Enterprise management optimization method and system based on big data matching

Abstract

The invention relates to the technical field of enterprise management optimization, in particular to an enterprise management optimization method and system based on big data matching, and the method comprises the following steps: S1, collecting enterprise operation data, industry reference data and supply chain dynamic data, and outputting standardized enterprise data; s2, matching the standardized enterprise data with a preset industry feature library to generate a multi-dimensional service label set; s3, constructing a dynamic priority evaluation model, and generating a priority ranking matrix; s4, establishing a resource characteristic spectrum database, and generating a strategy matching degree matrix; s5, generating a resource configuration scheme according to the strategy matching degree matrix; and S6, when the monitoring threshold changes, triggering a weight calibration mechanism. According to the invention, through big data matching and dynamic priority evaluation, enterprise resource configuration decisions are optimized, operation efficiency and market adaptability are improved, and risks and cost are reduced at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise management optimization, and in particular to an enterprise management optimization method and system based on big data matching. Background Art

[0002] In modern enterprise management, especially when faced with complex supply chains, production processes, and market fluctuations, companies often rely on big data analysis to optimize resource allocation and improve operational efficiency. However, most existing enterprise management optimization methods rely on static data or a single management dimension for analysis, making it difficult to fully integrate dynamic data from different sources and levels, resulting in the inability to achieve accurate resource allocation and real-time decision support. Especially in complex and volatile business environments, traditional decision-making models often ignore real-time industry trends, changes in resource demand, and multi-dimensional risk analysis, making it difficult to provide companies with accurate and timely optimization solutions.

[0003] Therefore, leveraging big data technology and intelligent models to build a comprehensive, dynamic enterprise management optimization system to address issues such as uneven resource allocation, address supply chain risks, and enhance market responsiveness has become a pressing technical challenge in the field of enterprise management. Existing optimization methods lack the ability to deeply mine and intelligently match multi-dimensional enterprise data, making it impossible to analyze the correlations between different business flows. Furthermore, the lack of real-time and collaborative nature of multiple data sources leads to the risk of delayed and inaccurate decision-making. Summary of the Invention

[0004] Based on the above objectives, the present invention provides an enterprise management optimization method and system based on big data matching.

[0005] A method for optimizing enterprise management based on big data matching, comprising the following steps:

[0006] S1: Collect enterprise operation data, industry benchmark data and supply chain dynamic data, standardize the collected data, and output standardized enterprise data;

[0007] S2: Build a business flow feature labeling system and match standardized enterprise data with a preset industry feature library to generate a multi-dimensional business label set;

[0008] S3: Build a dynamic priority assessment model to dynamically assign weights to multi-dimensional business tags based on real-time industry trend forecast data and generate a priority ranking matrix.

[0009] S4: Establish a resource feature map database, and calculate the matching degree between each service tag in the priority ranking matrix and the resource feature map to generate a strategy matching matrix;

[0010] S5: Generate a resource allocation plan based on the strategy matching matrix and dynamically monitor the execution results of the resource allocation plan;

[0011] S6: When threshold changes are detected in industry benchmark data or supply chain parameters, the weight calibration mechanism will be triggered to update the standardized enterprise data output.

[0012] Optionally, the S1 specifically includes:

[0013] S11: Collect enterprise operation data, including internal financial data, production data, sales data and inventory data;

[0014] S12: Collect industry benchmark data, including industry standards, market trends and industry competition analysis data;

[0015] S13: Collect supply chain dynamic data, including raw material procurement data, supplier performance data, and transportation time data;

[0016] S14: Standardize the collected enterprise operation data, industry benchmark data, and supply chain dynamic data. The standardization includes:

[0017] S141: Convert data formats and unify data units, measurement standards, and field definitions to ensure data uniformity;

[0018] S142: Unify data from different sources at the semantic level through semantic analysis, and address differences in field names, value ranges, and business meanings among various data sources;

[0019] S143: Use a weighted approach to adjust the weights of collected data based on their importance, reliability, and relevance, ultimately generating standardized enterprise data.

[0020] Optionally, the S2 specifically includes:

[0021] S21: Extract relevant business entities from standardized enterprise data, including product features, customer profiles, supply chain nodes, and business process nodes, and uniquely identify each business entity;

[0022] S22: Based on the classification rules in the preset industry feature library, a multi-dimensional label classification system is constructed. The classification system includes business type dimension, resource requirement dimension, risk level dimension, and timeliness dimension. A label tree structure of no less than three levels is set under each dimension.

[0023] S23: Matching the business entity description in the standardized enterprise data with the label tree structure by calculating the similarity between the business entity description vector and the label vector;

[0024] S24: Confidence scores are assigned to the tag matching results of each business entity under the four dimensions, and the comprehensive matching degree is calculated using a weighted average method. When the comprehensive matching degree is lower than a preset threshold, manual verification is performed.

[0025] S25: The verified tag matching results are stored in a business feature tag database to generate a multi-dimensional business tag set including a business entity identifier, a dimension tag, a matching time, and a confidence score.

[0026] Optionally, the S3 specifically includes:

[0027] S31: Construct a dynamic priority assessment model, which includes three dimensions: cost sensitivity factor dimension, timeliness coefficient dimension, and risk fluctuation parameter dimension;

[0028] S32: Establish an industry trend forecasting interface to obtain industry prosperity index, supply chain price volatility, and policy and regulatory change data in real time through the API, and use a time series analysis model to generate trend forecast values ​​within the next T period, where T ranges from [3,12] months;

[0029] S33: Adjust the evaluation weights based on the three-dimensional evaluation indicators and industry trends to dynamically update the priority evaluation model;

[0030] S34: Calculate the final comprehensive priority score of each service tag based on the initial weight and trend prediction results of each service tag;

[0031] S35: Arrange all business tags in descending order according to the comprehensive priority scores, and generate a priority ranking matrix with business tag IDs as rows and evaluation dimension scores as columns. The matrix elements include the original scores, trend adjustment coefficients, and final rankings.

[0032] Optionally, the S34 specifically includes:

[0033] S341: Extract the initial value V=(v1, v2, v3) of the label in the three-dimensional evaluation index, where v1 is the initial value of the cost sensitivity factor, v2 is the initial value of the timeliness coefficient, and v3 is the initial value of the risk volatility parameter;

[0034] S342: Convert the trend prediction value into a trend adjustment coefficient matrix K = [k1, k2, k3], where

[0035] k1 = 1 + α × (predicted change rate 1) represents the trend adjustment coefficient of the cost dimension, k2 = 1 + α × (predicted change rate 2) represents the trend adjustment coefficient of the timeliness dimension, and k3 = 1 + α × (predicted change rate 3) represents the trend adjustment coefficient of the risk dimension; α is the dimension adjustment coefficient, and α∈[0,1];

[0036] S343: Calculate the comprehensive priority score. The formula is: Among them, W new [i] is the dynamic weight of the i-th dimension, V[i] is the initial value of the i-th dimension, and K[i] is the trend adjustment coefficient of the i-th dimension.

[0037] Optionally, the S4 specifically includes:

[0038] S41: Establishing a resource feature map database, the database including multiple resource nodes, each resource node corresponding to a resource type including funds, equipment, personnel, and materials, and each resource node having at least five resource attributes including resource category, available quantity, allocation time, usage restrictions, and resource value;

[0039] S42: Use data standardization methods to normalize the attributes of resource nodes and generate standardized resource feature data R resource ;

[0040] S43: For each business tag in the priority sorting matrix, extract its related business dimension information L business ;

[0041] S44: A similarity calculation method is used to calculate the matching degree between each service tag and each resource node in the resource feature map database. The formula is:

[0042] Among them, w i is the weight of each resource attribute, l i is the attribute value of the i-th dimension in the business tag, r i is the value of the i-th attribute in the resource node;

[0043] S45: Calculate the matching degree of each business tag with all resource nodes in the resource feature map, and then generate the strategy matching matrix M strategy .

[0044] Optionally, the S5 specifically includes:

[0045] S51: According to the strategy matching matrix M strategy The matching degree between each service label and resource node in the resource node is used to determine the resource configuration priority; specifically, for each service label L business , select the resource node R with the highest matching degree resource Allocate resources;

[0046] S52: Use linear programming method to allocate resources. Set the objective function to maximize resource utilization efficiency and generate a resource allocation plan. The expression of the objective function is:

[0047] Among them, S allocation is the generated resource allocation plan, w i is the priority weight of the resource node, is the available resource amount of the i-th resource node, and n is the total number of resource nodes.

[0048] Optionally, the S5 further includes:

[0049] S53: Dynamically monitor the execution results of the resource allocation plan, use a real-time data monitoring system to track resource usage, and obtain actual resource usage data;

[0050] S54: By comparing the actual usage with the preset resource requirements, deviation analysis is performed to calculate the resource allocation execution efficiency. The calculation formula is: in, is the available resource amount of the i-th resource node, is the actual usage of the i-th resource node, n is the total number of resource nodes, and Efficiency indicates the degree of deviation between the actual usage and the preset demand; the smaller the deviation value, the higher the execution efficiency.

[0051] Optionally, the S6 specifically includes:

[0052] S61: The trigger condition of the calibration mechanism is that the industry benchmark data or supply chain parameter changes by more than a predetermined percentage or value interval, expressed as: ΔX = |X new -X old |>δ, where ΔX is the data change, X new and X old are the new and old values ​​respectively, and δ is the preset threshold;

[0053] S62: After the calibration mechanism is triggered, an adaptive algorithm is used to dynamically adjust the weights in the standardized enterprise data;

[0054] S63: After weight adjustment, update the standardized enterprise data output to generate a new standardized data set D new .

[0055] A big data matching-based enterprise management optimization system, used to implement the above-mentioned big data matching-based enterprise management optimization method, includes the following modules:

[0056] Data collection module: used to collect enterprise operation data, industry benchmark data and supply chain dynamic data, and pre-process the collected data to output standardized enterprise data;

[0057] Business flow feature label construction module: used to extract key business entities from standardized enterprise data and build a business flow feature label system, generating a multi-dimensional business label set by matching it with a preset industry feature library;

[0058] Dynamic priority assessment module: Dynamically assigns weights to business tags based on a three-dimensional assessment indicator system and real-time industry trend forecast data to generate a priority ranking matrix;

[0059] Resource feature map matching module: used to calculate the matching degree between the service tags in the priority sorting matrix and the resource feature map to generate a policy matching matrix;

[0060] Resource allocation module: used to generate resource allocation plans based on the strategy matching matrix, dynamically monitor the execution results of the resource allocation plans, conduct performance evaluations, and adjust resource allocation strategies in real time;

[0061] Data calibration module: used to trigger the weight calibration mechanism and update the standardized enterprise data output when threshold changes are detected in industry benchmark data or supply chain parameters.

[0062] Beneficial effects of the present invention:

[0063] The present invention uses big data matching technology to standardize enterprise operating data, industry benchmark data and supply chain dynamic data, and combines industry trend prediction models and multi-dimensional risk assessments to effectively improve the resource allocation efficiency of enterprises in complex market environments. Through deep mining and intelligent matching of data, it can reflect changes in business needs and market fluctuations in real time, dynamically adjust resource allocation strategies, thereby optimizing enterprise operational decisions and reducing risks caused by information lags or errors.

[0064] The present invention, through the precise matching of dynamic priority assessment models with resource feature maps, enables enterprises to adjust resource allocation plans based on real-time data, ensuring that resource utilization efficiency is maximized while meeting cost, timeliness and risk requirements; it can not only monitor execution effects in real time, but also quickly trigger adjustment mechanisms when industry benchmark data or supply chain parameters change, thereby maintaining the flexibility of enterprise operations and market adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1A schematic diagram of an enterprise management optimization method according to an embodiment of the present invention;

[0067] Figure 2 Schematic diagram of an enterprise management optimization system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It is also noted that, to provide a more detailed description, the following embodiments are best and preferred embodiments, and those skilled in the art may employ alternative methods for implementing certain known technologies. Furthermore, the accompanying drawings are intended only to provide a more detailed description of the embodiments and are not intended to limit the present invention.

[0069] It should be noted that references in the specification to "one embodiment," "an embodiment," "an exemplary embodiment," "some embodiments," etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not every embodiment necessarily includes such specific features, structures, or characteristics. In addition, when specific features, structures, or characteristics are described in conjunction with an embodiment, it is within the knowledge of persons skilled in the relevant art to implement such features, structures, or characteristics in conjunction with other embodiments (whether or not explicitly described).

[0070] In general, terms can be understood, at least in part, from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending at least in part on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0071] like Figure 1 As shown, an enterprise management optimization method based on big data matching includes the following steps:

[0072] S1: Collect enterprise operation data, industry benchmark data and supply chain dynamic data, standardize the collected data, and output standardized enterprise data;

[0073] S2: Build a business flow feature labeling system and match standardized enterprise data with a preset industry feature library to generate a multi-dimensional business label set;

[0074] S3: Build a dynamic priority assessment model to dynamically assign weights to multi-dimensional business tags based on real-time industry trend forecast data and generate a priority ranking matrix.

[0075] S4: Establish a resource feature map database, and calculate the matching degree between each service tag in the priority ranking matrix and the resource feature map to generate a strategy matching matrix;

[0076] S5: Generate a resource allocation plan based on the strategy matching matrix and dynamically monitor the execution results of the resource allocation plan;

[0077] S6: When threshold changes are detected in industry benchmark data or supply chain parameters, the weight calibration mechanism will be triggered to update the standardized enterprise data output.

[0078] S1 specifically includes:

[0079] S11: Collect enterprise operational data, including internal financial data, production data, sales data, and inventory data. This data is automatically collected through the enterprise resource planning (ERP) system to ensure comprehensiveness and real-time data;

[0080] S12: Collect industry benchmark data, including industry standards, market trends, and industry competition analysis data. This data is obtained through industry databases, government-issued industry reports, and market research data, and is screened based on actual application needs.

[0081] S13: Collect dynamic supply chain data, including raw material procurement data, supplier performance data, and transportation time data. Connect the data with suppliers and logistics systems through the supply chain management system to ensure data accuracy and real-time availability.

[0082] S14: Standardize the collected enterprise operation data, industry benchmark data, and supply chain dynamic data. Standardization includes:

[0083] S141: Convert data formats and unify data units, measurement standards, and field definitions to ensure data uniformity;

[0084] S142: Unify data from different sources at the semantic level through semantic analysis, and address differences in field names, value ranges, and business meanings among various data sources;

[0085] S143: A weighted approach is used to adjust the weights of collected data based on their importance, reliability, and relevance, ultimately generating standardized enterprise data. This approach ensures efficiency and consistency throughout the entire data collection and standardization process, avoiding data biases caused by differences in data sources and collection errors, and providing a reliable foundation for subsequent business tag matching and priority assessment.

[0086] S2 specifically includes:

[0087] S21: Extract relevant business entities from standardized enterprise data, including product features, customer portraits, supply chain nodes and business process nodes, and uniquely identify and encode each business entity;

[0088] S22: Based on the classification rules in the preset industry feature library, a multi-dimensional label classification system is constructed, including business type dimension, resource demand dimension, risk level dimension and timeliness dimension, and a label tree structure with not less than three levels is set under each dimension;

[0089] S23: Match the business entity description in the standardized enterprise data with the label tree structure, match by calculating the similarity between the business entity description vector and the label vector, the similarity calculation formula is: The cosine similarity between the business entity vector 匹配 and the label vector is S , the business entity description vector is , the label vector is , and and are the norms of the business entity vector and the label vector respectively; the similarity value S is in the range of [-1, 1], the matching result is sorted according to the size of the similarity value, and the label with high similarity value is selected for matching;

[0090] S24: Score the confidence of the label matching result of each business entity in four dimensions, calculate the comprehensive matching degree by weighted average method, the calculation formula is as follows: Where C 综合 is the comprehensive matching degree, w i is the weight of the i-th label in the corresponding dimension, C 标签 is the confidence score of the i-th label, and n1 is the number of labels; when the comprehensive matching degree is lower than the preset threshold, manual verification is carried out;

[0091] S25: Store the verified label matching result to the business feature label database, generate a multi-dimensional business label set containing business entity identification, dimension label, matching time and confidence score; the above method ensures the accurate construction of the business flow feature label system through multi-dimensional label classification and confidence scoring mechanism, so that the enterprise can efficiently generate a multi-dimensional business label set according to standardized data, and provide reliable basis for subsequent decision support and resource optimization.

[0092] S3 specifically includes:

[0093] S31: Construct a dynamic priority evaluation model, which includes cost sensitivity factor dimension, timeliness coefficient dimension and risk fluctuation parameter dimension; wherein:

[0094] The cost sensitivity factor dimension determines its initial value by calculating the proportion of the full life cycle cost of the resources corresponding to the business tag;

[0095] The timeliness coefficient dimension is scored in reverse order based on the difference between the deadline of the process associated with the business tag and the current time;

[0096] The risk volatility parameter dimension uses historical data variance analysis combined with industry risk index to calculate the benchmark value;

[0097] S32: Establish an industry trend forecasting interface to obtain industry prosperity index, supply chain price volatility, and policy and regulatory change data in real time through the API, and use a time series analysis model to generate trend forecasts within the next T period, where T ranges from [3,12] months;

[0098] S33: Adjust the evaluation weights based on the three-dimensional evaluation indicators and industry trends to dynamically update the priority evaluation model;

[0099] The specific steps to adjust the assessment weights are as follows:

[0100] S331: Calculate the basic weight W of the three-dimensional evaluation index based on the entropy weight method base =(w1,w2,w3) where w1,w2,w3 represent the basic weights of cost sensitivity factor, timeliness coefficient and risk volatility parameter respectively;

[0101] S332: Introduce the trend impact factor matrix F = [f1, f2, f3], where f1 corresponds to the trend sensitivity of the cost dimension, f2 corresponds to the trend sensitivity of the timeliness dimension, and f3 corresponds to the trend sensitivity of the risk dimension;

[0102] S333: Calculate the dynamic weight according to the following formula: Among them, W new represents the dynamic weight, ⊙ represents the Hadamard product, ∑(W base ⊙F) is the normalization factor.

[0103] S34: Calculate the final comprehensive priority score of each service tag based on the initial weight and trend prediction results of each service tag;

[0104] S35: Arrange all business tags in descending order according to their comprehensive priority scores, and generate a priority ranking matrix with business tag IDs as rows and evaluation dimension scores as columns. The matrix elements include the original scores, trend adjustment coefficients, and final ranking positions. Through the above steps, not only can business tags be comprehensively evaluated in multiple dimensions, but the evaluation results can also be adjusted in real time when the industry changes dynamically, ensuring that the decision-making process can quickly respond to changes and improve the company's operational efficiency.

[0105] S34 specifically includes:

[0106] S341: Extract the initial value V=(v1, v2, v3) of the label in the three-dimensional evaluation index, where v1 is the initial value of the cost sensitivity factor, v2 is the initial value of the timeliness coefficient, and v3 is the initial value of the risk fluctuation parameter;

[0107] S342: Convert the trend prediction value into a trend adjustment coefficient matrix K=[k1, k2, k3], where

[0108] k1=1+α×(predicted change rate 1) represents the trend adjustment coefficient of the cost dimension, k2=1+α×(predicted change rate 2) represents the trend adjustment coefficient of the timeliness dimension, and k3=1+α×(predicted change rate 3) represents the trend adjustment coefficient of the risk dimension; α is a dimension adjustment coefficient, and α∈[0, 1];

[0109] S343: Calculate the comprehensive priority score, the formula is: Where W new [i] is the dynamic weight of the ith dimension, V[i] is the initial value of the ith dimension, and K[i] is the trend adjustment coefficient of the ith dimension.

[0110] S4 specifically includes:

[0111] S41: Establish a resource feature map database, which includes a plurality of resource nodes, each resource node corresponding to a resource type, the resource type including funds, equipment, personnel and materials, and at least five resource attributes are set under each resource node, the resource attributes including resource category, available quantity, allocation time, use restriction and resource value;

[0112] S42: Normalize each attribute of the resource node by using a data standardization method to generate standardized resource feature data R resource , represented as R resource =(r1, r2, r3, r4, r5), where r1 is the resource category, r2 is the available quantity, r3 is the allocation time, r4 is the use restriction, and r5 is the resource value;

[0113] S43: For each business label in the priority sorting matrix, extract its related business dimension information L business , represented as L business =(l1, l2, l3, l4), where l1 is the business type, l2 is the resource demand, l3 is the risk level, and l4 is the timeliness requirement;

[0114] S44: Calculate the matching degree of each business label and each resource node in the resource feature map database by using a similarity calculation method, the formula is:

[0115] Among them, w i is the weight of each resource attribute, l i is the attribute value of the i-th dimension in the business tag, r i is the value of the i-th attribute in the resource node. The calculated similarity value indicates the matching degree between the service label and the resource node.

[0116] S45: Calculate the matching degree of each business tag with all resource nodes in the resource feature map, and then generate the strategy matching matrix M strategy , whose expression is:

[0117]

[0118] Here, m is the number of service tags, n is the total number of resource nodes, and each element in the matrix represents the matching degree between a service tag and a resource node. Through the above steps, it is possible to achieve an accurate match between service tags and resource nodes, thereby optimizing resource allocation strategies and improving resource utilization efficiency and allocation accuracy.

[0119] S5 specifically includes:

[0120] S51: According to the strategy matching matrix M strategy The matching degree between each service label and resource node in the resource node is used to determine the resource configuration priority; specifically, for each service label L business , select the resource node R with the highest matching degree resource Perform resource allocation to ensure that resources that are highly aligned with business needs are prioritized;

[0121] S52: Use linear programming method to allocate resources, and generate resource allocation plan by setting the objective function to maximize resource utilization efficiency where s i is the allocation amount of the i-th resource node, and the expression of the objective function is:

[0122] Among them, S allocation is the generated resource allocation plan, w i is the priority weight of the resource node, is the available resource amount of the i-th resource node, and n is the total number of resource nodes.

[0123] The S5 also includes:

[0124] S53: Dynamically monitor the execution results of the resource allocation plan, use the real-time data monitoring system to track the use of resources, and obtain the actual resource usage data U actual =(u1, u2, ..., u i), where u i is the actual usage of the i-th resource node;

[0125] S54: By comparing the actual usage with the preset resource requirements, deviation analysis is performed to calculate the resource allocation execution efficiency. The calculation formula is: in, is the available resource amount of the i-th resource node, is the actual usage of the i-th resource node, n is the total number of resource nodes, and Efficiency indicates the degree of deviation between the actual usage and the preset demand. The smaller the deviation value, the higher the execution efficiency. The above steps generate a resource allocation plan based on the strategy matching matrix and combine it with the dynamic monitoring and efficiency evaluation model to ensure the accuracy and dynamic optimization of resource allocation. It can adjust resource allocation in time according to actual demand changes, thereby improving the enterprise's resource utilization efficiency and decision-making timeliness.

[0126] S6 specifically includes:

[0127] S61: The trigger condition of the calibration mechanism is that the industry benchmark data or supply chain parameter changes by more than a predetermined percentage or value interval, expressed as: ΔX = |X new -X old |>δ, where ΔX is the data change, X new and X old are the new and old values ​​respectively, and δ is the preset threshold;

[0128] S62: After the calibration mechanism is triggered, an adaptive algorithm is used to dynamically adjust the weights in the standardized enterprise data. The formula is: W new =W old ·(1+α·ΔX), where W new is the adjusted weight coefficient, W old is the original weight coefficient, α1 is the adjustment coefficient, and ΔX is the monitored change in value. Through this algorithm, the weight is dynamically adjusted according to the size of the change, so that the data can more accurately reflect the latest industry and supply chain status.

[0129] S63: After weight adjustment, update the standardized enterprise data output to generate a new standardized data set D new , the formula is: Among them, D new For updated standardized enterprise data, D old is the original standardized data, W new is the updated weight of each data item, and n2 is the total number of data items. The above steps trigger the weight calibration mechanism and dynamically adjust the weight of the data source based on changes in industry and supply chain parameters to ensure that standardized enterprise data always reflects the latest market and supply chain changes, thereby improving the timeliness of the data and the accuracy of decision-making.

[0130] like Figure 2 As shown, an enterprise management optimization system based on big data matching is used to implement the above-mentioned enterprise management optimization method based on big data matching, including the following modules:

[0131] Data collection module: used to collect enterprise operation data, industry benchmark data and supply chain dynamic data, and pre-process the collected data to output standardized enterprise data;

[0132] Business flow feature label construction module: used to extract key business entities from standardized enterprise data and build a business flow feature label system, generating a multi-dimensional business label set by matching it with a preset industry feature library;

[0133] Dynamic priority assessment module: Dynamically assigns weights to business tags based on a three-dimensional assessment indicator system and real-time industry trend forecast data to generate a priority ranking matrix;

[0134] Resource feature map matching module: used to calculate the matching degree between the service tags in the priority sorting matrix and the resource feature map to generate a policy matching matrix;

[0135] Resource allocation module: used to generate resource allocation plans based on the strategy matching matrix, dynamically monitor the execution results of the resource allocation plans, conduct performance evaluations, and adjust resource allocation strategies in real time;

[0136] Data calibration module: used to trigger the weight calibration mechanism when threshold changes are detected in industry benchmark data or supply chain parameters, and update the standardized enterprise data output to maintain the timeliness and accuracy of the data.

[0137] The present invention encompasses any alternatives, modifications, equivalents, and solutions that fall within the spirit and scope of the present invention. To provide a thorough understanding of the present invention, specific details are described in detail below in connection with the preferred embodiments of the present invention, but those skilled in the art will be able to fully understand the present invention without these detailed descriptions. Furthermore, to avoid unnecessary confusion regarding the essence of the present invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0138] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. An enterprise management optimization method based on big data matching, characterized in that: The following steps are involved: S1: Collect enterprise operation data, industry benchmark data and supply chain dynamic data, standardize the collected data, and output standardized enterprise data; S2: Build a business flow feature labeling system and match standardized enterprise data with a preset industry feature library to generate a multi-dimensional business label set; S3: Build a dynamic priority assessment model to dynamically assign weights to multi-dimensional business tags based on real-time industry trend forecast data and generate a priority ranking matrix. S4: Establish a resource feature map database, and calculate the matching degree between each service tag in the priority ranking matrix and the resource feature map to generate a strategy matching matrix; S5: Generate a resource allocation plan based on the strategy matching matrix and dynamically monitor the execution results of the resource allocation plan; S6: When threshold changes are detected in industry benchmark data or supply chain parameters, the weight calibration mechanism will be triggered to update the standardized enterprise data output.

2. The enterprise management optimization method based on big data matching according to claim 1 is characterized in that: Said S1 specifically includes: S11: Collect enterprise operation data, including internal financial data, production data, sales data and inventory data; S12: Collect industry benchmark data, including industry standards, market trends and industry competition analysis data; S13: Collect supply chain dynamic data, including raw material procurement data, supplier performance data, and transportation time data; S14: Standardize the collected enterprise operation data, industry benchmark data, and supply chain dynamic data. The standardization includes: S141: Convert data formats and unify data units, measurement standards, and field definitions to ensure data uniformity; S142: Unify data from different sources at the semantic level through semantic analysis, and address differences in field names, value ranges, and business meanings among various data sources; S143: Use a weighted approach to adjust the weights of collected data based on their importance, reliability, and relevance, ultimately generating standardized enterprise data.

3. The enterprise management optimization method based on big data matching according to claim 1 is characterized in that: The S2 specifically includes: S21: Extract relevant business entities from standardized enterprise data, including product features, customer profiles, supply chain nodes, and business process nodes, and uniquely identify each business entity; S22: Based on the classification rules in the preset industry feature library, a multi-dimensional label classification system is constructed. The classification system includes business type dimension, resource requirement dimension, risk level dimension, and timeliness dimension. A label tree structure of no less than three levels is set under each dimension. S23: Matching the business entity description in the standardized enterprise data with the label tree structure by calculating the similarity between the business entity description vector and the label vector; S24: Confidence scores are assigned to the tag matching results of each business entity under the four dimensions, and the comprehensive matching degree is calculated using a weighted average method. When the comprehensive matching degree is lower than a preset threshold, manual verification is performed. S25: The verified tag matching results are stored in a business feature tag database to generate a multi-dimensional business tag set including a business entity identifier, a dimension tag, a matching time, and a confidence score.

4. The enterprise management optimization method based on big data matching according to claim 1 is characterized in that: The S3 specifically includes: S31: Construct a dynamic priority assessment model, which includes three dimensions: cost sensitivity factor dimension, timeliness coefficient dimension, and risk fluctuation parameter dimension; S32: Establish an industry trend forecasting interface to obtain industry prosperity index, supply chain price volatility, and policy and regulatory change data in real time through the API, and use a time series analysis model to generate trend forecast values ​​within the next T period, where T ranges from [3,12] months; S33: Adjust the evaluation weights based on the three-dimensional evaluation indicators and industry trends to dynamically update the priority evaluation model; S34: Calculate the final comprehensive priority score of each service tag based on the initial weight and trend prediction results of each service tag; S35: Arrange all business tags in descending order according to the comprehensive priority scores, and generate a priority ranking matrix with business tag IDs as rows and evaluation dimension scores as columns. The matrix elements include the original scores, trend adjustment coefficients, and final rankings.

5. The enterprise management optimization method based on big data matching according to claim 4 is characterized in that: The S34 specifically includes: S341: Extract the initial value V=(v1, v2, v3) of the label in the three-dimensional evaluation index, where v1 is the initial value of the cost sensitivity factor, v2 is the initial value of the timeliness coefficient, and v3 is the initial value of the risk volatility parameter; S342: Convert the trend prediction value into a trend adjustment coefficient matrix K = [k1, k2, k3], where k1 = 1 + α × (predicted change rate 1) represents the trend adjustment coefficient of the cost dimension, k2 = 1 + α × (predicted change rate 2) represents the trend adjustment coefficient of the timeliness dimension, and k3 = 1 + α × (predicted change rate 3) represents the trend adjustment coefficient of the risk dimension; α is the dimension adjustment coefficient, and α∈[0,1]; S343: Calculate the comprehensive priority score. The formula is: Among them, W new [i] is the dynamic weight of the i-th dimension, V[i] is the initial value of the i-th dimension, and K[i] is the trend adjustment coefficient of the i-th dimension.

6. The enterprise management optimization method based on big data matching according to claim 1 is characterized in that: The S4 specifically includes: S41: Establishing a resource feature map database, the database including multiple resource nodes, each resource node corresponding to a resource type including funds, equipment, personnel, and materials, and each resource node having at least five resource attributes including resource category, available quantity, allocation time, usage restrictions, and resource value; S42: Use data standardization methods to normalize the attributes of resource nodes and generate standardized resource feature data R resource ; S43: For each business tag in the priority sorting matrix, extract its related business dimension information L business ; S44: A similarity calculation method is used to calculate the matching degree between each service tag and each resource node in the resource feature map database. The formula is: Among them, w i is the weight of each resource attribute, l i is the attribute value of the i-th dimension in the business tag, r i is the value of the i-th attribute in the resource node; S45: Calculate the matching degree of each business tag with all resource nodes in the resource feature map, and then generate the strategy matching matrix M strategy .

7. The enterprise management optimization method based on big data matching according to claim 1 is characterized in that: The S5 specifically includes: S51: According to the strategy matching matrix M strategy The matching degree between each service label and resource node in the resource node is used to determine the resource configuration priority; specifically, for each service label L business , select the resource node R with the highest matching degree resource Allocate resources; S52: Use linear programming method to allocate resources. Set the objective function to maximize resource utilization efficiency and generate a resource allocation plan. The expression of the objective function is: Among them, S allocation is the generated resource allocation plan, w i is the priority weight of the resource node, is the available resource amount of the i-th resource node, and n is the total number of resource nodes.

8. The enterprise management optimization method based on big data matching according to claim 7 is characterized in that: The S5 further includes: S53: Dynamically monitor the execution results of the resource allocation plan, use a real-time data monitoring system to track resource usage, and obtain actual resource usage data; S54: By comparing the actual usage with the preset resource requirements, deviation analysis is performed to calculate the resource allocation execution efficiency. The calculation formula is: in, is the available resource amount of the i-th resource node, is the actual usage of the i-th resource node, n is the total number of resource nodes, and Efficiency indicates the degree of deviation between the actual usage and the preset demand; the smaller the deviation value, the higher the execution efficiency.

9. The enterprise management optimization method based on big data matching according to claim 1 is characterized in that: The S6 specifically includes: S61: The triggering condition of the calibration mechanism is that the industry benchmark data or supply chain parameters change by more than a predetermined percentage or value interval, expressed as: Among them, ΔX is the data change, X new and X old are the new and old values ​​respectively, and δ is the preset threshold; S62: After the calibration mechanism is triggered, an adaptive algorithm is used to dynamically adjust the weights in the standardized enterprise data; S63: After weight adjustment, update the standardized enterprise data output to generate a new standardized data set D new .

10. An enterprise management optimization system based on big data matching, used to implement an enterprise management optimization method based on big data matching according to any one of claims 1 to 9, characterized in that: Includes the following modules: Data collection module: used to collect enterprise operation data, industry benchmark data and supply chain dynamic data, and pre-process the collected data to output standardized enterprise data; Business flow feature label construction module: used to extract key business entities from standardized enterprise data and build a business flow feature label system, generating a multi-dimensional business label set by matching it with a preset industry feature library; Dynamic priority assessment module: Dynamically assigns weights to business tags based on a three-dimensional assessment indicator system and real-time industry trend forecast data to generate a priority ranking matrix; Resource feature map matching module: used to calculate the matching degree between the service tags in the priority sorting matrix and the resource feature map to generate a policy matching matrix; Resource allocation module: used to generate resource allocation plans based on the strategy matching matrix, dynamically monitor the execution results of the resource allocation plans, conduct performance evaluations, and adjust resource allocation strategies in real time; Data calibration module: used to trigger the weight calibration mechanism and update the standardized enterprise data output when threshold changes are detected in industry benchmark data or supply chain parameters.

Images