Enterprise financial data evaluation method and system and computer readable storage medium

Abstract

The invention discloses an enterprise financial data evaluation method and system and a computer readable storage medium, and the method is characterized in that the method specifically comprises the following steps: S1, obtaining department financial data corresponding to at least two project types of each operation department, the department financial data at least comprising first project financial data and second project financial data; s2, performing clustering processing on the operating departments for the first project financial data and the second project financial data to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data; s3, performing regional division on each operating department according to the first clustering result and the second clustering result to obtain an operating region corresponding to each operating department; and S4, evaluating the regional financial data of each operation region to obtain a regional decision result of each operation region.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for evaluating enterprise financial data, and a computer-readable storage medium. Background Art

[0002] Large enterprises accumulate vast amounts of financial data over the course of their operations. This data provides a clear understanding of the performance of each department, project, or business unit. For example, data such as asset turnover and inventory turnover for each department, project, or business unit can contain valuable information for decision-making. However, current analysis and evaluation of corporate financial data relies heavily on subjective judgment, making it difficult to tailor assessments to specific regions. Therefore, effectively mining corporate financial data and leveraging it to inform decision-making has become a pressing issue. Summary of the Invention

[0003] The technical problem solved by the present invention is: how to reasonably divide the large number of business departments under an enterprise into regions, so as to conduct financial data evaluation tailored to local conditions for each region, thereby improving the accuracy and rationality of the enterprise's financial data evaluation.

[0004] In a first aspect, to solve the above technical problems, the present invention provides the following technical solution: a method for evaluating enterprise financial data, characterized in that it specifically comprises the following steps:

[0005] Step S1, obtaining department financial data corresponding to at least two project types of each business department, wherein the department financial data at least includes: first project financial data and second project financial data;

[0006] Step S2: performing clustering processing on each of the operating departments for the first project financial data and the second project financial data, respectively, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data;

[0007] Step S3, dividing each of the business departments into regions according to the first clustering result and the second clustering result to obtain a business region corresponding to each of the business departments;

[0008] Step S4: Evaluate the regional financial data of each of the business areas to obtain a regional decision result for each of the business areas.

[0009] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, step S2 performs clustering processing on each of the operating departments for the first project financial data and the second project financial data, respectively, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data, including:

[0010] Performing feature extraction on the first project financial data and the second project financial data to obtain data features corresponding to the first project financial data and the second project financial data, respectively;

[0011] Determine multiple central business departments as cluster centers, and use data features corresponding to the central business departments as central data features, and use data features of candidate business departments other than the central business departments as candidate data features;

[0012] Based on the K-Means clustering algorithm, the central data feature corresponding to each of the candidate data features is determined, thereby obtaining the first clustering result and the second clustering result.

[0013] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, the step of extracting features from the first project financial data or the second project financial data to obtain data features corresponding to the first project financial data or the second project financial data includes:

[0014] Obtaining geographical location attributes of each of the business departments, wherein the geographical location attributes include at least: administrative division attributes, climate type attributes, and geographical coordinate attributes;

[0015] Joining the geographic location attribute with the first project financial data and the second project financial data respectively to obtain the first project data and the second project data corresponding to each business department;

[0016] Feature extraction is performed on the first project data and the second project data to obtain first data features and second data features.

[0017] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, the step of determining a plurality of central operating departments as cluster centers includes:

[0018] Obtain the overall financial data corresponding to each of the operating departments, and calculate the aggregation index of each of the operating departments based on the overall financial data:

[0019]

[0020] Where N is the number of business units, x iis the overall financial data of the i-th operating department, x j is the overall financial data of the j-th operating department, is the average value of the overall financial data of each operating department, w ij is the weight matrix x i with x j The weights between them, W is the sum of all weights in the weight matrix;

[0021] In the area where the clustering index meets the preset conditions, the spatial attribute value of each business department is calculated using the following formula:

[0022] The overall financial data is used as the horizontal coordinate, and the spatial attribute value is used as the vertical coordinate; the target business department located in the first quadrant is obtained, and the central business department is determined based on the target business department.

[0023] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, x is calculated based on the following formula: i with x j The weights between get the weight matrix:

[0024]

[0025] Among them, w ij is the weight matrix x i with x j The weight between ij is x i with x j The difference between them, σ is the preset bandwidth parameter, which is used to control the speed at which the weight decays with distance.

[0026] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, step S3, dividing each of the operating departments into regions based on the first clustering result and the second clustering result to obtain the operating regions corresponding to each of the operating departments, includes:

[0027] Comparing the first clustering result and the second clustering result, determining the business departments that belong to the same cluster in the first clustering result and the second clustering result as core business departments of the core area corresponding to the business area, and determining the business departments that belong to different clusters in the first clustering result and the second clustering result as marginal business departments;

[0028] Determining the core characteristics of the core business departments included in the core areas corresponding to the core areas, and the marginal characteristics of the marginal business departments;

[0029] Comparing the edge features with the core features of adjacent core areas to obtain similarities between the edge features and the core features, and determining a target core area with the greatest similarity;

[0030] The business area to which the target core area belongs is determined as the business area to which the marginal business department belongs.

[0031] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, step S4 evaluates the regional financial data of each of the operating areas to obtain the regional decision results of each of the operating areas, including:

[0032] Acquiring regional financial data for each of the operating areas, the regional financial data including at least first regional data and second regional data corresponding to different project types;

[0033] Determine a first time series based on the first region data, and determine a second time series based on the second region data;

[0034] The first time series and the second time series are evaluated to determine a regional decision result of the operating area.

[0035] As a preferred embodiment of the enterprise financial data evaluation method of the present invention, the step of evaluating the first time series and the second time series to determine the regional decision result of the operating area includes:

[0036] The first time series and the second time series are evaluated respectively based on a preset long short-term memory neural network to obtain at least one of an inventory management strategy, a marketing strategy, and a pricing strategy for the first item type and the second item type.

[0037] In a second aspect, an embodiment of the present application further provides an enterprise financial data evaluation system, the system comprising:

[0038] A data acquisition module is used to acquire department financial data corresponding to at least two project types of each operating department, wherein the department financial data includes at least: first project financial data and second project financial data;

[0039] a data clustering module, configured to perform clustering processing on each of the operating departments based on the first project financial data and the second project financial data, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data;

[0040] a region division module, configured to divide each of the business departments into regions according to the first clustering result and the second clustering result, to obtain a business region corresponding to each of the business departments;

[0041] The regional evaluation module is used to evaluate the regional financial data of each of the operating regions and obtain regional decision-making results for each of the operating regions.

[0042] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the enterprise financial data evaluation method as described in any one of the embodiments of the present application are implemented.

[0043] Beneficial effects of the present invention: The present application provides a method, system and computer-readable storage medium for evaluating enterprise financial data. The present application obtains departmental financial data corresponding to at least two project types of each business department, and the departmental financial data includes at least: first project financial data and second project financial data; clusters the first project financial data and the second project financial data for each business department to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data; divides each business department into regions based on the first clustering result and the second clustering result to obtain the business area corresponding to each business department; evaluates the regional financial data of each business area to obtain the regional decision result of each business area. The business areas described by the business departments are divided according to the financial data corresponding to different types of projects to obtain the business areas to which each business department belongs, thereby realizing reasonable regional division of a large number of business departments under the enterprise, facilitating financial data evaluation tailored to local conditions for each business area, and improving the accuracy and rationality of enterprise financial data evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 A schematic diagram of the basic flow of a method for evaluating enterprise financial data provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0047] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0048] Embodiments of the present application provide a method, system, and computer-readable storage medium for evaluating enterprise financial data.

[0049] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0050] Please refer to Figure 1 , Figure 1 A flow chart of a method for evaluating enterprise financial data provided in accordance with an embodiment of the present application. The method for evaluating enterprise financial data can be used in a terminal or server to achieve targeted and accurate evaluation of enterprise financial data. The terminal can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, and wearable device; the server can be an independent server, a server cluster, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0051] like Figure 1 As shown, the enterprise financial data evaluation method includes steps S1 to S4.

[0052] Step S1: Acquire department financial data corresponding to at least two project types of each operating department, wherein the department financial data at least includes: first project financial data and second project financial data.

[0053] For example, for sales companies, the operating department can be the company's various stores, such as the clothing stores under a clothing sales company and the various branches under a catering brand; for service companies, the operating department can be the company's various service outlets, such as the service outlets of a technology service company; for platform companies, the business department can also be the business unit established in various regions.

[0054] For example, a company may have many different types of projects in the same region. For example, in a clothing sales company, clothing may be divided into women's clothing and men's clothing based on gender, and may be divided into high-end and low-end lines based on pricing; or in a restaurant brand, food may be divided into spicy food, light food, sweet food, and sour food based on taste. Different regions have regional preferences for different types of projects. For example, different regions have different clothing habits and eating habits due to different climates. Therefore, this solution divides department financial data by project type and obtains department financial data corresponding to each project type, so that business departments can be divided into regions with different preferences based on department financial data, which is conducive to mining the consumption habits of consumers in different regions from corporate financial data.

[0055] Of course, it is not limited to this. Business departments can also be divided from a larger dimension. For example, a city can be regarded as an business department, and the financial data of all stores in the city can be used as department financial data to reduce the amount of calculation of department financial data.

[0056] It is understandable that the number of project types can be two or more, and the department financial data includes but is not limited to the first project financial data and the second project financial data, and may also include the third project financial data, the fourth project financial data, etc., which are not limited here.

[0057] It is understandable that the departmental financial data includes a series of data indicators. Taking the first project financial data as an example, it may include the inventory, turnover, operating profit, etc. of multiple commodities corresponding to the project type.

[0058] Step S2: clustering the operating departments for the first project financial data and the second project financial data to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data.

[0059] For example, clustering the operating departments according to the financial data of each department can be understood as dividing the operating departments into regions according to the financial data of each department, so as to determine the final regional division method based on the regional division results corresponding to different project types.

[0060] In some embodiments, step S2 performs clustering processing on each of the operating departments for the first project financial data and the second project financial data, respectively, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data, including:

[0061] Performing feature extraction on the first project financial data and the second project financial data to obtain data features corresponding to the first project financial data and the second project financial data, respectively;

[0062] Determine multiple central business departments as cluster centers, and use data features corresponding to the central business departments as central data features, and use data features of candidate business departments other than the central business departments as candidate data features;

[0063] Based on the K-Means clustering algorithm, the central data feature corresponding to each of the candidate data features is determined, thereby obtaining the first clustering result and the second clustering result.

[0064] For example, each cluster in the clustering results can be pre-assigned a central business department seat cluster center. For example, to divide business departments nationwide, a large city or provincial capital city can be pre-assigned as a cluster center, and the business departments therein can be designated as central business departments. Clusters can then be formed around these central business departments. This is not limited to this, and regional divisions can also be performed across the province, city, or other dimensions, which are not limited here.

[0065] For example, the K-Means clustering algorithm can divide the first project financial data or the second project financial data with similar data features into the same cluster by minimizing the sum of the distances from the data points in the cluster to the cluster center, so that the data points in the cluster are as similar as possible and the data points between different clusters are as different as possible.

[0066] The first clustering result is obtained by clustering the financial data of the first project, and the second clustering result is obtained by clustering the financial data of the second project.

[0067] In some embodiments, extracting features from the first project financial data or the second project financial data to obtain data features corresponding to the first project financial data or the second project financial data includes:

[0068] Obtaining geographical location attributes of each of the business departments, wherein the geographical location attributes include at least: administrative division attributes, climate type attributes, and geographical coordinate attributes;

[0069] Joining the geographic location attribute with the first project financial data and the second project financial data respectively to obtain the first project data and the second project data corresponding to each business department;

[0070] Feature extraction is performed on the first project data and the second project data to obtain first data features and second data features.

[0071] For example, since business departments are immovable, this solution clusters business departments based on their geographic location. Geographic location attributes include at least: administrative division attributes, climate type attributes, and geographic coordinate attributes. Specifically, administrative division attributes represent the administrative region to which a business department belongs, such as the province or city; climate type attributes reflect the climate type at the location of the business department, and each climate type can be pre-coded; and geographic coordinate attributes reflect the geographic coordinates of the business department, such as latitude and longitude.

[0072] Exemplarily, the geographical location attribute is concatenated with the first project financial data and the second project financial data to obtain the first project data and the second project data, thereby using the geographical location of the business department as a factor for clustering.

[0073] In some embodiments, determining a plurality of central business departments as cluster centers includes:

[0074] Obtain the overall financial data corresponding to each of the operating departments, and calculate the aggregation index of each of the operating departments based on the overall financial data:

[0075]

[0076] Where N is the number of business units, x i is the overall financial data of the i-th operating department, x j is the overall financial data of the j-th operating department, is the average value of the overall financial data of each operating department, w ij is the weight matrix x i with x j The weights between them, W is the sum of all weights in the weight matrix;

[0077] In the area where the clustering index meets the preset conditions, the spatial attribute value of each business department is calculated using the following formula:

[0078] The overall financial data is used as the horizontal coordinate, and the spatial attribute value is used as the vertical coordinate; the target business department located in the first quadrant is obtained, and the central business department is determined based on the target business department.

[0079] For example, the overall financial data may be the turnover of all project types of each business department.

[0080] It is understandable that a central business department has a higher turnover, and the business departments clustered around the central business department should also have a higher turnover. Therefore, the degree of clustering of such business departments can be determined by calculating the clustering index I. Specifically, the Moran index can be used as a clustering index. If the clustering index is greater than a preset threshold, it indicates that the area is clustered with business departments with higher or lower turnover. Conversely, if the clustering index is less than the preset threshold, it indicates that the area has both business departments with higher turnover and business departments with lower turnover. The preset threshold can be, for example, 0. The area targeted by the clustering index I can be an administrative region of a specific level, such as a city-level administrative region.

[0081] For example, the cluster center needs to be located in an area where business departments with high sales are concentrated. However, the clustering index cannot distinguish between business departments with high sales and those with low sales. In this case, spatial attribute values ​​can be calculated for areas with a clustering index greater than a preset threshold, and the spatial attribute values ​​can be used as the vertical coordinates of the business departments in a preset coordinate system, and the overall financial data as the horizontal coordinates. If a business department is located in the first quadrant of the preset coordinate system, it means that the overall financial data in this area is high, and the overall financial data of the neighboring areas is also high, indicating that it is a cluster of business departments with high overall financial data. Conversely, if it is located in the second quadrant, it means that the overall financial data in this area is low, but the overall financial data of the neighboring areas is high; if it is located in the third quadrant, it means that the overall financial data in this area is low, and the values ​​of the neighboring areas are also low; if it is located in the fourth quadrant, it means that the overall financial data in this area is high, but the overall financial data of the neighboring areas is low. Therefore, the target business department in the first quadrant can be used as the central business area.

[0082] Understandably, the target business departments in the first quadrant will cluster in a certain area on the map. These target business departments can be clustered on the map, and the business department at the center of each cluster in the clustering results can be used as the central business department. Specifically, if the distance between two clusters is less than a preset threshold, the business department at the center of one of the two clusters can be used as the central business department.

[0083] In some embodiments, x is calculated based on the following formula: i with x j The weights between , get the weight matrix, including:

[0084]

[0085] Among them, w ij is the weight matrix x i with x j The weight between ij is x i with x jThe difference between them, σ is the preset bandwidth parameter, which is used to control the speed at which the weight decays with distance.

[0086] For example, the weight between the overall financial data of any two operating departments can be calculated by the Gaussian kernel function, thereby obtaining the weight matrix between the overall financial data of the i-th operating department and the overall financial data of the j-th operating department, where i and j are any positive integers less than the number of operating departments; the bandwidth parameter σ is used to control the weight with the difference d ij The speed of attenuation and the specific size can be set according to actual needs.

[0087] Step S3: Divide each of the business departments into regions according to the first clustering result and the second clustering result to obtain a business region corresponding to each of the business departments.

[0088] For example, the classification results of business departments may be different according to different project types, that is, the first clustering result and the second clustering result may have business departments divided into different clusters, but there will be overlapping areas. Therefore, the final regional division result can be determined based on the overlapping and non-overlapping parts between the first clustering result and the second clustering result.

[0089] In some implementations, step S3, dividing each of the business departments into regions based on the first clustering result and the second clustering result to obtain a business region corresponding to each of the business departments, includes:

[0090] Comparing the first clustering result and the second clustering result, determining the business departments that belong to the same cluster in the first clustering result and the second clustering result as core business departments of the core area corresponding to the business area, and determining the business departments that belong to different clusters in the first clustering result and the second clustering result as marginal business departments;

[0091] Determining the core characteristics of the core business departments included in the core areas corresponding to the core areas, and the marginal characteristics of the marginal business departments;

[0092] Comparing the edge features with the core features of adjacent core areas to obtain similarities between the edge features and the core features, and determining a target core area with the greatest similarity;

[0093] The business area to which the target core area belongs is determined as the business area to which the marginal business department belongs.

[0094] Exemplarily, the overlapping portion of a specific cluster between the first clustering result and the second clustering result is determined as the core business department, the area formed by the core business department is the core area of ​​the cluster, and the business departments other than the core business department are marginal business departments.

[0095] It's understandable that the core business department is the one that can be directly determined to belong to the cluster, while the cluster to which the peripheral business department belongs remains to be determined. Specifically, the similarity between the peripheral business department's edge features and the core features of the surrounding core areas can be calculated, and the cluster containing the core area corresponding to the core feature with the smallest similarity is determined as the cluster to which the peripheral business department belongs.

[0096] The similarity may be the Euclidean distance, Manhattan distance, cosine similarity, etc. between the edge feature and the core feature, which is not limited here.

[0097] Step S4: Evaluate the regional financial data of each of the business areas to obtain a regional decision result for each of the business areas.

[0098] For example, after determining business areas with similar consumption habits, the business areas are used as units for financial data evaluation. Specifically, regional financial data of each business area is obtained and evaluated to obtain regional decision results for the business area.

[0099] In some embodiments, step S4 evaluates the regional financial data of each of the operating areas to obtain a regional decision result for each of the operating areas, including:

[0100] Acquiring regional financial data for each of the operating areas, the regional financial data including at least first regional data and second regional data corresponding to different project types;

[0101] Determine a first time series based on the first region data, and determine a second time series based on the second region data;

[0102] The first time series and the second time series are evaluated to determine a regional decision result of the operating area.

[0103] Exemplarily, the first time series and the second time series consisting of the first regional data and the second regional data corresponding to different project types in the regional financial data are evaluated respectively, for example, the first time series and the second time series are predicted.

[0104] The first regional data is the historical financial data of the first project type in the operating area, and the second regional data is the historical financial data of the second project type in the operating area. The first regional data and the second regional data are respectively timestamp-ed.

[0105] It is understandable that the regional financial data may also include third-region data, which will not be elaborated here.

[0106] In some embodiments, evaluating the first time series and the second time series to determine the regional decision result of the business area includes:

[0107] The first time series and the second time series are evaluated respectively based on a preset long short-term memory neural network to obtain at least one of an inventory management strategy, a marketing strategy, and a pricing strategy for the first item type and the second item type.

[0108] Exemplarily, the first time series and the second time series can be predicted by a long short-term memory neural network (LTSM) to obtain regional decision results corresponding to the first project type and the second project type.

[0109] The regional decision results include the inventory management strategy, marketing strategy, and pricing strategy for the first and second item types in the operating region. Each of these strategies includes both positive and negative results. A positive inventory management strategy indicates a need to increase inventory, while a negative strategy indicates a need to decrease inventory. This is not detailed here.

[0110] The present application also provides a system for evaluating enterprise financial data, the system comprising:

[0111] A data acquisition module is used to acquire department financial data corresponding to at least two project types of each operating department, wherein the department financial data includes at least: first project financial data and second project financial data;

[0112] a data clustering module, configured to perform clustering processing on each of the operating departments based on the first project financial data and the second project financial data, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data;

[0113] a region division module, configured to divide each of the business departments into regions according to the first clustering result and the second clustering result, to obtain a business region corresponding to each of the business departments;

[0114] The regional evaluation module is used to evaluate the regional financial data of each of the operating regions and obtain regional decision-making results for each of the operating regions.

[0115] In one embodiment, clustering is performed on each of the operating departments for the first project financial data and the second project financial data, respectively, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data, including:

[0116] Performing feature extraction on the first project financial data and the second project financial data to obtain data features corresponding to the first project financial data and the second project financial data, respectively;

[0117] Determine multiple central business departments as cluster centers, and use data features corresponding to the central business departments as central data features, and use data features of candidate business departments other than the central business departments as candidate data features;

[0118] Based on the K-Means clustering algorithm, the central data feature corresponding to each of the candidate data features is determined, thereby obtaining the first clustering result and the second clustering result.

[0119] In one embodiment, extracting features from the first project financial data or the second project financial data to obtain data features corresponding to the first project financial data or the second project financial data includes:

[0120] Obtaining geographical location attributes of each of the business departments, wherein the geographical location attributes include at least: administrative division attributes, climate type attributes, and geographical coordinate attributes;

[0121] Joining the geographic location attribute with the first project financial data and the second project financial data respectively to obtain the first project data and the second project data corresponding to each business department;

[0122] Feature extraction is performed on the first project data and the second project data to obtain first data features and second data features.

[0123] In one embodiment, determining a plurality of central business departments as cluster centers includes:

[0124] Obtain the overall financial data corresponding to each of the operating departments, and calculate the aggregation index of each of the operating departments based on the overall financial data:

[0125]

[0126] Where N is the number of business units, x i is the overall financial data of the i-th operating department, x j is the overall financial data of the j-th operating department, is the average value of the overall financial data of each operating department, w ij is the weight matrix x i with x j The weights between them, W is the sum of all weights in the weight matrix;

[0127] In the area where the clustering index meets the preset conditions, the spatial attribute value of each business department is calculated using the following formula:

[0128]

[0129] The overall financial data is used as the horizontal coordinate, and the spatial attribute value is used as the vertical coordinate; the target business department located in the first quadrant is obtained, and the central business department is determined based on the target business department.

[0130] In one embodiment, x is calculated based on the following formula: i with x j The weights between get the weight matrix:

[0131]

[0132] Among them, w ij is the weight matrix x i with x j The weight between ij is x i with x j The difference between them, σ is the preset bandwidth parameter.

[0133] In one embodiment, each of the business departments is divided into regions according to the first clustering result and the second clustering result to obtain a business region corresponding to each of the business departments, including:

[0134] Comparing the first clustering result and the second clustering result, determining the business departments that belong to the same cluster in the first clustering result and the second clustering result as core business departments of the core area corresponding to the business area, and determining the business departments that belong to different clusters in the first clustering result and the second clustering result as marginal business departments;

[0135] Determining the core characteristics of the core business departments included in the core areas corresponding to the core areas, and the marginal characteristics of the marginal business departments;

[0136] Comparing the edge features with the core features of adjacent core areas to obtain similarities between the edge features and the core features, and determining a target core area with the greatest similarity;

[0137] The business area to which the target core area belongs is determined as the business area to which the marginal business department belongs.

[0138] In one embodiment, evaluating the regional financial data of each of the operating regions to obtain a regional decision result for each of the operating regions includes:

[0139] Acquiring regional financial data for each of the operating areas, the regional financial data including at least first regional data and second regional data corresponding to different project types;

[0140] Determine a first time series based on the first region data, and determine a second time series based on the second region data;

[0141] The first time series and the second time series are evaluated to determine a regional decision result of the operating area.

[0142] In one embodiment, evaluating the first time series and the second time series to determine the regional decision result of the business area includes:

[0143] The first time series and the second time series are evaluated respectively based on a preset long short-term memory neural network to obtain at least one of an inventory management strategy, a marketing strategy, and a pricing strategy for the first item type and the second item type.

[0144] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the enterprise financial data evaluation method of the present application.

[0145] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc., equipped on the computer device.

[0146] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0147] It should also be understood that the term "and / or" used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0148] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for evaluating enterprise financial data, characterized in that: The specific steps include: Step S1, obtaining department financial data corresponding to at least two project types of each business department, wherein the department financial data at least includes: first project financial data and second project financial data; Step S2: performing clustering processing on each of the operating departments for the first project financial data and the second project financial data, respectively, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data; Step S3, dividing each of the business departments into regions according to the first clustering result and the second clustering result to obtain a business region corresponding to each of the business departments; Step S4: Evaluate the regional financial data of each of the business areas to obtain a regional decision result for each of the business areas.

2. The enterprise financial data evaluation method according to claim 1, characterized in that: Step S2 performs clustering processing on each of the operating departments for the first project financial data and the second project financial data, respectively, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data, including: Performing feature extraction on the first project financial data and the second project financial data to obtain data features corresponding to the first project financial data and the second project financial data, respectively; Determine multiple central business departments as cluster centers, and use data features corresponding to the central business departments as central data features, and use data features of candidate business departments other than the central business departments as candidate data features; Based on the K-Means clustering algorithm, the central data feature corresponding to each of the candidate data features is determined, thereby obtaining the first clustering result and the second clustering result.

3. The enterprise financial data evaluation method according to claim 2, characterized in that: The extracting features of the first project financial data or the second project financial data to obtain data features corresponding to the first project financial data or the second project financial data includes: Obtaining geographical location attributes of each of the business departments, the geographical location attributes including at least: administrative division attributes, climate type attributes, and geographical coordinate attributes; Joining the geographic location attribute with the first project financial data and the second project financial data respectively to obtain first project data and second project data corresponding to each business department; Feature extraction is performed on the first project data and the second project data to obtain first data features and second data features.

4. The enterprise financial data evaluation method according to claim 2, characterized in that: The step of determining a plurality of central business departments as cluster centers includes: Obtain the overall financial data corresponding to each of the operating departments, and calculate the aggregation index of each of the operating departments based on the overall financial data: Where N is the number of business units, x i is the overall financial data of the i-th operating department, x j is the overall financial data of the j-th operating department, is the average value of the overall financial data of each operating department, w ij is the weight matrix x i with x j The weights between them, W is the sum of all weights in the weight matrix; In the area where the clustering index meets the preset conditions, the spatial attribute value of each business department is calculated using the following formula: The overall financial data is used as the horizontal coordinate, and the spatial attribute value is used as the vertical coordinate; the target business department located in the first quadrant is obtained, and the central business department is determined based on the target business department.

5. The enterprise financial data evaluation method according to claim 4, characterized in that: Calculate x based on the following formula i with x j The weights between get the weight matrix: Among them, w ij is the weight matrix x i with x j The weight between ij is x i with x j The difference between them, σ is the preset bandwidth parameter.

6. The enterprise financial data evaluation method according to claim 1, characterized in that: Step S3, dividing each of the business departments into regions according to the first clustering result and the second clustering result to obtain a business region corresponding to each of the business departments, including: Comparing the first clustering result and the second clustering result, determining the business departments that belong to the same cluster in the first clustering result and the second clustering result as core business departments of the core area corresponding to the business area, and determining the business departments that belong to different clusters in the first clustering result and the second clustering result as marginal business departments; Determining the core characteristics of the core business departments included in the core areas corresponding to the core areas, and the marginal characteristics of the marginal business departments; Comparing the edge features with the core features of adjacent core areas to obtain similarities between the edge features and the core features, and determining a target core area with the greatest similarity; The business area to which the target core area belongs is determined as the business area to which the marginal business department belongs.

7. The enterprise financial data evaluation method according to claim 1, characterized in that: Step S4 evaluates the regional financial data of each of the operating areas to obtain regional decision results for each of the operating areas, including: Acquiring regional financial data for each of the operating areas, the regional financial data including at least first regional data and second regional data corresponding to different project types; Determine a first time series based on the first region data, and determine a second time series based on the second region data; The first time series and the second time series are evaluated to determine a regional decision result of the operating area.

8. The enterprise financial data evaluation method according to claim 7, characterized in that: The evaluating the first time series and the second time series to determine the regional decision result of the operating area includes: The first time series and the second time series are evaluated respectively based on a preset long short-term memory neural network to obtain at least one of an inventory management strategy, a marketing strategy, and a pricing strategy for the first item type and the second item type.

9. An enterprise financial data evaluation system, characterized in that: The system comprises: A data acquisition module is used to acquire department financial data corresponding to at least two project types of each operating department, wherein the department financial data includes at least: first project financial data and second project financial data; a data clustering module, configured to perform clustering processing on each of the operating departments based on the first project financial data and the second project financial data, to obtain a first clustering result corresponding to the first project financial data and a second clustering result corresponding to the second project financial data; a region division module, configured to divide each of the business departments into regions according to the first clustering result and the second clustering result, to obtain a business region corresponding to each of the business departments; The regional evaluation module is used to evaluate the regional financial data of each of the operating regions and obtain regional decision-making results for each of the operating regions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the enterprise financial data evaluation method according to any one of claims 1 to 8 are implemented.

Images