Store state analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses a store state analysis method and apparatus, an electronic device and a storage medium. The method comprises the steps of performing data extraction on to-be-detected store data to obtain an initial data dimension index; the initial data dimension indexes comprise a first initial dimension index and a second initial dimension index; calculating the second initial dimension index to obtain a target non-zero dimension number; performing data conversion on the second initial dimension index to obtain a second target dimension index; calculating the second target dimension index and the target non-zero dimension number to obtain a reference activeness index; inputting the first initial dimension index and the second target dimension index into a target prediction model to obtain a target confidence coefficient; and calculating the target confidence and the reference activeness index to obtain a target activeness value, and determining the active state of the store according to the target activeness value. The method can comprehensively and accurately evaluate the active state of the store, improves the evaluation efficiency of the active state of the store, and can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a store status analysis method, device, electronic device and storage medium. Background Art

[0002] In the related technology, there are methods for estimating store status. The current estimation methods often use single-dimensional data to evaluate the store situation, which makes it difficult to comprehensively and accurately evaluate the actual operating conditions of the store, thus affecting the evaluation accuracy, and there are also obvious deficiencies in the evaluation efficiency.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The embodiments of the present application aim to solve at least one of the technical problems in the related art to a certain extent. To this end, the main purpose of the embodiments of the present application is to propose a store status analysis method, device, electronic device and storage medium, which can comprehensively and accurately evaluate the store activity status, improve the evaluation efficiency of the store activity status, and provide data support for activities such as store inspections.

[0005] To achieve the above purpose, one aspect of an embodiment of the present application provides a store status analysis method, which includes the following steps:

[0006] Acquire the store data to be detected corresponding to the store to be detected, and perform data extraction processing on the store data to be detected to obtain initial data dimension indicators; wherein the initial data dimension indicators include a first initial dimension indicator and a second initial dimension indicator;

[0007] Calculating the second initial dimension index to obtain a target non-zero dimension number;

[0008] Performing data conversion processing on the second initial dimensional index to obtain a second target dimensional index;

[0009] Calculating the second target dimension index and the target non-zero dimension quantity to obtain a benchmark activity index;

[0010] Inputting the first initial dimension indicator and the second target dimension indicator into a target prediction model to obtain a target confidence;

[0011] The target confidence and the benchmark activity index are calculated to obtain a target activity value, and the store activity status of the store to be detected is determined according to the target activity value.

[0012] In some embodiments, calculating the second initial dimension index to obtain a target number of non-zero dimensions includes:

[0013] The second initial dimension indicator is input into a non-zero dimension quantity counting program, and the second initial dimension indicator is calculated by the non-zero dimension quantity counting program to obtain the target non-zero dimension quantity.

[0014] In some embodiments, the second initial dimension indicator includes a second initial operation indicator and a second initial sales indicator, the second target dimension indicator includes a second target operation indicator and a second target sales indicator, and the data conversion processing of the second initial dimension indicator to obtain the second target dimension indicator includes:

[0015] Inputting the second initial dimensional indicator into a dimensional indicator conversion program, and performing data conversion processing on the second initial operating indicator by using a first data conversion formula through the dimensional indicator conversion program to obtain the second target operating indicator in the second target dimensional indicator;

[0016] The second initial sales indicator is subjected to data conversion processing by using the second data conversion formula through the dimensional indicator conversion program to obtain the second target sales indicator in the second target dimensional indicator.

[0017] In some embodiments, the calculating the second target dimension index and the target non-zero dimension quantity to obtain a benchmark activity index includes:

[0018] The second target dimension indicator and the target non-zero dimension number are input into the dimension indicator summary program, and the second target dimension indicator and the target non-zero dimension number are calculated by the dimension indicator summary formula through the dimension indicator summary program to obtain the benchmark activity indicator.

[0019] In some embodiments, the method further comprises the step of constructing the target prediction model, wherein constructing the target prediction model comprises:

[0020] Get the historical store data to be trained;

[0021] Performing data extraction processing on the historical store data to be trained to obtain historical data dimension indicators; wherein the historical data dimension indicators include a first historical dimension indicator and a second historical dimension indicator;

[0022] Performing data conversion processing on the second historical dimension indicator to obtain a historical standardized dimension indicator;

[0023] The initial prediction model is trained based on the first historical dimension index and the historical standardized dimension index to obtain the target prediction model.

[0024] In some embodiments, the calculating the target confidence and the benchmark activity index to obtain a target activity value, and determining the store activity status of the store to be detected according to the target activity value includes:

[0025] Inputting the target confidence and the benchmark activity index into a store activity prediction program, calculating the target confidence and the benchmark activity index according to a store activity prediction formula to obtain the target activity value;

[0026] Determining a target activity label according to the target activity value;

[0027] The store activity status of the store to be detected is determined according to the target activity tag.

[0028] In some embodiments, after calculating the target confidence and the benchmark activity index to obtain a target activity value, and determining the store activity status of the store to be detected according to the target activity value, the method further includes:

[0029] Acquire the store management data of the store to be inspected; wherein the store management data includes store inspection records and new store opening data;

[0030] Calculating the warning index value of the store to be detected according to the store management data, the target confidence and the target activity value;

[0031] The store attention level of the store to be detected is determined according to the warning indicator value.

[0032] To achieve the above purpose, another aspect of the embodiment of the present application provides a store status analysis device, which includes the following modules:

[0033] A data extraction and processing module is used to obtain the store data to be detected corresponding to the store to be detected, and perform data extraction and processing on the store data to be detected to obtain initial data dimension indicators; wherein the initial data dimension indicators include a first initial dimension indicator and a second initial dimension indicator;

[0034] A non-zero dimension quantity calculation module, used to calculate the second initial dimension index to obtain a target non-zero dimension quantity;

[0035] A data conversion processing module, used for performing data conversion processing on the second initial dimensional index to obtain a second target dimensional index;

[0036] A benchmark activity index calculation module, used to calculate the second target dimension index and the target non-zero dimension number to obtain a benchmark activity index;

[0037] A confidence acquisition module, used for inputting the first initial dimension indicator and the second target dimension indicator into a target prediction model to obtain a target confidence;

[0038] The store activity status analysis module is used to calculate the target confidence and the benchmark activity index to obtain a target activity value, and determine the store activity status of the store to be detected according to the target activity value.

[0039] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned method when executing the computer program.

[0040] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0041] The embodiments of the present application include at least the following beneficial effects: The present application provides a store status analysis method, device, electronic device and storage medium. The scheme obtains the store data to be detected corresponding to the store to be detected, and performs data extraction processing on the store data to be detected to obtain an initial data dimension indicator; wherein the initial data dimension indicator includes a first initial dimension indicator and a second initial dimension indicator; the second initial dimension indicator is calculated to obtain a target non-zero dimension number; the second initial dimension indicator is data converted to obtain a second target dimension indicator; the second target dimension indicator and the target non-zero dimension number are calculated to obtain a baseline activity indicator; the first initial dimension indicator and the second target dimension indicator are input into a target prediction model to obtain a target confidence; the target confidence and the baseline activity indicator are calculated to obtain a target activity value, and the store activity status of the store to be detected is determined according to the target activity value. The embodiments of the present application analyze store activity data from multiple dimensions to comprehensively and accurately evaluate the store activity status of a store. Through automated data processing and calculation processes, the activity value and activity status of a store can be quickly derived, thereby improving the efficiency of evaluating the store activity status. At the same time, data support can be provided for activities such as store inspections to prompt business personnel to pay attention to the corresponding stores, thereby improving the efficiency and accuracy of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of the steps of a store status analysis method provided by an embodiment of the present application;

[0043] Figure 2 It is a flow chart of a store status analysis method provided in an embodiment of the present application;

[0044] Figure 3 is a structural schematic diagram of a store status analysis device provided in an embodiment of the present application;

[0045] Figure 4 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0047] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0048] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0050] At present, stores use mini programs, investment promotion systems, etc. to conduct commercial activities. Commercial activities may include but are not limited to live broadcast appointments, prize verification, training viewing, contacting business opportunity customers, and signing retail orders. When employees use related applications, the background will also record the store's GPS (Global Positioning System) location information, which can reflect the store's activity. If there is an abnormality in the store, such as a fake store, the data in the store background will also be abnormal, so as to monitor the store's situation. By using a big data platform to collect these system data, obtain store business activities and location information, and summarize and count store data. However, normal stores may also have data anomalies. For example, store order data may not be true, and there may be a situation where another store is used to place an order uniformly; store locations overlap, and there are multiple stores next to each other, which cannot be distinguished based on GPS; employee data will be distorted, and the store will be invalid but the employee status will not be updated, resulting in employees still having operation records. If it is difficult to evaluate the store's situation from a single dimension of data, it is difficult for general statistical techniques to analyze store activity data from multiple dimensions, and there is a lack of appropriate rules to infer the store's activity.

[0051] In view of this, a store status analysis method, device, electronic device and storage medium are provided in an embodiment of the present application. The scheme obtains the store data to be detected corresponding to the store to be detected, and performs data extraction processing on the store data to be detected to obtain an initial data dimension indicator; wherein the initial data dimension indicator includes a first initial dimension indicator and a second initial dimension indicator; the second initial dimension indicator is calculated to obtain a target non-zero dimension number; the second initial dimension indicator is data converted to obtain a second target dimension indicator; the second target dimension indicator and the target non-zero dimension number are calculated to obtain a baseline activity indicator; the first initial dimension indicator and the second target dimension indicator are input into a target prediction model to obtain a target confidence; the target confidence and the baseline activity indicator are calculated to obtain a target activity value, and the store activity status of the store to be detected is determined according to the target activity value. The embodiments of the present application analyze store activity data from multiple dimensions to comprehensively and accurately evaluate the store activity status of a store. Through automated data processing and calculation processes, the activity value and activity status of a store can be quickly derived, thereby improving the efficiency of evaluating the store activity status. At the same time, data support can be provided for activities such as store inspections to prompt business personnel to pay attention to the corresponding stores, thereby improving the efficiency and accuracy of decision-making.

[0052] The store status analysis method provided in the embodiment of the present application relates to the field of data processing technology. The store status analysis method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network, content distribution network) and big data and artificial intelligence platforms and other basic cloud computing services. The cloud server, the server can also be a node server in the blockchain network; the software can be an application that implements the store status analysis method, etc., but is not limited to the above forms.

[0053] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs (Personal Computers, personal computers), minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0054] See also Figure 1 , Figure 1 is an optional step flow chart of the store status analysis method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0055] Step S101, obtaining the store data to be detected corresponding to the store to be detected, and performing data extraction processing on the store data to be detected to obtain initial data dimension indicators; wherein the initial data dimension indicators include a first initial dimension indicator and a second initial dimension indicator;

[0056] Among them, the store to be tested refers to a specific store that needs to undergo data testing and analysis. The store data to be tested corresponding to the store to be tested refers to all data related to the store to be tested, and the store data to be tested includes business activity information, basic store information, and store employee-related information. Among them, business activity information includes live broadcast reservation data, prize verification data, training viewing data, contact business opportunity customer data, and retail order data. In the specific implementation, a big data platform can be used to collect front-end system data to obtain the store data to be tested.

[0057] The initial data dimension indicators are a series of indicators extracted from the store data to be tested, which are used to measure and describe different aspects of the data and are the basis for further analysis and decision-making. The initial data dimension indicators include the first initial dimension indicator and the second initial dimension indicator. The first initial dimension indicator refers to the original data that does not require subsequent dimensional conversion, and the second initial dimension indicator refers to the original data that requires subsequent dimensional conversion.

[0058] In the specific implementation, the number of live broadcast reservations is counted based on the live broadcast reservation data; the number of prizes written off is counted based on the prize writing data; the number of training viewers is counted based on the training viewing data; the number of business opportunity customers churned, the number of business opportunity customers to be assigned, the number of business opportunity customers to be followed up, the number of business opportunity customers being followed up, the number of business opportunity customers who naturally enter the store, the number of business opportunity customers who have placed orders, the number of non-transferred business opportunity customers, the number of non-transferred business opportunity churned, and the number of non-transferred business opportunity transactions are counted based on the business opportunity customer contact data; the number of retail orders and the retail amount are counted based on the retail order data; the nature of the store and the city level are obtained based on the basic store information; the number of positioning days and login days are counted based on the operation records of store employees using various front-end systems.

[0059] Among them, the first initial dimension indicators include store nature and city level. Store nature is identified by x_1, which is the attribute category of a store, and the attribute category may include but is not limited to mall store, new channel store, independent store, shopping center store, display store, local mall store, guest and dining store, bedding store and sofa store, etc.; city level is identified by x_2, and city level may include but is not limited to first-class, second-class, third-class, fourth-class and special-class, etc.

[0060] For the second initial dimension indicators, they include the number of live broadcast reservations, the number of prizes redeemed, the number of business opportunity customers churned, the number of business opportunity customers to be assigned, the number of business opportunity customers to be followed up, the number of business opportunity customers being followed up, the number of business opportunity customers who enter the store naturally, the number of business opportunity customers who have placed orders, the number of non-converted business opportunity customers, the number of non-converted business opportunity churned and the number of non-converted business opportunity transactions, the number of people watching the training, the number of retail orders, the number of positioning days, the number of login days, and the retail amount.

[0061] Among them, the number of live broadcast reservations is represented by x_3, which refers to the number of records of a store booking live broadcasts in the live broadcast system; the number of redeemed prizes is represented by x_4, which refers to the number of customers who received redeemed prizes in a store after winning the store event; the number of business opportunity customer churn is marked by x_5, which refers to the number of customers who did not successfully place an order after the business opportunity customers were sent to a store; the number of business opportunity customers to be assigned is marked by x_6, which refers to the number of customers who have not yet been assigned employees to follow up after the business opportunity customers were sent to a store; the number of business opportunity customers to be followed up is represented by x_7 The number of business opportunity customers who are being followed up is marked with x_8, which means that after the business opportunity customers are sent to a certain store, the store has assigned employees to handle them, but the employees have not contacted them yet and are waiting for follow-up; the number of business opportunity customers who are being followed up is marked with x_8, which means that after the business opportunity customers are sent to a certain store, the store has followed up with the customers and is in the process of following up; the number of business opportunity customers who come to the store naturally is marked with x_9, which means that after the business opportunity customers are sent to a certain store, the store has not followed up with them, and the customers come to the store automatically; the number of business opportunity customers who have placed orders is marked with x_10, which means that after the business opportunity customers are sent to a certain store, the customers have become The number of successful in-store orders and consumption; the number of customers who have not converted business opportunities is marked with x_11, which refers to the number of customers that a store has obtained through other channels instead of the business opportunity system; the number of lost business opportunities that have not been converted is marked with x_12, which refers to the number of customers that a store has obtained through other channels instead of the business opportunity system, but ultimately failed to place an order; the number of transactions that have not converted business opportunities is marked with x_13, which refers to the number of customers that a store has obtained through other channels instead of the business opportunity system, but ultimately failed to place an order; the number of training viewers is marked with x_14, which refers to the number of times a store employee has used training software to train viewers; the number of retail orders is marked with x_15, which refers to the number of retail orders that a store has completed within a specific period of time; the number of positioning days is marked with x_16, which refers to the number of days that a store employee punches in and locates near the store; the number of login days is marked with x_17, which refers to the number of days that a store employee logs into the front-end system; the retail amount is marked with x_18, which refers to the total retail amount of a store transaction within a specific period of time.

[0062] In a specific implementation, in order to avoid fluctuations, data within a week and a month can be counted. Considering that many activity data are missing, the retail order data range can be extended to the last month, that is, data within two months can be taken for statistics. Those skilled in the art can make settings according to actual conditions, and the embodiments of the present application do not limit this.

[0063] Step S102, calculating the second initial dimension index to obtain a target non-zero dimension number;

[0064] In some embodiments, step S102 may include: inputting the second initial dimension indicator into a non-zero dimension quantity counting program, calculating the second initial dimension indicator through the non-zero dimension quantity counting program, and obtaining a target non-zero dimension quantity.

[0065] Among them, the non-zero dimension quantity statistics program is a program used to calculate the number of non-zero dimensions of indicator data, which mainly summarizes the behavior data with actual value in a store. In actual applications, most stores cannot count the above sixteen dimensional indicators from x_3 to x_18, and some behavior data may have values ​​of zero. For example, if a store does not use the live broadcast system, the number of live broadcast reservations for the store is 0.

[0066] In the embodiment of the present application, a non-zero dimension quantity counting program is developed, and the second initial dimension index (x_3 to x_18) is calculated using the non-zero dimension quantity counting program to obtain the target non-zero dimension quantity, wherein the target non-zero dimension quantity is identified by x_19. That is, the indicator values ​​that are not equal to 0 among the sixteen dimension indicator values ​​x_3 to x_18 of a store are counted.

[0067] In a specific implementation, the second initial dimension index (x_3 to x_18) is input into a non-zero dimension quantity statistics program, and the second initial dimension index is calculated by the non-zero dimension quantity statistics program to obtain a target non-zero dimension quantity (x_19 = f(x_3, ..., x_18)).

[0068] The number of target non-zero dimensions is the number of behavioral data with actual value in a store.

[0069] In step S102 of the embodiment of the present application, by extracting the number of non-zero dimensions, valuable data can be more effectively utilized and the efficiency of data analysis and mining can be improved.

[0070] Step S103, performing data conversion processing on the second initial dimension index to obtain a second target dimension index;

[0071] In some embodiments, step S103 may include: inputting the second initial dimensional indicator into a dimensional indicator conversion program, performing data conversion processing on the second initial operating indicator using the first data conversion formula through the dimensional indicator conversion program to obtain a second target operating indicator in the second target dimensional indicator; performing data conversion processing on the second initial sales indicator using the second data conversion formula through the dimensional indicator conversion program to obtain a second target sales indicator in the second target dimensional indicator.

[0072] Since the indicator values ​​of 18 different dimensions from x_1 to x_18 have a large range, for example, the number of store orders may be a few, but the amount of the store may reach tens of thousands, which will be unstable when input into deep learning or machine learning training. The main function of conversion is to standardize the data to improve the stability of deep learning training; on the other hand, a summary operation is required after conversion, and the summary method is to find the average. That is, it is necessary to convert to the same value range and then find the average to make comparison meaningful.

[0073] In order to solve the problem that dimensional indicators of different stores are difficult to compare (for example, the number of business opportunity customers within a month can be 0 or a very large integer with a large span range), the embodiment of the present application has developed a dimensional indicator conversion program. The dimensional indicator conversion principle of the dimensional indicator conversion program is to convert different indicator value span ranges into standardized data within the same value range [0,1], thereby improving the stability of deep learning training.

[0074] Among them, the second initial dimension indicators include the second initial operation indicators and the second initial sales indicators, and the second target dimension indicators include the second target operation indicators and the second target sales indicators.

[0075] For the second initial operating indicators (x_3 to x_17), they are the number of live broadcast reservations (x_3), the number of prizes written off (x_4), the number of business opportunity customers lost (x_5), the number of business opportunity customers to be allocated (x_6), the number of business opportunity customers to be followed up (x_7), the number of business opportunity customers being followed up (x_8), the number of business opportunity customers who naturally enter the store (x_9), the number of business opportunity customers who have placed orders (x_10), the number of unconverted business opportunity customers (x_11), the number of unconverted business opportunity lost (x_12), the number of unconverted business opportunity transactions (x_13), the number of people who watch the training (x_14), the number of retail orders (x_15), the number of positioning days (x_16), and the number of login days (x_17). The second initial operating indicators are the original indicator data that have not been dimensionally converted and are used to reflect the indicator data related to store operations; and for the second target operating indicators, they are the first data conversion formula converted to the second by the dimension indicator conversion program. The target operation indicator data obtained by data conversion processing of the initial operation indicators, the second target operation indicators include the number of live broadcast reservations after dimension conversion (x_new_3), the number of prizes written off (x_new_4), the number of business opportunity customers lost (x_new_5), the number of business opportunity customers to be allocated (x_new_6), the number of business opportunity customers to be followed up (x_new_7), the number of business opportunity customers being followed up (x_new_8), the number of business opportunity customers who naturally enter the store (x_new_9), the number of business opportunity customers who have placed orders (x_new_10), the number of customers who have not converted business opportunities (x_new_11), the number of unconverted business opportunities lost (x_new_12), the number of unconverted business opportunities closed (x_new_13), the number of people watching the training (x_new_14), the number of retail orders (x_new_15), the number of positioning days (x_new_16), and the number of login days (x_new_17).

[0076] For the second initial sales indicator (x_18), it is the above-mentioned retail amount (x_18). The second initial sales indicator is the original indicator data that has not been dimensionally converted, and is used to reflect the indicator associated with the retail amount; and for the second target sales indicator, it is the target sales indicator data obtained by converting the second initial sales indicator through the dimension indicator conversion program using the second data conversion formula. The second target sales indicator includes the retail amount after dimension conversion (x_new_18).

[0077] It should be noted that, in actual applications, the content of the second initial operating indicator in the second initial dimension indicator can add other data in addition to x_3 to x_17 listed in the embodiment of the present application. It is easy to understand that if other data is added to the second initial operating indicator, then x_18 of the second initial sales indicator in the second initial dimension indicator can be represented by other serial numbers. Exemplarily, assuming that the data in the second initial operating indicator in the second initial dimension indicator is increased from the original x_3 to x_17 to x_3 to x_18, and the corresponding second target operating indicators are x_new_13 to x_new_18; then x_18 of the second initial sales indicator in the second initial dimension indicator can be set to x_19, and the corresponding second target sales indicator is x_new_19. It should be noted that if the data is deferred, the subsequent data calculation identifier should also be modified accordingly, and the embodiment of the present application will not be described in detail here. The embodiment of the present application mainly describes x_1 to x_18 listed in the embodiment of the present application.

[0078] It is worth mentioning that the first initial dimension indicators (store nature (x_1) and city level (x_2)) do not need to be converted into dimensional indicators.

[0079] Among them, the first data conversion formula is to perform data conversion processing on the second initial operating indicator (x_3 to x_17) to obtain the formula of the second target operating indicator (x_new_3 to x_new_17) in the second target dimension indicator. The expression of the first data conversion formula is as follows:

[0080]

[0081] Among them, i=3,...,17.

[0082] The second data conversion formula is a formula for performing data conversion processing on the second initial sales indicator (x_18) to obtain the second target sales indicator (x_new_18) in the second target dimension indicator. The expression of the second data conversion formula is as follows:

[0083]

[0084] In step S103 of the embodiment of the present application, by constraining the data within the same range, the optimization algorithm can find the global minimum more easily, thereby improving the generalization ability and prediction stability of the model.

[0085] Step S104, calculating the second target dimension index and the target non-zero dimension quantity to obtain a benchmark activity index;

[0086] In some embodiments, step S104 may include: inputting the second target dimension indicator and the target non-zero dimension quantity into a dimension indicator summary program, and calculating the second target dimension indicator and the target non-zero dimension quantity using a dimension indicator summary formula through the dimension indicator summary program to obtain a baseline activity indicator.

[0087] In actual applications, since a store may have 18 indicators of different dimensions from x_1 to x_18, it is difficult to evaluate the store situation as a whole. However, the embodiment of the present application uses 18 indicators of different dimensions from x_1 to x_18 to calculate a total score for overall evaluation of the store situation.

[0088] Among them, the dimension indicator summary program is a program for calculating the second target dimension indicator and the target non-zero dimension number, and summarizing the indicator values ​​of different dimensions to obtain the baseline activity indicator. As for the dimension indicator summary formula, it is a formula for calculating according to the second target dimension indicator and the target non-zero dimension number to obtain the baseline activity indicator. The expression of the dimension indicator summary formula is:

[0089] x_20=(x_new_3+...+x_new_18) / (x_19*x_19)

[0090] Among them, x_19 represents the target non-zero dimension number, x_20 represents the benchmark activity index, and x_new_3 to x_new_18 represent the standardized data obtained by the second initial dimension index through the dimension index conversion process performed by the dimension index conversion program.

[0091] Among them, the benchmark activity index is used to summarize the indicator values ​​of different dimensions. The more activity dimensions and the more activities there are, the higher the activity.

[0092] Step S105, inputting the first initial dimension indicator and the second target dimension indicator into a target prediction model to obtain a target confidence;

[0093] In some embodiments, the step of constructing a target prediction model may also be included. Constructing the target prediction model may include: obtaining historical store data to be trained; performing data extraction processing on the historical store data to be trained to obtain historical data dimension indicators; wherein the historical data dimension indicators include a first historical dimension indicator and a second historical dimension indicator; performing data conversion processing on the second historical dimension indicator to obtain a historical standardized dimension indicator; training the initial prediction model based on the first historical dimension indicator and the historical standardized dimension indicator to obtain a target prediction model.

[0094] Among them, the historical store data to be trained is the training data used to build the target prediction model, which is the same data type as the store data to be tested. For the historical data dimension indicators, they are the various indicator data extracted from the historical store data to be trained, which are the same data type as the initial data dimension indicators. Among them, the historical data dimension indicators include the first historical dimension indicator and the second historical dimension indicator, the first historical dimension indicator and the first initial dimension indicator contain the same data type; the second historical dimension indicator and the second initial dimension indicator contain the same data type. For the historical standardized dimension indicator, it is the data of the second historical dimension indicator after the dimension indicator conversion program has been used to convert the dimension indicator.

[0095] The initial prediction model is an initial prediction model that has not been trained with training data. The target prediction model is obtained by training and optimizing the initial prediction model based on the historical store data to be trained.

[0096] Specifically, a model training program for training a deep learning Autoencoder model is developed to train an initial Autoencoder model containing five layers, and then the initial Autoencoder model is trained and optimized through the historical store data to be trained to obtain a target Autoencoder model. The prediction model used in the embodiment of the present application is an Autoencoder model.

[0097] Among them, the Autoencoder model includes the following architecture:

[0098] (1) Create an input layer with a dimension of 18;

[0099] (2) Create three coding layers with dimensions of 128, 64, and 32 respectively;

[0100] (3) Create an intermediate hidden state layer with a dimension of 32;

[0101] (4) Create three decoding layers with dimensions of 32, 64, and 128 respectively;

[0102] (5) Create an output layer with a dimension of 18;

[0103] (6) Create a loss function, which uses the mean square error between the original data and the predicted data.

[0104] Among them, the deep learning encoder (Autoencoder) is an unsupervised learning algorithm, which is mainly used for data dimensionality reduction, feature extraction and data reconstruction. The autoencoder consists of two main parts: encoder and decoder. Normal data is mapped to a low-dimensional latent space, and there should be a set of implicit states. This set of implicit state variables can describe the characteristics of the data. The original data is encoded into an intermediate implicit state. The normal data can be restored (decoded) from the implicit state to the original data. The difference between the original data and the predicted data obtained by decoding represents the confidence of the data. The larger the data difference, the more suspicious it is.

[0105] In the specific implementation, the above-mentioned Autoencoder model is created through TensorFlow. Then, the various indicator data extracted from the historical store data within one year (except the historical store nature x_1 and the historical city level x_2) are input into the dimension indicator conversion program for dimension indicator conversion to obtain historical standardized dimension indicators (historical indicator data x_new_3 to historical indicator data x_new_18), that is, the historical dimension indicator data of different stores can be obtained in the end (historical store nature x_1 and historical city level x_2, historical indicator data x_new_3 to historical indicator data x_new_18). Among them, each row of the historical data used for training represents the data of a store at a certain point in time, and each column represents the above 18 indicator values ​​of the store, which are input into the Autoencoder model in batches of 256 to train the initial Autoencoder model, obtain the model parameters to optimize the initial Autoencoder model, and obtain the target Autoencoder model.

[0106] Among them, the target Autoencoder model can output the average error between the original data and the predicted data, which is used to represent the confidence. The confidence is identified by x_21. The confidence represents the difference between the original data and the predicted data. The smaller the difference value, the more credible it is. The confidence is used as an adjustment coefficient. For example, assuming that a store has a very significant and active activity index, but the confidence is very low, it means that this store may be untrue in some behavioral indicators and suspected of fraud. Multiplying the activity index by the confidence adjustment coefficient can reduce the significance of the original activity index.

[0107] In step S105 of the embodiment of the present application, the target confidence can be obtained by inputting the second target dimensional indicators (x_new_3 to x_new_18) obtained by the dimensional indicator conversion program through the second initial dimensional indicators (x_3 to x_18) corresponding to the store data to be detected into the trained target Autoencoder model, and the target confidence is identified by x_21.

[0108] Step S106, calculating the target confidence and the benchmark activity index to obtain a target activity value, and determining the store activity status of the store to be detected according to the target activity value.

[0109] In some embodiments, step S106 may include: inputting the target confidence and the benchmark activity index into the store activity prediction program, calculating the target confidence and the benchmark activity index according to the store activity prediction formula to obtain the target activity value; determining the target activity label according to the target activity value; determining the store activity status of the store to be tested according to the target activity label.

[0110] The store activity prediction program is a program used to calculate the target activity value based on the target confidence (x_21) and the benchmark activity index (x_20), which is calculated using the store activity prediction formula. The expression of the store activity prediction formula is:

[0111] x_22=x_21*x_20

[0112] Among them, x_22 is the target activity value, also known as the adjusted activity value, that is, the adjusted activity value = confidence * benchmark activity index.

[0113] In the specific implementation, suppose a store has a very significant and active activity index (x_20), but a very low confidence level (x_21). This means that the store may not be true in some behavioral indicators and may be suspected of fraud. Multiplying the activity index by the confidence adjustment coefficient can reduce the significance of the original activity index.

[0114] Among them, for the store data with a value of 0 in the number of non-zero dimensions (x_19), the corresponding target activity value (x_22) is a null value. Therefore, the embodiment of the present application only considers the store data with values ​​in the target activity value (x_22), sorts the target activity value (x_22) in reverse order from large to small, and divides the activity label (x_23) into the top 5%, the middle 90%, and the bottom 5% according to the normal distribution of the target activity value (x_22). Specifically, the activity label of the top 5% is low, the activity label of the middle 90% is medium, and the activity label of the bottom 5% is high. For store data with no value for the target activity value (x_22), the activity label is no activity.

[0115] In some embodiments, after step S106, the process may also include: obtaining store management data of the store to be inspected; wherein the store management data includes store inspection records and new store opening data; calculating the warning index value of the store to be inspected based on the store management data, target confidence and target activity value; and determining the store attention of the store to be inspected based on the warning index value.

[0116] Store management data includes store inspection records and new store opening data. Store inspection records include inspectors, stores to be inspected, inspection time, and store status (normal, closed, abnormal, etc.); new store opening data mainly uses the store opening date to calculate the store opening month. Stores opened within one year are considered new stores, and those opened more than one year are not considered new stores.

[0117] In the specific implementation, the months between the most recent store inspections (x_24) can be calculated based on the store inspection records. Specifically, taking 2 months ago as the benchmark, the number of weeks between the most recent inspection date and the benchmark date is calculated to obtain the months between the most recent store inspections (x_24). Furthermore, the inspection index (x_25) is calculated based on the months between the most recent store inspections (x_24). The calculation formula for the inspection index (x_25) is:

[0118]

[0119] Since x_24 is an integer, the value of x_25 is in the interval [0,1]. In particular, x_25=1 represents that there is no inspection record.

[0120] In the specific implementation, the new store opening data mainly uses the store opening date. Taking one month ago as the benchmark, the number of weeks between the store opening date and the benchmark date is calculated to obtain the store opening month (x_26). Furthermore, the store opening index (x_27) is calculated based on the store opening month (x_26), where the calculation formula of the store opening index (x_27) is:

[0121]

[0122] Among them, when x_27<49, it means that the store is considered a new store within one year of opening; conversely, when x_27>=49, the store is no longer a new store.

[0123] For the warning indicator value, x_28 is used for identification, and the corresponding calculation formula is:

[0124]

[0125] Among them, ① if the activity label (x_23) is medium or high, the warning indicator value (x_28) takes the adjusted activity value (x_22);

[0126] ② If the activity tag (x_23) is low, the warning index value (x_28) is the inspection index (x_25) multiplied by the adjusted activity value (x_22);

[0127] ③ If the activity label (x_23) is inactive and there is inspection (i.e. the inspection index (x_25) is not equal to 1), the warning index value (x_28) is the inspection index (x_25) multiplied by the confidence (x_21) output by the deep learning Autoencoder model;

[0128] ④ If the activity label (x_23) is inactive and there is no inspection (i.e. the inspection index (x_25) is equal to 1), and it is a new store (i.e. the store opening index (x_27) is less than 49), then the warning index value (x_28) is the store opening index (x_27) multiplied by the confidence (x_21) output by the deep learning Autoencoder model;

[0129] ⑤ If the activity label (x_23) is inactive, and there is no inspection (that is, the inspection index (x_25) is equal to 1), and it is not a new store (that is, the store opening index (x_27) is greater than or equal to 49), then the warning index value (x_28) is 1.

[0130] Among them, the warning indicator value (x_28) corresponding to the warning indicator (i.e. store attention) is as follows:

[0131] ① If x_28=0, the warning indicator (green / yellow / red) is green;

[0132] ②If x_28<1, the warning indicator (green / yellow / red) is yellow;

[0133] ③If x_28>=1, the warning indicator (green / yellow / red) is red;

[0134] Among them, green represents normal, yellow represents need for attention, and red represents special attention.

[0135] Specifically, the principle of obtaining the warning indicator of the store is as follows:

[0136] ① If the store activity is relatively high, such as medium / high, the adjusted activity value is directly used to determine the warning indicator;

[0137] ② If the store activity is relatively low, the warning indicator should be determined based on the recent inspection records. The warning indicator should gradually change from yellow to red according to the recent inspection intervals from short to long. The main principle is that if the store was inspected a long time ago and the activity is relatively low, then the store needs to be vigilant and paid attention to;

[0138] ③ If the store has no activity, there is no activity index value. Then the warning index can only be evaluated using the confidence obtained by the trained deep learning model, and the warning index is determined in combination with recent inspection records. The confidence is gradually reduced from short to long according to the most recent inspection interval, so that the warning index can achieve a trend change from yellow to red.

[0139] ④ If the store has no activity and no inspection records, the warning indicator is evaluated based on whether the store is newly opened. Considering that it is normal for the latest store to have no active records, the warning indicator is gradually changed from yellow to red according to the date of the newly opened store from short to long;

[0140] ⑤ If the store has no activity, no inspection records, and is not a newly opened store, a red warning will be issued directly to indicate that it is a major concern.

[0141] It is worth mentioning that the embodiment of the present application also regularly outputs the latest results to the store operating status inference analysis report for use by departments such as the market center supervision department, providing data support for activities such as store inspections.

[0142] In the specific implementation, a warning indicator calculation program is developed. The warning indicator calculation program calculates the warning indicator value and the corresponding warning indicator based on the activity value adjusted by the inspection records and the new store opening situation fed back by the business personnel, so as to prompt the business personnel to pay attention to the corresponding stores, and summarize the important store business activities and display them to the business personnel, thereby supporting activities such as store inspections and improving the efficiency and accuracy of decision-making.

[0143] Steps S101 to S106 shown in the embodiment of the present application are to obtain the store data to be detected corresponding to the store to be detected, and perform data extraction processing on the store data to be detected to obtain the initial data dimension index; wherein, the initial data dimension index includes a first initial dimension index and a second initial dimension index; the second initial dimension index is calculated to obtain the target non-zero dimension number; the second initial dimension index is subjected to data conversion processing to obtain the second target dimension index; the second target dimension index and the target non-zero dimension number are calculated to obtain the benchmark activity index; the first initial dimension index and the second target dimension index are input into the target prediction model to obtain the target confidence; the target confidence and the benchmark activity index are calculated to obtain the target activity value, and the store activity status of the store to be detected is determined according to the target activity value. The embodiment of the present application can comprehensively and accurately evaluate the store activity status of the store by analyzing the store activity data in a comprehensive manner from multiple dimensions; through the automated data processing and calculation process, the store activity value and activity status can be quickly obtained, which improves the evaluation efficiency of the store activity status, and can also provide data support for activities such as store inspections to prompt business personnel to pay attention to the corresponding stores, thereby improving the efficiency and accuracy of decision-making.

[0144] In order to explain the principle of the technical solution of the present invention in detail, the overall process of the present invention is described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and cannot be regarded as a limitation of the present invention.

[0145] See also Figure 2 , Figure 2 is a flow chart of a store status analysis method provided in an embodiment of the present application; Figure 2 As shown in the figure, the general process of store status analysis is as follows: first, obtain the store data corresponding to the store to be detected in each system; then perform data extraction processing on the store data to be detected to obtain different data dimension indicators; then perform dimension aggregation processing on the different data dimension indicators to calculate the activity index, and at the same time, input the different data dimension indicators into the deep learning automatic encoding model for calculation to obtain the confidence; further, calculate the confidence and activity index to obtain the adjusted activity value; finally, determine the activity label according to the adjusted activity value, and then determine the store activity status of the store to be detected according to the activity label. After determining the store activity status of the store to be detected according to the activity label, the warning indicator value of the store to be detected can also be calculated based on the store inspection record, new store opening data, confidence, adjusted activity value, activity label and other data; then determine the store attention of the store to be detected according to the warning indicator value.

[0146] It should be pointed out that this embodiment only briefly illustrates the general process of the store status analysis method. The detailed description of each step can refer to the relevant content in the aforementioned embodiment and will not be repeated here. It can be understood that the present invention is not limited to this.

[0147] The embodiments of the present application provide a store status analysis method, device, electronic device and storage medium. The solution obtains the store data to be detected corresponding to the store to be detected, and performs data extraction processing on the store data to be detected to obtain an initial data dimension indicator; wherein the initial data dimension indicator includes a first initial dimension indicator and a second initial dimension indicator; the second initial dimension indicator is calculated to obtain a target non-zero dimension number; the second initial dimension indicator is data converted to obtain a second target dimension indicator; the second target dimension indicator and the target non-zero dimension number are calculated to obtain a baseline activity indicator; the first initial dimension indicator and the second target dimension indicator are input into a target prediction model to obtain a target confidence; the target confidence and the baseline activity indicator are calculated to obtain a target activity value, and the store activity status of the store to be detected is determined according to the target activity value. The embodiments of the present application analyze store activity data from multiple dimensions to comprehensively and accurately evaluate the store activity status of a store. Through automated data processing and calculation processes, the activity value and activity status of a store can be quickly derived, thereby improving the efficiency of evaluating the store activity status. At the same time, data support can be provided for activities such as store inspections to prompt business personnel to pay attention to the corresponding stores, thereby improving the efficiency and accuracy of decision-making.

[0148] In summary, the embodiment of the present application uses deep learning Autoencoder technology to analyze data, infer the store activity status, and divide the red, yellow and green warning indicators according to the store activity status, paying special attention to suspected abnormal stores and fake stores, and also regularly outputs the latest results to the store business status inference analysis report for use by the market center supervision department and other departments, providing data support for activities such as store inspections, and improving the efficiency and accuracy of decision-making. At the same time, from a marketing perspective, the activity level of the store can be monitored and evaluated, and targeted management can be carried out according to different activity levels.

[0149] See also Figure 3 , Figure 3 : is a structural diagram of a store status analysis device provided in an embodiment of the present application. The embodiment of the present application also provides a store status analysis device 300, which can implement the above-mentioned store status analysis method. The device includes the following modules:

[0150] The data extraction and processing module 301 is used to obtain the store data to be detected corresponding to the store to be detected, and perform data extraction and processing on the store data to be detected to obtain initial data dimension indicators; wherein the initial data dimension indicators include a first initial dimension indicator and a second initial dimension indicator;

[0151] A non-zero dimension quantity calculation module 302 is used to calculate the second initial dimension index to obtain a target non-zero dimension quantity;

[0152] A data conversion processing module 303 is used to perform data conversion processing on the second initial dimension index to obtain a second target dimension index;

[0153] A benchmark activity index calculation module 304 is used to calculate the second target dimension index and the target non-zero dimension number to obtain a benchmark activity index;

[0154] A confidence acquisition module 305 is used to input the first initial dimension indicator and the second target dimension indicator into a target prediction model to obtain a target confidence;

[0155] The store activity status analysis module 306 is used to calculate the target confidence and the benchmark activity index to obtain a target activity value, and determine the store activity status of the store to be detected according to the target activity value.

[0156] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0157] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned store status analysis method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0158] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0159] See also Figure 4 , Figure 4 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0160] The processor 401 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0161] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the store status analysis method of the embodiment of this application;

[0162] Input / output interface 403, used to implement information input and output;

[0163] Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0164] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0165] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0166] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned store status analysis method is implemented.

[0167] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0168] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The store status analysis method, store status analysis device, electronic device and storage medium provided in the embodiments of the present application obtain the store data to be detected corresponding to the store to be detected, and perform data extraction processing on the store data to be detected to obtain an initial data dimension indicator; wherein the initial data dimension indicator includes a first initial dimension indicator and a second initial dimension indicator; the second initial dimension indicator is calculated to obtain a target non-zero dimension number; the second initial dimension indicator is data converted to obtain a second target dimension indicator; the second target dimension indicator and the target non-zero dimension number are calculated to obtain a baseline activity indicator; the first initial dimension indicator and the second target dimension indicator are input into a target prediction model to obtain a target confidence; the target confidence and the baseline activity indicator are calculated to obtain a target activity value, and the store activity status of the store to be detected is determined according to the target activity value. The embodiments of the present application analyze store activity data from multiple dimensions to comprehensively and accurately evaluate the store activity status of a store. Through automated data processing and calculation processes, the activity value and activity status of a store can be quickly derived, thereby improving the efficiency of evaluating the store activity status. At the same time, data support can be provided for activities such as store inspections to prompt business personnel to pay attention to the corresponding stores, thereby improving the efficiency and accuracy of decision-making.

[0170] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0171] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0172] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0174] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0175] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0176] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0177] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0179] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0180] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A store status analysis method, characterized in that: The method comprises the following steps: Acquire the store data to be detected corresponding to the store to be detected, and perform data extraction processing on the store data to be detected to obtain initial data dimension indicators; wherein the initial data dimension indicators include a first initial dimension indicator and a second initial dimension indicator; Calculating the second initial dimension index to obtain a target non-zero dimension number; Performing data conversion processing on the second initial dimensional index to obtain a second target dimensional index; Calculating the second target dimension index and the target non-zero dimension quantity to obtain a benchmark activity index; Inputting the first initial dimension indicator and the second target dimension indicator into a target prediction model to obtain a target confidence; The target confidence and the benchmark activity index are calculated to obtain a target activity value, and the store activity status of the store to be detected is determined according to the target activity value.

2. The method according to claim 1, characterized in that The calculating the second initial dimension index to obtain a target non-zero dimension quantity includes: The second initial dimension indicator is input into a non-zero dimension quantity counting program, and the second initial dimension indicator is calculated by the non-zero dimension quantity counting program to obtain the target non-zero dimension quantity.

3. The method according to claim 1, characterized in that The second initial dimension indicator includes a second initial operation indicator and a second initial sales indicator, the second target dimension indicator includes a second target operation indicator and a second target sales indicator, and the data conversion processing of the second initial dimension indicator to obtain the second target dimension indicator includes: Inputting the second initial dimensional indicator into a dimensional indicator conversion program, and performing data conversion processing on the second initial operating indicator by using a first data conversion formula through the dimensional indicator conversion program to obtain the second target operating indicator in the second target dimensional indicator; The second initial sales indicator is subjected to data conversion processing by using the second data conversion formula through the dimensional indicator conversion program to obtain the second target sales indicator in the second target dimensional indicator.

4. The method according to claim 1, characterized in that: The calculating the second target dimension index and the target non-zero dimension quantity to obtain a benchmark activity index includes: The second target dimension indicator and the target non-zero dimension number are input into the dimension indicator summary program, and the second target dimension indicator and the target non-zero dimension number are calculated by the dimension indicator summary formula through the dimension indicator summary program to obtain the benchmark activity indicator.

5. The method according to claim 1, characterized in that The method further comprises the step of constructing the target prediction model, wherein the step of constructing the target prediction model comprises: Get the historical store data to be trained; Performing data extraction processing on the historical store data to be trained to obtain historical data dimension indicators; wherein the historical data dimension indicators include a first historical dimension indicator and a second historical dimension indicator; Performing data conversion processing on the second historical dimension indicator to obtain a historical standardized dimension indicator; The initial prediction model is trained based on the first historical dimension index and the historical standardized dimension index to obtain the target prediction model.

6. The method according to claim 1, characterized in that The calculating the target confidence and the benchmark activity index to obtain a target activity value, and determining the store activity status of the store to be detected according to the target activity value, includes: Inputting the target confidence and the benchmark activity index into a store activity prediction program, calculating the target confidence and the benchmark activity index according to a store activity prediction formula to obtain the target activity value; Determining a target activity label according to the target activity value; The store activity status of the store to be detected is determined according to the target activity tag.

7. The method according to claim 1, characterized in that After calculating the target confidence and the benchmark activity index to obtain a target activity value, and determining the store activity status of the store to be detected according to the target activity value, the method further includes: Acquire the store management data of the store to be inspected; wherein the store management data includes store inspection records and new store opening data; Calculating the warning index value of the store to be detected according to the store management data, the target confidence and the target activity value; The store attention level of the store to be detected is determined according to the warning indicator value.

8. A store status analysis device, characterized in that: The device comprises the following modules: A data extraction and processing module is used to obtain the store data to be detected corresponding to the store to be detected, and perform data extraction and processing on the store data to be detected to obtain initial data dimension indicators; wherein the initial data dimension indicators include a first initial dimension indicator and a second initial dimension indicator; A non-zero dimension quantity calculation module, used to calculate the second initial dimension index to obtain a target non-zero dimension quantity; A data conversion processing module, used for performing data conversion processing on the second initial dimensional index to obtain a second target dimensional index; A benchmark activity index calculation module, used to calculate the second target dimension index and the target non-zero dimension number to obtain a benchmark activity index; A confidence acquisition module, used for inputting the first initial dimension indicator and the second target dimension indicator into a target prediction model to obtain a target confidence; The store activity status analysis module is used to calculate the target confidence and the benchmark activity index to obtain a target activity value, and determine the store activity status of the store to be detected according to the target activity value.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images