Enterprise operation evaluation method and system based on enterprise power consumption data

Abstract

The invention relates to the technical field of enterprise operation and credit evaluation, in particular to an enterprise operation evaluation method and system based on enterprise power consumption data, first-level data is obtained by arranging collected data, a second-level model is constructed after the first-level data is processed, and the second-level model is subjected to score assignment and optimization. Dynamic and non-tampering data generated by intelligent devices such as an intelligent electric meter and a load control device are utilized, the credible data are fused into an enterprise evaluation model, the real-time operation condition of an enterprise is reflected more objectively, and the evaluation accuracy is improved; besides, the evaluation result of the model provides important data reference for the financial institution before the loan is approved, the rechecking cost is reduced, and the financial risk is effectively reduced by dynamically monitoring the warning bit value; meanwhile, an enterprise can use a model result to supervise an operation condition, formulate an accurate control strategy and enhance dynamic monitoring of production and operation of branches and sub-companies, so that development of the enterprise is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise operation and credit evaluation, and in particular to an enterprise operation evaluation method and system based on enterprise electricity consumption data. Background Art

[0002] Enterprise operation / credit evaluation is a very important topic in the financial field, and it is of great significance to banking, finance, investment institutions and government departments. At present, the credit evaluation of enterprises with digital technology has become the mainstream. General enterprise evaluation data covers the annual report data, tax information, etc. of enterprises. These data are generally long behind the actual situation, and the timeliness of data application is relatively poor, resulting in the rating lagging behind the business, making it difficult to truly identify the risks in the process. With the continuous development of big data and artificial intelligence technology, power data is increasingly used in the credit risk assessment of small and medium-sized enterprises. Power data has the characteristics of high credibility, strong timeliness, continuous integrity, and full coverage. In addition, since power data belongs to user privacy, it is generally not directly applicable to commercial application scenarios. Therefore, the processing of the model should ensure that the data can maintain the evaluation characteristics of the model to objectively describe the original data after desensitization and declassification, and truly feedback the production and operation status of the enterprise.

[0003] In summary, the enterprise operation evaluation method and system based on enterprise electricity consumption data provide an efficient and real-time way to evaluate the operation and credit status of enterprises. By using enterprise electricity consumption data, a highly reliable and timely information source, this method can not only capture the real-time operation status of the enterprise more quickly, but also ensure the security and privacy protection of the data through big data and artificial intelligence technology. By desensitizing and declassifying power data, the system can accurately reflect the actual operation of the enterprise without leaking sensitive information, providing a powerful decision-making support tool for banks, investment institutions and government departments. The application of this method marks the development of enterprise credit assessment technology in a more modern and digital direction, greatly improving the accuracy and response speed of the assessment. Summary of the invention

[0004] In view of the above problems existing in the prior art, the present invention is proposed.

[0005] Therefore, the technical problem to be solved by the present invention is to provide a corporate credit evaluation model method based on corporate electricity consumption data, which can more accurately evaluate the operating status of the enterprise, and under the premise of user authorization and permission, provide a more dynamic monitoring method for the financial industry, lending institutions and government departments, and effectively identify and control process risks.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an enterprise operation evaluation method based on enterprise electricity consumption data, comprising: collating the collected data to obtain primary data; performing primary processing on the primary data; constructing a secondary model and assigning points; and optimizing the secondary model.

[0007] As a preferred solution of the enterprise operation evaluation method based on enterprise electricity consumption data described in the present invention, the data collection includes preliminary sorting of the collected basic data to obtain primary data as preparation data for data analysis and further processing.

[0008] As a preferred solution of the enterprise operation evaluation method based on enterprise electricity consumption data described in the present invention, wherein: the primary processing of the primary data includes further processing of the sorted primary data, involving extracting deep information from the primary data for model construction and optimization.

[0009] As a preferred solution of the enterprise operation evaluation method based on enterprise electricity consumption data described in the present invention, the construction of the secondary model and the scoring include constructing a model using the data after primary processing, calculating and processing the data in the model to obtain a comprehensive score.

[0010] As a preferred solution of the enterprise operation evaluation method based on enterprise electricity consumption data described in the present invention, the optimization of the secondary model includes evaluating and fitting the model with the data processed by the model, and checking, verifying and optimizing the evaluation results.

[0011] As a preferred solution of the enterprise operation evaluation method based on enterprise electricity consumption data described in the present invention, the collated and collected data also includes basic data of the collected and constructed primary model, and preliminary collation and classification are performed to obtain primary data as the input basis for primary processing and construction of the secondary model.

[0012] As a preferred solution of the enterprise operation evaluation method based on enterprise electricity consumption data described in the present invention, wherein: the primary data includes the enterprise's business expansion work order data, electricity consumption data, and payment data.

[0013] Another object of the present invention is to provide an enterprise operation evaluation system based on enterprise electricity consumption data, which uses the specific data of enterprise electricity consumption to evaluate the enterprise's operating efficiency and credit status. This system includes a data acquisition module, a data processing module, a model building module, and a model optimization module, which can extract key information from the enterprise's business expansion work order data, electricity consumption data, and payment data, and realize dynamic and accurate evaluation of the enterprise's operating status through advanced data processing and model optimization technology. In addition, the system also includes corresponding computer equipment and computer-readable storage media, in which the stored computer program can execute the above evaluation method, thereby providing reliable decision support for banking financial institutions, investment companies and government departments.

[0014] In order to solve the above technical problems, the present invention provides the following technical solutions: an enterprise operation evaluation system based on enterprise electricity consumption data, comprising: a data acquisition module, a data processing module, a model building module and a model optimization module;

[0015] The data collection module organizes the collected data to obtain primary data;

[0016] The data processing module performs primary processing on the primary data;

[0017] The model building module builds a secondary model and assigns points;

[0018] The model optimization module optimizes the secondary model.

[0019] A computer device includes a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the enterprise operation evaluation method based on enterprise electricity consumption data as described above when executing the computer program.

[0020] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the enterprise operation evaluation method based on enterprise electricity consumption data as described above are implemented.

[0021] The beneficial effects of the present invention are as follows: the evaluation model is more accurate: the power data is introduced into the traditional enterprise model evaluation results, and the dynamic, tamper-proof and trusted data generated by smart devices such as smart meters and load control devices are integrated into the enterprise evaluation model to more objectively reflect the dynamic operating conditions of the enterprise and improve the accuracy of the enterprise's production and operation status and credit and capacity evaluation.

[0022] Reduce financial industry risks: The evaluation results of this model can provide important data references for financial institutions, banks, etc. before loan approval and during the loan disbursement process, thereby reducing the cost of verifying the authenticity of the information; at the same time, through dynamic monitoring and identification of warning digit values, dynamic post-loan monitoring can be achieved, effectively reducing financial industry risks.

[0023] Promote the development of the enterprise itself: The enterprise itself can formulate more precise management and control strategies based on the evaluation results of this model to supervise its own operation. The enterprise can effectively refer to the analysis results of this model in the process of dynamic monitoring of the production, operation and operation of its branches, subsidiaries and subsidiaries. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0025] Figure 1 An overall flow chart of an enterprise operation evaluation method based on enterprise electricity consumption data provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0027] Example 1, reference Figure 1 , is an embodiment of the present invention, which provides an enterprise operation evaluation method based on enterprise electricity consumption data, including:

[0028] S1: Organize the collected data to obtain primary data.

[0029] It should be noted that if Figure 1 In S10, arranging the collected data includes preliminarily arranging the collected basic data to obtain primary data as preparatory data for data analysis and further processing; arranging the collected data also includes collecting the basic data of the constructed primary model, and preliminarily arranging and classifying it to obtain primary data as the input basis for primary processing and construction of the secondary model.

[0030] Furthermore, the basic data for model construction are sorted and collected, mainly including the enterprise's business expansion work order data, electricity consumption data, and payment data; the business expansion work order data include the transformer capacity and time period information for the enterprise's application for electricity capacity increase or reduction, the electricity consumption data include the enterprise's daily / monthly electricity consumption, real-time electricity load, etc., the payment data include the enterprise's electricity bill payment record, breach of contract and arrears, etc.; external data introduces external enterprise basic information data and non-power data evaluation model result data.

[0031] Furthermore, business data in the power system is stored in different business systems. For example, user bills and payment data are stored in the power marketing system, and meter collection data is stored in the power consumption collection system. To achieve data aggregation, the original data can be collected with the help of enterprise-level data centers. The tools used include enterprise-level ETL collection platforms. If point-to-point collection is required, the dataX heterogeneous data synchronization tool can be used for data collection.

[0032] In an embodiment of the present application, the primary model is the primary data obtained from the collated and collected data, which mainly come from the business system of the enterprise, including but not limited to business expansion work order data, electricity consumption data and payment data; the business expansion work order data covers the transformer capacity and time period information for the enterprise's application for electricity capacity increase or reduction; the electricity consumption data includes the enterprise's daily or monthly electricity consumption and real-time electricity load; the payment data includes the enterprise's electricity bill payment record and breach of contract and arrears; in addition, the primary model also integrates the external enterprise basic information data and non-power data evaluation model results, which are integrated and collected in the enterprise-level data center by using the enterprise-level ETL collection platform and dataX heterogeneous data synchronization tool to ensure the integrity and accuracy of the data; such data collation and collection provide an accurate input basis for the construction of the secondary model.

[0033] In an optional embodiment, the primary model can also be implemented in other ways, such as enhancing data processing efficiency through automated data identification and classification technology. This method may include using machine learning algorithms to identify and classify different types of enterprise data, such as distinguishing normal electricity consumption data from abnormal data, or automatically extracting valuable information from large amounts of unstructured data. Although this method is not as direct and effective as the method of directly using ETL tools and dataX synchronization tools in the aforementioned embodiment, it can reduce the need for manual operations and improve the level of automation in data processing.

[0034] In an optional embodiment, the first-level model can also be implemented in other ways, such as using a cloud computing platform to perform preliminary data organization and storage, and using the powerful computing power and flexible resource configuration provided by cloud services to process and analyze various enterprise electricity consumption data; in this model, distributed computing resources can be used to accelerate the data processing process, while using advanced security technologies on the cloud platform to protect the privacy and security of the data; this approach may require more initial investment and increased dependence on the cloud platform.

[0035] In the embodiment of the present application, the primary data is the business expansion work order data, electricity consumption data, and payment data of the enterprise, among which the business expansion work order data includes the transformer capacity and time period information for the enterprise's application for electricity capacity increase or reduction, the electricity consumption data includes the enterprise's daily or monthly electricity consumption and real-time electricity load, and the payment data includes the enterprise's electricity bill payment record and breach of contract and arrears; in addition, the primary data also integrates the evaluation model results of the enterprise's basic information data and non-power data obtained from the outside, ensuring the comprehensiveness and depth of the evaluation; to achieve data integration and collection, an enterprise-level ETL collection platform and dataX heterogeneous data synchronization tools are used, which help to efficiently collect and process raw data point-to-point in the enterprise-level data center, providing a reliable data foundation for building a more accurate secondary model.

[0036] In an optional embodiment, primary data can also be implemented in other ways, such as by integrating data from more sources to enhance the richness and availability of primary data. In addition to standard business expansion work order data, electricity consumption data and payment data, macroeconomic data such as market dynamics, weather information and regional economic conditions can be introduced to enhance the model's predictive accuracy and reliability. By integrating these broad data into primary data, the relationship between an enterprise's electricity consumption behavior and external factors can be more comprehensively analyzed, thereby more effectively predicting and adjusting the enterprise's electricity consumption strategy and financial budget. However, this approach may bring higher costs and data management challenges.

[0037] In an optional embodiment, primary data may also be achieved through other means, such as automatically collecting a company's public data by using Internet crawler technology; this method can obtain a company's public reports, news releases, and social media data, thereby providing support for the construction of primary data without directly accessing the company's internal data system; however, this method relies on publicly available data and may not be as detailed and accurate as data collected directly from the company's internal system, and is only suitable for preliminary market analysis and trend monitoring.

[0038] Example 2, reference Figure 1 , is an embodiment of the present invention, which provides an enterprise operation evaluation method based on enterprise electricity consumption data, including:

[0039] S2: Perform primary processing on primary data.

[0040] It should be noted that if Figure 1 In S11, the primary processing of the primary data includes further processing of the sorted primary data, which involves extracting deep information from the primary data for model construction and optimization.

[0041] Furthermore, the first-level processing is to standardize the collected raw data, using data cleaning, dirty data removal, duplicate data deduplication, missing value filling, outlier processing and other operations to ensure the quality and reliability of the data on the power consumption side. Since the integrity of the unified credit code in the power data is not high, it is difficult to directly apply it to external application scenarios. It is necessary to combine the external basic information of the enterprise and the regional location information with the power archives for data matching to achieve the cleaning and completion of the power data.

[0042] Furthermore, the collected raw data needs to be standardized because the business requirements of the original business systems are different, including:

[0043] Missing value processing: Delete data with a small proportion of missing values ​​that does not affect the overall model calculation; use the average value of the previous month and the same period last year to fill in the missing data; ensure that the data quality of the power-side dimensional model calculation meets the calculation requirements;

[0044] Deleting duplicate data: Use a unique business primary key (such as elec_cust_no) to identify duplicate records, and record and delete duplicate data based on the principle of retaining the most recent data.

[0045] Abnormal data processing: For abnormal data that occurs during the transfer of business systems to data centers, such as negative electricity charges and out-of-bounds electricity charges, we define non-erroneous data and delete them directly. In addition, to maintain the confidentiality of power data, we use boundary values ​​(power consumption capacity*statistical duration, where the statistical duration can be the number of working days in the month / the number of working days in the quarter / the number of working days in the year) to replace abnormal data that exceeds the range. If abnormal values ​​appear repeatedly among users, they are considered to be meaningful data and marked as valid data.

[0046] Data standard normalization: To avoid leakage of user sensitive information during the output of raw data, a linear compression method is used to compress the data to the range of [-1,11], so that the linear relationship of the data is retained to feedback business characteristics while meeting security requirements;

[0047] The linear compression method is specifically illustrated as follows: In a certain month, there are 1,000 users, the maximum power consumption is 10,000 kWh, and the minimum is 0 kWh. The maximum power consumption is regarded as 1, and the minimum power consumption is regarded as -1. The other power consumption will be calculated into this interval, for example, 9,000 kWh is calculated as 0.8.

[0048] Since the unified credit code in the power data is not necessary data for billing and settlement of the power system, its completeness is not high compared to the overall enterprise information, and it is difficult to be directly applied to external data connection; use the basic information of the enterprise and the regional location information data purchased from the outside, match the data with the power archives according to the keywords + location information, and complete the data after review and confirmation to realize the completion of the unified credit code power data.

[0049] S3: Build a secondary model and assign points.

[0050] It should be noted that if Figure 1 In S12, a secondary model is constructed and scored, including constructing a model using the primary processed data, calculating and processing the data in the model, and obtaining a comprehensive score.

[0051] Furthermore, the processed data is scored in six business dimensions: capacity dimension, power dimension, arrears dimension, timely payment rate dimension, power continuity dimension, and default power behavior. In addition, the time dimensions of the past 4 weeks, the past 3 months, and the past 4 quarters are constructed, and the weighted average is calculated with weights of 40%, 30%, 20%, and 10% to obtain a comprehensive score on the power side. The weighted sum is then taken with the enterprise evaluation model score of the external data (the weights of the two factors are determined by the data dimensions of the external data), and the evaluation model score is finally obtained.

[0052] Furthermore, the model is divided into two parts: comprehensive score and early warning flag. This step only processes the comprehensive score value, and the early warning flag is initially set to No. Construct business models with six business dimensions: capacity, power consumption, arrears, payment timeliness, power continuity, and default power consumption behavior. Construct three time dimensions: the past 4 weeks, the past 3 months, the past 4 quarters, and the past 3 years. Perform weighted average according to the weights of 40%, 30%, 20%, and 10% to obtain a comprehensive score on the power side.

[0053] The specific calculation formula is as follows:

[0054] Capacity Dimension:

[0055]

[0056] Where CAP is the user's operating capacity, AVG(CAP) is the industry's average capacity, MAX(CAP / AVG(CAP)) is the maximum value of the user's operating capacity compared to the industry's average capacity, and MIN(CAP / AVG(VAP)) is the minimum value of the user's operating capacity compared to the industry's average capacity.

[0057] Power consumption dimensions:

[0058]

[0059] Wherein, EU is the user's unit capacity electricity consumption (power PQ / CAP), AVG(EU) is the industry's average unit capacity electricity consumption, MAX(EU / AVG(EU)) is the maximum value of the user's unit capacity electricity consumption compared to the industry's average unit capacity electricity consumption, and MIN(EU / AVG(EU)) is the minimum value of the user's unit capacity electricity consumption compared to the industry's average unit capacity electricity consumption;

[0060] Arrears dimensions:

[0061]

[0062] Among them, ARR is the user's outstanding charges, and AVG(EU)1 is the average electricity charge of this user;

[0063] Timeliness dimension:

[0064]

[0065] Among them, Day pay Dayd is the payment date. eadline The starting date for liquidated damages. If the date is within the starting date, the value is 1. If the date is beyond the starting date, the value will be deducted on a daily basis. After 100 days, the value will be deducted to 0.

[0066] Continuity Dimension:

[0067] S coil =FLAG coil

[0068] Among them, FLAG is the continuity flag, excluding the influence of fixed-period rest days, continuous is 1, and discontinuous is 0;

[0069] Dimensions of electricity theft due to breach of contract:

[0070] S breach =FLAG breachh

[0071] Among them, FLAG is the flag of power theft due to breach of contract, which is 0 by default and 1 if breach of contract occurs;

[0072] The scores of individual dimensions are calculated based on a table similar to the following one, as shown in Table 1:

[0073] Table 1 Unidirectional dimension scores

[0074]

[0075] The weighted sum is then taken together with the enterprise evaluation model score of the external data (the weights of the two factors are determined by the data dimensions of the external data and shaped by the external data), and finally the evaluation model score is obtained.

[0076] Example 3, reference Figure 1 , is an embodiment of the present invention, which provides an enterprise operation evaluation method based on enterprise electricity consumption data, including:

[0077] S4: Optimize the secondary model.

[0078] It should be noted that if Figure 1 In S13, the optimization of the secondary model includes evaluating and fitting the model with the data processed by the model, and checking, verifying and optimizing the evaluation results.

[0079] Furthermore, the historical data is used to evaluate and fit the model, the data evaluation results on the power side are checked and verified with the non-power side model evaluation at the same time, the dynamic adjustment factors are calculated by using logistic regression and decision tree models, and the model is tuned by setting coefficient factors to improve the scientific nature of the model and dynamically optimize the calculation value of the enterprise credit evaluation data model; Figure 1 In S20, taking advantage of the timeliness of power data, a set of data identification rules are established to dynamically monitor business data. When data that meets the rule conditions is retrieved, the value of the model evaluation warning bit is modified until the business warning rule data is eliminated.

[0080] Furthermore, the historical data is used to evaluate and fit the model, and the data evaluation results of the power side are checked and verified with the non-power side model evaluation at the same time. The logistic regression algorithm is used to calculate the KL divergence of the power side evaluation value and the external evaluation value as a dynamic adjustment factor, and the model is tuned by adjusting the coefficient factor on a monthly basis to dynamically optimize the enterprise evaluation data model; set data trigger rules, monitor real-time data, and modify the warning flag when the corresponding user has an event that meets the rules. The specific rules include:

[0081] The capacity reduction or suspension of services exceeds 50% and the duration exceeds 3 months;

[0082] Handle account cancellation business;

[0083] No reduction in production such as account cancellation, capacity reduction, or suspension has been processed, and the electricity consumption for 10 consecutive working days is less than 20% of the average electricity consumption in the previous three months;

[0084] like Figure 1 In S90, the evaluation model is output to the third-party organization authorized by the user;

[0085] The specific applications of the model are as follows:

[0086] Loans from financial institutions and banks: When approving corporate loans, financial institutions and banks can refer to the evaluation results of the model and integrate the power model data into the judgment results of their free models to judge the operating status of the enterprise and estimate the repayment ability and credit status of the loan recipients;

[0087] Government regional policy formulation: When formulating regional policies, government agencies can use this model to screen the operating conditions of enterprises, thereby identifying the scope of policy implementation for analysis in a targeted manner, formulating policies more accurately, and supporting enterprise development;

[0088] Group enterprise risk management: Group enterprises can use this model to evaluate the operating conditions and management status of themselves or their subsidiaries, timely identify and respond to potential risks, and enhance the data capabilities of the enterprise for centralized management and cost reduction and efficiency improvement.

[0089] The above is a schematic scheme of an enterprise operation evaluation method based on enterprise electricity consumption data in this embodiment. It should be noted that the technical scheme of the system of the enterprise operation evaluation method based on enterprise electricity consumption data and the technical scheme of the enterprise operation evaluation method based on enterprise electricity consumption data mentioned above belong to the same concept. For details not described in detail in the technical scheme of the enterprise operation evaluation system based on enterprise electricity consumption data in this embodiment, please refer to the description of the technical scheme of the enterprise operation evaluation method based on enterprise electricity consumption data mentioned above.

[0090] Embodiment 4 is an embodiment of the present invention, which provides an enterprise operation evaluation system based on enterprise electricity consumption data, including: a data acquisition module, a data processing module, a model building module and a model optimization module;

[0091] The data collection module organizes the collected data to obtain primary data;

[0092] The data processing module performs primary processing on the primary data;

[0093] The model building module builds a secondary model and assigns points;

[0094] The model optimization module optimizes the secondary model.

[0095] This embodiment further provides a computing device, which is applicable to the enterprise operation evaluation method based on enterprise electricity consumption data, and includes:

[0096] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the enterprise operation evaluation method based on enterprise electricity consumption data as proposed in the above embodiment.

[0097] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the enterprise operation evaluation method based on enterprise electricity consumption data proposed in the above embodiment is implemented.

[0098] The storage medium proposed in this embodiment and the enterprise operation evaluation method based on enterprise electricity consumption data proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0099] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0100] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0101] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0102] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An enterprise operation evaluation method based on enterprise electricity consumption data, characterized by: include: Organize the collected data to obtain primary data; Perform primary processing on primary data; Construct a secondary model and assign points; Optimize the secondary model.

2. The enterprise operation evaluation method based on enterprise electricity consumption data according to claim 1, characterized in that: The data collection includes preliminary sorting of the collected basic data to obtain primary data as preparatory data for data analysis and further processing.

3. The enterprise operation evaluation method based on enterprise electricity consumption data according to claim 2, characterized in that: The primary processing of the primary data includes further processing the sorted primary data, which involves extracting deep information from the primary data for model construction and optimization.

4. The enterprise operation evaluation method based on enterprise electricity consumption data according to claim 3, characterized in that: The construction of the secondary model and the scoring include constructing a model using the data after primary processing, calculating and processing the data in the model, and obtaining a comprehensive score.

5. The enterprise operation evaluation method based on enterprise electricity consumption data according to claim 4, characterized in that: The optimization of the secondary model includes evaluating and fitting the model with the data processed by the model, and checking, verifying and optimizing the evaluation results.

6. The enterprise operation evaluation method based on enterprise electricity consumption data according to claim 5, characterized in that: The data collected and sorted also includes collecting basic data for constructing a primary model, and performing preliminary sorting and classification to obtain primary data as an input basis for primary processing and constructing a secondary model.

7. The enterprise operation evaluation method based on enterprise electricity consumption data according to claim 6, characterized in that: The first-level data includes the enterprise's business expansion work order data, electricity consumption data, and payment data.

8. A system for evaluating enterprise operation based on enterprise electricity consumption data according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, data processing module, model building module and model optimization module; The data collection module organizes the collected data to obtain primary data; The data processing module performs primary processing on the primary data; The model building module builds a secondary model and assigns points; The model optimization module optimizes the secondary model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the enterprise operation evaluation method based on enterprise electricity consumption data described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the enterprise operation evaluation method based on enterprise electricity consumption data described in any one of claims 1 to 7 are implemented.

Images