Business event chain response efficiency evaluation method and device, computer device, medium and product

Abstract

This application relates to a method, apparatus, computer equipment, medium, and product for evaluating the response efficiency of a business event chain. The method includes: obtaining a business event chain based on the business events corresponding to the original data of each business system; obtaining a current evaluation index set from an evaluation index library based on the event flow structure entropy and information freshness; obtaining the current index value corresponding to each current evaluation index for the business event chain; assigning corresponding scenario attribute factors; obtaining a comprehensive weight influence factor based on historical contribution factors and real-time fluctuation factors; obtaining dynamic weights; correcting the current index value according to the type of the current evaluation index to obtain a target index value; processing the dynamic weights and target index value through a response efficiency model to obtain the comprehensive response efficiency of the business event chain; and evaluating the efficiency of the business event chain based on the comprehensive response efficiency. This method can improve the evaluation accuracy.

Description

Technical Field

[0001] This application relates to the field of data intelligence analysis technology, and in particular to a method, apparatus, computer equipment, medium and product for evaluating the response efficiency of a business event chain. Background Technology

[0002] With the advancement of supply chain digitalization, enterprises typically build multiple business systems such as procurement, contracts, warehousing, e-commerce, and transportation management, generating massive amounts of supply chain business data. However, this data exhibits characteristics of multi-source heterogeneity: different systems have different data modeling logics, significantly different data structures, inconsistent entity representations, and scattered business relationships, making it difficult to directly conduct cross-system efficiency analysis. Furthermore, supply chain operations encompass different scenarios such as emergency repairs, business expansion, and routine reserves. The evaluation focus for response efficiency varies significantly across these scenarios; for example, emergency repair scenarios require high timeliness, while routine reserve scenarios emphasize resource turnover and process standardization.

[0003] In traditional technologies, the assessment of supply chain response efficiency mainly revolves around a single dimension or a fixed indicator system, such as assessment methods based on process time statistics and fixed-weight indicators. However, due to limitations in data processing capabilities and weight allocation methods, these methods cannot adapt to the multi-scenario and multi-dimensional supply chain management needs in the context of digitalization, resulting in low assessment accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, medium, and product for evaluating the response efficiency of business event chains that can improve the evaluation accuracy, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for evaluating the response efficiency of a business event chain, including:

[0006] Obtain the business events corresponding to the raw data of each business system, and obtain the business event chain based on the business events;

[0007] Obtain a pre-established evaluation indicator library, and retrieve the current evaluation indicator set from the evaluation indicator library based on the event flow structure entropy and information freshness; the current evaluation indicator set includes multiple current evaluation indicators.

[0008] Obtain the current indicator value corresponding to each current evaluation indicator in the business event chain, and assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario;

[0009] For each current evaluation indicator, obtain the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator, and obtain the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor and real-time volatility factor.

[0010] Dynamic weights are obtained based on the comprehensive weighting influence factor and the number of current evaluation indicators. The current indicator values ​​are then corrected according to the type of current evaluation indicators to obtain the target indicator values.

[0011] The dynamic weights and target index values ​​are processed by the response efficiency model to obtain the comprehensive response efficiency of the business event chain, and the efficiency of the business event chain is evaluated based on the comprehensive response efficiency.

[0012] In one embodiment, the step of obtaining a business event chain based on a business event includes: obtaining the participating entities of the business event; mapping the participating entities to preset entity identifiers, and aligning the fields of the mapped business events to obtain standardized events; sorting the standardized events according to business relationships to obtain a business event chain; and arranging the business events in the business event chain in order of business time.

[0013] In one embodiment, the step of obtaining the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator includes:

[0014] Obtain the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods prior to the current evaluation period, and obtain the correlation coefficient between the first historical indicator value and the historical response efficiency;

[0015] The correlation coefficients are normalized to obtain the historical contribution factors corresponding to the current evaluation indicators.

[0016] Obtain the second historical indicator value from the previous assessment period for the current assessment period, and obtain the volatility rate based on the current indicator value and the second historical indicator value.

[0017] The volatility change rate is normalized to obtain the real-time volatility factor corresponding to the current evaluation index.

[0018] In one embodiment, the step of obtaining the comprehensive weighted influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor, and real-time volatility factor includes:

[0019] A weighted coupling function and a linear modulation function are constructed based on the dimension sensitivity coefficient, and a scenario correction function is obtained based on the current business scenario.

[0020] Based on the weighted coupling function, linear modulation function, and scenario correction function, scenario attribute factors, historical contribution factors, and real-time volatility factors are coupled to obtain the comprehensive weight influence factor corresponding to the current evaluation index; among them, the dimension sensitivity coefficient is used to adjust the influence ratio of scenario attribute factors, historical contribution factors, and real-time volatility factors in the coupling process.

[0021] In one embodiment, the step of correcting the current indicator value according to the type of the current evaluation indicator to obtain the target indicator value includes:

[0022] If the current evaluation indicator is a Category I indicator, the current indicator value will be used as the target indicator value.

[0023] If the current evaluation indicator is a second type of indicator, the difference between 1 and the current indicator value will be used as the target indicator value.

[0024] Given that the current evaluation indicator is a third type of indicator, the absolute distance between the current indicator value and the preset indicator value is obtained, and the difference between 1 and the absolute distance is taken as the target indicator value. Among them, the first type of indicator is a positive indicator that affects the overall response efficiency, the second type of indicator is a negative indicator that affects the overall response efficiency, and the third type of indicator is an interval indicator that affects the overall response efficiency.

[0025] In one embodiment, the process of obtaining the response efficiency model includes:

[0026] A nonlinear correction function is constructed based on the nonlinear correction coefficient of the indicator contribution, and a collaborative equilibrium correction function is also constructed; the nonlinear correction coefficient of the indicator contribution is used to nonlinearly amplify the target indicator value.

[0027] The response efficiency model is obtained based on the nonlinear correction function and the cooperative equilibrium correction function.

[0028] Secondly, this application also provides a business event chain response efficiency evaluation device, comprising:

[0029] The event chain acquisition module is used to acquire the business events corresponding to the raw data of each business system, and to acquire the business event chain based on the business events.

[0030] The indicator acquisition module is used to acquire a pre-established evaluation indicator library and, based on the event flow structure entropy and information freshness, retrieve the current evaluation indicator set from the evaluation indicator library; the current evaluation indicator set includes multiple current evaluation indicators.

[0031] The indicator calculation module is used to obtain the current indicator value corresponding to each current evaluation indicator in the business event chain, and to assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario.

[0032] The weight acquisition module is used to obtain the historical contribution factor and real-time volatility factor corresponding to each current evaluation indicator, and to obtain the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor and real-time volatility factor.

[0033] The indicator correction module is used to obtain dynamic weights based on the comprehensive weight influence factor and the number of current evaluation indicators, and to correct the current indicator values ​​according to the type of the current evaluation indicators to obtain the target indicator values.

[0034] The efficiency evaluation module is used to process dynamic weights and target indicator values ​​through a response efficiency model to obtain the comprehensive response efficiency of the business event chain, and to evaluate the efficiency of the business event chain based on the comprehensive response efficiency.

[0035] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps of any one of the first aspects.

[0036] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method steps of any one of the first aspects.

[0037] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps of any one of the first aspects.

[0038] The aforementioned business event chain response efficiency evaluation method, device, computer equipment, medium, and product obtains the business event chain based on the business events corresponding to the original data of each business system. Based on the event flow structure entropy and information freshness, it retrieves the current evaluation indicator set from the evaluation indicator library, obtains the current indicator value corresponding to each current evaluation indicator for the business event chain, and assigns corresponding scenario attribute factors. Based on historical contribution factors and real-time fluctuation factors, it obtains a comprehensive weight influence factor, thereby obtaining dynamic weights. Based on the type of the current evaluation indicator, it corrects the current indicator value to obtain the target indicator value. The dynamic weights and target indicator value are processed through a response efficiency model to obtain the comprehensive response efficiency of the business event chain. The efficiency of the business event chain is then evaluated based on the comprehensive response efficiency. This eliminates data structure differences, improves the matching degree between evaluation indicators and scenario requirements, makes the weight allocation more closely aligned with the dynamic operating characteristics of the business event chain, and ensures that the evaluation results accurately reflect the real-time response efficiency of the business event chain, thereby improving the intelligence and refinement level of business management. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a diagram illustrating the application environment of a business event chain response efficiency evaluation method in one embodiment.

[0041] Figure 2 This is a flowchart illustrating a business event chain response efficiency evaluation method in one embodiment;

[0042] Figure 3 This is a flowchart illustrating the business event chain response efficiency evaluation method in another embodiment;

[0043] Figure 4 This is a structural block diagram of a business event chain response efficiency evaluation device in one embodiment;

[0044] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] The business event chain response efficiency evaluation method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. Terminal 102 is used to acquire business events corresponding to the raw data of each business system, obtain business event chains based on the business events, acquire a pre-established evaluation index library, and obtain the current evaluation index set from the evaluation index library based on the event flow structure entropy and information freshness. It also acquires the current index values ​​corresponding to each current evaluation index for the business event chain, assigns corresponding scenario attribute factors to the current index values ​​based on the current business scenario, acquires the historical contribution factor and real-time fluctuation factor corresponding to each current evaluation index, and acquires the comprehensive weight influence factor corresponding to the current evaluation index based on the scenario attribute factor, historical contribution factor, and real-time fluctuation factor. It acquires the dynamic weight based on the comprehensive weight influence factor and the number of current evaluation indicators, and corrects the current index value based on the type of current evaluation index to obtain the target index value. It processes the dynamic weight and target index value through a response efficiency model to obtain the comprehensive response efficiency of the business event chain, and evaluates the efficiency of the business event chain based on the comprehensive response efficiency. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0047] In one exemplary embodiment, such as Figure 2 As shown, a method for evaluating the response efficiency of a business event chain is provided, and this method is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 212. Wherein:

[0048] S202: Obtain the business events corresponding to the raw data of each business system, and obtain the business event chain based on the business events.

[0049] Optionally, raw data from various business systems can be collected, which often exhibit significant structural differences. For example, a complete supply chain process typically involves multiple business systems such as procurement, contracts, warehousing, e-commerce, and transportation management. The procurement system focuses on projects, the contract system on contracts, the warehousing system on inventory changes, the e-commerce platform generates sporadic procurement transactions, and the transportation platform provides delivery tracking information, each offering distinct business information. These heterogeneous data are then integrated to form standardized business event flow data. The definition of a business event is based on the division of business processes, including demand submission events, bid-winning announcement events, contract signing events, material warehousing events, and delivery receipt events. Each event contains four core elements: event type, occurrence time, participating entities, and business attributes. For example, when a bid-winning announcement record is transformed into a bid-winning event, its occurrence time corresponds to the announcement release time, participating entities include the procurement department and the winning supplier, and business attributes include the bid amount and procurement method.

[0050] Furthermore, for the same business process, by combining pre-defined business association rules (such as the mapping relationship between project numbers and contract numbers), related events scattered across different systems are linked into a complete business event chain. For example, based on the business association rules, the correspondence between the numbers used in different stages is identified, and events such as demand submission, bid-winning announcement, contract signing, and material warehousing are arranged in chronological order to form a complete response path from demand generation to material arrival. This chronological association allows subsequent analysis to accurately calculate the time consumed in each stage, and even if different stages use different numbers, the integrity of the chain can be guaranteed through the mapping relationship.

[0051] S204: Obtain the pre-established evaluation index library, and obtain the current evaluation index set from the evaluation index library based on the event flow structure entropy and information freshness; the current evaluation index set includes multiple current evaluation indices.

[0052] Optionally, the business scenario to which a business event belongs can be automatically identified based on its business attributes, such as business expansion, emergency repair, or routine reserves, and the scenario tag can be written into the event record. The same type of event may have different analytical value in different scenarios, and the attachment of scenario tags provides a contextual recognition basis for the subsequent dynamic adjustment of indicator weights. Based on the factors affecting the response efficiency of the business event chain, combined with the business scenario tags of the business event flow, an evaluation indicator library is constructed to store core evaluation indicators of different dimensions, and differentiated indicator thresholds are set for different business scenarios. For example, based on the entire process business logic of the supply chain from demand submission to material delivery, four core evaluation dimensions are defined: process timeliness, collaboration quality, resource adaptation, and anomaly control. Among them, the process timeliness dimension focuses on the execution time of each business link, the collaboration quality dimension focuses on the efficiency of collaboration between participating entities, the resource adaptation dimension reflects the degree of matching between resources such as inventory and transportation capacity and business needs, and the anomaly control dimension measures the ability to detect and handle abnormal events. The four dimensions cover the core influencing factors of supply chain response efficiency, and the indicators under each dimension correspond one-to-one with the business attributes of the event flow data, with no overlap.

[0053] Examples of indicators include: process timeliness indicators such as procurement response time (the time difference between the demand submission event and the bid-winning announcement event), contract signing time (the time difference between the bid-winning announcement event and the contract signing event), and timely warehousing rate (the number of timely warehousing events / the total number of warehousing events); collaboration quality indicators such as cross-departmental collaboration waiting time, supplier response timeliness, and warehouse-construction unit matching degree; resource matching indicators such as inventory turnover rate, transportation capacity utilization rate, and material demand fulfillment rate; and anomaly control indicators such as anomaly occurrence rate, anomaly handling time, and anomaly closure rate. All indicator calculation data are directly derived from the standardized event flow data output in step S1, ensuring data traceability and consistency. Under the four core dimensions, a dynamically expandable basic evaluation indicator library is constructed, clearly defining five core attributes for each indicator: indicator name, indicator type, calculation method, data source, and unit.

[0054] Furthermore, for all indicators in the evaluation indicator library, they are filtered based on the event flow structure entropy and information freshness corresponding to each indicator. Event flow structure entropy is an indicator that quantifies the topological disorder, hierarchical chaos, and event distribution uncertainty of a time-series event sequence, treating it as a dynamic graph / network. Low entropy indicates a clear event flow structure, stable patterns, and well-defined clustering, while high entropy indicates a chaotic event flow, variable patterns, and scattered distribution. Information freshness measures the timeliness, decay rate, and proportion of the latest valid information in the event flow, reflecting whether the data still reflects the current true state. Filtering indicators using event flow structure entropy and information freshness allows for dynamic evaluation of indicator effectiveness, resulting in more stable and reliable filtering results.

[0055] For example, for each indicator i in the candidate indicator set, based on its calculation logic, all relevant business chain instances within the historical M periods are extracted from the business event chain. For each completed business chain, its structural features are extracted to form a vector K, which includes: duration (total time of the chain), number of nodes (number of business events traversed by the chain), and number of backflows (whether event state rollback or repetition occurs in the chain). In the current scenario j, these chain vectors are clustered, and chains with similar patterns are grouped into one category. The business chain structure entropy of the indicator in the current scenario is calculated. The formula is as follows:

[0056]

[0057] in, This represents the proportion of chains belonging to process mode c in the historical cycle to the total number of chains. The higher the value, the more diverse and unstable the business chain behind the indicator, and the more unpredictable the process is.

[0058] Furthermore, for index i, a kernel density estimation probability distribution model is constructed using the business chain feature vectors of its first M-1 cycles. Then, obtain the feature vector of the business chain formed in the current cycle. The likelihood value is calculated by inputting it into a probability model. A lower likelihood value indicates that the current behavioral pattern is historically rarer, reflecting the freshness of the information. The higher the value, the better. The formula is as follows:

[0059]

[0060] in, It is the probability density of the current data under the historical probability model, which has been normalized to the [0,1] interval.

[0061] Furthermore, a screening value score is calculated for each indicator i in the current scenario j. :

[0062]

[0063] in, The normalized structural entropy value (takes values ​​[0,1]); The normalized information freshness value (values ​​range from [0,1]); η is the balance coefficient, with a range of 0 ≤ η ≤ 1, and an initial value of 0.5 can be set. All indicators are then processed according to... Sort from highest to lowest, the system automatically selects the top K indicators, or selects... Indicators that exceed the dynamic threshold constitute the optimal set of evaluation indicators for the current period.

[0064] S206: Obtain the current indicator value corresponding to each current evaluation indicator in the business event chain, and assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario.

[0065] Optionally, core information such as event time, participating entities, and business attributes can be extracted from standardized data in the business event chain to calculate the actual values ​​of each indicator. These values ​​are then normalized to generate a four-dimensional data table consisting of indicator-actual value-normalized value-scenario label. Subsequently, based on a preset scenario-indicator importance mapping rule, a scenario attribute factor is assigned to each selected evaluation indicator. This factor directly reflects the indicator's core importance in the current business scenario. For example, for high-priority indicators such as procurement response time in emergency repair scenarios, the scenario attribute factor ranges from 0.7 to 1.0.

[0066] In other embodiments, the current business scenario can also be used to filter the evaluation indicator library to obtain the current evaluation indicator set. Specifically, based on preset scenario-indicator association rules, the evaluation indicator set applicable to the current business scenario is automatically filtered from the basic evaluation indicator library. For example, for emergency repair scenarios, indicators with high timeliness and urgency are prioritized, such as procurement response time, timely warehousing rate of emergency supplies, and abnormal event handling time, while low-timeliness related indicators under regular reserve scenarios are eliminated; for business expansion scenarios, indicators related to process timeliness and resource adaptation are retained, such as contract signing time, material demand fulfillment rate, and cross-departmental collaboration efficiency; for regular reserve scenarios, indicators covering all four dimensions are comprehensively covered, with emphasis on indicators such as inventory turnover rate, long-term supplier collaboration quality, and process standardization execution rate. The indicator set after scenario-based filtering serves as the core indicator for the current evaluation, supports manual fine-tuning according to business needs, and the fine-tuning records will be retained by the system for subsequent self-optimization of the indicator system.

[0067] S208: For each current evaluation indicator, obtain the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator, and obtain the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor and real-time volatility factor.

[0068] Optionally, for each current evaluation indicator, the correlation coefficient between the indicator value and the overall response efficiency over the past N evaluation periods is calculated. After normalizing the correlation coefficient, a historical contribution factor is obtained. The higher the correlation coefficient, the greater the historical impact of the indicator on efficiency evaluation, and the higher the value of the historical contribution factor, thus quantifying the long-term value of the indicator. Simultaneously, the rate of change of each indicator value relative to the previous period is calculated, and the rate of change is inversely normalized to obtain a real-time volatility factor. The greater the fluctuation of the indicator value (such as a sudden rise / fall in anomaly control indicators), the more significant its current impact on efficiency, and the higher the value of the real-time volatility factor, thus effectively capturing the impact of real-time changes in the indicator on the evaluation. Finally, the scenario attribute factor, historical contribution factor, and real-time volatility factor are coupled to obtain a comprehensive weighted influence factor for each evaluation indicator.

[0069] S210: Obtain dynamic weights based on the comprehensive weighting influence factor and the number of current evaluation indicators, and correct the current indicator values ​​according to the type of current evaluation indicators to obtain the target indicator values.

[0070] Optionally, dynamic weights for indicators are generated using a comprehensive weighting factor as the core, and corresponding dynamic weights are assigned to the current evaluation indicators, ensuring that the sum of the dynamic weights of all current evaluation indicators is 1, thus achieving reasonable weight allocation and scenario adaptation. The current evaluation indicators include positive, negative, and range indicators that affect overall response efficiency. Higher values ​​for positive indicators contribute more positively to the overall supply chain response efficiency, aligning perfectly with the evaluation objective of "the higher the efficiency, the better," directly reflecting improvements in supply chain execution quality, response timeliness, and closed-loop capabilities. Higher values ​​for negative indicators have a greater negative impact on overall supply chain response efficiency, contradicting the evaluation objective and directly reducing process timeliness, extending business cycles, and slowing emergency response. Range indicators, whether too high or too low, weaken overall supply chain response efficiency. They contribute most to efficiency improvement only when close to the optimal value; deviations from the optimal range lead to resource waste, supply-demand imbalances, or increased costs, thereby reducing overall response effectiveness. By calibrating different types of evaluation indicators according to evaluation logic, we ensure that all indicators meet the unified logic that "the larger the value, the higher the supply chain response efficiency".

[0071] S212: The dynamic weights and target index values ​​are processed through the response efficiency model to obtain the comprehensive response efficiency of the business event chain, and the efficiency of the business event chain is evaluated based on the comprehensive response efficiency.

[0072] Optionally, after calibrating all indicators, they are input into the response efficiency model along with their corresponding dynamic weights to obtain the comprehensive supply chain response efficiency index. The response efficiency model includes nonlinear correction and collaborative equilibrium correction, avoiding the homogenization of conventional weighted summation. It considers not only the weight and value of individual indicators but also incorporates the nonlinear characteristics of indicator contribution and the collaborative equilibrium of the entire supply chain, thus more accurately reflecting the actual response efficiency. Finally, the comprehensive response efficiency is graded based on preset positive thresholds, and the grading results directly serve management decisions. For example, a comprehensive response efficiency ≥ 0.8 is excellent; 0.6 ≤ comprehensive response efficiency < 0.8 is good; 0.4 ≤ comprehensive response efficiency < 0.6 is average; and a comprehensive response efficiency < 0.4 is poor.

[0073] The aforementioned business event chain response efficiency evaluation method obtains the business event chain based on the business events corresponding to the original data of each business system. Based on the event flow structure entropy and information freshness, it retrieves the current evaluation indicator set from the evaluation indicator library, obtains the current indicator value corresponding to each current evaluation indicator for the business event chain, and assigns corresponding scenario attribute factors. Based on historical contribution factors and real-time fluctuation factors, it obtains a comprehensive weight influence factor, thereby obtaining dynamic weights. The current indicator value is then corrected according to the type of the current evaluation indicator to obtain the target indicator value. The dynamic weights and target indicator value are processed through a response efficiency model to obtain the comprehensive response efficiency of the business event chain. The efficiency of the business event chain is then evaluated based on the comprehensive response efficiency. This method can eliminate data structure differences, improve the matching degree between evaluation indicators and scenario requirements, and make the weight allocation more closely aligned with the dynamic operating characteristics of the business event chain. It ensures that the evaluation results accurately reflect the real-time response efficiency of the business event chain, thereby improving the intelligence and refinement level of business management.

[0074] In an exemplary embodiment, the step of obtaining a business event chain based on a business event includes: obtaining the participating entities of the business event; mapping the participating entities to preset entity identifiers, and aligning the fields of the mapped business events to obtain standardized events; sorting the standardized events according to business relationships to obtain a business event chain; and arranging the business events in the business event chain in order of business time.

[0075] Optionally, entity alignment is performed on business events. Since the representation of the same entity may differ across systems—for example, the supplier name in a procurement system may not be entirely consistent with the contracting entity in a contract system—entity names in each system are mapped to unified entity identifiers by loading the master data dictionary. This ensures that records of the same supplier, department, or warehouse in different business processes can be accurately associated. After entity alignment, various fields in the event are uniformly converted. For example, the time field is converted to a unified format and time zone is calibrated; the amount and quantity fields are converted to a unified numerical precision; and the status field is mapped to a predefined set of enumerated values. This process eliminates format inconsistencies caused by differences in data modeling across systems, making the same type of event comparable across different sources.

[0076] Furthermore, after field standardization, based on the business document numbering system and combined with pre-defined business association rules, related events scattered across different systems are linked into a complete business chain. Through this process, the heterogeneous data originally scattered across various systems is transformed into event stream data with unified timestamps, standardized fields, clear entity identifiers, temporal relationships, and scenario tags. These event streams are no longer unordered business records, but rather continuous sequences organized chronologically. Each record retains its traceability to the original business document and possesses the capability for cross-system correlation analysis. The final output event stream data is persistently stored for subsequent indicator system construction, network modeling, and dynamic weight calculation.

[0077] In this embodiment, by obtaining the participating entities of the business event, mapping the participating entities to preset entity identifiers, and aligning the fields of the mapped business events to obtain standardized events, and sorting the standardized events according to the business relationship to obtain the business event chain, the differences in data structure can be eliminated, the problem of inconsistent entity descriptions can be avoided, thereby ensuring the integrity, consistency and traceability of the evaluation data and improving the reliability of the data.

[0078] In an exemplary embodiment, the steps of obtaining the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator include: obtaining the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods prior to the current evaluation period, and obtaining the correlation coefficient between the first historical indicator value and the historical response efficiency; normalizing the correlation coefficient to obtain the historical contribution factor corresponding to the current evaluation indicator; obtaining the second historical indicator value within the previous evaluation period of the current evaluation period, and obtaining the volatility change rate based on the current indicator value and the second historical indicator value; and normalizing the volatility change rate to obtain the real-time volatility factor corresponding to the current evaluation indicator.

[0079] Optionally, the Pearson correlation coefficient between each indicator value and the overall supply chain response efficiency over the past N evaluation periods is calculated. The correlation coefficient is then normalized to obtain the historical contribution factor β (β takes values ​​of [0,1]). A higher correlation coefficient indicates a greater historical impact of the indicator on efficiency assessment, and a higher β value quantifies the long-term value of the indicator. The formula for calculating the Pearson correlation coefficient is as follows:

[0080]

[0081] Where r is the Pearson correlation coefficient between a single evaluation indicator and the overall supply chain response efficiency, with a value range of [-1, 1]; r > 0 indicates a positive correlation (indicator optimization helps improve efficiency), r < 0 indicates a negative correlation (indicator optimization needs to be suppressed to improve efficiency), and the larger |r| is, the stronger the correlation; N is the preset number of historical evaluation periods (which can be adjusted according to business needs, such as N = 12 representing the last 12 periods); x i The normalized index value corresponding to the current evaluation index in the i-th historical evaluation period; This is the average value of the current evaluation indicator over the past N historical evaluation periods, i.e. ;y i This represents the overall response efficiency value for the i-th historical evaluation period; It is the average of the overall response efficiency values ​​over the past N historical evaluation periods, i.e. .

[0082] The historical contribution factor β is converted to meet the requirements through normalization, as shown in the following formula:

[0083]

[0084] Wherein, β is the historical contribution factor, with a value range of [0,1]. A higher value indicates a greater historical impact of this indicator on efficiency assessment; r min The minimum Pearson correlation coefficient between the current evaluation indicator and the overall response efficiency value over the past N historical evaluation periods; r max It represents the maximum Pearson correlation coefficient between the current evaluation indicator and the overall response efficiency value over the past N historical evaluation periods.

[0085] Optionally, the rate of change of the normalized value of each indicator within the current evaluation period relative to the previous period is calculated, and the rate of change is inversely normalized to obtain the real-time volatility factor γ (with a value of [0,1]). The greater the fluctuation of the indicator value (such as a sudden rise / fall in abnormal control indicators), the more significant its current impact on efficiency, and the higher the γ value, thus capturing the impact of real-time changes in the indicators on the evaluation.

[0086] For example, calculate the rate of change Δx of the indicator value during the current evaluation period:

[0087]

[0088] Where, x curr x is the normalized value of a certain evaluation indicator within the current evaluation period; prev This is the normalized value of the indicator for the previous evaluation period.

[0089] Normalizing the rate of change of volatility by Δx yields the real-time volatility factor γ:

[0090]

[0091] Where, Δx min This represents the minimum rate of change of this indicator over the historical evaluation period (the lowest historical value across the entire domain, initially set at 0, and continuously updated over the evaluation period); Δx max This represents the maximum rate of change of this indicator during the historical evaluation period (the maximum historical value across the entire domain, continuously updated with each evaluation period).

[0092] In this embodiment, by obtaining the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods prior to the current evaluation period, and obtaining the correlation coefficient between the first historical indicator value and the historical response efficiency, and normalizing the correlation coefficient, the historical contribution factor corresponding to the current evaluation indicator is obtained. The second historical indicator value within the previous evaluation period of the current evaluation period is obtained, and the fluctuation rate is obtained based on the current indicator value and the second historical indicator value. The fluctuation rate is normalized to obtain the real-time volatility factor corresponding to the current evaluation indicator. This can accurately quantify the long-term impact and real-time change impact of the evaluation indicator, thereby improving the accuracy of subsequent comprehensive weighting.

[0093] In an exemplary embodiment, the step of obtaining the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor, and real-time volatility factor includes: constructing a weighted coupling function and a linear modulation function based on the dimensionality sensitivity coefficient, and obtaining a scenario correction function based on the current business scenario; coupling the scenario attribute factor, historical contribution factor, and real-time volatility factor based on the weighted coupling function, the linear modulation function, and the scenario correction function to obtain the comprehensive weight influence factor corresponding to the current evaluation indicator; wherein, the dimensionality sensitivity coefficient is used to adjust the influence ratio of the scenario attribute factor, historical contribution factor, and real-time volatility factor in the coupling process.

[0094] Optionally, the weighted coupling function adjusts the influence ratio of each factor in the coupling process through a dimensionality sensitivity coefficient, making the coupling closer to the business logic that "when the scenario is of high importance and fluctuates greatly in real time, the weight should be non-linearly amplified," resulting in a more accurate weighting result. The scenario correction function presents different calculation logics under different business scenarios, such as "emergency repair scenario (high α)" and "routine reserve scenario (low α)," without the need for manual parameter adjustment, achieving scenario adaptive adjustment.

[0095] For example, based on a weighted coupling function, a linear modulation function, and a scene correction function, the scene attribute factor, historical contribution factor, and real-time volatility factor are coupled. The mathematical expression for the comprehensive weighted influence factor is then:

[0096]

[0097] Where μ, ν, and ω are the dimensionality sensitivity coefficients of the scene attribute factor α, the historical contribution factor β, and the real-time volatility factor γ, respectively, which are used to adjust the influence ratio of each factor in the coupling process. It is a three-dimensional factor geometric weighted coupling function; Let ξ be the linear reference modulation function, and ξ be the linear reference modulation coefficient. This constitutes the scene dynamic correction module; λ is the gain coefficient.

[0098] Furthermore, the comprehensive weighting influence factor F of the screening and evaluation indicators is weighted to obtain the dynamic weight W of each indicator, and its mathematical formula is as follows:

[0099]

[0100] Among them, W i F represents the dynamic weight of the i-th evaluation indicator. i Let be the comprehensive weighting factor of the i-th evaluation indicator; n is the number of evaluation indicators in the current business scenario, and satisfies . This enables reasonable weight allocation and scene adaptation.

[0101] In this embodiment, a weighted coupling function and a linear modulation function are constructed based on the dimensionality sensitivity coefficient, and a scenario correction function is obtained based on the current business scenario. Based on the weighted coupling function, the linear modulation function, and the scenario correction function, the scenario attribute factor, the historical contribution factor, and the real-time volatility factor are coupled to obtain the comprehensive weight influence factor corresponding to the current evaluation indicator. This can comprehensively consider the differences in the importance of indicators under different scenarios, accurately quantify the long-term impact and real-time change impact of indicators, avoid the distortion of evaluation results caused by fixed weights, and make the weight allocation more in line with the dynamic operation characteristics of the supply chain, thereby improving the accuracy of evaluation.

[0102] In an exemplary embodiment, the step of correcting the current indicator value according to the type of the current evaluation indicator to obtain the target indicator value includes: if the current evaluation indicator is a first type of indicator, taking the current indicator value as the target indicator value; if the current evaluation indicator is a second type of indicator, taking the difference between 1 and the current indicator value as the target indicator value; if the current evaluation indicator is a third type of indicator, obtaining the absolute distance between the current indicator value and a preset indicator value, and taking the difference between 1 and the absolute distance as the target indicator value; wherein, the first type of indicator is a positive indicator affecting the comprehensive response efficiency, the second type of indicator is a negative indicator affecting the comprehensive response efficiency, and the third type of indicator is an interval indicator affecting the comprehensive response efficiency.

[0103] Optionally, for indicators of different logic types, logic calibration is performed in the positive number range of 0-1 to ensure that all indicators meet the unified logic that "the larger the value, the better the supply chain response efficiency".

[0104] Specifically, for high-efficiency logical indicators (such as on-time warehousing rate, supplier response time rate, and abnormal event closure rate): calibration value Xi′=X i (X) i The current indicator value is [0,1], and the original numerical logic is consistent with the evaluation target, so no adjustment is needed.

[0105] For inefficient logical indicators (such as procurement response time, contract signing time, and abnormal event handling time): Calibration value Xi′=1-X i The logic is reversed by subtracting positive numbers, and the value range after calibration is still [0,1], which matches the unified evaluation logic.

[0106] For interval logic indicators (such as inventory turnover rate and transportation capacity utilization rate): Calibration value (X0 is a preset index value, which takes the value of [0,1]). After calibration, the value range is still [0,1], realizing the evaluation logic that "the closer the value is to the optimal value, the larger the calibration value is, and the better the efficiency".

[0107] In this embodiment, by correcting the current indicator value according to the type of the current evaluation indicator, the target indicator value can be obtained, which can ensure the consistency of the evaluation logic and thus improve the accuracy of the evaluation results.

[0108] In an exemplary embodiment, the process of obtaining the response efficiency model includes: constructing a nonlinear correction function based on the nonlinear correction coefficient of the indicator contribution, and constructing a collaborative equilibrium correction function; the nonlinear correction coefficient of the indicator contribution is used to nonlinearly amplify the target indicator value; and obtaining the response efficiency model based on the nonlinear correction function and the collaborative equilibrium correction function.

[0109] For example, the mathematical expression for the response efficiency model is:

[0110]

[0111] Where E represents the overall response efficiency; It is a nonlinear correction function; W is the cooperative equilibrium correction function; i X represents the dynamic weight of the i-th evaluation indicator; i ′ represents the target value of the i-th evaluation indicator; W k X represents the dynamic weight of the k-th evaluation indicator; k ' is the target value of the k-th evaluation indicator; n is the number of evaluation indicators in the current business scenario; α E This is a nonlinear correction coefficient for the contribution of indicators, used to slightly amplify the calibrated indicator values ​​nonlinearly, strengthen the positive contribution of high-value indicators, and conform to the evaluation logic of "maximizing the contribution of excellent indicators and weakening the contribution of poor indicators".

[0112] The value of E ranges from [0,1]. The closer the value of E is to 1, the higher the response efficiency; the closer the value of E is to 0, the lower the response efficiency. The results intuitively match industry evaluation practices.

[0113] In this embodiment, by employing nonlinear correction and collaborative equilibrium correction, it is possible to ensure that the evaluation results accurately reflect the real-time response efficiency of the business event chain, thereby improving the accuracy of the evaluation results and enhancing the intelligence and refinement of business management.

[0114] In one exemplary embodiment, such as Figure 3 As shown, a method for evaluating the response efficiency of a business event chain is provided, which includes the following steps:

[0115] (1) Standardized processing of business event chain: Obtain the business events corresponding to the original data of each business system and obtain the participating entities of the business events; map the participating entities to preset entity identifiers and perform field alignment on the mapped business events to obtain standardized events; sort the standardized events according to the business relationship to obtain the business event chain; the business events in the business event chain are arranged in the order of business time.

[0116] (2) Evaluation index set selection: Obtain the pre-established evaluation index library, and obtain the current evaluation index set from the evaluation index library according to the event flow structure entropy and information freshness; the current evaluation index set includes multiple current evaluation indicators.

[0117] (3) Multi-dimensional factor calculation: Obtain the current indicator value corresponding to each current evaluation indicator in the business event chain, and assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario. For each current evaluation indicator, obtain the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods before the current evaluation period, and obtain the correlation coefficient between the first historical indicator value and the historical response efficiency; normalize the correlation coefficient to obtain the historical contribution factor corresponding to the current evaluation indicator; obtain the second historical indicator value within the previous evaluation period of the current evaluation period, normalize the fluctuation rate to obtain the real-time volatility factor corresponding to the current evaluation indicator.

[0118] (4) Dynamic weight coupling: Construct a weighted coupling function and a linear modulation function based on the dimension sensitivity coefficient, and obtain a scenario correction function based on the current business scenario; based on the weighted coupling function, the linear modulation function and the scenario correction function, couple the scenario attribute factor, the historical contribution factor and the real-time volatility factor to obtain the comprehensive weight influence factor corresponding to the current evaluation index; obtain the dynamic weight based on the comprehensive weight influence factor and the number of current evaluation indicators; among them, the dimension sensitivity coefficient is used to adjust the influence ratio of the scenario attribute factor, the historical contribution factor and the real-time volatility factor in the coupling process.

[0119] (5) Dynamic scenario indicator correction: When the current evaluation indicator is a first-class indicator, the current indicator value is used as the target indicator value; when the current evaluation indicator is a second-class indicator, the difference between 1 and the current indicator value is used as the target indicator value; when the current evaluation indicator is a third-class indicator, the absolute distance between the current indicator value and the preset indicator value is obtained, and the difference between 1 and the absolute distance is used as the target indicator value; where the first-class indicator is a positive indicator affecting the comprehensive response efficiency, the second-class indicator is a negative indicator affecting the comprehensive response efficiency, and the third-class indicator is an interval indicator affecting the comprehensive response efficiency.

[0120] (6) Comprehensive Response Efficiency Assessment: A nonlinear correction function is constructed based on the nonlinear correction coefficient of the indicator contribution, and a collaborative equilibrium correction function is also constructed. The nonlinear correction coefficient of the indicator contribution is used to nonlinearly amplify the target indicator value. Based on the nonlinear correction function and the collaborative equilibrium correction function, a response efficiency model is obtained. The dynamic weights and target indicator values ​​are processed through the response efficiency model to obtain the comprehensive response efficiency of the business event chain, and the efficiency of the business event chain is assessed based on the comprehensive response efficiency.

[0121] In this embodiment, a business event chain is obtained based on the business events corresponding to the original data of each business system. Based on the event flow structure entropy and information freshness, the current evaluation indicator set is retrieved from the evaluation indicator library. The current indicator value corresponding to each current evaluation indicator for the business event chain is obtained, and corresponding scenario attribute factors are assigned. Based on the historical contribution factor and real-time fluctuation factor, a comprehensive weight influence factor is obtained, leading to dynamic weights. The current indicator value is then corrected according to the type of the current evaluation indicator to obtain the target indicator value. The dynamic weights and target indicator value are processed through a response efficiency model to obtain the comprehensive response efficiency of the business event chain. The efficiency of the business event chain is then evaluated based on the comprehensive response efficiency. This process eliminates data structure differences, improves the matching degree between evaluation indicators and scenario requirements, and makes the weight allocation more closely aligned with the dynamic operating characteristics of the business event chain. This ensures that the evaluation results accurately reflect the real-time response efficiency of the business event chain, thereby improving the intelligence and refinement of business management.

[0122] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0123] Based on the same inventive concept, this application also provides a business event chain response efficiency evaluation device for implementing the business event chain response efficiency evaluation method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more embodiments of the business event chain response efficiency evaluation device provided below can be found in the limitations of the business event chain response efficiency evaluation method described above, and will not be repeated here.

[0124] In one exemplary embodiment, such as Figure 4 As shown, a business event chain response efficiency evaluation device is provided, including: an event chain acquisition module 10, an indicator acquisition module 20, an indicator calculation module 30, a weight acquisition module 40, an indicator correction module 50, and an efficiency evaluation module 60, wherein:

[0125] The event chain acquisition module 10 is used to acquire the business events corresponding to the raw data of each business system, and to acquire the business event chain based on the business events.

[0126] The indicator acquisition module 20 is used to acquire a pre-established evaluation indicator library and, based on the event flow structure entropy and information freshness, acquire the current evaluation indicator set from the evaluation indicator library; the current evaluation indicator set includes multiple current evaluation indicators.

[0127] The indicator calculation module 30 is used to obtain the current indicator value corresponding to each current evaluation indicator in the business event chain, and to assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario.

[0128] The weight acquisition module 40 is used to obtain the historical contribution factor and real-time volatility factor corresponding to each current evaluation indicator, and to obtain the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor and real-time volatility factor.

[0129] The indicator correction module 50 is used to obtain dynamic weights based on the comprehensive weight influence factor and the number of current evaluation indicators, and to correct the current indicator value according to the type of the current evaluation indicator to obtain the target indicator value.

[0130] The efficiency evaluation module 60 is used to process the dynamic weights and target indicator values ​​through the response efficiency model to obtain the comprehensive response efficiency of the business event chain, and to evaluate the efficiency of the business event chain based on the comprehensive response efficiency.

[0131] In an exemplary embodiment, the event chain acquisition module 10 is further configured to acquire the participating entities of the business event; map the participating entities to preset entity identifiers, and perform field alignment on the mapped business events to obtain standardized events; sort the standardized events according to the business association relationship to obtain a business event chain; and arrange the business events in the business event chain in the order of business time.

[0132] In an exemplary embodiment, the weight acquisition module 40 is further configured to acquire the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods prior to the current evaluation period, and acquire the correlation coefficient between the first historical indicator value and the historical response efficiency; normalize the correlation coefficient to obtain the historical contribution factor corresponding to the current evaluation indicator; acquire the second historical indicator value within the previous evaluation period of the current evaluation period, and acquire the volatility change rate based on the current indicator value and the second historical indicator value; normalize the volatility change rate to obtain the real-time volatility factor corresponding to the current evaluation indicator.

[0133] In an exemplary embodiment, the weight acquisition module 40 is further configured to construct a weighted coupling function and a linear modulation function based on the dimension sensitivity coefficient, and to acquire a scenario correction function based on the current business scenario; based on the weighted coupling function, the linear modulation function, and the scenario correction function, the scenario attribute factor, the historical contribution factor, and the real-time volatility factor are coupled to obtain the comprehensive weight influence factor corresponding to the current evaluation index; wherein, the dimension sensitivity coefficient is used to adjust the influence ratio of the scenario attribute factor, the historical contribution factor, and the real-time volatility factor in the coupling process.

[0134] In an exemplary embodiment, the indicator correction module 50 is further configured to: when the current evaluation indicator is a first type of indicator, use the current indicator value as the target indicator value; when the current evaluation indicator is a second type of indicator, use the difference between 1 and the current indicator value as the target indicator value; when the current evaluation indicator is a third type of indicator, obtain the absolute distance between the current indicator value and a preset indicator value, and use the difference between 1 and the absolute distance as the target indicator value; wherein, the first type of indicator is a positive indicator affecting the comprehensive response efficiency, the second type of indicator is a negative indicator affecting the comprehensive response efficiency, and the third type of indicator is an interval indicator affecting the comprehensive response efficiency.

[0135] In an exemplary embodiment, the efficiency evaluation module 60 is further configured to construct a nonlinear correction function based on the nonlinear correction coefficient of the indicator contribution, and to construct a collaborative equilibrium correction function; the nonlinear correction coefficient of the indicator contribution is used to nonlinearly amplify the target indicator value; and the response efficiency model is obtained based on the nonlinear correction function and the collaborative equilibrium correction function.

[0136] Each module in the aforementioned business event chain response efficiency evaluation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0137] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for evaluating the response efficiency of a business event chain. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0138] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0139] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps: acquiring business events corresponding to the original data of each business system, and acquiring business event chains based on the business events; acquiring a pre-established evaluation index library, and acquiring a current evaluation index set from the evaluation index library based on the event flow structure entropy and information freshness; the current evaluation index set includes multiple current evaluation indicators; acquiring the current index values ​​corresponding to each current evaluation indicator for the business event chain, and assigning corresponding scenario attribute factors to the current index values ​​based on the current business scenario; for each current evaluation indicator, acquiring the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator, and acquiring the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, historical contribution factor, and real-time volatility factor; acquiring dynamic weights based on the comprehensive weight influence factor and the number of current evaluation indicators, and correcting the current index values ​​based on the type of current evaluation indicators to obtain target index values; processing the dynamic weights and target index values ​​through a response efficiency model to obtain the comprehensive response efficiency of the business event chain, and evaluating the efficiency of the business event chain based on the comprehensive response efficiency.

[0140] In one embodiment, the process of obtaining a business event chain based on business events when the processor executes a computer program includes: obtaining participating entities of the business events; mapping the participating entities to preset entity identifiers and aligning the fields of the mapped business events to obtain standardized events; sorting the standardized events according to business relationships to obtain a business event chain; and arranging the business events in the business event chain in business time order.

[0141] In one embodiment, the process of obtaining the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator when the processor executes the computer program includes: obtaining the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods prior to the current evaluation period, and obtaining the correlation coefficient between the first historical indicator value and the historical response efficiency; normalizing the correlation coefficient to obtain the historical contribution factor corresponding to the current evaluation indicator; obtaining the second historical indicator value within the previous evaluation period of the current evaluation period, and obtaining the volatility change rate based on the current indicator value and the second historical indicator value; and normalizing the volatility change rate to obtain the real-time volatility factor corresponding to the current evaluation indicator.

[0142] In one embodiment, when a processor executes a computer program, it obtains the comprehensive weight influence factor corresponding to the current evaluation indicator based on scenario attribute factors, historical contribution factors, and real-time volatility factors. This includes: constructing a weighted coupling function and a linear modulation function based on a dimensionality sensitivity coefficient, and obtaining a scenario correction function based on the current business scenario; coupling the scenario attribute factors, historical contribution factors, and real-time volatility factors based on the weighted coupling function, the linear modulation function, and the scenario correction function to obtain the comprehensive weight influence factor corresponding to the current evaluation indicator; wherein, the dimensionality sensitivity coefficient is used to adjust the influence ratio of the scenario attribute factors, historical contribution factors, and real-time volatility factors in the coupling process.

[0143] In one embodiment, when the processor executes a computer program, it corrects the current indicator value according to the type of the current evaluation indicator to obtain a target indicator value, including: if the current evaluation indicator is a first type of indicator, taking the current indicator value as the target indicator value; if the current evaluation indicator is a second type of indicator, taking the difference between 1 and the current indicator value as the target indicator value; if the current evaluation indicator is a third type of indicator, obtaining the absolute distance between the current indicator value and a preset indicator value, and taking the difference between 1 and the absolute distance as the target indicator value; wherein, the first type of indicator is a positive indicator affecting the overall response efficiency, the second type of indicator is a negative indicator affecting the overall response efficiency, and the third type of indicator is an interval indicator affecting the overall response efficiency.

[0144] In one embodiment, the process of obtaining the response efficiency model involved when the processor executes a computer program includes: constructing a nonlinear correction function based on the nonlinear correction coefficient of the indicator contribution, and constructing a collaborative equilibrium correction function; the nonlinear correction coefficient of the indicator contribution is used to nonlinearly amplify the target indicator value; and obtaining the response efficiency model based on the nonlinear correction function and the collaborative equilibrium correction function.

[0145] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0146] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0147] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0148] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0149] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for evaluating the response efficiency of a business event chain, characterized in that, The method includes: Obtain the business events corresponding to the raw data of each business system, and obtain the business event chain based on the business events; Obtain a pre-established evaluation index library, and retrieve the current evaluation index set from the evaluation index library based on the event flow structure entropy and information freshness; the current evaluation index set includes multiple current evaluation indicators. Obtain the current indicator value corresponding to each current evaluation indicator for the business event chain, and assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario; For each of the current evaluation indicators, obtain the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator, and obtain the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, the historical contribution factor and the real-time volatility factor. Dynamic weights are obtained based on the comprehensive weighting influence factor and the number of current evaluation indicators, and the current indicator values ​​are corrected according to the type of the current evaluation indicators to obtain the target indicator values. The dynamic weights and target index values ​​are processed by a response efficiency model to obtain the comprehensive response efficiency of the business event chain, and the efficiency of the business event chain is evaluated based on the comprehensive response efficiency.

2. The method according to claim 1, characterized in that, The step of obtaining the business event chain based on the business event includes: Obtain the participating entities of the business event; The participating entities are mapped to preset entity identifiers, and the fields of the mapped business events are aligned to obtain standardized events; The standardized events are sorted according to business relationships to obtain a business event chain; the business events in the business event chain are arranged in business time order.

3. The method according to claim 1, characterized in that, The step of obtaining the historical contribution factor and real-time volatility factor corresponding to the current evaluation indicator includes: Obtain the first historical indicator value and historical response efficiency within a preset number of historical evaluation periods prior to the current evaluation period, and obtain the correlation coefficient between the first historical indicator value and the historical response efficiency; The correlation coefficients are normalized to obtain the historical contribution factors corresponding to the current evaluation indicators. Obtain the second historical indicator value from the previous evaluation period of the current evaluation period, and obtain the volatility rate based on the current indicator value and the second historical indicator value; The volatility change rate is normalized to obtain the real-time volatility factor corresponding to the current evaluation index.

4. The method according to claim 1, characterized in that, The step of obtaining the comprehensive weighting influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, the historical contribution factor, and the real-time volatility factor includes: A weighted coupling function and a linear modulation function are constructed based on the dimension sensitivity coefficient, and a scenario correction function is obtained based on the current business scenario. Based on the weighted coupling function, the linear modulation function, and the scene correction function, the scene attribute factor, the historical contribution factor, and the real-time volatility factor are coupled to obtain the comprehensive weight influence factor corresponding to the current evaluation index; wherein, the dimensionality sensitivity coefficient is used to adjust the influence ratio of the scene attribute factor, the historical contribution factor, and the real-time volatility factor in the coupling process.

5. The method according to claim 1, characterized in that, The step of correcting the current indicator value according to the type of the current evaluation indicator to obtain the target indicator value includes: If the current evaluation indicator is a first-class indicator, the current indicator value will be used as the target indicator value. When the current evaluation indicator is a second type of indicator, the difference between 1 and the current indicator value is taken as the target indicator value; When the current evaluation indicator is a third type of indicator, the absolute distance between the current indicator value and the preset indicator value is obtained, and the difference between 1 and the absolute distance is taken as the target indicator value; wherein, the first type of indicator is a positive indicator affecting the comprehensive response efficiency, the second type of indicator is a negative indicator affecting the comprehensive response efficiency, and the third type of indicator is an interval indicator affecting the comprehensive response efficiency.

6. The method according to claim 1, characterized in that, The process of obtaining the response efficiency model includes: A nonlinear correction function is constructed based on the nonlinear correction coefficient of the indicator contribution, and a collaborative equilibrium correction function is also constructed; the nonlinear correction coefficient of the indicator contribution is used to nonlinearly amplify the target indicator value. The response efficiency model is obtained based on the nonlinear correction function and the cooperative equilibrium correction function.

7. A business event chain response efficiency evaluation device, characterized in that, The device includes: The event chain acquisition module is used to acquire the business events corresponding to the raw data of each business system, and to acquire the business event chain based on the business events. The indicator acquisition module is used to acquire a pre-established evaluation indicator library and, based on the event flow structure entropy and information freshness, acquire the current evaluation indicator set from the evaluation indicator library; the current evaluation indicator set includes multiple current evaluation indicators. The indicator calculation module is used to obtain the current indicator value corresponding to each current evaluation indicator of the business event chain, and to assign the corresponding scenario attribute factor to the current indicator value according to the current business scenario; The weight acquisition module is used to acquire the historical contribution factor and real-time volatility factor corresponding to each current evaluation indicator, and to acquire the comprehensive weight influence factor corresponding to the current evaluation indicator based on the scenario attribute factor, the historical contribution factor and the real-time volatility factor. The indicator correction module is used to obtain dynamic weights based on the comprehensive weight influence factor and the number of current evaluation indicators, and to correct the current indicator value according to the type of the current evaluation indicator to obtain the target indicator value. The efficiency evaluation module is used to process the dynamic weights and the target indicator values ​​through a response efficiency model to obtain the comprehensive response efficiency of the business event chain, and to evaluate the efficiency of the business event chain based on the comprehensive response efficiency.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images