Franchise chain store service management system

Abstract

The invention discloses a franchise chain store service management system, which comprises a data collection module, a data preprocessing module, an intelligent allocation module, a deep data analysis module and an anomaly detection module, the data preprocessing module is in data connection with the intelligent deployment module, the depth data analysis module and the anomaly detection module; according to the invention, the intelligent allocation module determines a feasible replenishment scheme based on shop and warehouse information by predicting inventory demands, so as to improve the timeliness of replenishment; according to the invention, the deep data analysis module analyzes the market trend and the competition relationship, thereby helping the franchise to better understand the market demand and the competition situation, and improving the scientificity and accuracy of decision making; according to the invention, the anomaly detection module judges whether the store is abnormal by calculating the anomaly scores of the plurality of key indexes, so that problems in store operation can be found in time, the management risk is reduced, and a scientific solution is provided.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, in particular to a franchise chain store service management system. Background Art

[0002] Franchise chain stores refer to a large number of small-scale, dispersed retail stores of the same brand that sell similar goods and services. Under the organization and leadership of the headquarters, they adopt a common business policy and consistent marketing actions, implement an organic combination of centralized procurement and decentralized sales, and achieve economies of scale through standardized operations. Franchise chain store service management system is a management software tool designed specifically for franchise chain stores, which uses information technology to uniformly manage and coordinate all aspects of franchise chain stores. However, the existing franchise chain store service management system has the following shortcomings when in use: First, the management system directly allocates goods from the warehouse when replenishing the chain store's goods, which results in that when out of stock occurs, some chain stores that are far away from the warehouse find it difficult to replenish the goods in time, thus affecting the operation of the store; Second, although the existing management system has certain data analysis functions, it can only provide simple sales data statistics, inventory turnover rate and other basic indicators, and the depth and breadth of the analysis are often insufficient. For example, the analysis capabilities of market trends, sales forecasts, etc. are insufficient, which makes it difficult for franchisees to make scientific and accurate decisions based on the data analysis results provided by the system when facing a complex market environment and competitive pressure; Third, the management system's functions in abnormal situation monitoring and early warning are not perfect enough, and it is impossible to timely discover problems in the operation of franchise stores, such as inventory backlogs, sales declines, and increased customer complaints. At the same time, the management system cannot provide targeted optimization suggestions and solutions based on the actual situation of the franchise stores. Franchisees still need to rely on their own experience and subjective judgment to solve problems, which increases the difficulty and risk of management. Summary of the invention

[0003] The purpose of the present invention is to provide a franchise chain store service management system to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a franchise chain store service management system, comprising a data collection module, a data preprocessing module, an intelligent allocation module, a deep data analysis module and an anomaly detection module, wherein the data collection module establishes a data connection with the data preprocessing module, and the data preprocessing module establishes data connections with the intelligent allocation module, the deep data analysis module and the anomaly detection module respectively.

[0005] Preferably, the data collection module includes a store data collection submodule, a customer data collection submodule and a market data collection submodule.

[0006] Preferably, the intelligent allocation module includes a demand forecasting submodule, a safety inventory threshold adjustment submodule, an inventory status evaluation submodule and a goods allocation submodule, and the inventory status evaluation submodule establishes data connections with the demand forecasting submodule, the safety inventory threshold adjustment submodule and the goods allocation submodule respectively, and the algorithm formula used by the demand forecasting submodule is as follows:

[0007] In the formula, is the demand forecast value, is the influencing factor of historical sales data, is the festival impact factor, is the seasonal influence factor, is the store location influencing factor, , , and is the regression coefficient of each influencing factor, is a constant term, is the error term;

[0008] In the formula, is the quantity of goods required, is the unit conversion factor; The algorithm formula used by the inventory status assessment submodule is as follows: when When the inventory is insufficient, it is judged as insufficient; In the formula, is the current inventory of the goods, is the safety stock threshold.

[0009] Preferably, the demand forecasting submodule includes a demand forecasting unit and an impact factor adjustment unit, and the demand forecasting unit and the impact factor adjustment unit establish a data connection.

[0010] Preferably, the goods allocation submodule includes an allocation plan generation unit, a feasibility judgment unit and an allocation plan execution unit, and the feasibility judgment unit establishes data connections with the allocation plan generation unit and the allocation plan execution unit respectively. The allocation plan generated by the allocation plan generation unit specifically includes: directly transferring goods from the warehouse, transferring goods from nearby stores, transferring goods from nearby stores, and simultaneously transferring goods from the warehouse to supplement nearby stores.

[0011] Preferably, the in-depth data analysis module includes a market trend analysis submodule, a competitive relationship analysis submodule and a decision support submodule, and the decision support submodule establishes data connections with the market trend analysis submodule and the competitive relationship analysis submodule respectively.

[0012] Preferably, the market trend analysis submodule includes a sales trend analysis unit, a customer demand trend analysis unit and a market competition trend analysis unit. The sales trend analysis unit adopts an exponential smoothing algorithm, the customer demand trend analysis unit adopts an association rule mining algorithm, and the market competition trend analysis unit adopts the Herfindahl-Hirschman index. The exponential smoothing algorithm formula is as follows:

[0013] In the formula, is the predicted value for the next period, is the actual value of this period, is the forecast value for this period, is the smoothing coefficient, and .

[0014] Preferably, the competitive relationship analysis submodule includes a competitor identification unit, a competitive advantage analysis unit and a price competition analysis unit. The competitive advantage analysis unit adopts comparative advantage index analysis, and the price competition analysis unit adopts price elasticity coefficient analysis. The formula of comparative advantage index is as follows:

[0015] In the formula, is the comparative advantage index, It is a shop In product Sales on Is the market where the store is located in the product Total sales on It is a shop Total sales, is the total market sales, A value greater than 1 indicates a store In product have comparative advantages; A value less than 1 indicates a store In product has a comparative disadvantage; The formula for the price elasticity coefficient is as follows:

[0016] In the formula, is the current price of the product, For sales volume, is the adjusted price, For the sales volume after price adjustment, the price elasticity coefficient is greater than 1, which means that the demand for the product is sensitive to price changes, and lowering the price can increase sales; the price elasticity coefficient is less than 1, which means that the demand for the product is not sensitive to price changes, and lowering the price will not significantly increase sales.

[0017] Preferably, the decision support submodule includes a sales strategy formulation unit and an inventory management decision unit.

[0018] Preferably, the anomaly detection module includes an anomaly score calculation submodule, an anomaly judgment submodule, an anomaly cause analysis submodule, a solution generation submodule, an anomaly cause knowledge base and a solution knowledge base, and the anomaly judgment submodule establishes data connections with the anomaly score calculation submodule and the anomaly cause analysis submodule respectively, the anomaly cause analysis submodule establishes data connections with the anomaly cause knowledge base and the solution generation submodule respectively, the solution generation submodule establishes data connections with the solution knowledge base, the anomaly score calculation submodule adopts an algorithm based on standard deviation, and the anomaly score calculation formula is as follows:

[0019] In the formula, Is an indicator The anomaly score, Key store data, including sales, customer traffic, inventory levels, and employee work hours; The calculation formula for the comprehensive anomaly score is as follows:

[0020] In the formula, Is an indicator The weight of .

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows: the intelligent allocation module of the present invention predicts inventory demand and then determines a feasible replenishment plan based on store and warehouse information to improve the timeliness of replenishment; the deep data analysis module of the present invention analyzes market trends and competitive relationships to help franchisees better understand market demand and competitive situation and improve the scientificity and accuracy of decision-making; the anomaly detection module of the present invention determines whether there is an anomaly in a store by calculating the anomaly scores of multiple key indicators, thereby promptly discovering problems in store operations, reducing management risks, and providing scientific solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a system structure block diagram of the present invention; Figure 2 It is a structural block diagram of the data collection module of the present invention; Figure 3 It is a structural block diagram of the intelligent deployment module of the present invention; Figure 4 It is a structural block diagram of the deep data analysis module of the present invention; Figure 5 This is a structural block diagram of the anomaly detection module of the present invention.

[0023] In the figure: 1. Data collection module; 11. Store data collection submodule; 12. Customer data collection submodule; 13. Market data collection submodule; 2. Data preprocessing; 3. Intelligent allocation module; 31. Demand forecasting submodule; 311. Demand forecasting unit; 312. Influencing factor adjustment unit; 32. Safety stock threshold adjustment submodule; 33. Inventory status assessment submodule; 34. Goods allocation submodule; 341. Allocation plan generation unit; 342. Feasibility judgment unit; 343. Allocation plan execution unit; 4. Deep data analysis module; 41. Market trend analysis submodule; 411. Sales trend analysis unit; 412, customer demand trend analysis unit; 413, market competition trend analysis unit; 42, competition relationship analysis submodule; 421, competitor identification unit; 422, competitive advantage analysis unit; 423, price competition analysis unit; 43, decision support submodule; 431, sales strategy formulation unit; 432, inventory management decision unit; 5, anomaly detection module; 51, anomaly score calculation submodule; 52, anomaly judgment submodule; 53, anomaly cause analysis submodule; 54, solution generation submodule; 55, anomaly cause knowledge base; 56, solution knowledge base. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not 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.

[0025] Please refer to the attached Figure 1 -Attached Figure 5, an embodiment provided by the present invention: a franchise chain store service management system, including a data collection module 1, a data preprocessing module 2, an intelligent allocation module 3, a deep data analysis module 4 and an anomaly detection module 5, the data collection module 1 establishes a data connection with the data preprocessing module 2, the data preprocessing module 2 establishes a data connection with the intelligent allocation module 3, the deep data analysis module 4 and the anomaly detection module 5 respectively, the data collection module 1 is used to collect data, and then the collected data is preprocessed by the data preprocessing module 2, including outlier processing, data conversion and normalization processing, and then the preprocessed data is transmitted to the intelligent allocation module 3, the deep data analysis module 4 and the anomaly detection module 5, the intelligent allocation module 3 analyzes the data and realizes intelligent replenishment, the deep data analysis module 4 analyzes the data and realizes decision support, and the anomaly detection module 5 analyzes the data and realizes store anomaly detection; the data collection module 1 includes a store data collection submodule 11, a customer data collection submodule 12 and a market data collection submodule The data collection submodule 13 collects store data through the store data collection submodule 11, collects customer data through the customer data collection submodule 12, and collects market data through the market data collection submodule 13; the intelligent allocation module 3 includes a demand prediction submodule 31, a safety stock threshold adjustment submodule 32, an inventory status evaluation submodule 33 and a goods allocation submodule 34, and the inventory status evaluation submodule 33 establishes data connections with the demand prediction submodule 31, the safety stock threshold adjustment submodule 32 and the goods allocation submodule 34 respectively. The demand prediction submodule 31 is used to predict inventory demand, the safety stock threshold adjustment submodule 32 is used to adjust the safety stock threshold, and the inventory status evaluation submodule 33 determines whether the inventory is in a critical state by analyzing the goods demand, the current inventory and the safety stock threshold. Once the inventory is determined to be in a critical state, the goods allocation submodule 34 is started, and the allocation plan generation unit 341 is used to generate an allocation plan. The algorithm formula used by the demand prediction submodule 31 is as follows:

[0026] In the formula, is the demand forecast value, is the influencing factor of historical sales data, is the festival impact factor, is the seasonal influence factor, is the store location influencing factor, , , and is the regression coefficient of each influencing factor, is a constant term, is the error term;

[0027] In the formula, is the quantity of goods required, is the unit conversion factor; The algorithm formula used by the inventory status evaluation submodule 33 is as follows: when When the inventory is insufficient, it is judged as insufficient; In the formula, is the current inventory of the goods, is the safety stock threshold; the demand forecasting submodule 31 includes a demand forecasting unit 311 and an influencing factor adjustment unit 312, and the demand forecasting unit 311 and the influencing factor adjustment unit 312 establish a data connection, the demand forecasting submodule 31 combines multiple influencing factors to predict the demand for goods in the future, the demand forecasting unit 311 uses a multivariate linear regression and time series combination algorithm to predict the demand for goods, and the influencing factor adjustment unit 312 dynamically adjusts the influencing factor according to time changes; the goods allocation submodule 34 includes an allocation plan generation unit 341, a feasibility judgment unit 342 and an allocation plan execution unit 343, and The feasibility judgment unit 342 establishes data connections with the allocation plan generation unit 341 and the allocation plan execution unit 343 respectively. The allocation plan generated by the allocation plan generation unit 341 specifically includes: directly transferring goods from the warehouse, transferring goods from nearby stores, transferring goods from nearby stores, and transferring goods from the warehouse to supplement nearby stores. After the allocation plan generation unit 341 generates the plan, the feasibility judgment unit 342 judges the feasibility of the plan in turn, and then the allocation plan execution unit 343 executes the feasible plan; the deep data analysis module 4 includes a market trend analysis submodule 41, a competitive relationship analysis submodule 42 and a decision support submodule 43, and the decision The decision support submodule 43 establishes data connection with the market trend analysis submodule 41 and the competition relationship analysis submodule 42 respectively. The market trend analysis submodule 41 is used to analyze market trends, the competition relationship analysis submodule 42 is used to analyze competition relationships, and the decision support submodule 43 is used to provide decision support; the market trend analysis submodule 41 includes a sales trend analysis unit 411, a customer demand trend analysis unit 412 and a market competition trend analysis unit 413. The market trend analysis submodule 41 analyzes the changing trends of sales indicators such as sales volume and sales volume through the sales trend analysis unit 411, and predicts the sales trend in the future. , providing a reference for the store's inventory management and production plan. The customer demand trend analysis unit 412 predicts the customer's future demand trend by analyzing the customer's purchase history and consumption preferences, providing a basis for the store's product development and marketing strategy formulation. The market competition trend analysis unit 413 analyzes the sales data and market share changes of competitors to provide a reference for the store's competition strategy formulation. The sales trend analysis unit 411 adopts an exponential smoothing algorithm, the customer demand trend analysis unit 412 adopts an association rule mining algorithm, and the market competition trend analysis unit 413 adopts the Herfindahl-Hirschman index. The exponential smoothing algorithm formula is as follows:

[0028] In the formula, is the predicted value for the next period, is the actual value of this period, is the forecast value for this period, is the smoothing coefficient, and The competitive relationship analysis submodule 42 includes a competitor identification unit 421, a competitive advantage analysis unit 422 and a price competition analysis unit 423. The competitive relationship analysis submodule 42 determines the main competitors of the store through the competitor identification unit 421, and analyzes the advantages and disadvantages of the competitors. The competitive advantage analysis unit 422 is used to analyze whether the product has a competitive advantage. The price competition analysis unit 423 is used to determine the pricing strategy of the product. The competitive advantage analysis unit 422 uses a comparative advantage index analysis, and the price competition analysis unit 423 uses a price elasticity coefficient analysis. The formula of the comparative advantage index is as follows:

[0029] In the formula, is the comparative advantage index, It is a shop In product Sales on Is the market where the store is located in the product Total sales on It is a shop Total sales, is the total market sales, A value greater than 1 indicates a store In product have comparative advantages; A value less than 1 indicates a store In product has a comparative disadvantage; The formula for the price elasticity coefficient is as follows:

[0030] In the formula, is the current price of the product, For sales volume, is the adjusted price, For the sales volume after adjusting the price, if the price elasticity coefficient is greater than 1, it means that the demand for the product is sensitive to price changes, and lowering the price can increase sales; if the price elasticity coefficient is less than 1, it means that the demand for the product is not sensitive to price changes, and lowering the price will not significantly increase sales; the decision support submodule 43 includes a sales strategy formulation unit 431 and an inventory management decision unit 432, and the sales strategy is generated by the sales strategy formulation unit 431, and the inventory management strategy is generated by the inventory management decision unit 432; the anomaly detection module 5 includes an anomaly score calculation submodule 51, an anomaly judgment submodule 52, an anomaly cause analysis submodule 53, a solution generation submodule 54, an anomaly cause knowledge base 55 and a solution knowledge base 56, and the anomaly judgment submodule 52 is respectively connected to the anomaly score calculation submodule 51 The abnormal cause analysis submodule 53 establishes data connection with the abnormal cause knowledge base 55 and the solution generation submodule 54 respectively. The solution generation submodule 54 establishes data connection with the solution knowledge base 56. The abnormal score calculation submodule 51 is used to calculate the comprehensive abnormal score of the store. The abnormal judgment submodule 52 judges whether there is an abnormality in the store by the threshold method. The abnormal cause analysis submodule 53 is based on the abnormal cause knowledge base 55. The abnormal index and the possible causes are analyzed and then a cause list containing the possibility of each cause is generated. The solution generation submodule 54 obtains the solution from the solution knowledge base 56 according to the cause list. The abnormal score calculation submodule 51 adopts an algorithm based on the standard deviation. The abnormal score calculation formula is as follows:

[0031] In the formula, Is an indicator The anomaly score, Key store data, including sales, customer traffic, inventory levels, and employee work hours; The calculation formula for the comprehensive anomaly score is as follows:

[0032] In the formula, Is an indicator The weight of .

[0033] Working principle: When using the present invention, data is collected using the data collection module 1, that is, store data is collected through the store data collection submodule 11, customer data is collected through the customer data collection submodule 12, and market data is collected through the market data collection submodule 13. Then, the collected data is preprocessed through the data preprocessing 2, including outlier processing, data conversion and normalization processing, and then the preprocessed data is transmitted to the intelligent allocation module 3, the deep data analysis module 4 and the anomaly detection module 5. The intelligent allocation module 3 analyzes the data and realizes intelligent replenishment, the deep data analysis module 4 analyzes the data and realizes decision support, and the anomaly detection module 5 analyzes the data and realizes store anomaly detection. Specifically, the demand forecasting submodule 31 comprehensively predicts the demand for goods in the future period of time, the demand forecasting unit 311 adopts a multivariate linear regression and time series combination algorithm to predict the demand for goods, and the influencing factor adjustment unit 312 dynamically adjusts the influencing factors according to time changes. The safety stock threshold adjustment submodule 32 is used to adjust the safety stock threshold, and the inventory status evaluation submodule 33 analyzes the demand for goods. , current inventory and safety inventory thresholds, and judge whether the inventory is in a critical situation. Once it is judged that the inventory is in a critical situation, the goods allocation submodule 34 is started, and the allocation plan generation unit 341 generates the following three plans: the first is to directly transfer goods from the warehouse, the second is to transfer goods from nearby stores, and the third is to transfer goods from nearby stores, and at the same time transfer goods from the warehouse to supplement nearby stores. The feasibility judgment unit 342 judges the feasibility of the three plans in turn, and then the allocation plan execution unit 343 executes the feasible plan. The judgment basis is whether the transfer time is within the out-of-stock time range that the store can bear. For example, if it is judged that the out-of-stock store can be replenished before the goods are sold out by directly transferring goods from the warehouse, the allocation plan execution unit 343 executes the plan. If it is judged that the transfer time from the nearby store meets the requirements and will not cause the inventory of the nearby store to be in a critical situation, then the plan is executed. If it is judged that the transfer time from the nearby store meets the requirements, but it will cause the inventory of the nearby store to be in a critical situation, and if the goods are directly transferred from the warehouse, the transfer time will exceed the tolerable out-of-stock time, then the goods are transferred from the nearby store, and at the same time, the goods are transferred from the warehouse to supplement the nearby store. There can be multiple nearby stores;The market trend analysis submodule 41 analyzes the changing trends of sales indicators such as sales volume and sales volume through the sales trend analysis unit 411, predicts the sales trend in the future, and provides a reference for the store's inventory management and production plan. The customer demand trend analysis unit 412 predicts the customer's future demand trend through the analysis of the customer's purchase history and consumption preferences, and provides a basis for the product development and marketing strategy formulation of the store. The market competition trend analysis unit 413 analyzes the sales data and market share changes of competitors, and provides a reference for the formulation of the store's competition strategy. The competitive relationship analysis submodule 42 determines the main competitors of the store through the competitor identification unit 421, and analyzes the advantages and disadvantages of the competitors. The competitive advantage analysis unit 422 is used to analyze whether the product has a competitive advantage. The price competition analysis unit 423 is used to determine the pricing strategy of the product. The decision support submodule 43 integrates the analysis results of the market trend analysis submodule 41 and the competitive relationship analysis submodule 42, generates a sales strategy through the sales strategy formulation unit 431, and generates a sales strategy through the inventory management decision unit Element 432 generates inventory management strategy; abnormal score calculation submodule 51 uses the standard deviation-based method to calculate the comprehensive abnormal score of the store; abnormal judgment submodule 52 uses the threshold method to judge whether the store has abnormalities; abnormal cause analysis submodule 53, based on the abnormal cause knowledge base 55, associates abnormal indicators with possible causes for analysis; for example, if sales volume decreases, possible causes include reduced customer flow, reduced customer unit price, unpopular products, etc., and further analyzes related indicators such as customer flow and customer unit price to determine the specific cause, and then generates a cause list containing the possibility of each cause; solution generation submodule 54 obtains solutions from the solution knowledge base 56 according to the cause list, and proposes key points according to the possibility. For example, if the abnormal cause is intensified market competition, the solution may be to launch new products, strengthen market promotion, change sales strategies, etc.; if the abnormal cause is a decline in service level, the solution may be to strengthen employee training, establish a service quality supervision mechanism, etc.; the possibility of intensified market competition is low, and the possibility of decline in service level is high, so the focus is on improving service level. ;

[0034] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A franchise chain store service management system, comprising a data collection module (1), a data preprocessing module (2), an intelligent allocation module (3), a deep data analysis module (4) and an anomaly detection module (5), characterized in that: The data collection module (1) establishes a data connection with the data preprocessing module (2), and the data preprocessing module (2) establishes data connections with the intelligent allocation module (3), the deep data analysis module (4) and the anomaly detection module (5) respectively.

2. A franchise chain store service management system according to claim 1, characterized in that: The data collection module (1) comprises a store data collection submodule (11), a customer data collection submodule (12) and a market data collection submodule (13).

3. A franchise chain store service management system according to claim 1, characterized in that: The intelligent allocation module (3) comprises a demand forecasting submodule (31), a safety inventory threshold adjustment submodule (32), an inventory status evaluation submodule (33) and a goods allocation submodule (34), and the inventory status evaluation submodule (33) respectively establishes data connections with the demand forecasting submodule (31), the safety inventory threshold adjustment submodule (32) and the goods allocation submodule (34), and the demand forecasting submodule (31) adopts the following algorithm formula: In the formula, is the demand forecast value, is the influencing factor of historical sales data, is the festival impact factor, is the seasonal influence factor, is the store location influencing factor, , , and is the regression coefficient of each influencing factor, is a constant term, is the error term; In the formula, is the quantity of goods required, is the unit conversion factor; The algorithm formula used by the inventory status assessment submodule (33) is as follows: when When the inventory is insufficient, it is judged as insufficient; In the formula, is the current inventory of the goods, is the safety stock threshold.

4. A franchise chain store service management system according to claim 3, characterized in that: The demand prediction submodule (31) comprises a demand prediction unit (311) and an impact factor adjustment unit (312), and the demand prediction unit (311) and the impact factor adjustment unit (312) establish a data connection.

5. The franchise chain store service management system according to claim 3, characterized in that: The goods allocation submodule (34) includes an allocation plan generation unit (341), a feasibility judgment unit (342) and an allocation plan execution unit (343), and the feasibility judgment unit (342) establishes data connections with the allocation plan generation unit (341) and the allocation plan execution unit (343), respectively. The allocation plan generated by the allocation plan generation unit (341) specifically includes: directly transferring goods from the warehouse, transferring goods from nearby stores, transferring goods from nearby stores, and simultaneously transferring goods from the warehouse to supplement nearby stores.

6. A franchise chain store service management system according to claim 1, characterized in that: The in-depth data analysis module (4) comprises a market trend analysis submodule (41), a competitive relationship analysis submodule (42) and a decision support submodule (43), and the decision support submodule (43) establishes data connections with the market trend analysis submodule (41) and the competitive relationship analysis submodule (42), respectively.

7. A franchise chain store service management system according to claim 6, characterized in that: The market trend analysis submodule (41) comprises a sales trend analysis unit (411), a customer demand trend analysis unit (412) and a market competition trend analysis unit (413). The sales trend analysis unit (411) adopts an exponential smoothing algorithm, the customer demand trend analysis unit (412) adopts an association rule mining algorithm, and the market competition trend analysis unit (413) adopts the Herfindahl-Hirschman index. The exponential smoothing algorithm formula is as follows: In the formula, is the predicted value for the next period, is the actual value of this period, is the forecast value for this period, is the smoothing coefficient, and .

8. A franchise chain store service management system according to claim 6, characterized in that: The competitive relationship analysis submodule (42) includes a competitor identification unit (421), a competitive advantage analysis unit (422) and a price competition analysis unit (423). The competitive advantage analysis unit (422) uses a comparative advantage index analysis, and the price competition analysis unit (423) uses a price elasticity coefficient analysis. The formula of the comparative advantage index is as follows: In the formula, is the comparative advantage index, It is a shop In product Sales on Is the market where the store is located in the product Total sales on It is a shop Total sales, is the total market sales, A value greater than 1 indicates a store In product have comparative advantages; A value less than 1 indicates a store In product has a comparative disadvantage; The formula for the price elasticity coefficient is as follows: In the formula, is the current price of the product, For sales volume, is the adjusted price, For the sales volume after price adjustment, the price elasticity coefficient is greater than 1, which means that the demand for the product is sensitive to price changes, and lowering the price can increase sales; the price elasticity coefficient is less than 1, which means that the demand for the product is not sensitive to price changes, and lowering the price will not significantly increase sales.

9. A franchise chain store service management system according to claim 6, characterized in that: The decision support submodule (43) includes a sales strategy formulation unit (431) and an inventory management decision unit (432).

10. A franchise chain store service management system according to claim 1, characterized in that: The anomaly detection module (5) comprises an anomaly score calculation submodule (51), an anomaly judgment submodule (52), an anomaly cause analysis submodule (53), a solution generation submodule (54), an anomaly cause knowledge base (55) and a solution knowledge base (56), and the anomaly judgment submodule (52) respectively establishes data connections with the anomaly score calculation submodule (51) and the anomaly cause analysis submodule (53), the anomaly cause analysis submodule (53) respectively establishes data connections with the anomaly cause knowledge base (55) and the solution generation submodule (54), and the solution generation submodule (54) establishes data connections with the solution knowledge base (56). The anomaly score calculation submodule (51) adopts an algorithm based on standard deviation, and the anomaly score calculation formula is as follows: In the formula, Is an indicator The anomaly score, Key store data, including sales, customer traffic, inventory levels, and employee work hours; The calculation formula for the comprehensive anomaly score is as follows: In the formula, Is an indicator The weight of .

Images