Shop inspection early warning method, device, equipment and medium

Abstract

The invention relates to the technical field of data analysis, in particular to a shop inspection early warning method, device and equipment and a medium. According to data of different dimensions in a shop, corresponding operation characteristics are calculated, risk early warning monitoring is carried out according to the data of different dimensions, the operation characteristics and the contribution degree of data of each dimension to the operation characteristics, and an early warning monitoring result is obtained. Fusion monitoring is carried out on the multi-dimensional data, the operation characteristics and the contribution degree of the data of each dimension to the operation characteristics, the monitoring accuracy is improved, and therefore the reliability of an early warning monitoring result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a store inspection and early warning method, device, equipment and medium. Background Art

[0002] The operation monitoring platform of a store provides a management means for production operation management monitoring, and can realize the integrated evaluation of the store development index and the project health index. With the rapid development of society, risks in store operation data also emerge. It is necessary to form a method for store operation analysis and risk early warning monitoring to achieve a good guarantee for store operation. It can provide reliable data basis for relevant management personnel and supervision personnel in a timely manner, so as to facilitate relevant personnel to carry out subsequent management work or supervision work. The existing problems in the existing store operation and risk monitoring methods are mainly low reliability of operation analysis and poor risk monitoring effect. Summary of the Invention

[0003] In view of this, the embodiments of the present invention provide a store inspection and early warning method, device, equipment and medium to solve the problem of low reliability of risk monitoring in the risk monitoring of stores.

[0004] In a first aspect, the embodiments of the present invention provide a store inspection and early warning method, and the store inspection and early warning method includes: Obtain order data, passenger flow data, commodity sales data, lease management data and financial data of the store for different warning periods; According to the order data, passenger flow data, commodity sales data, lease management data and financial data of different warning periods, calculate the eigenvalue of N preset operation characteristics of the store in the current warning period, where N is an integer greater than 1; Obtain the contribution value of the order data, passenger flow data, commodity sales data, lease management data and financial data to each of the preset operation characteristics, and splice and fuse the order data, passenger flow data, commodity sales data, lease management data and financial data of different warning periods, the index values of the N preset operation characteristics and each of the contribution values to obtain the fused characteristics; According to the fused characteristics, perform risk early warning on the store in the current warning period to obtain the early warning result of the store.

[0005] In a second aspect, the embodiments of the present invention provide a store inspection and early warning device, and the store inspection and early warning device includes: An obtaining module, configured to obtain order data, passenger flow data, commodity sales data, lease management data and financial data of the store for different warning periods; A calculation module, configured to calculate eigenvalue of N preset operation characteristics of the store in the current warning period according to the order data, passenger flow data, commodity sales data, lease management data and financial data in different warning periods, where N is an integer greater than 1; A fusion module, configured to obtain contribution values of the order data, passenger flow data, commodity sales data, lease management data and financial data to each of the preset operation characteristics, splice and fuse the order data, passenger flow data, commodity sales data, lease management data and financial data in different warning periods, the index values of the N preset operation characteristics and each of the contribution values to obtain fused characteristics; A warning module, configured to perform risk warning on the store in the current warning period according to the fused characteristics to obtain a warning result of the store.

[0006] In a third aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned store inspection and warning method is implemented.

[0007] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned store inspection and warning method is implemented.

[0008] The beneficial effects of the present invention compared with the prior art are as follows: In the present invention, order data, passenger flow data, commodity sales data, lease management data and financial data of a store in different warning periods are obtained. According to the order data, passenger flow data, commodity sales data, lease management data and financial data in different warning periods, eigenvalue of N preset operation characteristics of the store in the current warning period is calculated, where N is an integer greater than 1. Contribution values of the order data, passenger flow data, commodity sales data, lease management data and financial data to each of the preset operation characteristics are obtained. The order data, passenger flow data, commodity sales data, lease management data and financial data in different warning periods, the index values of the N preset operation characteristics and each of the contribution values are spliced and fused to obtain fused characteristics. According to the fused characteristics, risk warning is performed on the store in the current warning period to obtain a warning result of the store. According to data in different dimensions in the store, corresponding operation characteristics are calculated. Risk warning monitoring is performed according to data in different dimensions, operation characteristics and the contribution degree of each dimension data to the operation characteristics to obtain a warning monitoring result. The multi-dimensional data, operation characteristics and the contribution degree of each dimension data to the operation characteristics are fused and monitored to improve the accuracy of monitoring, thereby improving the reliability of the warning monitoring result. Description of the Drawings

[0009] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 Schematic diagram of the application environment of a store inspection and warning method provided in Embodiment 1 of the present invention; Figure 2 Flow chart of a store inspection and warning method provided in Embodiment 2 of the present application; Figure 3 Flow chart of a store inspection and warning method provided in Embodiment 3 of the present invention; Figure 4 Flow chart of a store inspection and warning method provided in Embodiment 4 of the present invention; Figure 5 Flow chart of a store inspection and warning method provided in Embodiment 5 of the present invention; Figure 6 Flow chart of a store inspection and warning method provided in Embodiment 6 of the present invention; Figure 7 Flow chart of a store inspection and warning method provided in Embodiment 7 of the present invention; Figure 8 Schematic diagram of a store inspection and warning device provided in Embodiment 8 of the present invention; Figure 9 Schematic diagram of the structure of a computer device provided in Embodiment 9 of the present invention. Detailed implementation manners

[0011] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0012] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0013] It should also be understood that the term "and / or" as used in the specification and appended claims of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0014] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0015] In addition, in the description of the specification and appended claims of this application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0016] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0017] It should be understood that the magnitudes of the sequence numbers of the steps in the following embodiments do not mean the order of execution is prior or posterior. The order of execution of each process should be determined by its function and internal logic and should not constitute any limitation to the implementation process of the embodiments of this application.

[0018] To illustrate the technical solution of this application, the following specific embodiments are used for illustration.

[0019] As Figure 1As shown in the figure, it is a schematic diagram of the application environment of a store patrol warning method provided by Embodiment 1 of the present invention. Among them, the client and the server are connected for communication. Users can provide conditions, requirements, operation instructions, etc. for store patrol warning to the server by operating the client. The server is used to execute the store patrol warning method of the present invention according to the relevant content sent by the client. Among them, the client includes, but is not limited to, various computer devices such as personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The computer device corresponding to the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0020] See Figure 2 , which is a schematic flowchart of a store patrol warning method provided by Embodiment 2 of the present application. As Figure 2 shown, the store patrol warning method may include the following steps: S201: Obtain order data, passenger flow data, commodity sales data, lease management data, and financial data of the store for different warning cycles.

[0021] In step S201, the warning cycle is pre-set and used to determine the frequency of risk warning monitoring for the store. The warning cycle can be one week, one month, or other time periods, which are not limited in this embodiment. The order data includes the quantity of each commodity order and the cost of each commodity. The passenger flow data is the passenger flow entering the store within each warning cycle. The commodity sales data is the sales amount within each warning cycle. The lease management data is the rent within each warning cycle. The financial data includes the asset data of the store and the data.

[0022] In this embodiment, when obtaining the order data, passenger flow data, commodity sales data, lease management data, and financial data of the store for different warning cycles, it can be obtained from the stored database. For example, the order data corresponding to different warning cycles is obtained from the database storing the order quantity, and the passenger flow data corresponding to different warning cycles is obtained from the database storing the passenger flow. Among them, the order data, passenger flow data, commodity sales data, lease management data, and financial data of the current warning cycle and the historical warning cycles before the current warning cycle among the order data, passenger flow data, commodity sales data, lease management data, and financial data of different warning cycles.

[0023] It should be noted that the order data, passenger flow data, commodity sales data, lease management data, and financial data of different warning cycles are the order data, passenger flow data, commodity sales data, lease management data, and financial data of consecutive warning cycles.

[0024] In this embodiment, order data, customer flow data, product sales data, lease management data, and financial data of different warning cycles of the store are obtained, so as to compare the order data, customer flow data, product sales data, lease management data, and financial data in the current warning cycle with those in the historical warning cycle, analyze the store operation situation, and determine whether the store operation is normal.

[0025] S202: According to the order data, customer flow data, product sales data, lease management data, and financial data of different warning cycles, the eigenvalue of N preset operation characteristics of the store in the current warning cycle is calculated, where N is an integer greater than 1.

[0026] In step S202, the N preset operation characteristics are index characteristics representing the store operation situation. The N preset operation characteristics may include cost efficiency characteristics, customer flow trend characteristics, sales growth rate characteristics, and financial health rate characteristics, etc. The eigenvalue is the value obtained by quantifying the N preset operation characteristics.

[0027] In this embodiment, N preset operation characteristics are obtained, and the calculation formulas for calculating the N preset operation characteristics are based on one-dimensional data or multi-dimensional data in the order data, customer flow data, product sales data, lease management data, and financial data of different warning cycles. Combining with the calculation formula of each preset operation characteristic, the eigenvalue of the corresponding preset operation characteristic is calculated.

[0028] In this embodiment, the N preset operation characteristics may include cost efficiency characteristics, customer flow trend characteristics, sales growth rate characteristics, and financial health rate characteristics. The cost efficiency characteristic is an index reflecting the relationship between cost expenditure and effect, and the calculation formula is the ratio of total sales to total cost. Among them, the total sales is the sales amount recorded in the product sales data in the current warning cycle, and the total cost includes product cost and the store's lease cost. The product cost can be calculated according to the order data in the current warning cycle, that is, the product cost is calculated based on the order data volume in the current warning cycle and the cost of each order. The lease cost can be determined according to the lease management data in the current warning cycle, that is, the store's lease cost is determined based on the rent data in the current warning cycle. Adding the product cost and the store's lease cost together to obtain the total cost. According to the ratio of total sales to total cost, the eigenvalue of the cost efficiency characteristic in the current warning cycle is calculated.

[0029] The passenger flow trend feature is an indicator used to reflect the popularity of a store. The passenger flow month-on-month growth rate can be used as the passenger flow trend feature. Therefore, the calculation formula for the passenger flow trend feature is the ratio of the difference between the passenger flow in the current warning period and the passenger flow in the previous warning period to the passenger flow in the previous warning period. Among them, the passenger flow in the current warning period and the passenger flow in the previous warning period can be obtained based on the passenger flow data of different warning periods.

[0030] The sales growth rate is an indicator that measures the change in the store's sales performance, reflects the growth rate of sales over a certain period, and is used to evaluate the store's market expansion ability and operating conditions. The calculation formula for the sales growth rate is the ratio of the difference between the sales in the current warning period and the sales in the previous warning period to the sales in the previous warning period. Among them, the sales in the current warning period and the sales in the previous warning period can be obtained based on the commodity sales data.

[0031] The financial health degree is a comprehensive indicator for evaluating the store's sustainable operation ability, risk resistance ability, and growth potential, and requires a linkage analysis of multi-dimensional financial indicators. The financial health degree includes the store's profit margin, current ratio, and debt ratio, etc. Among them, the profit margin is used to measure the profitability of the core business, the current ratio is used to evaluate the store's short-term debt repayment ability, and the debt ratio is the proportion of debt financing in the total assets. Among them, the calculation formula for the profit margin is the ratio of the difference between the total sales in the current warning period and the total cost to the total sales. Among them, the total sales are the sales recorded in the commodity sales data in the current warning period, and the total cost includes the commodity cost and the store's rental cost. The commodity cost can be calculated based on the order data in the current warning period, that is, the commodity cost is calculated based on the order data volume in the order data in the current warning period and the cost of each order. The rental cost can be determined based on the lease management data in the current warning period. The calculation formula for the current ratio is the ratio between current assets and current liabilities. Among them, current assets and current liabilities can be determined based on the financial data. The debt ratio is the ratio of the total debt to the total assets. Among them, the total debt and the total assets can be determined through the financial data. Calculate the financial health degree of the current warning period based on the profit margin, current ratio, and debt ratio. Among them, when calculating the financial health degree, weighted summation can be performed, that is, corresponding weights are set for the profit margin, current ratio, and debt ratio. When setting corresponding weights for different financial indicators, the same weight can be set for each financial indicator, or different weights can be set for each financial indicator. Among them, when setting different weights for each financial indicator, it can be set according to the influence degree of each financial indicator on the financial health degree. If the influence degree on the financial health degree is large, a larger weight is set for this financial indicator. If the influence degree on the financial health degree is small, a smaller weight is set for this financial indicator. It can also set different weights for each financial indicator according to other bases, which is not limited in this embodiment.

[0032] In this embodiment, according to the order data, passenger flow data, commodity sales data, lease management data and financial data of different warning cycles, the eigenvalue of N preset operation characteristics of the store in the current warning cycle is calculated, so as to analyze the operation situation of the store according to the corresponding operation characteristics, consider multi-dimensional operation characteristics, and improve the accuracy of store warning.

[0033] S203: Obtain the contribution values of the order data, passenger flow data, commodity sales data, lease management data and financial data to each preset operation characteristic, and splice and fuse the order data, passenger flow data, commodity sales data, lease management data and financial data of different warning cycles, the index values of N preset operation characteristics and each contribution value to obtain the fused characteristics.

[0034] In step S203, the contribution values of the order data, passenger flow data, commodity sales data, lease management data and financial data to each preset operation characteristic are the influence degrees of the order data, passenger flow data, commodity sales data, lease management data and financial data on each preset operation characteristic. When the influence degree is larger, the corresponding contribution value is larger; when the influence degree is smaller, the corresponding contribution value is smaller.

[0035] In this embodiment, when obtaining the contribution values of the order data, passenger flow data, commodity sales data, lease management data and financial data to each preset operation characteristic, the corresponding contribution values can be determined by calculating the average marginal contribution of each dimension data to each operation characteristic.

[0036] When calculating the average marginal contribution of each dimension data to each operation characteristic, first determine the prediction model of each operation characteristic, that is, the prediction model when using the order data, passenger flow data, commodity sales data, lease management data and financial data dimensions to predict the corresponding operation characteristic. Among them, the prediction model is a trained prediction model. The calculation formula for calculating the average marginal contribution of each dimension data to each operation characteristic is as follows: Among them, is the prediction model of each operation characteristic. When calculating the contribution values for different operation characteristics, the corresponding prediction models are different. F represents the set of all dimension data, including the set of order data, passenger flow data, commodity sales data, lease management data and financial data in the current warning cycle. S is a subset of F. represents the dimension data on this subset, which is one or more data among the order data, passenger flow data, commodity sales data, lease management data and financial data in the current warning cycle. It is shown that for the dimensional data of the i-th dimension, its contribution to each operation feature is: the operation feature data predicted by adding i to any subset that does not contain i minus the operation feature data predicted by that subset, and the mean value is taken after traversing once.

[0037] It should be noted that for any operation feature, the prediction model therein is the prediction model corresponding to the operation feature. When training the prediction model for the operation feature, an initial prediction model, sample data, and sample labels are obtained. Among them, the initial prediction model can be a linear model or a non-linear model. The sample data is multiple sets of order data, passenger flow data, commodity sales data, lease management data, and financial data. The sample label is the value of the operation feature under each set of order data, passenger flow data, commodity sales data, lease management data, and financial data. The initial prediction model is supervised and trained according to the sample data and sample labels to obtain a trained prediction model.

[0038] In this embodiment, the average marginal contribution is used to calculate the contribution values of the order data, passenger flow data, commodity sales data, lease management data, and financial data to each preset operation feature, and the influence degree of each dimension data on each operation feature can be accurately analyzed.

[0039] The order data, passenger flow data, commodity sales data, lease management data, and financial data of different warning periods, the index values of N preset operation features, and each contribution value are spliced and fused to obtain a fused feature. Among them, when splicing and fusing, they are sorted and spliced in the order of the order data, passenger flow data, commodity sales data, lease management data, and financial data of different warning periods, the index values of N preset operation features, and each contribution value to obtain the feature vector of the fused feature. Among them, the order data, passenger flow data, commodity sales data, lease management data, and financial data can be multiple data or single data, and can be data of multiple consecutive warning periods or data of the current warning period. Among them, each contribution value includes the contribution value of the order data, passenger flow data, commodity sales data, lease management data, and financial data to the cost efficiency respectively, the contribution value of the order data, passenger flow data, commodity sales data, lease management data, and financial data to the passenger flow trend respectively, the contribution value of the order data, passenger flow data, commodity sales data, lease management data, and financial data to the sales growth rate respectively, and the contribution value of the order data, passenger flow data, commodity sales data, lease management data, and financial data to the financial health respectively.

[0040] It should be noted that the order data, passenger flow data, commodity sales data, lease management data, and financial data in the fused features respectively contain data for different warning cycles. For example, [(a1,a2,a3) (b1,b2,b3) (c1,c2.c3) (d1,d2,d3) (e1,e2,e3) (z1,z2,z3,z4) ( , , , , ) ( , , , , ) ( , , , , ) ( , , , , )], where (a1,a2,a3) is the order data in the current warning cycle and its two previous warning cycles, (b1,b2,b3) is the passenger flow data in the current warning cycle and its two previous warning cycles, (c1,c2.c3) is the commodity sales data in the current warning cycle and its two previous warning cycles, (d1,d2,d3) is the lease management data in the current warning cycle and its two previous warning cycles, (e1,e2,e3) is the financial data in the current warning cycle and its two previous warning cycles, (z1,z2,z3,z4) are the eigenvalue of cost efficiency, passenger flow trend, sales growth rate, and financial health respectively, ( , , , , ) are the contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to cost efficiency respectively, ( , , , , ) are the contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to passenger flow trend respectively, ( , , , , ) are the contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to sales growth rate respectively, ( , , , , ), which are the contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to the financial health, respectively.

[0041] In this embodiment, the contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to each preset operation feature are obtained, and the order data, passenger flow data, commodity sales data, lease management data, and financial data, the index values of N preset operation features, and each contribution value in different warning cycles are spliced and fused, so as to fuse data in different dimensions, expand the dimension of the fused feature, and improve the accuracy of the fused feature.

[0042] As Figure 3 shown, it is a schematic flowchart of a store inspection and warning method provided by Embodiment 3 of the present invention. Obtaining the contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to each preset operation feature in step S203 includes: S301: Obtain the mapping relationships between order data, passenger flow data, commodity sales data, and lease management data and each preset operation feature respectively; S302: For any preset operation feature, determine the contribution values of order data, passenger flow data, commodity sales data, and lease management data to the preset operation feature according to the mapping relationship.

[0043] In this embodiment, the preset operation features are index features characterizing the store operation situation, which may include cost efficiency features, passenger flow trend features, sales growth rate features, and financial health rate features, etc. The feature values are the quantified values of N preset operation features. Obtain the mapping relationships between order data, passenger flow data, commodity sales data, and lease management data and each preset operation feature respectively, where the mapping relationship is the data in the corresponding dimension used in the process of calculating the feature value of the corresponding operation feature. For example, in the process of calculating the cost efficiency feature, commodity sales data and lease management data are used, then it can be considered that there is a mapping relationship between commodity sales data and lease management data and the cost efficiency feature. In the process of calculating the passenger flow trend feature, the corresponding passenger flow data is used, then it is considered that there is a mapping relationship between the passenger flow data and the passenger flow trend feature. In the process of calculating the sales growth rate, commodity sales data is used, then it is considered that there is a mapping relationship between commodity sales data and the sales growth rate. In the process of calculating the financial health, commodity sales data, lease management data, and financial data are used, then it is considered that there is a mapping relationship between commodity sales data, lease management data, and financial data and the financial health.

[0044] For any preset operation feature, according to the mapping relationship, determine the contribution values of order data, passenger flow data, commodity sales data, and lease management data to the preset operation feature. When determining the contribution values of order data, passenger flow data, commodity sales data, and lease management data to the preset operation feature, the weight values can be assigned to the corresponding dimension data according to the number of dimensions having a mapping relationship with the corresponding operation feature, and the corresponding weight values are determined as the corresponding contribution values. For example, commodity sales data and lease management data have a mapping relationship with the cost efficiency feature, that is, the number of dimensions having a mapping relationship with the cost efficiency feature is 2. The corresponding weight values can be evenly assigned to each dimension. For example, the weight value of 0.5 is assigned to the commodity sales data, and the weight value of 0.5 is assigned to the lease management data. Then the contribution values of the commodity sales data and the lease management data to the cost efficiency feature are 0.5 respectively, and the contribution values of other dimension data to the cost efficiency feature are 0. The passenger flow data has a mapping relationship with the passenger flow trend feature, that is, the number of dimensions having a mapping relationship with the passenger flow trend feature is 1. The weight value of 1 is assigned to the passenger flow data, the contribution value of the passenger flow data and the passenger flow trend feature is 1, and the contribution values of other dimension data to the cost efficiency feature are 0. The commodity sales data has a mapping relationship with the sales growth rate, that is, the number of dimensions having a mapping relationship with the sales growth rate is 1. The weight value of 1 is assigned to the commodity sales data, the contribution value of the commodity sales data to the sales growth rate is 1, and the contribution values of other dimension data to the cost efficiency feature are 0. The commodity sales data, lease management data, and financial data have a mapping relationship with the financial health degree. The number of dimensions having a mapping relationship with the financial health degree is 3. The values of 1 / 3 are respectively assigned to the commodity sales data, lease management data, and financial data for the financial health degree. The contribution values of the commodity sales data, lease management data, and financial data to the financial health degree are 1 / 3 respectively.

[0045] In this embodiment, according to the mapping relationship, determine the contribution values of order data, passenger flow data, commodity sales data, and lease management data to the preset operation feature, that is, according to the contribution value of each dimension data point of the dimension data having a direct correlation with the preset operation feature, without considering the dimension data having an indirect correlation with the preset operation feature, so as to improve the efficiency of calculating the contribution value.

[0046] S204: Perform risk early warning on the stores in the current early warning period according to the fused features, and obtain the early warning results of the stores.

[0047] In step S204, perform risk early warning on the stores in the current early warning period according to the fused features, and obtain the early warning results of the stores, where the early warning results are the risk early warning results of the stores.

[0048] In this embodiment, a preset early warning model is used to perform risk early warning on the fused features to obtain the early warning result of the store. Among them, the preset early warning model is a trained neural network model. The early warning result may include the risk early warning result of the overall operation situation of the store, that is, predicting whether there is a risk in the store, such as the existence of a risk and the non-existence of a risk. The fused features are input into the preset early warning model, and the early warning result of the store is output. In this embodiment, according to the fused features, risk early warning is performed on the store in the current early warning cycle, that is, after fusing the order data, passenger flow data, commodity sales data, lease management data and financial data, the index values and respective contribution values of N preset operation features, risk early warning is performed on the store in the current early warning cycle, improving the reliability of the early warning.

[0049] Such as Figure 4 As shown, it is a schematic flowchart of a store inspection and early warning method provided in Embodiment 4 of the present invention. In step S204, according to the fused features, risk early warning is performed on the store in the current early warning cycle to obtain the early warning result of the store, including: S401: Obtain a trained early warning model; S402: Input the fused features into the trained early warning model, and output the order early warning result, passenger flow early warning result, sales early warning result and the early warning results of each preset operation feature.

[0050] In this embodiment, the early warning result includes the order early warning result, passenger flow early warning result, sales early warning result and the results of each preset operation feature. The trained early warning model is a neural network model that can output multiple prediction results. The fused features are input into the trained early warning model, and the order early warning result, passenger flow early warning result, sales early warning result and the early warning results of each preset operation feature are output.

[0051] It should be noted that the order early warning result includes order early warning anomaly and order early warning normal, the passenger flow early warning result includes passenger flow early warning anomaly and passenger flow early warning normal, the sales early warning result includes sales early warning anomaly and sales early warning normal, and the early warning results of each preset operation feature include the early warning anomaly and early warning normal of each preset operation feature.

[0052] In this embodiment, the fused features are input into the trained early warning model, and risk early warning is respectively performed on the order data, passenger flow data, sales early warning result and each preset operation feature to obtain the corresponding order early warning result, passenger flow early warning result, sales early warning result and the early warning results of each preset operation feature, performing risk early warning on different dimension data, so as to perform risk analysis according to the early warning results of different dimensions and improve the reliability of store risk analysis.

[0053] Such asFigure 5 As shown in the figure, it is a schematic flowchart of a store patrol warning method provided in the fifth embodiment of the present invention. Before obtaining the trained warning model in step S401, it further includes: S501: Obtain an initial warning model, training samples, and labels of the training samples. The training samples include sample order data for different warning cycles, sample passenger flow data, sample commodity sales data, sample lease management data, sample financial data, eigenvalue of N operating characteristics in the target warning cycle, and sample contribution value of order data, passenger flow data, commodity sales data, lease management data, and financial data in the target warning cycle to each preset operating characteristic. The labels include order warning label, passenger flow warning label, sales warning label, and warning labels of each operating characteristic of N operating characteristics; S502: Concatenate and fuse the sample order data, sample passenger flow data, sample commodity sales data, sample lease management data, sample, financial data, eigenvalue of N operating characteristics, and each sample contribution value in the target warning cycle to obtain the fused sample features; S503: Supervise and train the initial warning model according to the fused sample features, order warning label, passenger flow warning label, sales warning label, and warning labels of each operating characteristic to obtain the trained warning model.

[0054] In this embodiment, an initial warning model is obtained. The initial warning model is a neural network model and can predict risks in the store through training. The initial warning model is supervised and trained. During training, first, training samples and labels of the training samples are obtained. Among them, the training samples include sample order data for different warning cycles, sample passenger flow data, sample commodity sales data, sample lease management data, sample financial data, eigenvalue of N operating characteristics in the target warning cycle, and sample contribution value of order data, passenger flow data, commodity sales data, lease management data, and financial data in the target warning cycle to each preset operating characteristic. The labels include order warning label, passenger flow warning label, sales warning label, and warning labels of each operating characteristic of N operating characteristics. Among them, different warning cycles are consecutive warning cycles. The eigenvalue of N operating characteristics in the target warning cycle is calculated based on one-dimensional data or multiple-dimensional data in the order data, sample passenger flow data, sample commodity sales data, sample lease management data, and sample financial data in the target warning cycle and one or more warning cycles before the target warning cycle.

[0055] The sample order data, sample passenger flow data, sample commodity sales data, sample lease management data, sample financial data, eigenvalue of N operation characteristics and each sample contribution value of the target warning period are spliced and fused to obtain the fused sample characteristics. When splicing and fusing, splicing is performed in the order of sample order data, sample passenger flow data, sample commodity sales data, sample lease management data, sample financial data, eigenvalue of N operation characteristics and each sample contribution value.

[0056] Based on the fused sample characteristics, order warning label, passenger flow warning label, sales warning label and warning labels of each operation characteristic, the initial warning model is supervised and trained to obtain a trained warning model.

[0057] As Figure 6 shown, it is a schematic flowchart of a store inspection and warning method provided by Embodiment 6 of the present invention. After obtaining the warning result of the store in step S204, it further includes: S601: Extract keywords in the warning result, and sort the keywords according to the preset abnormal priority of the keywords to obtain a sorting result; S602: Determine the target optimization suggestion matching the sorting result according to the sorting result.

[0058] In this embodiment, after obtaining the warning result of the store, extract the keywords in the warning result. The corresponding keywords are order warning exception, passenger flow warning exception, sales warning exception, cost efficiency feature warning exception, passenger flow trend feature warning exception, sales growth rate feature warning exception, and financial health feature warning exception.

[0059] According to the preset abnormal priority of the keywords, sort the keywords to obtain a sorting result. The preset abnormal priority of the keywords is the priority preset according to the abnormal emergency. For example, the sales growth rate feature exception warning is urgent. When the sales growth rate feature warning appears in the warning result, the sales growth rate feature warning can be ranked relatively in the front. In this embodiment, the preset abnormal priorities of the keywords are order warning exception, passenger flow warning exception, sales warning exception, cost efficiency feature warning exception, passenger flow trend feature warning exception, sales growth rate feature warning exception, and financial health feature warning exception in sequence. Sort according to the corresponding priorities to obtain a sorting result. Other abnormal priorities can also be set by the designer, which is not limited in this embodiment.

[0060] According to the corresponding keywords, sort the keywords according to the preset abnormal priority of the keywords. When sorting, if there are two keywords, sort the two keywords according to the abnormal priority. If there are three keywords, sort the three keywords according to the abnormal priority to obtain a sorting result.

[0061] According to the sorting result, determine the target optimization suggestion that matches the sorting result. Among them, the optimization suggestion is used to reduce the risk of the store. Match the first keyword in the sorting result with the pre-set optimization suggestions to obtain the target optimization suggestion.

[0062] For example, if the sales warning is abnormal, the corresponding target optimization suggestion can be to carry out promotional activities (such as reducing prices, increasing coupons, etc.) to increase sales, etc. Or other optimization suggestions are not limited in this embodiment.

[0063] In this embodiment, according to the warning result, determine the corresponding optimization suggestion, so as to execute the corresponding optimization suggestion to reduce the risk and improve the intelligence of store management.

[0064] As Figure 7 shown, it is a flowchart of a store inspection warning method provided by the seventh embodiment of the present invention. After determining the target optimization suggestion that matches the sorting result in step S602, it further includes: S701: Real-time monitor the execution result after executing the optimization suggestion, and judge whether the execution result meets the preset requirements; S702: If the execution result does not meet the preset requirements, adjust the order of the keywords to obtain the adjusted sorting result; S703: According to the adjusted sorting result, determine the target optimization suggestion that matches the adjusted sorting result.

[0065] In this embodiment, after determining the target optimization suggestion that matches the sorting result, after confirmation, execute the target optimization suggestion, real-time monitor the execution result after executing the optimization suggestion, and judge whether the execution result meets the preset requirements, that is, judge whether the store has reduced the risk after executing the corresponding target optimization suggestion. If the store has reduced the risk, it is considered that the execution result meets the preset requirements. If the store has not reduced the risk, it is considered that the execution result does not meet the preset requirements.

[0066] If the execution result does not meet the preset requirements, adjust the order of the keywords to obtain the adjusted sorting result. Among them, the preset requirement is that the execution result reduces the risk of the store. When adjusting the order of the keywords, the first keyword can be deleted, and the next keyword replaces the first keyword for adjustment. According to the adjusted sorting result, determine the target optimization suggestion that matches the adjusted sorting result. For example, if the first keyword is that the sales warning is abnormal, the corresponding target optimization suggestion (such as reducing prices, increasing coupons, etc.) can be to carry out promotional activities to increase sales, etc. After executing the corresponding target optimization suggestion, if the execution result of the promotional activity is not ideal, then according to the adjusted sorting result, determine the target optimization suggestion that matches the adjusted sorting result.

[0067] In this embodiment, the execution result after implementing the optimization suggestions is monitored in real time, so that the corresponding optimization suggestions can be adjusted in real time according to the monitoring results, reducing the risks of the store.

[0068] In the present invention, order data, customer flow data, commodity sales data, lease management data, and financial data of the store for different warning cycles are obtained. According to the order data, customer flow data, commodity sales data, lease management data, and financial data for different warning cycles, the eigenvalue of N preset operation characteristics of the store for the current warning cycle is calculated, where N is an integer greater than 1. The contribution values of the order data, customer flow data, commodity sales data, lease management data, and financial data to each preset operation characteristic are obtained. The order data, customer flow data, commodity sales data, lease management data, and financial data for different warning cycles, the index values of the N preset operation characteristics, and each contribution value are spliced and fused to obtain the fused characteristics. According to the fused characteristics, risk warning is performed on the store for the current warning cycle to obtain the warning result of the store. According to the data in different dimensions in the store, the corresponding operation characteristics are calculated. Risk warning monitoring is performed according to the data in different dimensions, operation characteristics, and the contribution degree of each dimension data to the operation characteristics to obtain the warning monitoring result. The multi-dimensional data, operation characteristics, and the contribution degree of each dimension data to the operation characteristics are fused and monitored to improve the accuracy of monitoring, thereby improving the reliability of the warning monitoring result.

[0069] As Figure 8 shown, it is a schematic diagram of a store inspection and warning device provided in Embodiment 8 of the present invention. This store inspection and warning device corresponds one-to-one with the store inspection and warning method in the above embodiment. The store inspection and warning device 80 includes an acquisition module 81, a calculation module 82, a fusion module 83, and a warning module 84.

[0070] The acquisition module 81 is used to acquire order data, customer flow data, commodity sales data, lease management data, and financial data of the store for different warning cycles.

[0071] The calculation module 82 is used to calculate the eigenvalue of N preset operation characteristics of the store for the current warning cycle according to the order data, customer flow data, commodity sales data, lease management data, and financial data for different warning cycles, where N is an integer greater than 1.

[0072] The fusion module 83 is used to obtain the contribution values of the order data, customer flow data, commodity sales data, lease management data, and financial data to each preset operation characteristic, and splice and fuse the order data, customer flow data, commodity sales data, lease management data, and financial data for different warning cycles, the index values of the N preset operation characteristics, and each contribution value to obtain the fused characteristics.

[0073] An early warning module 84 is used to perform risk early warning on the stores in the current early warning cycle according to the fused features, and obtain the early warning results of the stores.

[0074] Optionally, the fusion module 83 further includes: A first acquisition unit is used to acquire the mapping relationships between the order data, passenger flow data, commodity sales data, and lease management data and each preset operation feature respectively.

[0075] A determination unit is used to determine the contribution values of the order data, passenger flow data, commodity sales data, and lease management data to the preset operation feature according to the mapping relationship for any preset operation feature.

[0076] Optionally, the early warning module 84 includes: A second acquisition unit is used to acquire the trained early warning model.

[0077] An output unit is used to input the fused features into the trained early warning model, and output the order early warning results, passenger flow early warning results, sales early warning results, and early warning results of each preset operation feature.

[0078] Optionally, the early warning module 84 further includes: A third acquisition unit is used to acquire the initial early warning model, training samples, and labels of the training samples. The training samples include sample order data, sample passenger flow data, sample commodity sales data, sample lease management data, sample financial data, eigenvalue of N operation features in the target early warning cycle, and sample contribution values of order data, passenger flow data, commodity sales data, lease management data, and financial data to each preset operation feature in the target early warning cycle. The labels include order early warning labels, passenger flow early warning labels, sales early warning labels, and early warning labels of each operation feature of N operation features.

[0079] A fusion unit is used to splice and fuse the sample order data, sample passenger flow data, sample commodity sales data, sample lease management data, sample financial data, eigenvalue of N operation features, and each sample contribution value in the target early warning cycle to obtain the fused sample features.

[0080] A training unit is used to perform supervised training on the initial early warning model according to the fused sample features, order early warning labels, passenger flow early warning labels, sales early warning labels, and early warning labels of each operation feature, and obtain the trained early warning model.

[0081] Optionally, the store inspection early warning device 80 further includes: An extraction module is used to extract keywords in the early warning results, sort the keywords according to the preset abnormal priority, and obtain the sorting result.

[0082] The first determination module is configured to determine a target optimization suggestion that matches the sorting result according to the sorting result.

[0083] Optionally, the store inspection warning device 80 further includes: A monitoring module, configured to monitor the execution result after executing the optimization suggestion in real time, and determine whether the execution result meets a preset requirement.

[0084] An adjustment module, configured to, if the execution result does not meet the preset requirement, adjust the order of the keywords to obtain an adjusted sorting result.

[0085] The second determination module is configured to determine a target optimization suggestion that matches the adjusted sorting result according to the adjusted sorting result.

[0086] For the specific limitations of the store inspection warning device, reference may be made to the limitations on the store inspection warning method in the foregoing text, which will not be elaborated here. Each module in the foregoing store inspection warning device may be implemented in whole or in part by software, hardware, and their combination. The foregoing modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the foregoing modules.

[0087] As Figure 9 shown, a schematic structural diagram of a computer device provided in Embodiment 9 of the present invention is shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a store inspection warning method is implemented.

[0088] In an embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the store inspection warning method in the foregoing embodiment is implemented. For example Figures 2 to 7 shown, to avoid repetition, it will not be elaborated here. Or, when the processor executes the computer program, the functions of each module / unit in this embodiment of the store inspection warning device are implemented. For example Figure 8 shown, the functions of the acquisition module 81, the calculation module 82, the fusion module 83, and the warning module 84 will not be elaborated here to avoid repetition.

[0089] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the store patrol warning method in the above embodiment. As Figures 2 to 7 shown, to avoid repetition, it will not be elaborated here. Alternatively, when the computer program is executed by a processor, it implements the functions of each module / unit in the above embodiment of the store patrol warning device. For example Figure 7 shown, the functions of the acquisition module 81, the calculation module 82, the fusion module 83, and the warning module 84. To avoid repetition, it will not be elaborated here. The computer-readable storage medium can be non-volatile or volatile.

[0090] Those of ordinary skill in the art can understand that all or part of the processes in the above embodiment methods can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0091] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0092] 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A store inspection early warning method, characterized in that: The store inspection early warning method comprises: Obtain the store's order data, customer flow data, product sales data, rental management data, and financial data for different warning cycles; According to the order data, customer flow data, commodity sales data, rental management data and financial data of the different warning periods, characteristic values ​​of N preset operating characteristics of the store in the current warning period are calculated, where N is an integer greater than 1; Acquire the contribution values ​​of order data, passenger flow data, commodity sales data, rental management data and financial data to each of the preset operating characteristics, and merge the order data, passenger flow data, commodity sales data, rental management data and financial data of different warning cycles, the index values ​​of the N preset operating characteristics and each of the contribution values ​​to obtain the merged characteristics; According to the fused features, risk warning is performed on the store in the current warning cycle to obtain the warning result of the store.

2. The store inspection and early warning method according to claim 1, characterized in that: The warning results include order warning results, customer flow warning results, sales warning results and results of various preset operation characteristics; The step of performing risk warning on a store in the current warning cycle according to the fused features to obtain a warning result for the store includes: Obtain the trained early warning model; The fused features are input into the trained early warning model, and order early warning results, customer flow early warning results, sales early warning results and early warning results of each preset operation feature are output.

3. The store inspection early warning method according to claim 1, characterized in that: Before obtaining the trained early warning model, the method further includes: Obtain an initial warning model, training samples, and labels of the training samples, wherein the training samples include sample order data, sample passenger flow data, sample commodity sales data, sample rental management data, sample financial data, feature values ​​of N operating characteristics in a target warning cycle, and sample contribution values ​​of order data, passenger flow data, commodity sales data, rental management data, and financial data in the target warning cycle to each of the preset operating characteristics, and the labels include order warning labels, passenger flow warning labels, sales warning labels, and warning labels of each of the N operating characteristics; The sample order data, sample passenger flow data, sample commodity sales data, sample rental management data, sample financial data, and feature values ​​of N operational features in the target warning period are spliced ​​and fused with each sample contribution value to obtain the fused sample features; According to the fused sample features, the order warning labels, the customer flow warning labels, the sales warning labels and the warning labels of various operation features, the initial warning model is supervised and trained to obtain a trained warning model.

4. The store inspection and early warning method according to claim 2, characterized in that: The acquisition of contribution values ​​of order data, customer flow data, commodity sales data, rental management data and financial data to each of the preset operating characteristics includes: Obtaining a mapping relationship between the order data, the customer flow data, the commodity sales data, and the rental management data and each preset operation feature; For any preset operation feature, the contribution value of the order data, the customer flow data, the commodity sales data and the rental management data to the preset operation feature is determined according to the mapping relationship.

5. The store inspection and early warning method according to claim 1, characterized in that: After obtaining the early warning result of the store, the method further includes: Extracting keywords from the warning result, and sorting the keywords according to the abnormality priorities preset for the keywords to obtain a sorting result; According to the sorting result, a target optimization suggestion matching the sorting result is determined.

6. The store inspection and early warning method according to claim 5, characterized in that: After determining the target optimization suggestion matching the ranking result, the method further includes: Monitor the execution results of the optimization suggestions in real time to determine whether the execution results meet the preset requirements; If the execution result does not meet the preset requirement, the order of the keywords is adjusted to obtain an adjusted order result; According to the adjusted sorting result, a target optimization suggestion matching the adjusted sorting result is determined.

7. A shop inspection warning device, characterized in that: The shop inspection early warning device comprises: The acquisition module is used to obtain the store's order data, customer flow data, product sales data, rental management data and financial data in different warning cycles; A calculation module, used to calculate the characteristic values ​​of N preset operation characteristics of the store in the current warning period according to the order data, customer flow data, commodity sales data, rental management data and financial data of the different warning periods, where N is an integer greater than 1; A fusion module is used to obtain the contribution value of order data, passenger flow data, commodity sales data, rental management data and financial data to each of the preset operating characteristics, and to splice and fuse the order data, passenger flow data, commodity sales data, rental management data and financial data of different warning cycles, the index values ​​of the N preset operating characteristics and each of the contribution values ​​to obtain a fused feature; The early warning module is used to issue risk warnings to stores in the current early warning cycle according to the fused features, and obtain early warning results for the stores.

8. The store inspection and early warning device according to claim 7, characterized in that: The shop inspection early warning device also includes: A sorting module is used to extract keywords from the warning results, sort the keywords according to the abnormal priorities preset for the keywords, and obtain a sorting result; A determination module is used to determine, based on the sorting results, a target optimization suggestion that matches the sorting results.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the store inspection and early warning method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the store inspection and early warning method according to any one of claims 1 to 6 is implemented.

Images