Chain store remote inspection system based on artificial intelligence

Abstract

The invention belongs to the field of chain store management, relates to a remote inspection technology, and particularly relates to a chain store remote inspection system based on artificial intelligence, which is used for solving the problem that in the prior art, targeted decision analysis cannot be carried out on optimization directions of all chain stores in combination with all parameters of the stores. Comprising a store monitoring module, a store management module, a store optimization module, a targeted optimization module and a database. The store monitoring module is used for monitoring and analyzing the in-store operation state of the chain store: generating a monitoring period, carrying out video shooting on the in-store operation space through a camera, comparing monitoring parameters with regulation standards, and carrying out numerical value marking on rule values of the monitoring parameters through a comparison result; according to the invention, the in-store operation state of the chain store can be monitored and analyzed, after video shooting is carried out on the operation space, the execution state of each monitoring parameter is extracted and evaluated in combination with a video processing technology, and data support is provided for the store management process.

Description

Technical Field

[0001] The present invention belongs to the field of chain store management and relates to remote inspection technology, in particular to a chain store remote inspection system based on artificial intelligence. Background Art

[0002] Remote store inspection is a method of inspecting stores through modern scientific and technological means, such as remote video surveillance and AI technology. This method breaks the limitations of geographical space and allows managers to monitor store operations anytime and anywhere.

[0003] The store remote inspection system in the existing technology can only monitor various parameters of the business site, and impose penalties or hold accountable based on the remote inspection parameters when abnormal operations occur; however, the existing technology cannot conduct a comprehensive analysis based on all parameters of the store. Especially for chain stores, how to conduct targeted decision-making analysis on the optimization direction of all chain stores through remote inspection data to improve the overall operating results is a technical problem that urgently needs to be solved in this field.

[0004] In view of the above technical problems, this application proposes a solution. Summary of the invention

[0005] The purpose of the present invention is to provide a chain store remote inspection system based on artificial intelligence, which is used to solve the problem that the existing technology cannot combine all parameters of the store to conduct targeted decision analysis on the optimization direction of all chain stores; The technical problem to be solved by the present invention is: how to provide an artificial intelligence-based remote inspection system for chain stores that can perform targeted decision-making analysis on the optimization direction of all chain stores.

[0006] The purpose of the present invention can be achieved through the following technical solutions: An artificial intelligence-based remote inspection system for chain stores, including a store monitoring module, a store management module, a store optimization module, a targeted optimization module and a database; The store monitoring module is used to monitor and analyze the in-store business status of chain stores: generate a monitoring cycle, shoot a video of the in-store business space through a camera, decompose the shot video, perform feature recognition processing and extract monitoring parameters i, i=1, 2, ..., n, n is a positive integer, retrieve the procedure standard e set by the chain store headquarters through the database, e=1, 2, ..., n, n is a positive integer, compare the monitoring parameter i with the procedure standard e, and numerically mark the rule value GZi of the monitoring parameter i through the comparison result; The store management module is used to perform periodic management and analysis on the compliance status of chain stores: at the end of the monitoring period, the formula The management coefficient GL of the chain stores in the monitoring period is obtained, where t1 is the proportional coefficient; the chain stores are marked as compliant stores or optimized stores through the management coefficient GL; The store optimization module is used to analyze the optimization mode of the optimized stores: the ratio of the number of optimized stores to the total number of all chain stores is marked as a centralized necessary value, and the optimization mode of the optimized stores is marked by the centralized necessary value; The targeted optimization module is used to perform targeted optimization analysis on optimized stores.

[0007] Furthermore, the specific process of comparing the monitoring parameter i with the procedure standard e includes: if the monitoring parameter i meets the procedure standard e, it is determined that the monitoring parameter i meets the requirements; if the monitoring parameter i does not meet the procedure standard e, it is determined that the monitoring parameter i does not meet the requirements, and the rule value GZi of the monitoring parameter i is increased by one; the rule values ​​GZi of all monitoring parameters i of all chain stores are cleared at the beginning of the monitoring cycle.

[0008] Furthermore, the value-taking process of t1 includes: obtaining the number of customers and the number of sales staff in the store at the time when the rule value GZi of the monitoring parameter i is switched within the monitoring period and marking them as the flow value and the service value respectively, marking the ratio of the flow value to the service value as the service coverage value when the rule value GZi is switched, summing up and averaging the service coverage values ​​corresponding to the rule value GZi of all monitoring parameters i in the chain stores when they are switched to obtain the service coverage coefficient; retrieving the service coverage threshold through the database, and comparing the service coverage coefficient with the service coverage threshold: if the service coverage coefficient is less than the service coverage threshold, t1=1; if the service coverage coefficient is greater than or equal to the service coverage threshold, 0.85≤t1≤0.95, and at the same time generating a service supplement signal and sending the service supplement signal to the mobile phone terminal of the headquarters manager.

[0009] Furthermore, the specific process of marking a chain store as a compliant store or an optimized store includes: obtaining the management threshold GLmax through the database, and comparing the management coefficient GL of the chain store during the monitoring period with the management threshold GLmax: if the management coefficient GL is less than the management threshold GLmax, it is determined that the compliance status of the chain store during the monitoring period meets the requirements, and the corresponding chain store is marked as a compliant store; if the management coefficient GL is greater than or equal to the management threshold GLmax, it is determined that the compliance status of the chain store during the monitoring period does not meet the requirements, and the corresponding chain store is marked as an optimized store.

[0010] Furthermore, the specific process of marking the optimization mode of the optimized store includes: obtaining the centralized necessary threshold through the database, and comparing the centralized necessary value with the centralized necessary threshold: if the centralized necessary value is less than the centralized necessary threshold, the centralized optimization mode is used to optimize the optimized store; if the centralized necessary value is greater than or equal to the centralized necessary threshold, an optimization signal is generated and sent to the optimization module.

[0011] Furthermore, the specific process of optimizing the optimized stores using the centralized optimization mode includes: marking the sum of the rule values ​​GZi of the monitoring parameter i in all optimized stores as the optimization requirement value i of the monitoring parameter i, marking the L1 monitoring parameters i with the largest optimization requirement value i as centralized optimization parameters, and sending the centralized optimization parameters to the mobile phone terminals of the headquarters managers.

[0012] Furthermore, the specific process of the optimization module for conducting targeted optimization analysis on the optimized stores includes: arranging all the optimized stores in order from small to large according to the rule value GZi of the monitoring parameter i to obtain a targeted sequence i of the monitoring parameter i, performing variance calculation on the serial numbers of all the monitoring parameters i of the optimized stores in the corresponding targeted sequence i to obtain a targeted distribution coefficient, obtaining a targeted distribution threshold through the storage module, and comparing the targeted distribution coefficient with the targeted distribution threshold: if the targeted distribution coefficient is greater than or equal to the targeted distribution threshold, then the L2 monitoring parameters with the largest rule value GZi of the corresponding optimized store are marked as targeted optimization parameters, and the targeted optimization parameters are sent to the mobile phone terminal of the headquarters manager; if the targeted distribution coefficient is less than the targeted distribution threshold, then the corresponding optimized store is marked as a balanced store, and an in-depth optimization analysis is performed on the balanced store.

[0013] Furthermore, the specific process of conducting in-depth optimization analysis on balanced stores includes: summing and averaging all monitoring parameters i of the balanced stores corresponding to the serial numbers in sequence i to obtain the overall distribution coefficient of the balanced stores, obtaining the overall distribution threshold through the database, and comparing the overall distribution coefficient with the overall distribution threshold: if the overall distribution coefficient is less than the overall distribution threshold, a comprehensive training signal is generated and sent to the mobile phone terminal of the headquarters manager; if the overall distribution coefficient is greater than or equal to the overall distribution threshold, a penalty supervision signal is generated and sent to the mobile phone terminal of the headquarters manager.

[0014] The present invention has the following beneficial effects: 1. The store monitoring module can monitor and analyze the in-store operating status of chain stores. After taking video of the operating space, the execution status of each monitoring parameter can be extracted and evaluated by combining video processing technology, and non-compliant operations can be recorded to provide data support for the store management process; 2. The store management module can be used to conduct periodic management and analysis of the compliance status of chain stores. At the end of the monitoring period, the rule values ​​corresponding to various monitoring parameters are counted, and the store customer flow and store service personnel when non-compliance occurs are combined to conduct a comprehensive analysis and calculation to obtain the management coefficient. The management coefficient is used to provide feedback and evaluation on the compliance level of the chain stores during the monitoring period. 3. The store optimization module can be used to analyze the optimization mode of the optimized stores, and the number of optimized stores in the chain stores can be counted to obtain the centralized necessary value. The optimization mode of the optimized stores can be marked by the centralized necessary value, and different optimization modes can be used for store management optimization analysis according to different operating conditions; 4. Through the optimization module, targeted optimization analysis can be carried out on the optimized stores. According to the numerical characteristics of all monitoring parameters of the optimized stores, targeted optimization plans can be assigned to them, thereby improving the overall operating status of all chain stores. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A system block diagram of the present invention as a whole; Figure 2 is a system block diagram of Embodiment 1 of the present invention; Figure 3 is a system block diagram of Embodiment 2 of the present invention; Figure 4 This is a method flow chart of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, a remote inspection system for chain stores based on artificial intelligence includes an inspection management subsystem, an optimization management subsystem and a database.

[0019] Embodiment 1: Figure 2As shown, the inspection management subsystem includes a store monitoring module and a store management module. The store management module is communicatively connected with the store monitoring module and the optimization management subsystem.

[0020] The store monitoring module is used to monitor and analyze the in-store business status of chain stores: generate a monitoring cycle, shoot a video of the in-store business space through a camera, decompose the captured video, perform feature recognition processing and extract monitoring parameters i, i=1, 2,..., n, n is a positive integer, and exemplary monitoring parameters generally include personnel service processes, equipment operation processes, sanitation and cleaning processes, etc.; the personnel service process can be constructed by extracting key nodes of personnel service from the captured video, and the key nodes can be obtained through existing technologies such as video decomposition, image segmentation, and image recognition; retrieve the procedure standards e set by the chain store headquarters through the database, e=1, 2,..., n, n is a positive integer, and the monitoring parameters i and The procedure standard e corresponds one to one, that is, when monitoring parameter 1 is set to the personnel service process, procedure standard 1 is correspondingly set to the personnel service standard; the monitoring parameter i is compared with the procedure standard e: if the monitoring parameter i conforms to the procedure standard e, it is determined that the monitoring parameter i meets the requirements; if the monitoring parameter i does not conform to the procedure standard e, it is determined that the monitoring parameter i does not meet the requirements, and the rule value GZi of the monitoring parameter i is increased by one; the rule value GZi of all monitoring parameters i of all chain stores is cleared at the beginning of the monitoring cycle; after video shooting of the business space, the execution status of each monitoring parameter is extracted and evaluated in combination with video processing technology, and non-compliant operations are recorded to provide data support for the store management process.

[0021] The store management module is used to perform periodic management and analysis on the compliance status of chain stores: at the end of the monitoring period, the formula The management coefficient GL of the chain store in the monitoring period is obtained, where t1 is the proportional coefficient. The process of obtaining the value of t1 includes: obtaining the number of customers and the number of salespersons in the store at the time of switching the rule value GZi of the monitoring parameter i in the monitoring period and marking them as the flow value and the service value respectively, marking the ratio of the flow value to the service value as the service coverage value when the rule value GZi is switched, summing up and averaging the corresponding service coverage values ​​of the rule value GZi of all monitoring parameters i in the chain stores when they are switched to obtain the service coverage coefficient; retrieving the service coverage threshold through the database, and comparing the service coverage coefficient with the service coverage threshold: if the service coverage coefficient is less than the service coverage threshold, t1=1; if the service coverage coefficient is greater than or equal to the service coverage threshold, 0.85≤t1≤0.95, and generating a service supplement signal at the same time and sending the service supplement signal to the mobile phone terminal of the headquarters manager; The management threshold GLmax is obtained through the database, and the management coefficient GL of the chain store during the monitoring period is compared with the management threshold GLmax: if the management coefficient GL is less than the management threshold GLmax, it is determined that the compliance status of the chain store during the monitoring period meets the requirements, and the corresponding chain store is marked as a compliant store; if the management coefficient GL is greater than or equal to the management threshold GLmax, it is determined that the compliance status of the chain store during the monitoring period does not meet the requirements, and the corresponding chain store is marked as an optimized store; all optimized stores are sent to the optimization management subsystem; at the end of the monitoring period, the rule values ​​corresponding to each monitoring parameter are counted, and the management coefficient is obtained by comprehensive analysis and calculation based on the store customer flow and the number of store services when non-compliance occurs, and the compliance level of the chain store during the monitoring period is fed back and evaluated through the management coefficient.

[0022] Embodiment 2: Figure 3 As shown, the optimization management subsystem includes a store optimization module and a targeted optimization module.

[0023] The store optimization module is used to analyze the optimization mode of the optimized stores: mark the ratio of the number of optimized stores to the total number of all chain stores as the centralized necessary value, obtain the centralized necessary threshold through the database, and compare the centralized necessary value with the centralized necessary threshold: if the centralized necessary value is less than the centralized necessary threshold, the centralized optimization mode is used to optimize the optimized stores: mark the sum of the rule values ​​GZi of the monitoring parameter i in all optimized stores as the optimization demand value i of the monitoring parameter i, mark the L1 monitoring parameters i with the largest optimization demand value i as centralized optimization parameters, and send the centralized optimization parameters to the mobile phone terminal of the headquarters manager; if the centralized necessary value is greater than or equal to the centralized necessary threshold, generate a targeted optimization signal and send it to the targeted optimization module; statistically analyze the proportion of the number of optimized stores in the chain stores to obtain the centralized necessary value, mark the optimization mode of the optimized stores by the centralized necessary value, and adopt different optimization modes for store management optimization analysis according to different operating conditions.

[0024] The targeted optimization module is used to perform targeted optimization analysis on the optimized stores: all optimized stores are arranged in order from small to large according to the rule value GZi of the monitoring parameter i to obtain the targeted sequence i of the monitoring parameter i, and the variance of the serial numbers of all the monitoring parameters i of the optimized stores in the corresponding targeted sequence i is calculated to obtain the targeted distribution coefficient, and the targeted distribution threshold is obtained through the storage module, and the targeted distribution coefficient is compared with the targeted distribution threshold: if the targeted distribution coefficient is greater than or equal to the targeted distribution threshold, the L2 monitoring parameters with the largest rule value GZi of the corresponding optimized store are marked as targeted optimization parameters, and the targeted optimization parameters are sent to the mobile phone terminal of the headquarters manager; if the targeted distribution coefficient is less than the targeted distribution threshold, the corresponding optimized store is marked as a balanced store.

[0025] Conduct in-depth optimization analysis on balanced stores: sum and average all monitoring parameters i of balanced stores in the corresponding sequence i to obtain the overall distribution coefficient of the balanced stores, obtain the overall distribution threshold through the database, and compare the overall distribution coefficient with the overall distribution threshold: if the overall distribution coefficient is less than the overall distribution threshold, generate a comprehensive training signal and send it to the mobile phone terminal of the headquarters manager; if the overall distribution coefficient is greater than or equal to the overall distribution threshold, generate a penalty supervision signal and send it to the mobile phone terminal of the headquarters manager; according to the numerical characteristics of all monitoring parameters of the optimized store, assign targeted optimization plans to it, and improve the operating status of all chain stores as a whole.

[0026] Embodiment 3: Figure 4 As shown, a chain store remote inspection method based on artificial intelligence includes the following steps: Step 1: Monitor and analyze the in-store operating status of chain stores: Generate a monitoring cycle and use cameras to shoot videos of the in-store operating space; Step 2: Conduct periodic management analysis on the compliance status of chain stores: At the end of the monitoring period, obtain the management coefficient GL of the chain stores during the monitoring period, and use the management coefficient GL to determine whether the compliance status of the chain stores during the monitoring period meets the requirements; Step 3: Analyze the optimization mode of the optimized stores: mark the ratio of the number of optimized stores to the total number of all chain stores as the centralized necessary value, select the optimization mode through the centralized necessary value, and then use the optimization mode or centralized optimization mode to optimize the optimized stores.

[0027] A chain store remote inspection system based on artificial intelligence generates a monitoring cycle when working, and uses a camera to shoot a video of the business space in the store; at the end of the monitoring cycle, the management coefficient GL of the chain store in the monitoring cycle is obtained, and whether the compliance status of the chain store in the monitoring cycle meets the requirements is determined by the management coefficient GL; the ratio of the number of optimized stores to the total number of all chain stores is marked as a centralized necessary value, and an optimization mode is selected by the centralized necessary value, and then an optimization analysis is performed on the optimized stores using the targeted optimization mode or the centralized optimization mode.

[0028] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

[0029] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0030] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A chain store remote inspection system based on artificial intelligence, characterized in that: Including store monitoring module, store management module, store optimization module, targeted optimization module and database; The store monitoring module is used to monitor and analyze the in-store business status of chain stores: generate a monitoring cycle, shoot a video of the in-store business space through a camera, decompose the shot video, perform feature recognition processing and extract monitoring parameters i, i=1, 2, ..., n, n is a positive integer, retrieve the procedure standard e set by the chain store headquarters through the database, e=1, 2, ..., n, n is a positive integer, compare the monitoring parameter i with the procedure standard e, and numerically mark the rule value GZi of the monitoring parameter i through the comparison result; The store management module is used to perform periodic management and analysis on the compliance status of chain stores: at the end of the monitoring period, the formula The management coefficient GL of the chain stores during the monitoring period is obtained, where t1 is the proportional coefficient; Using the management coefficient GL to mark chain stores as compliant stores or optimized stores; The store optimization module is used to analyze the optimization mode of the optimized stores: the ratio of the number of optimized stores to the total number of all chain stores is marked as a centralized necessary value, and the optimization mode of the optimized stores is marked by the centralized necessary value; The targeted optimization module is used to perform targeted optimization analysis on optimized stores.

2. According to the artificial intelligence-based chain store remote inspection system of claim 1, it is characterized in that: The specific process of comparing the monitoring parameter i with the procedure standard e includes: if the monitoring parameter i meets the procedure standard e, it is determined that the monitoring parameter i meets the requirements; if the monitoring parameter i does not meet the procedure standard e, it is determined that the monitoring parameter i does not meet the requirements, and the rule value GZi of the monitoring parameter i is increased by one; the rule values ​​GZi of all monitoring parameters i of all chain stores are cleared at the beginning of the monitoring cycle.

3. The artificial intelligence-based chain store remote inspection system according to claim 2 is characterized in that: The value-taking process of t1 includes: obtaining the number of customers and the number of salespersons in the store at the time when the rule value GZi of the monitoring parameter i is switched within the monitoring period and marking them as the flow value and the service value respectively, marking the ratio of the flow value to the service value as the service coverage value when the rule value GZi is switched, summing up and averaging the corresponding service coverage values ​​when the rule value GZi of all monitoring parameters i in the chain stores is switched to obtain the service coverage coefficient; retrieving the service coverage threshold through the database, and comparing the service coverage coefficient with the service coverage threshold: if the service coverage coefficient is less than the service coverage threshold, t1=1; if the service coverage coefficient is greater than or equal to the service coverage threshold, 0.85≤t1≤0.95, and at the same time generating a service supplement signal and sending the service supplement signal to the mobile phone terminal of the headquarters manager.

4. The chain store remote inspection system based on artificial intelligence according to claim 3 is characterized in that: The specific process of marking a chain store as a compliant store or an optimized store includes: obtaining the management threshold GLmax through the database, and comparing the management coefficient GL of the chain store during the monitoring period with the management threshold GLmax: if the management coefficient GL is less than the management threshold GLmax, it is determined that the compliance status of the chain store during the monitoring period meets the requirements, and the corresponding chain store is marked as a compliant store; if the management coefficient GL is greater than or equal to the management threshold GLmax, it is determined that the compliance status of the chain store during the monitoring period does not meet the requirements, and the corresponding chain store is marked as an optimized store.

5. The artificial intelligence-based chain store remote inspection system according to claim 4 is characterized in that: The specific process of marking the optimization mode of the optimized store includes: obtaining the centralized necessary threshold through the database, and comparing the centralized necessary value with the centralized necessary threshold: if the centralized necessary value is less than the centralized necessary threshold, the centralized optimization mode is used to optimize the optimized store; if the centralized necessary value is greater than or equal to the centralized necessary threshold, an optimization signal is generated and sent to the optimization module.

6. The chain store remote inspection system based on artificial intelligence according to claim 5 is characterized in that: The specific process of optimizing the optimized stores using the centralized optimization mode includes: marking the sum of the rule values ​​GZi of the monitoring parameter i in all optimized stores as the optimization demand value i of the monitoring parameter i, marking the L1 monitoring parameters i with the largest optimization demand value i as centralized optimization parameters, and sending the centralized optimization parameters to the mobile terminals of the headquarters managers.

7. The artificial intelligence-based chain store remote inspection system according to claim 6 is characterized in that: The specific process of the optimization module for targeted optimization analysis of optimized stores includes: arranging all optimized stores in order from small to large according to the rule value GZi of monitoring parameter i to obtain a targeted sequence i of monitoring parameter i, performing variance calculation on the serial numbers of all monitoring parameters i of the optimized stores in the corresponding targeted sequence i to obtain a targeted distribution coefficient, obtaining a targeted distribution threshold through the storage module, and comparing the targeted distribution coefficient with the targeted distribution threshold: if the targeted distribution coefficient is greater than or equal to the targeted distribution threshold, the L2 monitoring parameters with the largest rule value GZi of the corresponding optimized store are marked as targeted optimization parameters, and the targeted optimization parameters are sent to the mobile phone terminal of the headquarters manager; if the targeted distribution coefficient is less than the targeted distribution threshold, the corresponding optimized store is marked as a balanced store, and an in-depth optimization analysis is performed on the balanced store.

8. The chain store remote inspection system based on artificial intelligence according to claim 7 is characterized in that: The specific process of in-depth optimization analysis of balanced stores includes: summing up and averaging all monitoring parameters i of the balanced stores corresponding to the serial numbers in sequence i to obtain the overall distribution coefficient of the balanced stores, obtaining the overall distribution threshold through the database, and comparing the overall distribution coefficient with the overall distribution threshold: if the overall distribution coefficient is less than the overall distribution threshold, a comprehensive training signal is generated and sent to the mobile phone terminal of the headquarters manager; if the overall distribution coefficient is greater than or equal to the overall distribution threshold, a penalty supervision signal is generated and sent to the mobile phone terminal of the headquarters manager.

Images