Alarm method and system based on dynamic configuration management caused by business rules, and storage medium

Abstract

The invention provides an alarm method based on dynamic configuration management caused by business rules, which comprises the following steps of: establishing an urban governance alarm business knowledge base (including lexicon) and a business model according to multiple national standards, and realizing urban governance AI alarm decision management driven by a business rule engine. And application functions such as a business model, rule definition, a rule strategy and automatic rule adaptation are provided. The invention further provides the dynamic configuration management system based on the business rule and the storage medium, the alarm storm is eliminated, the alarm accuracy and reliability are improved, and false alarm and missing alarm are reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent communication technology and equipment, and in particular relates to an alarm method, system and storage medium for dynamic configuration management based on business rules. Background Art

[0002] In recent years, with the rapid development of science and technology, especially the continuous breakthroughs in artificial intelligence technology, video intelligent analysis technology has become an indispensable and important driver of urban governance modernization. However, with the widespread application of AI video surveillance systems in urban governance, the massive alarm data generated by the system is mixed with a large amount of invalid and repeated "noise", forming an "alarm peak", drowning out the real emergency events that need attention, forcing monitoring personnel to spend a lot of time screening and verifying alarms.

[0003] Because the AI ​​video surveillance system still has major deficiencies in recognition accuracy, which not only affects the overall credibility of the system but may also lead to incorrect handling decisions, the lack of deep integration with specific business scenarios limits the full release of AI-assisted decision-making potential, making it difficult to meet the increasingly complex needs of urban governance, and invisibly adding extra burdens to managers and front-line workers. Now let's give examples to illustrate the existing problems.

[0004] (1) Technology does not match actual business needs, technology is separated from business, and practicality is insufficient. AI technology that is separated from application scenarios may not be able to effectively solve practical problems in urban governance. For example, some intelligent video recognition systems may be very advanced in theory, but in actual operation, they are difficult to play a role due to the lack of deep integration with specific scenarios.

[0005] (2) Low decision-making efficiency and poor algorithm adaptability. AI algorithms that are out of touch with the application scenario may not be able to adapt to the complex and changing environment and needs of urban governance. For example, some algorithms may perform well under certain conditions, but may fail or misjudge under other conditions.

[0006] (3) Alarm recognition is limited to a single technology. For example, an alarm is triggered when a single video is intelligently recognized, or when the IoT sensing water level exceeds a threshold. There is no integration of multiple factors, and no integration of multi-modal fusion technologies such as video, audio, IoT sensing, and VR / AR. For example:

[0007] Example 1: For example, if someone is eating while waiting for a bus with a suitcase on the roadside, he will be identified as a traveling merchant.

[0008] Example 2: Someone in a residential community poured a bucket of water at a waterlogging monitoring point (where a water level meter was installed), causing a false flood control and drainage warning. Summary of the invention

[0009] Technical solution: In order to solve the above technical problems, the present invention provides an alarm method for dynamic configuration management based on business rules, the method comprising:

[0010] Establish a knowledge base for urban governance warning services based on known national standards;

[0011] Build a business model supported by the characteristics of historical alarm events, and define rules, rule strategies and rule adaptation technologies; extract features of actual urban governance business scenarios, and compare features with business scenario data in the urban governance alarm business knowledge base; filter alarms according to rule definitions, rule strategies and rule adaptation through business rule adaptation, and issue alarm self-healing processing, alarm prediction processing, and decision analysis visualization processing.

[0012] As an improvement, alarm filtering includes the following methods:

[0013] (1) Pre-process alarm classification, use high-aggregation intelligent algorithms to extract key feature information of alarms, perform algorithmic clustering and noise reduction on alarms, associate key feature information with clustering results, and compress subsequent similar alarms into alarms that have not yet been closed;

[0014] (2) Compress the same event alarms based on time series, or automatically label the alarms with classification information based on classification algorithms, and compress, merge and reduce noise from multiple dimensions.

[0015] As an improvement, business rule self-adaptation includes a method for identifying and distinguishing based on a matching decision-making method and a method for issuing alarms at a set priority level. The method for identifying and distinguishing based on a matching decision-making method is used when there are multiple similar business scenarios under different business rules to train the business model to learn the characteristics of historical alarm events; the method for issuing alarms at a set priority level is a method for automatically learning historical alarm data characteristics, alarm handling conditions, and industry business rule knowledge, and automatically generating a priority ranking for business rules according to the nine-square grid method.

[0016] As an improvement, the specific steps of the matching decision method are as follows:

[0017] (1) Define a matching index to measure the matching degree between the rule and the current event;

[0018] (2) Assume that there are two rules R1 and R2, which have a set of conditions C1 = {c11, c12, ...} and C2 = {c21, c22, ...}, and corresponding matching weights W1 = {w11, w12, ...} and W2 = {w21, w22, ...};

[0019] (3) For each rule Ri, calculate the sum of the weighted matching degrees of all its conditions;

[0020] (4) Taking into account the priority, matching degree, and freshness of the rules, the rule with the highest evaluation score is selected for execution. The formula for comprehensive consideration is as follows:

[0021] EvaluationScore(Ri)=α×Priority(Ri)+β×MatchScore(Ri)+γ×Freshness(Ri)

[0022] Among them, α, β, γ are weight coefficients; Priority(Ri) is the priority of rule Ri, MatchScore(Ri) is the matching degree between rule Ri and the current alarm event, Freshness(Ri) is the freshness of rule Ri, and EvaluationScore(Ri) is the evaluation score of rule Ri.

[0023] As an improvement, business rule self-adaptation includes a multimodal fusion decision-making strategy, which is used for fusion of multi-source heterogeneous alarm data. By performing feature extraction and fusion, a single model is established to identify alarms, and a multimodal fusion decision-making strategy based on a weighted voting method is adopted to complete the final adaptation alarm processing. The multi-source heterogeneous alarm data includes video image recognition alarms, audio recognition (noise index, sensitive sounds), Internet of Things perception (the value of the physical quantity measured by the sensor exceeds the alarm threshold), and geographic space coordinates (alarm sensitive locations).

[0024] As an improvement, the specific steps for alarm processing of fused multi-source heterogeneous alarm data are as follows:

[0025] (1) Determine the alarm category

[0026] Assume there are N alarm categories, represented by C1, C2, …, CN respectively;

[0027] (2) Collecting modal alarm results

[0028] Assume that each mode j has a corresponding alarm result vector v j =[v j 1,v j 2,…,v j N], support degree v j , where n is the number of modes, v j Indicates the support degree of mode j for alarm category Ci, which is a probability value between 0 and 1;

[0029] (3) Determine the modal weight

[0030] Assign each mode j a weight w j , where the weight w jis a non-negative real number, and the sum of the weights of all modes is usually normalized to 1;

[0031] (4) Calculate the weighted sum

[0032] For each alarm category Ci, calculate its weighted sum Si, the calculation formula is as follows:

[0033]

[0034] Where Si reflects the comprehensive support degree of all modes for the alarm category Ci; n is the number of modes;

[0035] (5) Comparison of weighted sums

[0036] Among all alarm categories C1, C2, …, CN, compare their weighted sums S1, S2, …, SN;

[0037] (6) Select the maximum weighted sum

[0038] The alarm category with the largest weighted sum is selected as the final decision, that is, the final decision for this event should be the Ci alarm category that makes Si reach the maximum value.

[0039] As an improvement, the specific steps of alarm self-healing processing are based on the self-healing rules in the urban governance business rule engine. When a non-emergency urban governance alarm occurs, the system will automatically adapt the self-healing processing rules, trigger the corresponding self-healing process, and realize alarm self-healing. Then, it will verify whether the alarm exists through AI visual recognition technology, determine that there is no problem with self-healing, and close the alarm.

[0040] As an improvement, the specific steps of alarm prediction processing are:

[0041] (1) After the real-time alarm events are received, the alarm events are filtered and processed to generate a real-time alarm knowledge graph;

[0042] (2) Build an event graph model for urban governance and use a graph database to store and manage the graph model; define each alarm event as a node in the graph model, including detailed information about the alarm;

[0043] (3) Obtain the historical alarm knowledge graph related to (1) in the event graph model, and use the graph algorithm to calculate the similarity; the historical alarm knowledge graph whose similarity exceeds the set threshold is used as the candidate root cause graph;

[0044] (4) In the candidate root cause graph, the support and confidence of the alarm event indicators are calculated through the association analysis algorithm; the root causes are prioritized according to the severity and impact range of the alarm root causes;

[0045] (5) Make auxiliary decision-making analysis and event handling plans.

[0046] At the same time, the present invention also provides an alarm system for dynamic configuration management caused by business rules, including an alarm aggregation module, an alarm filtering module, and an alarm application scenario module;

[0047] The alarm aggregation module is used to collect alarm information through AI visual analysis of alarms and multiple types of alarms;

[0048] The alarm filtering module is used to issue decision-making alarm information according to any of the above alarm methods after receiving the alarm aggregation module information;

[0049] The alarm application scenario module is used to perform system self-healing processing, alarm prediction processing, conversion into work order events or analysis and visualization processing on the information sent by the alarm filtering module.

[0050] At the same time, the present invention also provides a storage medium, the computer program stored in the storage medium can be executed by one or more processors and can be used to implement any of the above-mentioned alarm methods.

[0051] Beneficial effects: The alarm method based on dynamic configuration management caused by business rules proposed in the present invention is based on a number of national standards, establishes an urban governance alarm business knowledge base (including a vocabulary) and a business model, realizes urban governance AI alarm decision management driven by a business rule engine, and provides application functions such as business models, rule definitions, rule strategies, and automatic rule adaptation; eliminates alarm storms, improves the accuracy and reliability of alarms, and reduces false alarms and missed alarms.

[0052] Compared with conventional technologies, the alarm method proposed in the present invention has the following advantages:

[0053] (1) Through the aggregation of multi-source heterogeneous alarm data and standard alarm data management, the problems of different management of different scenarios in urban governance, different platforms of different manufacturers, and scattered and chaotic alarm information have been solved.

[0054] (2) Through the business rule engine and the use of alarm self-healing applications, the need for manual intervention is greatly reduced, the risk of human error is reduced, and the alarm handling process is made more efficient and accurate. While reducing the burden, it also brings significant efficiency improvements to users.

[0055] (3) Through the application of root cause analysis and alarm prediction of graph algorithms, the source of the problem can be quickly located to reduce false alarms and missed alarms; through learning and analyzing historical alarm data, graph algorithms can discover the association rules and potential problems between alarms. These rules and patterns can help predict urban governance problems that may occur in the future, so that measures can be taken in advance to prevent them.

[0056] (4) Through the application of multimodal fusion decision-making and warning, the accuracy and reliability of warnings can be improved, and false alarms and missed alarms can be reduced.

[0057] (5) The alarm location can be accurately located by applying the positioning function of geographic space technology; the intelligent recognition technology using AI vision technology can simultaneously apply multiple algorithm alarms and obtain the actual alarm images at the same time; the real-time and high-precision technical features of the Internet of Things sensing technology can detect alarms in a more timely and accurate manner.

[0058] In the present invention, these various advanced technologies are integrated to achieve accurate screening of effective alarms from massive multi-source heterogeneous alarm data, reduce the occurrence of false alarms and missed alarms, improve the accuracy and effectiveness of alarms, and bring significant burden reduction and efficiency improvement experience to urban management staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of data flow of the system of the present invention.

[0060] Figure 2 It is a logical flow diagram of the alarm method of the present invention.

[0061] Figure 3 The figure is a schematic flow chart of the self-adaptation technology of the alarm method of the present invention.

[0062] Figure 4 It is a flow chart of the management method under the rule based on multimodal fusion decision in the alarm method of the present invention.

[0063] Figure 5 The present invention is a flowchart of the alarm self-healing process in the alarm method.

[0064] Figure 6 This is a flow chart of alarm prediction in the alarm method of the present invention.

[0065] Figure 7 Schematic diagram of a multimodal fusion decision-making scheme for fire identification and fireworks performance events according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present invention will be described clearly and completely below so that those skilled in the art can better understand the advantages and features of the present invention, thereby making a clearer definition of the protection scope of the present invention. The embodiments described in the present invention are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present invention.

[0067] The alarm method of dynamic configuration management based on business rules in the present invention realizes two sets of alarm engines, a business rule engine and an AI algorithm engine; the alarm application is the application function of the alarm system, which mainly includes alarm filtering, intelligent noise reduction of priority alarms, multimodal fusion decision alarms, alarm self-healing, i.e. automatic verification based on AI visual recognition technology, alarm prediction, i.e. root cause prediction analysis, decision analysis visualization, etc.

[0068] See Figure 1 As shown, it is a data flow diagram of the alarm system of the present invention based on dynamic configuration management caused by business rules. Specifically, the system includes an alarm aggregation module, an alarm filtering module, and an alarm application scenario module;

[0069] The alarm aggregation module is used to collect alarm information through AI visual analysis of alarms and multiple types of alarms;

[0070] The alarm filtering module is used to issue decision-making alarm information according to any of the above alarm methods after receiving the alarm aggregation module information;

[0071] The alarm application scenario module is used to perform system alarm self-healing processing, alarm prediction processing, conversion into work order events or analysis and visualization processing on the information sent by the alarm filtering module.

[0072] Further, see Figure 2 FIG. 1 is a flow chart of an alarm method for dynamic configuration management based on business rules of the present invention, and the method includes:

[0073] Establish a knowledge base for urban governance alarm services based on known national standards; for example, "GB / T 30428.2-2013 Digital Urban Governance Information System Part 2: Management Components and Events".

[0074] Build a business model supported by historical alarm event features, and define rules, rule strategies and rule adaptation technology; extract features of actual urban governance business scenarios, and compare features with business scenario data in the urban governance alarm business knowledge base. Through business rule adaptation, according to rule definition, rule strategy, and rule adaptation method, alarm self-healing processing, alarm prediction processing, and decision analysis visualization processing are issued. The adaptive method is shown in Figure 3 shown.

[0075] As a business rule self-adaptation technology, a method for issuing an alarm according to a set priority level is used when there are at least two business rules in the same business application scenario, and an alarm is issued according to the set priority level, specifically:

[0076] (1) Priority setting method: Automatically learn from historical alarm data characteristics, alarm handling conditions, and industry business rules knowledge, and automatically generate business rules priority ranking according to the nine-square grid method:

[0077] ① Collect all alarm data generated by the system in the past period of time and extract key features, such as alarm frequency, duration, and impact range. These data are important bases for analyzing business rules.

[0078] ② Record the handling process, handling results, time consumption, etc. after each alarm occurs. Analyze the correlation between different alarms, identify possible causal relationships or co-occurrence relationships, understand the triggering mechanism and impact path of alarms, and evaluate the urgency and handling efficiency of different alarms.

[0079] ③ Obtain business rule data of the urban governance industry, including industry standards, best practices, policies and regulations, and extract key features, such as alarm frequency, alarm urgency, and impact range, as a supplementary basis for the priority sorting of business rules.

[0080] ④ Use the classification algorithm to input the extracted feature data into the model for training, and then use the nine-square grid method to divide the rules into nine areas according to two key dimensions (such as urgency and scope of impact), and each area corresponds to a priority level.

[0081] ⑤ Based on the output of the model and the division results of the nine-square grid method, define the priority level of each business rule.

[0082] (2) The rule with the highest priority is selected and executed, and those with the same priority are merged into the first rule;

[0083] (3) Select rules with comparable logical priorities. The rules with the highest priority will be executed, and those with the same priority will be merged under the first rule.

[0084] Preferably, the method for setting the priority level for alarming is to set the rule: Assuming that there are two or more alarm judgment rules R1, R2, and Rn in the same business scenario, they are all triggered to respond to an event. Each rule has a priority attribute, which is recorded as P1, P2, and Pn respectively.

[0085] Strategy: Select the rule with the highest priority to execute. If the priorities are the same, merge them into the first rule to filter and deduplicate alarms.

[0086] Comparison logic: If P1>P2>Pn, P1 is retained as the alarm result and other alarms are eliminated; if P1=P2=Pn, P1 alarm is retained and other alarms are merged under P1.

[0087] Example 1: For example, to realize intelligent video recognition of the chef's uniform and the chef's not wearing a mask, the two alarms can be merged into one alarm based on the "open kitchen and bright stove" business rule.

[0088] Table 1 Example 1 of the method for issuing an alarm according to the priority level set by the present invention

[0089]

[0090]

[0091] As a business rule self-adaptation technology, it also includes a rule self-adaptation alarm management method based on matching degree to identify different rules for multiple similar business scenarios. Specifically, when there are multiple similar business scenarios under different business rules, the business model is trained to learn the characteristics of historical alarm events, and identification and differentiation are performed according to the matching degree decision method.

[0092] Among urban governance alarm events, there are many alarm events with similar business characteristics but completely different regulatory disposals. AI visual analysis alarms are often easily confused. It is necessary to learn the characteristics of historical alarm events and update the business model in a timely manner according to regulations and policies. It is also necessary to adapt relevant rules to accurately identify and distinguish them. Matching may be based on multiple conditions, and the matching degree of each condition may be different.

[0093] Preferably, the specific steps of the matching decision method are:

[0094] (1) Define a matching index to measure the matching degree between the rule and the current event;

[0095] (2) Assume that there are two rules R1 and R2, which have a set of conditions C1 = {c11, c12, ...} and C2 = {c21, c22, ...}, and corresponding matching weights W1 = {w11, w12, ...} and W2 = {w21, w22, ...};

[0096] (3) For each rule Ri, calculate the sum of the weighted matching degrees of all its conditions;

[0097] (4) Taking into account the priority, matching degree, and freshness of the rules, the rule with the highest evaluation score is selected for execution. The formula for comprehensive consideration is as follows:

[0098] EvaluationScore(Ri)=α×Priority(Ri)+β×MatchScore(Ri)+γ×Freshness(Ri)

[0099] Among them, α, β, γ are weight coefficients, Priority(Ri) is the priority of rule Ri, MatchScore(Ri) is the matching degree between rule Ri and the current alarm event, Freshness(Ri) is the freshness of rule Ri, and EvaluationScore(Ri) is the evaluation score of rule Ri.

[0100] Further, the evaluation strategy is: select the rule with the highest evaluation score to execute; Example 2 of this method is as follows:

[0101] For example, in street order management, there are three types of event alarms: out-of-store business, road occupation, and unlicensed peddling. There are many similarities in the forms of business activities, which can easily lead to conflicts in the automatic adaptation of rules. It is difficult to accurately determine which type of alarm it is relying solely on AI video recognition, and it is often misjudged. Then, the law enforcement management among the three is obviously different.

[0102] In Example 2 above, the similar features of the three are: unauthorized or beyond-scope operation; intuitive activities: shelves, goods, customers; dynamic changes; occupation of public resources; and impact on the city appearance. The differences between the three are shown in the following table.

[0103] Table 2 The differences between the three in Example 2 of the present invention

[0104]

[0105] As a business rule self-adaptation technology, it also includes a rule self-adaptation alarm management method based on multi-modal fusion decision-making, see Figure 4 As shown, it is used for fusion of multi-source heterogeneous alarm data. By performing feature extraction and fusion, a single model is established to identify alarms, and a multimodal fusion decision strategy based on a weighted voting method is adopted to complete the final adaptive alarm processing. The multi-source heterogeneous alarm data includes video, audio, Internet of Things perception, and geographic space information.

[0106] The specific steps for alarm processing of fused multi-source heterogeneous alarm data are as follows:

[0107] (1) Determine the alarm category

[0108] Assume there are N alarm categories, represented by C1, C2, …, CN respectively;

[0109] (2) Collecting modal alarm results

[0110] Assume that each mode j has a corresponding alarm result vector v j =[v j 1,v j 2,…,v j N], support degree v j i, where n is the number of modes, vj i represents the support degree of mode j for alarm category Ci, which is a probability value between 0 and 1;

[0111] (3) Determine the modal weight

[0112] Assign each mode j a weight w j , where the weight w j is a non-negative real number, and the sum of the weights of all modes is usually normalized to 1;

[0113] (4) Calculate the weighted sum

[0114] For each alarm category Ci, calculate its weighted sum Si, the calculation formula is as follows:

[0115]

[0116] Where Si reflects the comprehensive support degree of all modes for the alarm category Ci; n is the number of modes;

[0117] (5) Comparison of weighted sums

[0118] Among all alarm categories C1, C2, …, CN, compare their weighted sums S1, S2, …, SN;

[0119] (6) Select the maximum weighted sum

[0120] The alarm category with the largest weighted sum is selected as the final decision, that is, the final decision for this event should be the Ci alarm category that makes Si reach the maximum value.

[0121] Preferably, a rule-based adaptive alarm management method based on multimodal fusion decision-making, specific case:

[0122] For example, in the process of fusing video and sound signals in the "fighting" scene of urban governance, we first perform feature extraction and feature fusion based on the video signal and sound signal, and then train individual models to generate model prediction alarms. Finally, we use weighted voting to predict the results of each model to obtain a better recognition result, and finally identify whether it is a play or a fight.

[0123] See Figure 5 As shown, this is based on the self-healing rules in the urban governance business rule engine. When a non-emergency urban governance alarm occurs, the system will automatically adapt the self-healing processing rules, trigger the corresponding self-healing process, and realize alarm self-healing. Then, it will verify whether the alarm exists through AI visual recognition technology, determine that there is no problem with self-healing, and close the alarm.

[0124] For example, if the self-healing time of an illegally parked motor vehicle is set to 15 minutes, a voice reminder and a text message will be sent to the owner to notify the owner to move the vehicle; after 15 minutes of the alarm, the system automatically triggers the front-end to collect image data, and uses AI visual recognition technology to verify whether an alarm exists. If it is found that the illegally parked vehicle has left, the system automatically closes the alarm.

[0125] See Figure 6 As shown in the figure, it is a root cause analysis alarm prediction based on the graph algorithm, in which the specific steps of alarm prediction processing are:

[0126] (1) After the real-time alarm events are received, the alarm events are filtered and processed to generate a real-time alarm knowledge graph;

[0127] (2) Build an event graph model for urban governance and use a graph database to store and manage the graph model. Define each alarm event as a node in the graph model, including detailed information about the alarm, such as time, type, address, text description, etc.

[0128] (3) Obtain the historical alarm knowledge graph related to (1) in the event graph model, and use the graph algorithm to calculate the similarity; the historical alarm knowledge graph whose similarity exceeds the set threshold is used as the candidate root cause graph;

[0129] (4) In the candidate root cause graph, the support and confidence of the alarm event indicators are calculated through the association analysis algorithm; the root causes are prioritized according to the severity and impact range of the alarm root causes;

[0130] (5) Make auxiliary decision-making analysis and event handling plans.

[0131] The decision analysis visualization in this invention is the visualization of real-time alarm filtering, alarm self-healing, and alarm prediction data, which helps to achieve more refined urban governance and operation management. Through rich ready-to-use multi-dimensional reports, unified analysis of all alarm sources and alarm management is achieved, providing business personnel and leaders with analysis of alarms and work efficiency improvement.

[0132] Based on geographic space information, VR and AR technologies can be used to virtualize and augment reality the monitoring screen, provide more intuitive and comprehensive monitoring and early warning information, combine IoT sensing alarms, realize multi-source alarm data feature fusion, and use weighted voting analysis to verify decisions, improve the accuracy and reliability of alarms, and reduce false alarms and missed alarms. For example, we cannot warn of urban flooding just because a water level meter senses that the water level is too high. We can use video fusion technology to identify whether the high water level at that location is urban flooding or a water accumulation problem caused by an accidental event. For example, Figure 7 Multimodal fusion decision scheme for fire identification and fireworks show events.

[0133] See Figure 7As shown, the present invention, first, collects the data of image recognition alarm and smoke sensor and transmits them to the fire light recognition and smoke recognition module as the data of fire recognition; collects the data of audio recognition alarm and geographic space information and transmits them to the noise alarm such as the key word "beautiful", the fixed smoke release point such as the riverside, the VR and AR video fusion information module as the data of fireworks show.

[0134] Then, the fire identification data and the fireworks display data are combined into data for judging whether an alarm needs to be filtered; finally, a judgment is made as to whether an alarm is required.

[0135] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An alarm method for dynamic configuration management based on business rules, characterized in that: The method includes establishing a knowledge base of urban governance warning services based on known national standards; Build a business model supported by the characteristics of historical alarm events, and define rules, rule strategies and rule adaptation technologies; extract features of actual urban governance business scenarios, and compare features with business scenario data in the urban governance alarm business knowledge base; filter alarms according to rule definitions, rule strategies and rule adaptation through business rule adaptation, and issue alarm self-healing processing, alarm prediction processing, and decision analysis visualization processing.

2. The alarm method for dynamic configuration management based on business rules according to claim 1 is characterized in that: Alarm filtering includes the following methods: (1) Pre-process alarm classification, use high-aggregation intelligent algorithms to extract key feature information of alarms, perform algorithmic clustering and noise reduction on alarms, associate key feature information with clustering results, and compress subsequent similar alarms into alarms that have not yet been closed; (2) Compress the same event alarms based on time series, or automatically label the alarms with classification information based on classification algorithms, and compress, merge and reduce noise from multiple dimensions.

3. The alarm method for dynamic configuration management based on business rules according to claim 1 is characterized in that: Business rule self-adaptation includes a method for identifying and distinguishing based on a matching decision-making method and a method for issuing alarms based on a set priority level. The method for identifying and distinguishing based on a matching decision-making method is used when there are multiple similar business scenarios under different business rules to train the business model to learn the characteristics of historical alarm events; the method for issuing alarms based on a set priority level is a method for automatically learning through historical alarm data characteristics, alarm handling conditions, and industry business rule knowledge, and automatically generating a priority ranking method for business rules according to the nine-square grid method.

4. The alarm method for dynamic configuration management based on business rules according to claim 3 is characterized in that: The specific steps of the matching decision method are: (1) Define a matching index to measure the matching degree between the rule and the current event; (2) Assume that there are two rules R1 and R2, which have a set of conditions C1 = {c11, c12, ...} and C2 = {c21, c22, ...}, and corresponding matching weights W1 = {w11, w12, ...} and W2 = {w21, w22, ...}; (3) For each rule Ri, calculate the sum of the weighted matching degrees of all its conditions; (4) Taking into account the priority, matching degree, timestamp, and freshness of the rules, the rule with the highest evaluation score is selected for execution. The formula for comprehensive consideration is as follows: EvaluationScore(Ri)=α×Priority(Ri)+β×MatchScore(Ri)+γ×Freshness(Ri) Among them, α, β, γ are weight coefficients; Priority(Ri) is the priority of rule Ri, MatchScore(Ri) is the matching degree between rule Ri and the current alarm event, Freshness(Ri) is the freshness of rule Ri, and EvaluationScore(Ri) is the evaluation score of rule Ri.

5. The alarm method for dynamic configuration management based on business rules according to claim 1 is characterized in that: Business rule self-adaptation includes a multimodal fusion decision-making strategy, which is used to extract and fuse multi-source heterogeneous alarm data, establish a single model to identify alarms, and adopt a multimodal fusion decision-making strategy based on a weighted voting method to complete the final adaptation alarm processing. The multi-source heterogeneous alarm data includes video, audio, IoT perception, and geospatial information.

6. The alarm method for dynamic configuration management based on business rules according to claim 5 is characterized in that: The specific steps for alarm processing of fused multi-source heterogeneous alarm data are as follows: (1) Determine the alarm category Assume there are N alarm categories, represented by C1, C2, …, CN respectively; (2) Collecting modal alarm results Assume that each mode j has a corresponding alarm result vector v j =[v j 1,v j 2,…,v j N], support level v j i, where n is the number of modes, v j Indicates the support degree of mode j for alarm category Ci, which is a probability value between 0 and 1; (3) Determine the modal weight Assign each mode j a weight w j , where the weight w j is a non-negative real number, and the sum of the weights of all modes is usually normalized to 1; (4) Calculate the weighted sum For each alarm category Ci, calculate its weighted sum Si, the calculation formula is as follows: Where Si reflects the comprehensive support degree of all modes for the alarm category Ci; n is the number of modes; (5) Comparison of weighted sums Among all alarm categories C1, C2, …, CN, compare their weighted sums S1, S2, …, SN; (6) Select the maximum weighted sum The alarm category with the largest weighted sum is selected as the final decision, that is, the final decision for this event should be the Ci alarm category that makes Si reach the maximum value.

7. The alarm method for dynamic configuration management based on business rules according to claim 1 is characterized in that: The specific steps of alarm self-healing processing are based on the self-healing rules in the urban governance business rule engine. When a non-emergency urban governance alarm occurs, the system will automatically adapt the self-healing processing rules, trigger the corresponding self-healing process, and realize alarm self-healing. Then, it will verify whether the alarm exists through AI visual recognition technology, determine that there is no problem with self-healing, and close the alarm.

8. The alarm method for dynamic configuration management based on business rules according to claim 1 is characterized in that: The specific steps of alarm prediction processing are: (1) After the real-time alarm events are received, the alarm events are filtered and processed to generate a real-time alarm knowledge graph; (2) Build an event graph model for urban governance and use a graph database to store and manage the graph model; Define each alarm event as a node in the graph model, including detailed information of the alarm; (3) Obtain the historical alarm knowledge graph related to (1) in the event graph model and calculate the similarity using the graph algorithm; The historical alarm knowledge graphs whose similarity exceeds the set threshold are used as candidate root cause graphs; (4) In the candidate root cause graph, the support and confidence of the alarm event indicators are calculated through the association analysis algorithm; the root causes are prioritized according to the severity and impact range of the alarm root causes; (5) Make auxiliary decision-making analysis and event handling plans.

9. An alarm system for dynamic configuration management based on business rules, characterized in that: Includes alarm aggregation module, alarm filtering module, and alarm application scenario module; The alarm aggregation module is used to collect alarm information through AI visual analysis of alarms and multi-type alarms; the alarm filtering module is used to issue decision-making alarm information according to any alarm method described in claims 1-8 after receiving the alarm aggregation module information; The alarm application scenario module is used to perform system alarm self-healing processing, alarm prediction processing, conversion into work order events or analysis and visualization processing on the information sent by the alarm filtering module.

10. A storage medium, characterized in that: The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the alarm method as described in any one of claims 1 to 8.

Images