source data types (text / sensor / image); Reasoning Dimension: logical chain depth (single-step / multi-step backtracking), uncertainty handling method (probability threshold / fuzzy logic); Execution Dimension: action response speed (real-time / delayed), operation permission level (read-only / control instruction)), and construct an Agent feature vector based on the ability dimensions.

[0150] Modular Agent Component Assembly: Use the LangChain framework to build a pluggable Agent architecture, specifically including: Core Inference Module: Rely on the reasoning logic path in the thought chain, inject domain knowledge based on the GPT-4 model, and use the LoRA (Low-Rank Adaptation) fine-tuning technique to stack a rank decomposition matrix on the pre-trained weights; Task Execution Module: Define a Toolset for each subtask, including: Data Query Tool: Access the knowledge base through SQL / NoSQL connectors, Logic Verification Tool: Call the causal inference engine to verify the rationality of the decision chain, External Interaction Tool: Package enterprise APIs (such as the work order creation interface of the ERP system); Tool Invocation Module: Interact with external tools to call tools such as search engines, database query tools, mathematical operation tools, and code executors for task execution; Memory Management Module: Design a hierarchical memory structure: Short-term Memory: Use the LRU eviction policy to cache the recent interaction context, Long-term Memory: Persist the verified decision plan to the knowledge base.

[0151] Lightweight Deployment Optimization: Compress the Agent model through knowledge distillation technology, including: Teacher Model Selection: Retain the full version of GPT-4 as the teacher model, Student Model Construction: Use the TinyBERT architecture and design the distillation loss function. Dynamically select the model version according to the hardware resources during deployment.

[0152] In this embodiment, by involving business experts and employees in task chain and decision design, the tacit knowledge of business experts and employees is embedded in the task chain and the thinking chain, enhancing the professionalism and adaptability of the AI Agent in specific decision-making scenarios.

[0153] In this stage, relevant knowledge is first retrieved from the knowledge base for task chain and thinking chain design. First, according to the specific decision-making scenario, relevant decision nodes and processes are retrieved from the knowledge base to design the task chain that the AI Agent needs to execute when handling this decision. The task chain includes steps such as planning, decision-making, and action to ensure that the AI Agent can systematically complete the task of coping with uncertain events. In addition, based on the knowledge base retrieval of key decision-making scenarios and decision-making logics, combined with the Chain-of-Thought (CoT) method, a perception, memory, and reasoning thinking chain is designed to construct the reasoning path of the AI Agent, improving the decision-making transparency and interpretability of the AI Agent. Finally, by involving business experts and employees in task chain and decision design, the tacit knowledge of business experts and employees is embedded in the task chain and the thinking chain, enhancing the professionalism and adaptability of the AI Agent in specific decision-making scenarios.

[0154] Step S104: Receive the input command from the user and parse the input command through the AI Agent; the AI Agent infers and generates decision suggestions based on the parsed result according to the task chain and the thinking chain, and generates a decision plan for coping with uncertain events based on the task chain.

[0155] Optionally, in this embodiment, the AI Agent includes a perception module, an inference module, a decision-making module, and an execution module, enabling the Agent to perceive the business environment, make reasoning decisions, and execute corresponding operations. The modules interact through interfaces to ensure the flexibility and scalability of the system. Among them, the perception module, based on the perception thinking chain, identifies the current business environment and user input, including functions such as natural language understanding, situation recognition, and data collection. The inference module, based on the inference thinking chain and the task chain, conducts logical reasoning and information analysis to generate preliminary decision suggestions. The decision-making module, based on the task chain, combines the comprehensive inference result and business requirements to generate specific decision plans. The execution module, based on the task chain, executes the decision plan, such as generating reports, sending notifications, or calling external system interfaces for operations (such as calling a code interpreter for relevant analysis tasks). In this stage, the system integration ability of the LangChain framework is used to construct the overall architecture of the AI Agent. The entire system conducts data interaction and function calls through a unified interface to ensure the efficient operation and stability of the AI Agent.

[0156] In this embodiment, the multi-round natural language interaction mechanism between the AI Agent and business personnel optimizes the decision-making process and results through continuous feedback and learning. For example, business personnel can adjust the order priority criteria through dialogue, and the AI Agent regenerates the order selection plan according to the new criteria and provides corresponding analysis and reasons. By recording and analyzing the data in the interaction process, the decision-making model and reasoning logic of the AI Agent are continuously optimized to ensure that it can meet the personalized needs of business personnel.

[0157] In the process of order selection decision-making, business employees and the AI Agent make collaborative decisions in the form of dialogue, recording all interaction contents, including dialogue texts, decision-making processes, and feedback opinions. Using natural language understanding technology, analyze the interaction logs, and extract new experiences, improvement suggestions, and uncovered knowledge points of business employees in the decision-making process. According to the empirical knowledge and the business needs of business employees, retrain and optimize the AI Agent, and update the knowledge base. For example, analyze the common decision-making biases in the order selection process, optimize the decision-making rules of the AI Agent, reduce the influence of human factors, and improve the scientificity and consistency of decision-making.

[0158] To enhance the adaptability of the AI agent in a dynamic environment and enable the AI agent to make more accurate and timely responses in a complex and ever-changing environment, this application provides an embodiment of an organizational knowledge intelligent application device for implementing all or part of the content of the organizational knowledge intelligent application method for coping with uncertain events. See Figure 4 , the organizational knowledge intelligent application device for coping with uncertain events specifically includes the following contents:

[0159] Knowledge extraction module 10, used to obtain empirical knowledge for coping with uncertain events and extract key features from the empirical knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logic;

[0160] Knowledge base system construction module 20, used to establish a scenario model based on the collaborative scenario meta-model, associate the uncertain events, business scenarios, and collaborative participants with the scenario model to form decision-making knowledge nodes; define the relationships between decision-making knowledge nodes according to the process steps and the decision-making logic, and construct a knowledge base system based on the decision-making knowledge nodes and the relationships between the decision-making knowledge nodes;

[0161] The AI Agent generation module 30 is configured to retrieve the knowledge base system to obtain the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate a task chain and a thinking chain for the AI Agent based on the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; and generate an AI Agent based on the task chain and the thinking chain.

[0162] The interaction module 40 is configured to receive an input command from a user and parse the input command through the AI Agent; the AI Agent reasons based on the task chain and the thinking chain to generate a decision recommendation for the parsed result and generate a decision-making plan for coping with uncertain events based on the task chain.

[0163] As can be seen from the above description, the intelligent application device for organizational knowledge for coping with uncertain events provided by the embodiments of the present application obtains experience knowledge for coping with uncertain events from historical cases and simulation cases, constructs a knowledge base system based on the experience knowledge, transforms the experience knowledge into the nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and experience knowledge of business experts and employees in uncertain events and integrating them into the AI agent design, the professionalism and reliability of its decision-making are improved, thereby promoting the externalization and intelligent application of experience knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments.

[0164] From a hardware perspective, in order to achieve precise lighting adjustment control, break through the limitations of traditional fixed-mode dimming, and provide a comprehensive technical solution for the intelligent lighting system, the present application provides an embodiment of an electronic device for implementing all or part of the content in the method for intelligent application of organizational knowledge for coping with uncertain events, and the electronic device specifically includes the following content:

[0165] A processor, a memory, a communications interface, and a bus; wherein, the processor, the memory, and the communications interface communicate with each other through the bus; the communications interface is used to implement information transmission between the intelligent application device of organizational knowledge for coping with uncertain events and related devices such as a core business system, a user terminal, and a related database, etc.; the logic controller may be a desktop computer, a tablet computer, a mobile terminal, etc., and this embodiment is not limited thereto. In this embodiment, the logic controller may be implemented with reference to the embodiments of the method for intelligent application of organizational knowledge for coping with uncertain events and the embodiments of the device for intelligent application of organizational knowledge for coping with uncertain events in the embodiments, the content of which is incorporated herein, and the repeated parts will not be elaborated again.

[0166] It can be understood that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0167] In practical applications, part of the method for intelligent application of organizational knowledge for coping with uncertain events may be executed on the electronic device side as described above, or all operations may be completed in the client device. Specifically, it can be selected according to the processing capacity of the client device and the limitations of the user usage scenario, etc. This application does not make any limitations in this regard. If all operations are completed in the client device, the client device may further include a processor.

[0168] The above-mentioned client device may have a communication module (i.e., a communication unit), and may be communicatively connected to a remote server to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementation scenarios, it may also include a server of an intermediate platform, such as a server of a third-party server platform communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster composed of multiple servers, or a server structure of a distributed device.

[0169] Figure 5 It is a schematic block diagram of the system composition of the electronic device 9600 according to an embodiment of the present application. As Figure 5 shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It should be noted that this Figure 5 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0170] In one embodiment, the function of the intelligent application method of organizational knowledge for coping with uncertain events can be integrated into the central processing unit 9100. Among them, the central processing unit 9100 can be configured to perform the following controls:

[0171] Step S101: Obtain the empirical knowledge for coping with uncertain events, and extract key features from the empirical knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logics;

[0172] Step S102: Establish a situation model based on the collaborative situation meta-model, associate the uncertain event, business scenario, and collaborative participants with the situation model to form decision-making knowledge nodes; define the relationships between the decision-making knowledge nodes according to the process steps and the decision-making logics, and construct a knowledge base system based on the decision-making knowledge nodes and the relationships between the decision-making knowledge nodes;

[0173] Step S103: Retrieve the knowledge base system to obtain the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate a task chain and a thinking chain for the AI Agent based on the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate an AI Agent based on the task chain and the thinking chain;

[0174] Step S104: Receive the input command of the user, and parse the input command through the AI Agent; the AI Agent infers and generates decision-making suggestions based on the results of the parsing based on the task chain and the thinking chain, and generates a decision-making plan for coping with uncertain events based on the task chain.

[0175] As can be seen from the above description, the electronic device provided by the embodiment of the present application obtains the empirical knowledge for coping with uncertain events from historical cases and simulation cases, constructs a knowledge base system based on the empirical knowledge, transforms the empirical knowledge into the nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and empirical knowledge of business experts and employees under uncertain events and integrating them into the AI agent design, the professionalism and reliability of its decision-making are improved, thereby promoting the externalization and intelligent application of empirical knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments.[[ID=ID=18]]

[0176] In another embodiment, the intelligent application device of organizational knowledge for coping with uncertain events can be separately configured from the central processing unit 9100. For example, the intelligent application device of organizational knowledge for coping with uncertain events can be configured as a chip connected to the central processing unit 9100, and the functions of the intelligent application method of organizational knowledge for coping with uncertain events can be realized through the control of the central processing unit.

[0177] As Figure 5 shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It should be noted that the electronic device 9600 does not necessarily have to include Figure 5 all the components shown in Figure 5 ; in addition, the electronic device 9600 may further include

[0178] As Figure 5 shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The central processing unit 9100 receives inputs and controls the operations of the various components of the electronic device 9600.

[0179] Among them, the memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory, or other suitable devices. The above information related to failures can be stored, and in addition, programs for executing relevant information can also be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0180] The input unit 9120 provides inputs to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to supply power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display can be, for example, an LCD display, but is not limited thereto.

[0181] The memory 9140 can be a solid-state memory, such as, for example, a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that stores information even when power is off, can be selectively erased and has more data. Examples of such a memory are sometimes referred to as EPROMs, etc. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 can include an application / function storage unit 9142 for storing application programs and function programs or the processes for operating the electronic device 9600 by the central processing unit 9100.

[0182] The memory 9140 can also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 can include various drivers of the electronic device for communication functions and / or for performing other functions of the electronic device (such as a messaging application, an address book application, etc.).

[0183] The communication module 9110 is a transmitter / receiver that transmits and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0184] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, etc. The communication module 9110 (transmitter / receiver) is also coupled to the speaker 9131 and the microphone 9132 via the audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby implementing normal telecommunication functions. The audio processor 9130 can include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is also coupled to the central processing unit 9100, so that recording can be performed on the device via the microphone 9132, and the sound stored on the device can be played via the speaker 9131.

[0185] Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps of the organization knowledge intelligent application method for coping with uncertain events with the execution entity being a server or a client in the above embodiments. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all steps of the organization knowledge intelligent application method for coping with uncertain events with the execution entity being a server or a client in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0186] Step S101: Obtain experience knowledge for coping with uncertain events, and extract key features from the experience knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision logics;

[0187] Step S102: Establish a scenario model based on the collaborative scenario meta-model, associate the uncertain event, business scenario, and collaborative participant with the scenario model to form decision knowledge nodes; define the relationships between decision knowledge nodes according to the process steps and the decision logics, and construct a knowledge base system based on the decision knowledge nodes and the relationships between the decision knowledge nodes;

[0188] Step S103: Retrieve the knowledge base system to obtain the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes; generate a task chain and a thinking chain for an AI Agent based on the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes; generate an AI Agent based on the task chain and the thinking chain;

[0189] Step S104: Receive an input command from a user, and parse the input command through the AI Agent; the AI Agent reasons based on the task chain and the thinking chain to generate a decision suggestion for the parsed result, and generate a decision plan for coping with the uncertain event based on the task chain.

[0190] As can be seen from the above description, the computer-readable storage medium provided by the embodiments of the present application obtains experience knowledge for coping with uncertain events from historical cases and simulation cases, constructs a knowledge base system based on the experience knowledge, transforms the experience knowledge into nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and experience knowledge of business experts and employees in uncertain events and integrating them into the AI agent design, the professionalism and reliability of its decision-making are improved, thereby promoting the externalization and intelligent application of experience knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments.

[0191] An embodiment of the present application also provides a computer program product that can implement all steps of the above-mentioned organization knowledge intelligent application method for dealing with uncertain events with the execution entity being a server or a client. When the computer program / instructions are executed by a processor, the steps of the above-mentioned organization knowledge intelligent application method for dealing with uncertain events are implemented. For example, the computer program / instructions implement the following steps:

[0192] Step S101: Obtain experience knowledge for dealing with uncertain events, and extract key features from the experience knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logics; <U+

[0193] Step S102: Establish a scenario model based on the collaboration scenario meta-model, associate the uncertain events, business scenarios, and collaborative participants with the scenario model to form decision knowledge nodes; define the relationships between the decision knowledge nodes according to the process steps and the decision-making logics, and construct a knowledge base system based on the decision knowledge nodes and the relationships between the decision knowledge nodes;

[0194] Step S103: Retrieve the knowledge base system to obtain the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes; generate a task chain and a thinking chain for the AI Agent based on the decision knowledge nodes for various types of uncertain events and the relationships between the decision knowledge nodes; generate an AI Agent based on the task chain and the thinking chain;

[0195] Step S104: Receive an input command from the user, and parse the input command through the AI Agent; the AI Agent reasons based on the task chain and the thinking chain to generate a decision-making suggestion for the parsed result, and generate a decision-making plan for dealing with the uncertain event based on the task chain.

[0196] As can be seen from the above description, the computer program product provided by the embodiment of the present application obtains experience knowledge for dealing with uncertain events from historical cases and simulation cases, constructs a knowledge base system based on the experience knowledge, transforms the experience knowledge into the nodes and relationships of the knowledge base system, and then constructs an AI Agent according to its task chain and thinking chain to be responsible for task execution and decision-making. By efficiently extracting the insights and experience knowledge of business experts and employees in uncertain events and integrating them into the design of the AI agent, the professionalism and reliability of its decision-making are improved, thereby promoting the externalization and intelligent application of experience knowledge, enabling the AI agent to make more accurate and timely responses in complex and ever-changing environments.

[0197] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, apparatus, or computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0198] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (apparatuses), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0199] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0200] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0201] Specific embodiments are applied in the present invention to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. An intelligent application method of organizational knowledge for coping with uncertain events, characterized in that, The method includes: Obtain empirical knowledge for coping with uncertain events, and extract key features from the empirical knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logics; Establish a situation model based on the collaborative situation meta-model, associate the uncertain events, business scenarios, and collaborative participants with the situation model to form decision-making knowledge nodes; define the relationships between the decision-making knowledge nodes according to the process steps and the decision-making logics, and construct a knowledge base system based on the decision-making knowledge nodes and the relationships between the decision-making knowledge nodes; Retrieve the knowledge base system to obtain the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate a task chain and a thinking chain for an AI Agent based on the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes; generate an AI Agent based on the task chain and the thinking chain; Receive an input command from the user, and parse the input command through the AI Agent; the AI Agent infers and generates decision-making suggestions based on the results of the parsing according to the task chain and the thinking chain, and generates a decision-making plan for coping with uncertain events based on the task chain; The step of obtaining empirical knowledge for coping with uncertain events includes: Obtain a review file through the guidance of a review of coping with uncertain events, and obtain the first empirical knowledge of the uncertain events from the review file; Use a large language model to parse historical data to obtain the second empirical knowledge of the uncertain events; the historical data includes historical cases and meeting minutes; The step of defining the relationships between the decision-making knowledge nodes according to the process steps and the decision-making logics includes: Decompose the decision-making logic into a logical chain between decision-making conditions and execution actions, and convert the logical chain into causal rules, establish a deterministic mapping between event trigger conditions and disposal measures, and form an initial causal rule base; Establish a variable causal relationship template according to the initial causal rule base, allow the causal intensity to be dynamically adjusted according to the business scenario, and support the simulation of possible future causal relationships by embedding a causal inference engine.

2. The intelligent application method of organizational knowledge for coping with uncertain events according to claim 1, wherein The step of associating the uncertain events, business scenarios, collaborative participants with the situation model to form decision-making knowledge nodes includes: Use the uncertain event as a trigger condition to achieve dynamic response through the event-driven node in the situation model; Obtain operation data related to the business scenario, and convert the operation data into dynamic constraint variables of the situation model; Define the collaborative participants as role nodes in the situation model and bind their decision-making authorities.

3. The intelligent application method of organizational knowledge for coping with uncertain events according to claim 1, characterized in that The step of defining the relationships between the decision-making knowledge nodes according to the process steps and the decision-making logics further includes: Decompose the process steps into independent decision-making knowledge nodes, analyze the timing constraints between operations in the process steps, extract process sequence features, and convert the process sequence features into a timing dependence chain between the decision-making knowledge nodes to obtain a time dependence relationship.

4. The intelligent application method of organizational knowledge for coping with uncertain events according to claim 1, wherein The steps of generating a task chain and a thinking chain for an AI Agent based on the decision-making knowledge nodes for various types of uncertain events and the relationships between the decision-making knowledge nodes include: Decompose the execution process for an uncertain event into a series of subtasks, and determine the execution order and dependency relationships between the subtasks to generate a task chain for the AI Agent; Based on the decision-making logic for an uncertain event, combined with the chain-of-thought method, design a perception thinking chain, a memory thinking chain, and a reasoning thinking chain, and construct the reasoning path of the AI Agent to obtain a thinking chain for the AI Agent; Specify the associated set of thinking chain nodes for each subtask in the task chain to form a mapping relationship table.

5. The intelligent application method of organizational knowledge for coping with uncertain events according to claim 1, wherein The steps of generating an AI Agent based on the task chain and the thinking chain include: Define a set of ability dimensions for the AI Agent according to the subtask types in the task chain, and construct an Agent feature vector based on the ability dimensions; Use the LangChain framework to construct an Agent model architecture, and the Agent model architecture includes a core reasoning module, a task execution module, a tool invocation module, and a memory management module; Compress the Agent model through knowledge distillation technology, and dynamically select the model version according to the hardware resources to obtain the final AI Agent.

6. The intelligent application method of organizational knowledge for coping with uncertain events according to claim 1, wherein The steps of the AI Agent reasoning based on the task chain and the thinking chain to generate decision suggestions for the parsed results and generating a decision-making plan to cope with uncertain events based on the task chain further include: recording the interaction content between the AI Agent and the user, extracting new decision-making experiences from the interaction content, and optimizing the knowledge base system based on the new decision-making experiences.

7. An intelligent application device for organizational knowledge for coping with uncertain events, characterized in that, The device includes: A knowledge extraction module, configured to obtain experience knowledge for coping with uncertain events and extract key features from the experience knowledge; the key features include uncertain events, business scenarios, collaborative participants, process steps, and decision-making logic; the steps of obtaining experience knowledge for coping with uncertain events include: obtaining a review file through an uncertain event coping review guide, and obtaining the first experience knowledge of the uncertain event from the review file; using a large language model to parse historical data to obtain the second experience knowledge of the uncertain event; the historical data includes historical cases and meeting minutes; A knowledge base system construction module, which is used to establish a situation model based on a collaborative situation meta-model, associate the uncertain events, business situations, collaborative participants with the situation model to form decision knowledge nodes; define the relationships between decision knowledge nodes according to the process steps and the decision logic, and construct a knowledge base system based on the decision knowledge nodes and the relationships between the decision knowledge nodes; the step of defining the relationships between decision knowledge nodes according to the process steps and the decision logic includes: disassembling the decision logic into a logical chain between decision conditions and execution actions, converting the logical chain into causal rules, establishing a deterministic mapping between event trigger conditions and disposal measures, and forming an initial causal rule base; establishing a variable causal relationship template according to the initial causal rule base, allowing the causal strength to be dynamically adjusted according to the business situation, and supporting the simulation of possible causal relationships that may occur in the future by embedding a causal inference engine; An AI Agent generation module, which is used to retrieve the knowledge base system to obtain the decision knowledge nodes for various uncertain events and the relationships between the decision knowledge nodes; generate a task chain and a thinking chain for the AI Agent based on the decision knowledge nodes for various uncertain events and the relationships between the decision knowledge nodes; generate an AI Agent based on the task chain and the thinking chain; An interaction module, which is used to receive an input command from a user and parse the input command through the AI Agent; the AI Agent generates a decision suggestion based on the reasoning of the parsed result based on the task chain and the thinking chain, and generates a decision plan for coping with uncertain events based on the task chain.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for intelligent application of organizational knowledge for coping with uncertain events according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for intelligent application of organizational knowledge for coping with uncertain events according to any one of claims 1 to 6.

Images