Service optimization method and system based on multi-dimensional enterprise data fusion

Abstract

The invention relates to the technical field of enterprise data intelligent management, in particular to a service optimization method and system based on multi-dimensional enterprise data fusion, and the method comprises the following steps: taking a unified social credit code as a main key, and combining an enterprise name and an operation address as auxiliary matching keys; industrial and commercial registration data, tax declaration data, energy consumption monitoring data, social insurance payment data and operation development data are fused; the method has the beneficial effects that a real-time calculation framework and an intelligent algorithm are adopted, the sudden risk of an enterprise, such as sudden energy consumption increase and tax decline, can be captured in time, and an early warning and service intervention mechanism is automatically triggered. Therefore, enterprises can quickly respond to market changes, the operation risk is reduced, and the competitiveness is improved. And by accurately sensing enterprise demands and service states, the system can realize optimal configuration and efficient utilization of the service resources. Therefore, the service cost can be reduced, the service quality can be improved, and the customer satisfaction and loyalty can be enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of enterprise data intelligent governance, in particular to a service optimization method and system based on multi-dimensional enterprise data fusion. BACKGROUND

[0002] With the accelerated digital transformation, enterprises have accumulated massive amounts of multi-source heterogeneous data in the development process. These data come from a wide range of sources, including but not limited to business registration data, tax declaration data, energy consumption monitoring data, social security payment data, and business development data, etc.

[0003] However, traditional data analysis methods and technologies have obvious limitations, mainly in the following aspects: Data islands are serious: due to independent storage of each system data, there is a lack of effective data sharing and exchange mechanism, which makes it difficult for enterprises to form a panoramic view. For example, the energy consumption data is not shared by the tax system, so that the enterprise cannot fully consider the energy consumption factor when analyzing the business situation.

[0004] Data fusion technology is insufficient: existing data fusion technology cannot effectively handle complex scenarios such as address change (such as relocation without updating) and group subsidiary association, resulting in inaccurate or inconsistent data, affecting the reliability of the analysis results.

[0005] Health assessment is static: the traditional annual assessment method cannot capture sudden risks of enterprises, such as a 50% increase in energy consumption this month, etc. Short-term abnormal changes, so that enterprises cannot take timely measures to respond.

[0006] At the same time, the coupling effect of social security and tax is not quantified, such as a 20% reduction in social security personnel leading to a 15% decrease in tax in the next quarter, making the health assessment results not comprehensive and accurate.

[0007] Service response lag: low health degree enterprise identification delay is serious, such as a 40% decrease in tax for two consecutive months without triggering an early warning, resulting in service resource mismatch, and unable to provide effective support for enterprises in a timely manner.

[0008] Therefore, a service optimization method based on multi-dimensional enterprise data fusion is needed, which breaks down data barriers, builds a real-time computing framework, and introduces intelligent algorithms to achieve accurate perception, dynamic assessment and continuous optimization of enterprise service processes, thereby promoting the healthy development of enterprises. SUMMARY

[0009] The purpose of the present application is to provide a service optimization method and system based on multi-dimensional enterprise data fusion to solve the problems raised in the background technology.

[0010] To achieve the above purpose, the present application provides the following technical solution: a service optimization method based on multi-dimensional enterprise data fusion, comprising the following steps: By unifying the social credit code as the primary key, combining the enterprise name and operating address as the auxiliary matching key, integrating the business registration data, tax declaration data, energy consumption monitoring data, social security payment data, and business development data; The health degree of the enterprise is calculated by using a segmented function algorithm, wherein the tax same-period weight is 40%, the social security payment same-period weight is 10%, the energy consumption same-period weight is 20%, and the revenue same-period weight is 30%; when the energy consumption same-period increases by more than 20%, the energy consumption weight is automatically increased to 30%; according to the calculated health degree of the enterprise, the service strategy is dynamically adjusted, when the health degree score is lower than 60, the visiting task is automatically triggered, and the corresponding service scheme is matched based on the cause-effect analysis.

[0011] Preferably, the calculation of the health degree of the enterprise further comprises: performing single-point score calculation on the same-period changes of the tax, social security, energy consumption, and revenue indicators by using an exponential release function and a linear tolerance mechanism; when the GIS distance between the operating address and the energy consumption equipment is more than 1 km, a data verification process is started to ensure the accuracy and consistency of the data.

[0012] Preferably, the service intervention closed-loop mechanism specifically comprises: constructing a cause-effect analysis matrix of the root causes of tax decrease, energy consumption increase, labor shortage, and market shrinkage; positioning the main reason for the decrease of the health degree of the enterprise based on the cause-effect analysis matrix, and pushing a targeted service package according to the root cause analysis result, the service package content including but not limited to tax payment deferral application, energy-saving technical transformation subsidy, urgent hiring green channel, labor matching meeting, export tax rebate urgency, and e-commerce platform support.

[0013] Preferably, the multi-source data fusion management process comprises: for the problem of multiple tax subjects of the same enterprise in the tax data, selecting the subject with a district-level tax proportion of more than 70% as the main record; for the case that the operating address does not match the meter address in the energy consumption data, starting a field verification process when the distance between the two is more than 1 km; for the problem of sudden decrease of the number of people caused by labor dispatching in the social security data, correcting by associating the labor outsourcing contract filing data.

[0014] Preferably, it further comprises a conflict detection module to solve the data conflict problem of inconsistent tax subjects and inconsistent operating address and energy consumption equipment address; weight self-adaptation, dynamically adjusting the weight of each indicator in the calculation of the health degree of the enterprise according to the data changes, to ensure the timeliness and accuracy of the evaluation result.

[0015] A service optimization system based on multi-dimensional enterprise data fusion, comprising: a data fusion management module, an enterprise health degree calculation module, and a service intervention closed-loop module, wherein: The data fusion management module takes the unified social credit code as the primary key, and combines the enterprise name and the operating address as the auxiliary matching key, to realize the fusion of the business registration data, the tax declaration data, the energy consumption monitoring data, the social security payment data, and the business development data. The enterprise health degree calculation module adopts a segmented function algorithm, and calculates the enterprise health degree according to the tax same period: weight 40%, social security payment same period: 10%, energy consumption same period: 20%, and revenue same period: 30%, and can automatically increase the energy consumption weight to 30% when the energy consumption same period increases by more than 20%. The service intervention closed loop module automatically triggers a visit task when the enterprise health degree score is lower than 60, and matches the corresponding service scheme based on the cause and effect analysis.

[0016] Preferably, the enterprise health degree calculation module further comprises: The single index score calculation unit calculates the index score by using an exponential release function and a linear tolerance mechanism. The data verification unit starts the data verification process when the GIS distance between the operating address and the energy consumption equipment is more than 1 km, to ensure the accuracy and consistency of the data.

[0017] Preferably, the service intervention closed loop module comprises: The cause and effect analysis matrix construction unit is used to construct the cause and effect analysis matrix of the root causes of the tax decrease, the energy consumption increase, the labor shortage, and the market shrinkage. The service matching unit locates the main reason for the decrease of the enterprise health degree based on the cause and effect analysis matrix, and pushes a targeted service package according to the root cause analysis result, and the service package content covers the tax payment deferral application, the energy-saving technical transformation subsidy, the urgent hiring green channel, the labor matching meeting, the export tax rebate urgency, and the e-commerce platform support.

[0018] Preferably, the data fusion management module further comprises: The tax data conflict resolution unit selects the main record of the main tax subject whose district-level tax proportion is more than 70% for the problem of multiple tax subjects of the same enterprise. The energy consumption data conflict resolution unit starts the on-site verification process when the distance between the operating address and the meter address is more than 1 km for the case that the operating address does not match the meter address. The social security data conflict resolution unit corrects the data by associating the labor outsourcing contract filing data for the problem of sudden decrease of the number of people caused by labor dispatching.

[0019] Preferably, it further comprises: The conflict detection module is used to detect and solve the data fusion process of the inconsistent tax subjects, the inconsistent data conflict problem of the operating address and the energy consumption equipment address. The weight self-adaptive engine dynamically adjusts the weight of each index in the enterprise health degree calculation according to data changes, ensuring the timeliness and accuracy of the evaluation results. For example, when the energy consumption increases by more than 20% compared to the previous period, the weight of energy consumption is automatically increased to 30%.

[0020] Compared with the prior art, the beneficial effects of the present application are: The service optimization method and system based on multi-dimensional enterprise data fusion proposed by the present application have a dynamic weight self-adaptive mechanism: the system can dynamically adjust the weight of each index in the enterprise health degree calculation according to data changes. For example, when the energy consumption increases by more than 20% compared to the previous period, the weight of energy consumption is automatically increased to 30%, ensuring that the evaluation results can timely reflect the impact of enterprise energy consumption changes on enterprise health. At the same time, when the number of social security payers decreases for two consecutive months, the labor shortage early warning model is triggered to help enterprises timely discover and solve potential problems.

[0021] Service effect quantitative tracking: the system defines key indicators such as service response rate and health improvement rate to quantitatively track service effects. The service response rate is measured by the ratio of the number of enterprises adopting services to the number of recommended services, reflecting the accuracy of service recommendations and the acceptance of enterprises; the health improvement rate is evaluated by comparing the changes in enterprise health degree before and after the service, directly showing the improvement effect of the service on the enterprise health condition. Break down data barriers and achieve panoramic view: by building a fusion governance framework of industry and commerce, tax, energy consumption, social security and business development data, the system can break down the data barriers between different systems and form a panoramic view of the enterprise. This helps enterprises to understand business problems from a global perspective, optimize service processes and improve management efficiency.

[0022] Real-time calculation and intelligent intervention: the system uses real-time calculation framework and intelligent algorithms to timely capture enterprise sudden risks such as sudden increase in energy consumption and decrease in tax, and automatically trigger early warning and service intervention mechanism. This helps enterprises to quickly respond to market changes, reduce operating risks and improve competitiveness. Improve service resource utilization efficiency: by accurately sensing enterprise demand and service status, the system can realize optimal allocation and efficient utilization of service resources. This helps to reduce service cost, improve service quality, enhance customer satisfaction and loyalty. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The flowchart of the method of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme of the present application, and the advantages are clearer, more complete and clearer, the embodiments of the present application are further described in detail below in combination with the drawings. It should be understood that the specific embodiments described herein are part of the embodiments of the present application, not all embodiments, and are only used to explain the embodiments of the present application, and do not limit the embodiments of the present application. All other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0025] Embodiment one, the present application provides a technical scheme: a service optimization method based on multi-dimensional enterprise data fusion, comprising the following steps: Step 1: Multi-source data fusion management Data collection: first, the system collects enterprise data from industry and commerce, tax, energy consumption monitoring, social security payment and business development through API interface or data exchange platform.

[0026] Data matching and fusion: taking the unified social credit code as the primary key, combining the enterprise name and the operating address as the auxiliary matching key, matching and fusing the collected multi-source heterogeneous data. For example, for the case that there are multiple tax subjects for the same enterprise, the system selects the subject whose regional tax proportion exceeds 70% as the main record; for the energy consumption data whose operating address does not match the meter address, when the distance between them exceeds 1 kilometer, the on-site verification process is started; for the case that the social security number decreases sharply due to labor dispatch, the labor outsourcing contract record data is associated for correction.

[0027] Step 2: Enterprise health degree calculation Index selection and weight distribution: the system uses piecewise function algorithm to calculate the enterprise health degree according to the tax same period (weight 40%), social security payment same period (10%), energy consumption same period (20%), and revenue same period (30%) indexes.

[0028] Dynamic weight adjustment: when the energy consumption same period rises more than 20%, the system automatically increases the energy consumption weight to 30% to more accurately reflect the impact of enterprise energy consumption changes on enterprise health.

[0029] Single index score calculation: for each index, the system uses exponential release function (positive growth) and linear tolerance mechanism (negative growth) to calculate single score, ensuring the rationality and accuracy of the evaluation results.

[0030] Step 3: Service intervention closed loop Health score and early warning: the system scores according to the calculated enterprise health degree, and automatically triggers the early warning mechanism when the health score is less than 60.

[0031] Root cause analysis: System constructs the cause and effect analysis matrix of root causes such as tax reduction, energy consumption increase, labor shortage, market shrinkage, etc. Through algorithm, the main reason for the decline of enterprise health is located.

[0032] Service matching and pushing: According to the root cause analysis result, the system matches the corresponding service scheme from the preset service library and pushes it to the enterprise.

[0033] For example, for enterprises with tax reduction, the system may push services such as tax payment deferral application or energy-saving technical transformation subsidy; for enterprises with labor shortage, the system may push services such as green channel for urgent recruitment or labor matching meeting.

[0034] In embodiment two, on the basis of embodiment one, a service optimization system based on multi-dimensional enterprise data fusion is proposed, and the architecture, function modules and interaction mode of the system are as follows: System architecture The system adopts micro-service architecture and is composed of data fusion governance module, enterprise health calculation module, service intervention closed loop module, conflict detection module and weight self-adaptive engine and other modules. The modules communicate and exchange data through API interface.

[0035] Function modules Data fusion governance module Function description: responsible for collecting, matching and fusing enterprise data from different data sources.

[0036] Sub-modules: Data collection submodule: collect data through API interface or data exchange platform.

[0037] Data matching submodule: match data with unified social credit code as the primary key.

[0038] Data fusion submodule: solve data conflicts and realize data fusion.

[0039] For example, for the problem of multiple tax subjects of the same enterprise, select the subject with more than 70% of the district tax proportion as the main record.

[0040] Enterprise health calculation module Function description: calculate enterprise health according to preset indicators and weights.

[0041] Sub-modules: Indicator selection and weight distribution submodule: determine the indicators and weights for calculating enterprise health.

[0042] Dynamic weight adjustment submodule: dynamically adjust the indicator weight according to data changes. For example, when the energy consumption increases by more than 20% year-on-year, automatically increase the energy consumption weight to 30%.

[0043] Single indicator score calculation submodule: calculate the single score of each indicator.

[0044] Service intervention closed loop module Function description: trigger early warning according to enterprise health score, and conduct root cause analysis and service matching.

[0045] Submodule: Health score and early warning submodule: score and early warning according to enterprise health.

[0046] Root cause analysis submodule: build a cause and effect analysis matrix to locate the reasons for the decline in enterprise health.

[0047] Service matching and pushing submodule: match and push service solutions according to root cause analysis results.

[0048] Conflict detection module Function description: detect and solve the conflict problem in the data fusion process.

[0049] Submodule: Tax data conflict resolution submodule: solve the problem of multiple tax subjects of the same enterprise.

[0050] Energy consumption data conflict resolution submodule: solve the problem of inconsistent business address and meter address.

[0051] Social security data conflict resolution submodule: solve the problem of sudden drop in the number of people due to labor dispatching.

[0052] Weight self-adaptive engine Function description: dynamically adjust the weight of each indicator in the calculation of enterprise health according to data changes.

[0053] Working mechanism: real-time monitoring of changes in each indicator data, when significant changes in a specific indicator (such as energy consumption) are detected, automatically adjust its weight to ensure the timeliness and accuracy of the evaluation results.

[0054] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to these embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A service optimization method based on multi-dimensional enterprise data fusion, characterized in that: Comprising the following steps: By taking the unified social credit code as the primary key, combining the enterprise name and operating address as the auxiliary matching key, integrating business registration data, tax declaration data, energy consumption monitoring data, social security payment data, and business development data; Adopting a segmented function algorithm to calculate the enterprise health degree, wherein the tax same period weight is 40%, the social security payment same period weight is 10%, the energy consumption same period weight is 20%, and the revenue same period weight is 30%; when the energy consumption same period rises more than 20%, the energy consumption weight is automatically increased to 30%; according to the calculated enterprise health degree, the service strategy is dynamically adjusted, when the health degree score is lower than 60, the visit task is automatically triggered, and the corresponding service scheme is matched based on the cause-effect analysis. 2.The service optimization method based on multi-dimensional enterprise data fusion of claim 1, wherein: The calculation of the enterprise health degree further comprises: the single score calculation of the index of tax, social security, energy consumption, and revenue same period change by the exponential release function and the linear tolerance mechanism; when the GIS distance between the operating address and the energy consumption equipment is more than 1 kilometer, the data verification process is started to ensure the accuracy and consistency of the data. 3.The service optimization method based on multi-dimensional enterprise data fusion of claim 2, characterized in that: The service intervention closed loop mechanism specifically comprises: building a cause-effect analysis matrix of the root causes of tax decrease, energy consumption increase, labor shortage, and market shrinkage; positioning the main reason for the decline of the enterprise health degree based on the cause-effect analysis matrix, and pushing the targeted service package according to the root cause analysis result, the service package content includes but is not limited to tax payment application, energy-saving technical transformation subsidy, urgent hiring green channel, labor matching meeting, export tax rebate urgent, e-commerce platform support.

4. The service optimization method based on multi-dimensional enterprise data fusion according to claim 3, characterized in that: The multi-source data fusion governance process includes: for the problem of multiple tax subjects of the same enterprise in the tax data, selecting the subject whose district-level tax proportion is more than 70% as the main record; for the situation that the operating address and the meter address in the energy consumption data do not match, when the distance between the two is more than 1 kilometer, the on-site verification process is started; for the problem of sudden decrease of the number caused by labor dispatching in the social security data, the labor outsourcing contract record data is associated for correction.

5. The service optimization method based on multi-dimensional enterprise data fusion according to claim 4, characterized in that: It also includes conflict detection, solving the data conflict problem of inconsistent tax subjects and inconsistent operating address and energy consumption equipment address; Weight self-adaptation, dynamically adjusting the weight of each index in the calculation of the enterprise health degree according to the data change, to ensure the timeliness and accuracy of the evaluation result.

6. A service optimization system based on multi-dimensional enterprise data fusion, characterized in that: The method of claim 5, comprising: a data fusion governance module, an enterprise health degree calculation module, and a service intervention closed loop module, wherein: The data fusion governance module takes the unified social credit code as the primary key, and combines the enterprise name and operating address as the auxiliary matching key, to realize the fusion of business registration data, tax declaration data, energy consumption monitoring data, social security payment data, and business development data; The enterprise health degree calculation module adopts a segmented function algorithm, and calculates the enterprise health degree according to the tax same period: weight 40%, social security payment same period: 10%, energy consumption same period: 20%, and revenue same period: 30% indexes, and can automatically increase the energy consumption weight to 30% when the energy consumption same period rises more than 20%; The service intervention closed loop module automatically triggers the visit task when the enterprise health degree score is lower than 60, and matches the corresponding service scheme based on the cause-effect analysis.

7. The service optimization system based on multi-dimensional enterprise data fusion of claim 6, wherein: The enterprise health degree calculation module further comprises: The single index score calculation unit calculates the scores of each index by using an exponential release function and a linear tolerance mechanism. The data verification unit initiates a data verification process when the GIS distance between the operating address and the energy consumption equipment exceeds 1 km, to ensure the accuracy and consistency of the data.

8. The service optimization system based on multi-dimensional enterprise data fusion according to claim 7, characterized in that: The service intervention closed loop module comprises: The causal analysis matrix construction unit is configured to construct a causal analysis matrix of the root causes of tax reduction, energy consumption increase, labor shortage, and market shrinkage; The service matching unit is configured to locate the main reason for the decline in enterprise health degree based on the causal analysis matrix, and to push a targeted service package according to the root cause analysis result, wherein the service package content covers tax payment deferral application, energy-saving technical transformation subsidy, urgent hiring green channel, labor matching meeting, export tax rebate acceleration, and e-commerce platform support.

9. The service optimization system based on multi-dimensional enterprise data fusion according to claim 8, characterized in that: The data fusion governance module further comprises: The tax data conflict resolution unit selects a subject with a tax revenue proportion of more than 70% at the district level as the main record for the problem of multiple tax subjects of the same enterprise; The energy consumption data conflict resolution unit initiates a field verification process when the distance between the operating address and the meter address exceeds 1 km for the case that the operating address does not match the meter address; The social security data conflict resolution unit corrects the problem of sudden decrease in the number of people caused by labor dispatching by associating the labor outsourcing contract filing data.

10. The service optimization system based on multi-dimensional enterprise data fusion of claim 9, wherein: Further comprising: The conflict detection module is configured to detect and solve the data conflict problems of inconsistent tax subjects and inconsistent operating address and energy consumption equipment address in the data fusion process; The weight self-adaptive engine is configured to dynamically adjust the weight of each index in the calculation of the enterprise health degree according to the data changes, to ensure the timeliness and accuracy of the evaluation result, such as automatically increasing the energy consumption weight to 30% when the energy consumption increases by more than 20% compared with the previous year.

Images