Business risk intelligent early warning method and system based on rule engine and related device

Abstract

This invention relates to the field of risk warning technology, and discloses a business risk intelligent warning method, system, and related equipment based on a rule engine. The method includes: establishing risk warning rules; in response to business data updates, obtaining a unique identifier for the target spatial object corresponding to the business data update; based on the unique identifier, determining the target level of the target spatial object in the spatial hierarchy, and the target rule conditions of the risk warning rules bound to the target level; according to the target level, querying and aggregating data items associated with the target spatial object from at least two different business domains to form a data set for risk analysis; matching and evaluating the data set with the target rule conditions; and in response to the matching and evaluation result satisfying the target rule conditions, triggering the execution of a corresponding response action to generate warning information for the target spatial object. This improves risk response efficiency and reduces false alarm / false negative rates.

Description

Technical Field

[0001] This invention relates to the field of risk warning technology, and in particular to a business risk intelligent warning method based on a rule engine, a business risk intelligent warning system based on a rule engine, an electronic device, and a computer-readable storage medium. Background Technology

[0002] In the real estate industry, real estate companies have accumulated a wealth of project management experience and formed numerous risk control rules. At the same time, business data has been initially integrated.

[0003] In related technologies, setting simple thresholds within a single system or using "red, yellow, and green lights" to display the status of key indicators in a human cockpit makes risk assessment reliant on personal experience. This makes it difficult to comprehensively consider the complex relationships between multi-dimensional information, cannot cope with complex scenarios, increases false alarm / false negative rates, lacks correlation analysis, and reduces risk response efficiency. Summary of the Invention

[0004] This invention aims to at least partially address one of the technical problems in related technologies. Therefore, the first objective of this invention is to propose a business risk intelligent early warning method based on a rules engine, capable of performing complex root cause analysis, automatically assessing the cascading impact of changes on costs and schedules, automatically and accurately identifying risks and providing early warnings, improving risk response efficiency, increasing risk location accuracy, and reducing false alarm / missed alarm rates.

[0005] The second objective of this invention is to propose a business risk intelligent early warning system based on a rules engine.

[0006] The third objective of this invention is to provide an electronic device.

[0007] The fourth objective of this invention is to provide a computer-readable storage medium.

[0008] To achieve the above objectives, a first aspect of the present invention proposes a business risk intelligent early warning method based on a rule engine, comprising: establishing risk early warning rules; wherein the risk early warning rules include rule conditions and response actions, and the risk early warning rules are bound to a specific level in a preset spatial hierarchy; in response to business data updates, obtaining a unique identifier of the target spatial object corresponding to the business data update; based on the unique identifier, determining the target level of the target spatial object in the spatial hierarchy, and the target rule conditions of the risk early warning rules bound to the target level; according to the target level, querying and aggregating data items associated with the target spatial object from at least two different business domains to form a data set for risk analysis; matching and evaluating the data set with the target rule conditions; and in response to the matching and evaluation result satisfying the target rule conditions, triggering the execution of the corresponding response action to generate early warning information for the target spatial object.

[0009] In addition, the business risk intelligent early warning method based on a rule engine according to the above embodiments of the present invention may also have the following additional technical features: In some embodiments of the present invention, establishing risk warning rules includes: receiving rule logic set for any specific level in the spatial hierarchy through a rule configuration interface; wherein the rule logic includes judgment conditions based on one or more business indicators and thresholds of the business indicators; receiving one or more operation instructions configured for the rule logic through the rule configuration interface; wherein the operation instructions indicate the response action when the judgment conditions are met; and saving the rule logic, operation instructions, and their correspondence with the specific level as risk warning rules that can be parsed and executed by the rule engine.

[0010] In some embodiments of the present invention, the method further includes: capturing and responding to business data updates by at least one of listening to an event message queue, performing timed polling, or receiving a manual trigger command.

[0011] In some embodiments of the present invention, at least two different business areas include at least two of the following: cost area, design area, schedule area, and supply chain area.

[0012] In some embodiments of the present invention, matching and evaluating the data set with the target rule conditions includes: selecting all risk warning rules bound to the target level from the rule base as candidate rule sets based on the target level to which the target spatial object belongs in the spatial hierarchy; traversing the candidate rule sets and extracting data items related to the target rule conditions from the data set for each risk warning rule; and substituting the data items into the target rule conditions for logical calculation to obtain the matching evaluation result.

[0013] In some embodiments of the present invention, extracting data items related to target rule conditions from the constructed data set includes: parsing business indicators associated with the target rule conditions; and locating and obtaining data items corresponding to the business indicators from the constructed data set based on the business indicators.

[0014] In some embodiments of the present invention, triggering the execution of a corresponding response action includes: generating an early warning message based on the matching result; wherein the early warning message includes at least one of the following: a unique identifier of the target spatial object, a risk description, a core data item used to trigger the target rule condition, and a business event identifier associated with the data item of another business domain; determining the recipient of the early warning message according to a pre-configured responsibility relationship, and sending the early warning message to the recipient.

[0015] According to an embodiment of the present invention, a business risk intelligent early warning method based on a rule engine is proposed as follows: First, a risk early warning rule is established; wherein, the risk early warning rule includes rule conditions and response actions, and the risk early warning rule is bound to a specific level in a preset spatial hierarchy system; second, in response to business data updates, a unique identifier of the target spatial object corresponding to the business data update is obtained; further, based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy system, and the target rule conditions of the risk early warning rule bound to the target level are determined; then, according to the target level, data items associated with the target spatial object and originating from at least two different business domains are queried and aggregated to form a data set for risk analysis; next, the data set is matched and evaluated with the target rule conditions; finally, in response to the matching and evaluation result satisfying the target rule conditions, the corresponding response action is triggered to generate early warning information for the target spatial object. Therefore, this method can perform complex root cause analysis, automatically assess the chain reaction impact of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, increase risk location accuracy, and reduce false alarm / missed alarm rates.

[0016] The second objective of this invention is to propose a business risk intelligent early warning system based on a rules engine, which can perform complex root cause analysis, automatically assess the chain reaction of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, increase risk location accuracy, and reduce false alarm / missed alarm rates.

[0017] To achieve the above objectives, a second aspect of the present invention proposes a business risk intelligent early warning system based on a rule engine, comprising: a construction module configured to establish risk early warning rules; wherein the risk early warning rules include rule conditions and response actions, and the risk early warning rules are bound to a specific level in a preset spatial hierarchy; a first response module configured to obtain a unique identifier of a target spatial object related to the update in response to a business data update; a determination module configured to determine, based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy, and the target rule conditions of the risk early warning rules bound to the target level; a query module configured to query and aggregate data items associated with the target spatial object from at least two different business domains according to the target level, to form a data set for risk analysis; an evaluation module configured to match and evaluate the data set with the target rule conditions; and a second response module configured to trigger the execution of a corresponding response action in response to the matching evaluation result satisfying the target rule conditions, to generate early warning information for the target spatial object.

[0018] According to an embodiment of the present invention, a business risk intelligent early warning system based on a rule engine includes: a construction module configured to establish risk early warning rules; wherein the risk early warning rules include rule conditions and response actions, and the risk early warning rules are bound to a specific level in a preset spatial hierarchy; a first response module configured to obtain a unique identifier of a target spatial object related to the update in response to a business data update; a determination module configured to determine, based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy, and the target rule conditions of the risk early warning rules bound to the target level; a query module configured to query and aggregate data items associated with the target spatial object from at least two different business domains according to the target level, to form a data set for risk analysis; an evaluation module configured to match and evaluate the data set with the target rule conditions; and a second response module configured to trigger the execution of a corresponding response action in response to the matching evaluation result satisfying the target rule conditions, to generate early warning information for the target spatial object. Therefore, this system can perform complex root cause analysis, automatically assess the cascading impact of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, enhance risk location accuracy, and reduce false alarm / missed alarm rates.

[0019] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a program or instructions that can run on the processor, and when the program or instructions are executed by the processor, the steps of the above-described intelligent early warning method for business risks based on a rule engine are implemented.

[0020] The electronic device according to the embodiments of the present invention, by executing the above-described business risk intelligent early warning method based on rule engine, can perform complex root cause analysis, automatically assess the chain impact of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, increase risk location accuracy, and reduce false alarm / missed alarm rates.

[0021] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the steps of the above-described intelligent early warning method for business risks based on a rule engine.

[0022] According to embodiments of the present invention, a computer-readable storage medium, by executing the above-described business risk intelligent early warning method based on a rule engine, can perform complex root cause analysis, automatically assess the chain reaction of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, enhance risk location accuracy, and reduce false alarm / missed alarm rates.

[0023] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0024] Figure 1 A flowchart of a business risk intelligent early warning method based on a rule engine according to some embodiments of the present invention; Figure 2 An architecture diagram of a rule engine-based intelligent early warning method for business risks according to other embodiments of the invention; Figure 3 This is a block diagram of a business risk intelligent early warning system based on a rule engine according to some embodiments of the present invention; Figure 4 This is a block diagram of an electronic device according to some embodiments of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

[0026] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by those skilled in the art. The terms "first," "second," and similar terms used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0027] As mentioned in the background technology section, in the real estate industry, real estate companies have accumulated a lot of project management experience and formed many risk control rules (such as "a warning is required if the cost of a single procurement item exceeds the target by 10%"). At the same time, business data has been initially integrated.

[0028] In related technologies, setting simple thresholds (such as alarms if costs exceed 1 million) within a single system (e.g., setting an alarm if costs exceed 1 million) or displaying key indicator statuses using "red, yellow, and green lights" in a human dashboard (business intelligence dashboard) relies on personal experience for risk assessment. This makes it difficult to comprehensively consider the complex relationships between multi-dimensional information, cannot cope with complex scenarios, increases false alarm / false negative rates, lacks correlation analysis, and reduces risk response efficiency.

[0029] Relevant personnel need to regularly review reports to identify anomalies (such as cost overruns). By the time anomalies are discovered, the problem has often already occurred, leaving them in a reactive and costly state. Risk assessment relies on personal experience and struggles to comprehensively consider the complex interrelationships of multi-dimensional information. For example, seeing only "a material price has increased by 5%" does not immediately assess its impact on the total cost of "a specific building or apartment type." After a risk is identified, the responsible department must be manually identified and notified via email or phone, a lengthy process with unclear responsibilities, leading to a slow response.

[0030] Specifically, rigid rules, unable to handle complex scenarios, lead to high false alarm / false negative rates. For example, a rule stating "if concrete usage exceeds the budget by 10%, trigger an alarm" might still result in a false alarm due to a reasonable increase in usage caused by a project expansion. Conversely, a sudden price surge in a key component, even with a small total quantity, might not trigger the threshold, leading to a false alarm. Isolated risks, lacking correlation analysis, result in unclear root causes. For instance, a cost system alarm for "reinforcement overrun," but the dashboard cannot directly link to which "building" (individual building-level spatial unit) or which "design change" (Building Information Modeling event) caused it, requiring manual investigation. A disconnect between warnings and actions leads to low response efficiency. For example, after the system issues an alarm, manual judgment is still needed on who to notify and how to handle it, as the warning fails to directly drive collaborative action.

[0031] The following description, with reference to the accompanying drawings, describes the business risk intelligent early warning method based on a rule engine, the business risk intelligent early warning system based on a rule engine, the electronic device, and the computer-readable storage medium proposed in the embodiments of the present invention.

[0032] refer to Figure 1 This is a flowchart of a business risk intelligent early warning method based on a rule engine according to some embodiments of the present invention.

[0033] like Figure 1 As shown, the business risk intelligent early warning method based on a rule engine according to an embodiment of the present invention may include the following steps: S101, Establish risk warning rules; wherein, risk warning rules include rule conditions and response actions, and risk warning rules are bound to a specific level in the preset spatial hierarchy system.

[0034] Specifically, risk warning rules can be established in the rule engine. These rules are designed to identify and prevent potential risks in advance, and consist of two parts: rule conditions and response actions. Rule conditions are the basis for determining whether a risk warning is triggered, while response actions are the operations to be performed when the rule conditions are met. For example, in a project where the cost of a Type A unit (S5 level space) fluctuates due to the upgrade of external wall insulation materials, the rule conditions could be: for any S5 level space (a specific level in the preset spatial hierarchy), its [dynamic cost deviation rate] > 10% and the [source of deviation] includes "design change"; the response action could be: generate a "high-risk" warning, notify the cost manager and design manager of the space, and automatically create a "cost overrun analysis" task on the project management platform, associated with the unique identifier of the S5 level space. Among them, S5 level space is a room-level space unit, which involves the core operation level. It refers to the smallest space unit in the floor that has independent functions or can be independently identified, such as an office, an apartment, or an equipment room. For example, S5-R2109 represents "room 2109". It is the basic unit for accepting data linking and querying. The unique identifier is a string generated according to the relevant standard coding rules that can uniquely correspond to a specific space object.

[0035] S102, in response to business data update, obtain the unique identifier of the target space object corresponding to the business data update.

[0036] Specifically, to determine whether business data has been updated, when business data is updated, a unique identifier for the target spatial object corresponding to the updated business data is obtained. For example, if the cost system updates the cost data for unit A due to rising material prices, triggering event-driven synchronization, the rule engine receives the updated cost data for unit A and obtains the latest cost deviation rate of unit A as 12%. The rule engine automatically queries the unique identifier data association library to find the most recent BIM (Building Information Modeling) event associated with this cost deviation, which is "exterior wall insulation material changed from B1 grade to A grade". Here, BIM is a digital representation process that includes various physical and functional characteristics of a building. In this invention, it specifically refers to a BIM model that has embedded relevant standard codes, which is the data carrier and object source for intelligent querying.

[0037] S103, based on a unique identifier, determine the target level of the target spatial object in the spatial hierarchy, and the target rule conditions of the risk warning rule bound to the target level.

[0038] Specifically, a spatial hierarchy is a structure that divides and organizes spatial objects according to certain rules and levels. Different spatial objects may occupy different levels. For example, in a large-scale construction project, there may be different levels such as city-level spatial units (S1), project group-level spatial units (S2), individual building-level spatial units (S3), floor-level spatial units (S4), room-level spatial units (S5), and component-level spatial units (S6). The target spatial object is the specific space to be analyzed and judged. It can be found in the spatial hierarchy by a unique identifier, and this level is the target level. Each specific spatial level may be bound to corresponding risk warning rules. These rules are formulated based on the characteristics of the spatial objects at that level and business needs. The target rule conditions are the judgment conditions in the risk warning rules bound to the target level to which the target spatial object belongs. The purpose is to determine whether to trigger the corresponding risk warning and subsequent response actions based on pre-set rules when business data changes.

[0039] Among them, city-level spatial units are the highest level in the relevant standard spatial classification system, used to identify and manage projects located in different cities at the group level; project cluster-level spatial units refer to project clusters composed of multiple sub-projects or plots within the same city; single building-level spatial units refer to independent single buildings with complete functions within a project cluster, such as a residential building or a commercial building; floor-level spatial units refer to specific floors within a single building, such as the ground floor above ground or the second basement floor; component-level spatial units refer to physical components or equipment that constitute a room, such as a window, an air conditioning unit, or a section of pipe.

[0040] S104, based on the target level, query and aggregate data items associated with the target spatial object that originate from at least two different business domains to form a data set for risk analysis.

[0041] Specifically, the process begins by locating a specific target spatial object based on the target level. Then, data related to that target spatial object is collected from multiple different business areas. Finally, these data are integrated to form a dataset that can be used for risk analysis. This dataset can comprehensively acquire various information that affects the risk status of the target spatial object, providing data support for accurate risk assessment.

[0042] S105, perform matching and evaluation of the data set with the target rule conditions.

[0043] Specifically, each data item in the dataset is compared one by one with the corresponding conditions in the target rule conditions to check whether the data item meets the thresholds, ranges, or inclusion relationships set in the target rule conditions. By comparing the collected dataset with the pre-set target rule conditions, it is determined whether the target spatial object meets the conditions for triggering a risk warning or other corresponding actions.

[0044] Matching and evaluating datasets with target rules and conditions is a crucial bridge connecting data collection and subsequent decision-making. It enables the accurate identification of potential risks based on actual data, providing a basis for subsequent risk response and management.

[0045] S106, in response to the matching evaluation result meeting the target rule conditions, trigger the execution of the corresponding response action to generate early warning information for the target spatial object.

[0046] Specifically, determining whether the matching evaluation result meets the target rule conditions can be understood as a complete match when all data items in the dataset meet all the conditions of the target rule. This means that the target space object triggers the execution of corresponding risk warnings or other response actions to generate warning information for the target space object. For example, generating a "high-risk" warning message for the target space object notifies the cost manager and design manager of that space, and automatically creates a "cost overrun analysis" task on the project management platform, associated with the unique identifier of the S5 space. This enables complex root cause analysis, automatically assesses the cascading impact of changes on costs and schedules, automatically and accurately identifies risks and provides early warnings, improves risk response efficiency, increases risk location accuracy, and reduces false alarms / missed alarms.

[0047] In some embodiments of the present invention, establishing risk warning rules includes: receiving rule logic set for any specific level in the spatial hierarchy through a rule configuration interface; wherein the rule logic includes judgment conditions based on one or more business indicators and thresholds of the business indicators; receiving one or more operation instructions configured for the rule logic through the rule configuration interface; wherein the operation instructions indicate the response action when the judgment conditions are met; and saving the rule logic, operation instructions, and their correspondence with the specific level as risk warning rules that can be parsed and executed by the rule engine.

[0048] Specifically, establishing risk warning rules for any specific level means that personalized risk warning strategies can be formulated based on the characteristics and needs of different levels. For example, room-level risks might focus more on renovation costs and changes in functionality, while building-level risks might emphasize structural safety and fire protection facilities. The rule configuration interface provides a channel for inputting and configuring rule information, offering users a user-friendly interface or programming interface to easily input rule logic into the system. Through this interface, users can easily define rules without needing to understand the complex implementation details of the system. The rule logic includes judgment conditions based on one or more business indicators and their thresholds. Business indicators are data reflecting the status and characteristics of a business; for example, in a construction project, business indicators might include cost, schedule, and quality. Thresholds are critical values ​​for judging whether a business indicator is normal. For example, for room-level cost indicators, a judgment condition could be set as "dynamic cost deviation rate > 10%", where "dynamic cost deviation rate" is the business indicator and "10%" is the threshold.

[0049] Operational instructions are the response actions taken when a judgment condition is met. When the judgment condition in the rule logic is true, the system needs to execute the corresponding operation to deal with the risk. These operational instructions can be flexibly configured according to business needs. For example, when the judgment condition of "dynamic cost deviation rate > 10%" at the room level is met, the operational instruction could be "generate a 'high-risk' warning, notify the cost manager and design manager of the space, and automatically create a 'cost overrun analysis' task on the project management platform, associating it with the room's unique identifier." Integrating and saving the rule logic, operational instructions, and their correspondence with specific levels forms a complete risk warning rule set. These rules need to be stored in a format that the rule engine can understand and execute, typically using a specific data structure or file format.

[0050] Among them, the rule engine of the present invention is a rule engine for real estate. This engine takes spatial objects of relevant standards as its core and uses real-time events as the driving force for risk calculation.

[0051] In some embodiments of the present invention, the method further includes: capturing and responding to business data updates by at least one of listening to an event message queue, performing timed polling, or receiving a manual trigger command.

[0052] Specifically, an event message queue is a data structure used to store and transmit event messages. In a business system, when business data is updated, the system generates corresponding event messages and places them in the message queue. By listening to the event message queue, the system can obtain real-time notifications of business data updates.

[0053] Periodic polling refers to sending query requests to the business system at pre-set time intervals to obtain the latest status of business data. In this way, the system can periodically capture updates to business data.

[0054] Manually triggered commands refer to commands initiated by users through interface operations, command line input, etc., to trigger the system to capture business data updates. This method allows users to manually obtain the latest business data when needed.

[0055] In some embodiments of the present invention, at least two different business areas include at least two of the following: cost area, design area, schedule area, and supply chain area.

[0056] Specifically, the cost domain focuses on the management and control of various expenses involved in the implementation of a project or business, including cost budgeting, cost accounting, cost analysis, and cost optimization. The design domain emphasizes the planning and conceptualization of products, projects, or systems to meet specific functions and requirements, involving idea generation, solution design, technology selection, and design document preparation. The schedule domain focuses on the time arrangement and progress tracking of project or business activities, requiring the development of detailed project plans, clarifying the tasks, start and end times, and dependencies of each stage, and ensuring the project progresses according to plan through effective monitoring. The supply chain domain covers the entire process from raw material procurement to product delivery to the end user, including supplier management, procurement management, inventory management, and logistics distribution. Its goal is to achieve efficient supply chain operation, reduce costs, and improve service levels.

[0057] In some embodiments of the present invention, matching and evaluating the data set with the target rule conditions includes: selecting all risk warning rules bound to the target level from the rule base as candidate rule sets based on the target level to which the target spatial object belongs in the spatial hierarchy; traversing the candidate rule sets and extracting data items related to the target rule conditions from the data set for each risk warning rule; and substituting the data items into the target rule conditions for logical calculation to obtain the matching evaluation result.

[0058] Specifically, based on the spatial hierarchy (e.g., project group-level spatial units → individual building-level spatial units → floor-level spatial units → room-level spatial units), the target spatial object (e.g., "room 2109") is first identified, belonging to the target hierarchy (e.g., room-level spatial unit S5). Then, all risk warning rules bound to this hierarchy are selected from the rule base to form a candidate rule set. Each rule in the rule base is pre-bound to a specific hierarchy (e.g., S5-level rules only apply to room-level spaces). The selection process can be quickly matched using hierarchy identifiers (e.g., room-level spatial unit S5) to ensure a strong correlation between the candidate rule set and the target hierarchy.

[0059] For each rule in the candidate rule set, extract data items directly related to the target rule conditions from the dataset. The dataset is composed of data from multiple business domains (such as cost, design, schedule, and at least two of the supply chain domains). Substitute the extracted data items into the target rule conditions for logical calculations (such as numerical comparison, inclusion relationship judgment, and logical combination operations), and finally output the matching evaluation result of "condition met" (triggers an alert) or "condition not met" (does not trigger an alert).

[0060] Taking "dynamic cost deviation rate > 10% and deviation source includes 'design change'" as an example, if the data item shows a deviation rate of 12% (meets > 10%) and the source is "external wall insulation material change" (including "design change"), the logical calculation result is "meets the condition", triggering an early warning action (such as generating a high-risk warning, notifying the person in charge, or creating an analysis task). This enables accurate risk identification and automated response, supporting the timeliness and accuracy of decision-making.

[0061] In some embodiments of the present invention, extracting data items related to target rule conditions from the constructed data set includes: parsing business indicators associated with the target rule conditions; and locating and obtaining data items corresponding to the business indicators from the constructed data set based on the business indicators.

[0062] Specifically, the target rule conditions are pre-defined risk assessment logic (e.g., "dynamic cost deviation rate > 10% and the deviation source includes 'design changes'"), while business indicators are the core elements constituting these conditions. The parsing process requires breaking down the target rule conditions and identifying the specific business indicators involved and their definitions. The dataset is a risk analysis dataset aggregated from data across multiple business domains (e.g., data from at least two domains such as cost, design, schedule, and supply chain). Based on the business indicators, specific data items need to be located and extracted from the dataset to achieve precise and data-driven risk warnings.

[0063] In some embodiments of the present invention, triggering the execution of a corresponding response action includes: generating an early warning message based on the matching result; wherein the early warning message includes at least one of the following: a unique identifier of the target spatial object, a risk description, a core data item used to trigger the target rule condition, and a business event identifier associated with the data item of another business domain; determining the recipient of the early warning message according to a pre-configured responsibility relationship, and sending the early warning message to the recipient.

[0064] Specifically, when the rule matching evaluation result is "condition met" (i.e., an early warning is triggered), the system needs to generate a structured early warning message based on the matching result. The unique identifier of the target spatial object can clearly identify the specific location of the risk (e.g., room number "S5-R2109"), ensuring the recipient can quickly locate the source of the problem. The risk description can concisely summarize the risk type and severity (e.g., "Dynamic cost overrun of 12%, due to design changes"), helping the recipient quickly understand the nature of the risk. The core data items used to trigger the target rule conditions can extract key business data that triggers the rule conditions (e.g., dynamic cost deviation rate = 12%, deviation source = "change in external wall insulation materials"), providing a quantitative basis for risk analysis. Business event identifiers associated with data items from other business areas can link events from other business areas to avoid response delays or misjudgments due to missing information.

[0065] Based on pre-configured responsibility relationships (e.g., "cost overrun warnings sent to project managers and cost specialists"), warning messages are distributed to relevant responsible persons to ensure timely risk control. Pre-configured responsibility relationships enable automatic allocation of risk responsibility, avoiding the inefficiency or ambiguity of manual assignment. Generated warning messages are sent to recipients through preset channels (e.g., email, SMS, WeChat Work, in-system notifications, etc.) to ensure timely information delivery.

[0066] As a specific example, in a project where the cost of a Type A unit (S5 level space) fluctuated due to the upgrade of external wall insulation materials, the following references are made: Figure 2 The following is an architecture diagram of a business risk intelligent early warning method based on a rule engine according to other embodiments of the present invention. The rule condition can be that for any S5-level space, its dynamic cost deviation rate is >15% and the source of the deviation is "change in wall material". The response action can be to generate and send a "high risk" warning to the cost / design manager to notify the cost manager, design manager and construction manager of the space, and automatically create a "cost optimization" collaborative task on the project management platform, associated with the unique identifier of the S5-level space.

[0067] The rules engine continuously monitors real-time data streams from the "event-driven data synchronization" interface. Based on a pre-built rule base and querying a unique identifier data association database to obtain complete context, the rules engine performs risk matching calculations. Once a rule is triggered, precise early warning information is generated and distributed to relevant responsible parties. Tasks can also be created directly on the collaboration platform. This enables the transformation of risk management experience in the real estate sector into executable business rules. Based on real-time associated unique identifier data, it automatically and accurately identifies risks, automatically routes risk information to relevant responsible parties, and recommends or directly triggers handling procedures.

[0068] As another specific example, in a large-scale complex project, after applying this invention, the time to discover major cost risks was shortened from an average of 15 days (monthly reporting cycle) to within 2 hours after the problem occurred, the risk investigation and location time was shortened from an average of 1 day to immediate clarification, and the efficiency of risk closed-loop processing was improved by more than 80%.

[0069] In some embodiments, the present invention can be extended to supply chain compliance checks (such as automatically verifying whether incoming materials comply with environmental regulations) or intelligent quality inspection of customer service (such as automatically determining whether customer complaint handling violates service level agreement rules). A service level agreement is a formal commitment and quantifiable contract between a service provider and a customer regarding the quality, availability, and responsibilities of the service.

[0070] Therefore, relying on traditional manual judgment methods results in significant delays in cost overrun risks, which are often only discovered during monthly cost meetings; the impact of design changes depends on the experience of designers, making oversights easy; and supply chain risks are often only reported by purchasing staff upon discovering stock shortages. However, the intelligent early warning method of this invention provides real-time alerts the moment deviations occur, pinpointing the issue to the specific unit and resolving cost overruns to reduce overall project costs. Regarding the impact of design changes, it automatically assesses the cascading effects of changes on costs and schedules, improving design quality, reducing changes due to insufficient consideration, and shortening the design cycle. Finally, regarding supply chain risks, it predicts stock shortage risks based on inventory and construction plans and provides early warnings, preventing site shutdowns due to material shortages and ensuring the completion of key project milestones.

[0071] In summary, the definition and calculation of the rules in this invention are no longer based on vague overall project indicators, but are precisely anchored to specific S5 (room-level spatial unit) and S6 (component-level spatial unit) levels. This has qualitatively changed the accuracy of risk positioning, enabling granular management of "which room and which component has a problem." The input to the rule engine is no longer isolated data points, but data chains linked by unique identifiers (such as cost deviation + design change events). This allows the rules to perform complex root cause analysis (such as whether "cost overrun" is due to "design changes" or "material price fluctuations"), outputting more instructive early warning information. By transforming early warning information into executable action instructions (such as creating tasks and notifying responsible persons), an automated closed loop from "risk perception" to "collaborative handling" is achieved, greatly improving risk response efficiency.

[0072] In summary, the business risk intelligent early warning method based on a rule engine according to embodiments of the present invention firstly establishes risk early warning rules; wherein, the risk early warning rules include rule conditions and response actions, and the risk early warning rules are bound to a specific level in a preset spatial hierarchy system; secondly, in response to business data updates, a unique identifier of the target spatial object corresponding to the business data update is obtained; further, based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy system, and the target rule conditions of the risk early warning rules bound to the target level are determined; then, according to the target level, data items associated with the target spatial object and originating from at least two different business domains are queried and aggregated to form a data set for risk analysis; next, the data set is matched and evaluated with the target rule conditions; finally, in response to the matching and evaluation results satisfying the target rule conditions, the corresponding response action is triggered to generate early warning information for the target spatial object. Therefore, this method can perform complex root cause analysis, automatically assess the chain reaction impact of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, increase risk location accuracy, and reduce false alarm / missed alarm rates.

[0073] It should be noted that the method of this embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this embodiment, and the multiple devices will interact with each other to complete the above method.

[0074] It should be noted that the above description describes some embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0075] Corresponding to the above embodiments, the present invention also proposes a business risk intelligent early warning system based on a rules engine.

[0076] like Figure 3 As shown, the business risk intelligent early warning system based on the rule engine of this invention includes: a construction module 310, a first response module 320, a determination module 330, a query module 340, an evaluation module 350, and a second response module 360.

[0077] The system comprises the following modules: Construction module 310, configured to establish risk warning rules; each risk warning rule includes rule conditions and response actions, and is bound to a specific level in a preset spatial hierarchy; First response module 320, configured to respond to business data updates by obtaining a unique identifier for the target spatial object related to the update; Determination module 330, configured to determine, based on the unique identifier, the target level of the target spatial object in the spatial hierarchy, and the target rule conditions of the risk warning rule bound to the target level; Query module 340, configured to query and aggregate data items associated with the target spatial object from at least two different business domains, based on the target level, to form a data set for risk analysis; Evaluation module 350, configured to match and evaluate the data set against the target rule conditions; and Second response module 360, configured to trigger the execution of a corresponding response action in response to the matching evaluation result satisfying the target rule conditions, to generate warning information for the target spatial object.

[0078] In some embodiments of the present invention, the construction module 310 establishes risk warning rules, specifically for: receiving rule logic set for any specific level in the spatial hierarchy through a rule configuration interface; wherein the rule logic includes judgment conditions based on one or more business indicators and thresholds of the business indicators; receiving one or more operation instructions configured for the rule logic through the rule configuration interface; wherein the operation instructions indicate the response action when the judgment conditions are met; and saving the rule logic, operation instructions, and their correspondence with the specific level as risk warning rules that can be parsed and executed by the rule engine.

[0079] In some embodiments of the present invention, the first response module 320 is further configured to capture and respond to business data updates by at least one of listening to an event message queue, performing timed polling, or receiving a manual trigger instruction.

[0080] In some embodiments of the present invention, at least two different business areas include at least two of the following: cost area, design area, schedule area, and supply chain area.

[0081] In some embodiments of the present invention, the evaluation module 350 performs a matching evaluation between the data set and the target rule conditions. Specifically, it is used to: select all risk warning rules bound to the target level from the rule base as candidate rule sets based on the target level to which the target spatial object belongs in the spatial hierarchy; traverse the candidate rule sets and extract data items related to the target rule conditions from the data set for each risk warning rule; substitute the data items into the target rule conditions for logical calculation to obtain the matching evaluation result.

[0082] In some embodiments of the present invention, the evaluation module 350 extracts data items related to the target rule conditions from the constructed data set, specifically for: parsing business indicators associated with the target rule conditions; and locating and obtaining data items corresponding to the business indicators from the constructed data set based on the business indicators.

[0083] In some embodiments of the present invention, the second response module 360 ​​triggers the execution of a corresponding response action, specifically used for: generating an early warning message based on the matching result; wherein the early warning message includes at least one of the following: a unique identifier of the target space object, a risk description, a core data item used to trigger the target rule conditions, and a business event identifier associated with the data item of another business domain; determining the recipient of the early warning message according to the pre-configured responsibility relationship, and sending the early warning message to the recipient.

[0084] It should be noted that for details not disclosed in the cost optimization decision support system based on performance indicators in the embodiments of the present invention, please refer to the details disclosed in the cost optimization decision support method based on performance indicators in the embodiments of the present invention, and will not be repeated here.

[0085] In summary, the business risk intelligent early warning system based on a rule engine according to an embodiment of the present invention includes: a construction module configured to establish risk early warning rules; wherein the risk early warning rules include rule conditions and response actions, and the risk early warning rules are bound to a specific level in a preset spatial hierarchy; a first response module configured to obtain a unique identifier of a target spatial object related to the update in response to a business data update; a determination module configured to determine, based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy, and the target rule conditions of the risk early warning rules bound to the target level; a query module configured to query and aggregate data items associated with the target spatial object from at least two different business domains according to the target level, to form a data set for risk analysis; an evaluation module configured to match and evaluate the data set with the target rule conditions; and a second response module configured to trigger the execution of a corresponding response action in response to the matching evaluation result satisfying the target rule conditions, to generate early warning information for the target spatial object. Therefore, this system can perform complex root cause analysis, automatically assess the cascading impact of changes on costs and schedules, automatically and accurately identify risks and provide early warnings, improve risk response efficiency, enhance risk location accuracy, and reduce false alarm / missed alarm rates.

[0086] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing this invention, the functions of each module can be implemented in one or more software and / or hardware components.

[0087] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0088] Corresponding to the above embodiments, the present invention also proposes an electronic device.

[0089] refer to Figure 4 The diagram below is a block diagram of an electronic device according to some embodiments of the present invention. It illustrates a more specific hardware structure of the electronic device provided in this embodiment. The device may include: a processor 410, a memory 420, an input / output interface 430, a communication interface 440, and a bus 450. The processor 410, memory 420, input / output interface 430, and communication interface 440 are interconnected internally via the bus 450.

[0090] The processor 410 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0091] The memory 420 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 420 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 420 and is called and executed by the processor 410.

[0092] Input / output interface 430 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0093] The communication interface 440 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0094] Bus 450 includes a pathway for transmitting information between various components of the device, such as processor 410, memory 420, input / output interface 430, and communication interface 440.

[0095] It should be noted that although the above-described device only shows the processor 410, memory 420, input / output interface 430, communication interface 440, and bus 450, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0096] The electronic devices described above are used to implement the corresponding methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0097] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides a computer-readable storage medium storing computer instructions for causing a computer to perform the methods of any of the above embodiments.

[0098] The aforementioned computer-readable storage medium can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0099] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the methods of any of the above exemplary method sections, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0100] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Rather, the steps depicted in the flowchart may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0101] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0102] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by those skilled in the art. The terms "first," "second," and similar terms used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0103] While the spirit and principles of the invention have been described with reference to several specific embodiments, it should be understood that the invention is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for ease of description. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims is to be interpreted in the broadest sense, thereby encompassing all such modifications and equivalent structures and functions.

Claims

1. A business risk intelligent early warning method based on a rule engine, characterized in that, include: Establish risk warning rules; wherein, the risk warning rules include rule conditions and response actions, and the risk warning rules are bound to a specific level in a preset spatial hierarchy system; In response to business data updates, obtain the unique identifier of the target space object corresponding to the business data update; Based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy is determined, as well as the target rule conditions of the risk warning rule bound to the target level; Based on the target hierarchy, query and aggregate data items associated with the target spatial object that originate from at least two different business domains to form a data set for risk analysis; The dataset is matched and evaluated against the target rule conditions; In response to the matching evaluation result satisfying the target rule conditions, the corresponding response action is triggered to generate early warning information for the target spatial object.

2. The business risk intelligent early warning method based on a rule engine according to claim 1, characterized in that, The establishment of risk warning rules includes: For any specific level in the spatial hierarchy, the rule logic set for the specific level is received through the rule configuration interface; wherein, the rule logic includes judgment conditions based on one or more business indicators and the threshold of the business indicators; The rule configuration interface receives one or more operation instructions configured for the rule logic; wherein the operation instructions indicate the response action when the judgment condition is met. The rule logic, the operation instructions, and their correspondence with the specific level are saved as risk warning rules that can be parsed and executed by the rule engine.

3. The business risk intelligent early warning method based on a rule engine according to claim 1, characterized in that, The method further includes: The business data update is captured and responded to by at least one of the following methods: listening to the event message queue, performing timed polling, or receiving a manual trigger command.

4. The business risk intelligent early warning method based on a rule engine according to claim 1, characterized in that, The at least two different business areas include at least two of the following: cost area, design area, schedule area, and supply chain area.

5. The business risk intelligent early warning method based on a rule engine according to claim 1, characterized in that, The step of matching and evaluating the data set with the target rule conditions includes: Based on the target level to which the target spatial object belongs in the spatial hierarchy, all risk warning rules bound to the target level are selected from the rule base as a candidate rule set; Traverse the candidate rule set, and for each risk warning rule, extract data items related to the target rule conditions from the constructed data set; The data items are substituted into the target rule conditions for logical calculation to obtain the matching evaluation result.

6. The business risk intelligent early warning method based on a rule engine according to claim 5, characterized in that, The step of extracting data items related to the target rule conditions from the constructed dataset includes: Analyze the business metrics associated with the target rule conditions; Based on the business metrics, locate and retrieve the data items corresponding to the business metrics from the constructed data set.

7. The business risk intelligent early warning method based on a rule engine according to claim 1, characterized in that, The triggering of the corresponding response action includes: An early warning message is generated based on the matching result; wherein, the early warning message contains at least one of the following: a unique identifier of the target spatial object, a risk description, a core data item used to trigger the target rule condition, and a business event identifier from other business domains associated with the data item of the business domain; Based on the pre-configured responsibility relationship, the recipient of the warning message is determined, and the warning message is sent to the recipient.

8. A business risk intelligent early warning system based on a rules engine, characterized in that, include: The construction module is configured to establish risk warning rules; wherein, the risk warning rules include rule conditions and response actions, and the risk warning rules are bound to a specific level in a preset spatial hierarchy system; The first response module is configured to, in response to a business data update, obtain a unique identifier of the target spatial object related to the update; The determination module is configured to determine, based on the unique identifier, the target level to which the target spatial object belongs in the spatial hierarchy, and the target rule conditions of the risk warning rule bound to the target level; The query module is configured to query and aggregate data items associated with the target spatial object and originating from at least two different business domains, based on the target level, to form a data set for risk analysis. The evaluation module is configured to match and evaluate the dataset against the target rule conditions; The second response module is configured to trigger the execution of a corresponding response action in response to the matching evaluation result satisfying the target rule condition, so as to generate early warning information for the target spatial object.

9. An electronic device, characterized in that, include: A processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the business risk intelligent early warning method based on a rule engine as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The program or instructions are stored on the readable storage medium, and when the program or instructions are executed by a processor, they implement the steps of the business risk intelligent early warning method based on a rule engine as described in any one of claims 1 to 7.

Images