Drinking water industry store and distribution management method and system based on artificial intelligence

Abstract

The invention is suitable for the field of drinking water distribution, and provides a drinking water industry store and distribution management method and system based on artificial intelligence, and the method comprises the steps: collecting the historical distribution data, current distribution task data and season related data of a deliveryman; analyzing and extracting feature information in the historical distribution data, the current distribution task data and the seasonal related data, and generating a distribution reference index and a seasonal reference index; based on the distribution reference index and the season reference index, cooperatively adjusting the store inventory; and generating a distribution and distribution task based on the distribution reference index and the seasonal reference index. The method and the system have the beneficial effects that the inventory level is accurately adjusted by combining distribution and seasonal factors, the phenomena of inventory overstock and stockout can be effectively reduced, the inventory cost is reduced, and the fund utilization rate is improved. And individual differences of deliverymen and external environment changes are fully considered, so that task allocation is more scientific and reasonable, and the delivery efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention belongs to the field of drinking water distribution, and in particular relates to a method and system for store and distribution management in the drinking water industry based on artificial intelligence. Background Art

[0002] As people's living standards improve and their health awareness increases, the demand for drinking water continues to grow, and the drinking water industry is booming. The sales channels for drinking water include not only traditional store retail, but also increasingly important distribution services to meet the needs of consumers in different scenarios. However, in the process of rapid development of this industry, store and distribution management are facing many complex problems.

[0003] In the process of drinking water distribution, the working status, work efficiency and service quality of the distribution personnel are crucial to the distribution business. There are unreasonable aspects in the task allocation and inventory management of the distribution personnel, which affects the distribution efficiency and accuracy. In view of the above problems, in order to improve the level of distribution management, it is urgent to develop a method and system for store and distribution management in the drinking water industry based on artificial intelligence. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for store and distribution management in the drinking water industry based on artificial intelligence, aiming to solve the problems raised in the above-mentioned background technology.

[0005] The present invention is implemented in this way. On the one hand, a method for store and distribution management in the drinking water industry based on artificial intelligence, the method comprising:

[0006] Collect the delivery personnel's historical delivery data, current delivery task data, and season-related data;

[0007] Analyze and extract characteristic information from historical delivery data, current delivery task data, and season-related data to generate delivery reference index and season reference index;

[0008] Coordinate and adjust store inventory based on delivery reference indicators and seasonal reference indicators;

[0009] Generate and allocate delivery tasks based on delivery reference indicators and seasonal reference indicators.

[0010] As a further solution of the present invention, the analysis and extraction of characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index specifically includes:

[0011] Extract the current delivery task data including the delivery task duration data, the delivery task quantity data and the daily quota working time data.

[0012] Collect data on the distance to the delivery address, the weight of the water delivered, and the time limit for delivery in the current delivery task data;

[0013] Calculate and generate delivery reference index;

[0014] The calculation process of the distribution reference index is:

[0015]

[0016] F=D r +W w +T t ;

[0017] Where WL is the distribution reference index, T i is the duration of the i-th delivery task, n is the number of delivery tasks, H is the daily standard working time, F is the complexity coefficient of the delivery task, Dr is the delivery distance coefficient, Ww is the delivery quality coefficient, and Tt is the delivery time limit coefficient;

[0018] The delivery distance coefficient Dr is determined based on the straight-line distance d between the delivery address and the store. The short-distance threshold is set to 5 kilometers and the medium-distance threshold is set to 10 kilometers. When d≤5, Dr=0.3, when 5≤d≤10, Dr=0.6, when d≥10, Dr=1;

[0019] The distribution quality coefficient Ww is determined according to the total weight w of drinking water distributed in a single time. The light load threshold is set to 50 kg and the medium load threshold is set to 100 kg. When w≤50, Ww=0.2, when 50≤w≤100, Ww=0.5, when w≥100, Ww=0.8;

[0020] The delivery time limit coefficient Tt, if the delivery task has no special time requirements, Tt = 0.5; if the delivery task is completed during a specific peak period, Tt = 0.8; if the delivery task requires delivery within half an hour, Tt = 1.

[0021] As a further solution of the present invention, the analysis and extraction of characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index specifically further includes:

[0022] Extract temperature data and precipitation data from season-related data;

[0023] Collect statistics on holiday distribution data;

[0024] Calculate and generate seasonal reference indices;

[0025] The calculation process of the seasonal reference index is:

[0026]

[0027] Where SC is the seasonal reference index, p is the number of seasonal influencing factors, which includes temperature factor I1, precipitation factor I2 and holiday distribution factor I3, p = 3, I k is the k-th seasonal impact factor;

[0028] The temperature factor I1 is determined according to the average temperature t in different seasons. The low temperature threshold is set to 5°C and the comfortable temperature threshold is set to 26°C. When t≤5, I1=0.3; when 5≤t≤26, I1=0.5; when t≥26, I1=0.8;

[0029] The precipitation factor I2 is determined by the real-time precipitation probability r at that time. The low precipitation probability threshold is set to 30%, and the medium precipitation probability threshold is set to 60%. When r≤30, I2=0.2, when 30≤r≤60, I2=0.5, and when t≥60, I2=0.8;

[0030] The holiday distribution factor I3 is determined by the importance of the holiday. When it is a non-holiday, I3=0.5; on weekends and holidays, I3=0.7; and on Spring Festival, Labor Day, and National Day holidays, I3=0.9.

[0031] As a further solution of the present invention, the coordinated adjustment of store inventory based on the delivery reference index and the season reference index specifically includes:

[0032] Get the seasonal reference index SC;

[0033] Calculate and generate quarterly forecast distribution demand D and quarterly inventory turnover rate R;

[0034] The calculation process of the quarterly forecast distribution demand D is:

[0035] D=D h ×(1+g)×(1+SC);

[0036] Where D h is the mean of the delivery volume in the same period of history, g is the growth trend coefficient of the delivery task, which is determined according to the quarterly growth rate of the number of delivery tasks m;

[0037] The low growth rate threshold is preset to 5% and the medium growth rate threshold is preset to 20%. If m≤5, g=0.1; if 5≤m≤20, g=0.2; if m≥20, g=0.3;

[0038] The calculation process of the quarterly inventory turnover rate R is:

[0039]

[0040] In the formula, Q s is the total sales volume for the quarter, I a is the quarterly average inventory;

[0041] Calculate and generate inventory adjustment SI based on the quarterly forecast distribution demand D, quarterly inventory turnover rate R and seasonal reference index SC;

[0042] The calculation process of the inventory adjustment SI is:

[0043]

[0044] As a further solution of the present invention, the generation and allocation of delivery tasks based on the delivery reference index and the season reference index specifically includes:

[0045] Obtain the seasonal reference index SC and the delivery reference index WL;

[0046] Based on the seasonal reference index SC and the distribution reference index WL, calculate and generate the two-way comprehensive index CI;

[0047] The calculation process of the two-way comprehensive index CI is:

[0048] CI = WL + (1 + SC);

[0049] Based on the bidirectional comprehensive index CI, an ascending sequence of delivery personnel is generated;

[0050] Determine the priority delivery personnel based on the ascending order of the delivery personnel.

[0051] As a further solution of the present invention, on the other hand, a system for store and distribution management in the drinking water industry based on artificial intelligence, the system comprising:

[0052] The collection module is used to collect the delivery personnel's historical delivery data, current delivery task data, and season-related data;

[0053] Analysis and extraction module, used to analyze and extract characteristic information from historical delivery data, current delivery task data and season-related data;

[0054] The first generation module is used to generate a distribution reference index and a seasonal reference index;

[0055] Coordinated adjustment module, used to coordinate store inventory based on delivery reference indicators and seasonal reference indicators;

[0056] The second generation module is used to generate and allocate delivery tasks based on the delivery reference index and the season reference index.

[0057] As a further solution of the present invention, the first generating module specifically includes:

[0058] The first extraction unit is used to extract the current day's delivery task duration data, the current day's delivery task quantity data, and the single-day quota working time data from the current delivery task data;

[0059] The first statistical unit is used to count the delivery address distance data, the delivery water weight data, and the delivery time limit data in the current delivery task data;

[0060] The first calculation and generation unit is used to calculate and generate a delivery reference index.

[0061] As a further solution of the present invention, the first generating module specifically further includes:

[0062] The second extraction unit is used to extract temperature data and precipitation data from the season-related data;

[0063] The second statistical unit is used to count holiday distribution data;

[0064] A second calculation and generation unit, used for calculating and generating a seasonal reference index;

[0065] The second extraction unit extracts temperature data and precipitation data from season-related data, the second statistical unit counts holiday distribution data, and the second calculation and generation unit calculates and generates a seasonal reference index. Low temperatures may cause roads to freeze and affect delivery speed, while high temperatures may affect delivery personnel's physical strength and drinking water needs. Precipitation will affect road conditions and delivery efficiency. Delivery demand and traffic conditions usually change during holidays.

[0066] The present invention provides a method and system for store and distribution management in the drinking water industry based on artificial intelligence. The method and system can effectively reduce inventory backlogs and out-of-stock phenomena, reduce inventory costs, and improve capital utilization by accurately adjusting inventory levels in combination with distribution and seasonal factors. It fully considers individual differences of delivery personnel and changes in the external environment, making task allocation more scientific and reasonable, and improving distribution efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a main flow chart of a method for store and distribution management in the drinking water industry based on artificial intelligence.

[0068] Figure 2 The present invention is a flowchart of the first embodiment of a method for store and distribution management in the drinking water industry based on artificial intelligence, which analyzes and extracts characteristic information from historical distribution data, current distribution task data and season-related data to generate a distribution reference index and a season reference index.

[0069] Figure 3The present invention is a flowchart of the second embodiment of a method for store and distribution management in the drinking water industry based on artificial intelligence, which analyzes and extracts characteristic information from historical distribution data, current distribution task data and season-related data to generate a distribution reference index and a season reference index.

[0070] Figure 4 The present invention is a flowchart of collaboratively adjusting store inventory based on distribution reference indicators and seasonal reference indicators in a method of store and distribution management in the drinking water industry based on artificial intelligence.

[0071] Figure 5 The invention relates to a method for store and distribution management in the drinking water industry based on artificial intelligence, which generates a flow chart for allocating distribution tasks based on distribution reference indicators and seasonal reference indicators.

[0072] Figure 6 It is the main structure diagram of a system for store and distribution management in the drinking water industry based on artificial intelligence.

[0073] Figure 7 The present invention is a structural block diagram of the first embodiment of the first generation module in the system of drinking water industry store and distribution management based on artificial intelligence.

[0074] Figure 8 The present invention is a structural block diagram of the second embodiment of the first generation module in the system of store and distribution management in the drinking water industry based on artificial intelligence. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0076] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0077] The present invention provides a method and system for drinking water industry store and distribution management based on artificial intelligence, which solves the technical problems in the background technology.

[0078] like Figure 1 As shown, it is a main flow chart of a method for managing drinking water industry stores and distribution based on artificial intelligence provided by an embodiment of the present invention, and the method for managing drinking water industry stores and distribution based on artificial intelligence includes:

[0079] Step S100: Collect the delivery personnel's historical delivery data, current delivery task data and season-related data;

[0080] Step S200: Analyze and extract characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index;

[0081] Step S300: Coordinately adjust store inventory based on the delivery reference index and the season reference index;

[0082] Step S400: generating and allocating delivery tasks based on the delivery reference index and the season reference index;

[0083] When this embodiment is applied, the historical delivery data, current delivery task data and season-related data of the delivery personnel are collected. For the historical delivery data, information such as delivery time and number of tasks are covered; the current delivery task data includes the delivery address, the amount of water delivered, the delivery time requirements, etc.; the season-related data involves factors such as temperature, precipitation, holidays, etc. Analyze and extract the characteristic information in these data. The delivery reference index and the season reference index are calculated and generated by a specific formula. The delivery reference index comprehensively considers the workload of the delivery personnel, and the season reference index is obtained based on the degree of influence of climate and holidays in different seasons on delivery. Then, the store inventory is coordinated and adjusted based on the delivery reference index and the season reference index. According to the distribution results of the delivery task and the seasonal changes, the inventory adjustment amount is calculated by a quantitative formula to ensure that the store inventory is reasonable under different seasons and delivery requirements, and to ensure that the delivery service is not affected by insufficient inventory or backlog. Generate a delivery task allocation plan based on the delivery reference index and the season reference index, comprehensively consider the current workload and seasonal factors of the delivery personnel, reasonably arrange the work tasks of the delivery personnel, and improve the delivery efficiency and quality.

[0084] like Figure 2 As shown, as a preferred embodiment of the present invention, the analysis and extraction of characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index specifically includes:

[0085] Step S201: extracting the current day's delivery task duration data, the current day's delivery task quantity data, and the single-day quota working time data from the current delivery task data;

[0086] Step S202: Counting the delivery address distance data, the delivery water weight data, and the delivery time limit data in the current delivery task data;

[0087] Step S203: Calculate and generate a delivery reference index;

[0088] The calculation process of the distribution reference index is:

[0089]

[0090] F=D r +Ww +T t ;

[0091] Where WL is the distribution reference index, T i is the duration of the i-th delivery task, n is the number of delivery tasks, H is the daily standard working time, F is the complexity coefficient of the delivery task, Dr is the delivery distance coefficient, Ww is the delivery quality coefficient, and Tt is the delivery time limit coefficient;

[0092] The delivery distance coefficient Dr is determined based on the straight-line distance d between the delivery address and the store. The short-distance threshold is set to 5 kilometers and the medium-distance threshold is set to 10 kilometers. When d≤5, Dr=0.3, when 5≤d≤10, Dr=0.6, when d≥10, Dr=1;

[0093] The distribution quality coefficient Ww is determined according to the total weight w of drinking water distributed in a single time. The light load threshold is set to 50 kg and the medium load threshold is set to 100 kg. When w≤50, Ww=0.2, when 50≤w≤100, Ww=0.5, when w≥100, Ww=0.8;

[0094] The delivery time limit coefficient Tt, if the delivery task has no special time requirements, Tt = 0.5; if the delivery task is completed during a specific peak period, Tt = 0.8; if the delivery task requires delivery within half an hour, Tt = 1.

[0095] When this embodiment is applied, it extracts the current delivery task data, including the day's delivery task duration data, the day's delivery task quantity data, and the daily quota working time data, counts the delivery address distance data, the delivery water weight data, and the delivery time limit data in the current delivery task data, calculates and generates the delivery reference index WL, and introduces the delivery task complexity coefficient F, which is composed of the delivery distance coefficient Dr, the delivery quality coefficient Ww, and the delivery time limit coefficient Tt.

[0096] like Figure 3 As shown, as a preferred embodiment of the present invention, the analysis and extraction of characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index specifically further includes:

[0097] Step S211: extracting temperature data and precipitation data from season-related data;

[0098] Step S212: Counting holiday distribution data;

[0099] Step S213: Calculate and generate a seasonal reference index;

[0100] The calculation process of the seasonal reference index is:

[0101]

[0102] Where SC is the seasonal reference index, p is the number of seasonal influencing factors, which includes temperature factor I1, precipitation factor I2 and holiday distribution factor I3, p = 3, I k is the k-th seasonal impact factor;

[0103] The temperature factor I1 is determined according to the average temperature t in different seasons. The low temperature threshold is set to 5°C and the comfortable temperature threshold is set to 26°C. When t≤5, I1=0.3; when 5≤t≤26, I1=0.5; when t≥26, I1=0.8;

[0104] The precipitation factor I2 is determined by the real-time precipitation probability r at that time. The low precipitation probability threshold is set to 30%, and the medium precipitation probability threshold is set to 60%. When r≤30, I2=0.2, when 30≤r≤60, I2=0.5, and when t≥60, I2=0.8;

[0105] The holiday distribution factor I3 is determined by the importance of the holiday. For non-holidays, I3 = 0.5; for weekend holidays, I3 = 0.7; for Spring Festival, Labor Day, and National Day, I3 = 0.9;

[0106] When this embodiment is applied, the temperature data and precipitation data in the seasonal related data are first extracted, the holiday distribution data is counted, and the seasonal reference index is calculated and generated. The number of seasonal influencing factors includes the temperature factor I1, the precipitation factor I2 and the holiday distribution factor I3. The temperature factor I1 is determined according to the average temperature t in different seasons. The low temperature threshold is set to 5°C and the comfortable temperature threshold is set to 26°C. When t≤5, I1=0.3. Low temperature may cause road icing and affect the delivery speed. When 5≤t≤26, I1=0.5. When t≥26, I1=0.8. High temperature may affect the physical condition of the delivery personnel. power and drinking water demand; precipitation factor I2 is determined by the real-time precipitation probability r at that time, setting the low precipitation probability threshold to 30%, the medium precipitation probability threshold to 60%, when r≤30, I2=0.2, when 30≤r≤60, I2=0.5, when t≥60, I2=0.8, precipitation will affect road conditions and delivery efficiency; holiday distribution factor I3 is determined by the importance of holidays, when it is not a holiday, I3=0.5, weekend holidays, I3=0.7, Spring Festival, Labor Day, National Day holidays, I3=0.9, delivery demand and traffic conditions usually change during holidays.

[0107] like Figure 4 As shown, as a preferred embodiment of the present invention, the coordinated adjustment of store inventory based on the delivery reference index and the season reference index specifically includes:

[0108] Step S301: Obtaining a seasonal reference index SC;

[0109] Step S302: Calculate and generate quarterly forecasted distribution demand D and quarterly inventory turnover rate R;

[0110] The calculation process of the quarterly forecast distribution demand D is:

[0111] D=D h ×(1+g)×(1+SC);

[0112] Where D h is the mean of the delivery volume in the same period of history, g is the growth trend coefficient of the delivery task, which is determined according to the quarterly growth rate of the number of delivery tasks m;

[0113] The low growth rate threshold is preset to 5% and the medium growth rate threshold is preset to 20%. If m≤5, g=0.1; if 5≤m≤20, g=0.2; if m≥20, g=0.3;

[0114] The calculation process of the quarterly inventory turnover rate R is:

[0115]

[0116] In the formula, Q s is the total sales volume for the quarter, I a is the quarterly average inventory;

[0117] Step S303: Calculate and generate inventory adjustment SI based on the quarterly forecasted distribution demand D, the quarterly inventory turnover rate R and the seasonal reference index SC;

[0118] The calculation process of the inventory adjustment SI is:

[0119]

[0120] It should be understood that the seasonal reference index SC is obtained, the quarterly forecast delivery demand D and the quarterly inventory turnover rate R are calculated and generated, the delivery task growth trend coefficient g is introduced in the calculation process of the quarterly forecast delivery demand D, and the low growth rate threshold of 5% and the medium growth rate threshold of 20% are preset. If m≤5, g=0.1, if 5≤m≤20, g=0.2, if m≥20, g=0.3, the quarterly inventory turnover rate R is an indicator to measure the efficiency of store inventory management. Based on the quarterly forecast delivery demand D, the quarterly inventory turnover rate R and the seasonal reference index SC, the inventory adjustment amount SI is calculated and generated, and the inventory amount of the next quarter is appropriately adjusted according to the result of the inventory adjustment amount SI and the preset threshold.

[0121] like Figure 5 As shown, as a preferred embodiment of the present invention, the generation and allocation of distribution tasks based on the distribution reference index and the season reference index specifically includes:

[0122] Step S401: Obtaining a seasonal reference index SC and a delivery reference index WL;

[0123] Step S402: Calculate and generate a bidirectional comprehensive index CI based on the seasonal reference index SC and the delivery reference index WL;

[0124] The calculation process of the two-way comprehensive index CI is:

[0125] CI=WL+(1+SC)

[0126] Step S403: generating a sequence of delivery personnel in ascending order based on the bidirectional comprehensive index CI;

[0127] Step S404: Determine the priority delivery personnel based on the delivery personnel's ascending order sequence.

[0128] When this embodiment is applied, the seasonal reference index SC and the delivery reference index WL are obtained, and based on the seasonal reference index SC and the delivery reference index WL, a two-way comprehensive index CI is calculated and generated, which takes into account both the current work pressure of the delivery person and the impact of seasonal factors on the delivery task. Based on the two-way comprehensive index CI, an ascending sequence of delivery persons is generated. If the comprehensive index CI is smaller, it means that the delivery person is relatively more capable of taking on new delivery tasks under the current workload and seasonal conditions, and the ranking is higher; conversely, the larger the comprehensive index CI, the lower the ranking.

[0129] like Figure 6 As shown, as another preferred embodiment of the present invention, on the other hand, a system for store and distribution management in the drinking water industry based on artificial intelligence, the system comprises:

[0130] Collection module 100, used to collect the historical delivery data, current delivery task data and season-related data of the delivery personnel;

[0131] Analysis and extraction module 200, used to analyze and extract characteristic information from historical delivery data, current delivery task data and season-related data;

[0132] The first generating module 300 is used to generate a delivery reference index and a season reference index;

[0133] A collaborative adjustment module 400, for collaboratively adjusting store inventory based on a delivery reference index and a seasonal reference index;

[0134] The second generation module 500 is used to generate and allocate delivery tasks based on the delivery reference index and the season reference index.

[0135] When this embodiment is applied, the collection module 100 collects the delivery personnel's historical delivery data, current delivery task data and season-related data, the analysis and extraction module 200 analyzes and extracts feature information in the historical delivery data, current delivery task data and season-related data, the first generation module 300 generates a delivery reference index and a season reference index, based on the delivery reference index and the season reference index, the collaborative adjustment module 400 collaboratively adjusts the store inventory, based on the delivery reference index and the season reference index, the second generation module 500 generates and allocates delivery tasks.

[0136] like Figure 7 As shown, as another preferred embodiment of the present invention, the first generating module 300 specifically includes:

[0137] The first extraction unit 301 is used to extract the delivery task duration data, the delivery task quantity data and the daily quota working time data of the current delivery task data;

[0138] The first statistical unit 302 is used to count the delivery address distance data, the delivery water weight data, and the delivery time limit data in the current delivery task data;

[0139] The first calculation and generation unit 303 is used to calculate and generate a delivery reference index.

[0140] When this embodiment is applied, the first extraction unit 301 obtains the day's delivery task duration data, the day's delivery task quantity data and the single-day quota working time data in the current delivery task data, the first statistical unit 302 counts the delivery address distance data, the delivery water weight data, and the delivery time limit data in the current delivery task data, and the first calculation generation unit 303 calculates and generates a delivery reference index.

[0141] like Figure 8 As shown, as another preferred embodiment of the present invention, the first generating module 300 specifically further includes:

[0142] The second extraction unit 311 is used to extract temperature data and precipitation data from the season-related data;

[0143] The second statistical unit 312 is used to count holiday distribution data;

[0144] The second calculation and generation unit 313 is used to calculate and generate a seasonal reference index.

[0145] When this embodiment is applied, the second extraction unit 311 extracts temperature data and precipitation data from season-related data, the second statistical unit 312 counts holiday distribution data, and the second calculation and generation unit 313 calculates and generates a seasonal reference index. Low temperatures may cause roads to freeze and affect delivery speed, high temperatures may affect the delivery staff's physical strength and drinking water needs, precipitation will affect road conditions and delivery efficiency, and delivery demand and traffic conditions will usually change during holidays.

[0146] In the above embodiment of the present invention, a method for store and distribution management of the drinking water industry based on artificial intelligence is provided, and a system for store and distribution management of the drinking water industry based on artificial intelligence is provided, which collects historical distribution data, current distribution task data and season-related data of the delivery personnel. For historical distribution data, information such as distribution time and number of tasks is covered; current distribution task data includes distribution address, distribution water volume, distribution time requirements, etc.; season-related data involves factors such as temperature, precipitation, holidays, etc. Analyze and extract the characteristic information in these data. The distribution reference index and the season reference index are calculated and generated by a specific formula. The distribution reference index comprehensively considers the workload of the delivery personnel, and the season reference index is obtained based on the degree of influence of climate and holidays on distribution in different seasons. Then, the store inventory is coordinated and adjusted based on the distribution reference index and the season reference index. According to the distribution task allocation results and seasonal changes, the inventory adjustment amount is calculated by a quantitative formula to ensure that the store inventory is reasonable under different seasons and distribution needs, and to ensure that the distribution service is not affected by insufficient inventory or backlog. A distribution task allocation plan is generated based on distribution reference indicators and seasonal reference indicators, and the current workload of the delivery personnel and seasonal factors are comprehensively considered to reasonably arrange the work tasks of the delivery personnel and improve the distribution efficiency and quality. This method and system can effectively reduce inventory backlogs and out-of-stock phenomena, reduce inventory costs, and improve capital utilization by accurately adjusting inventory levels based on distribution and seasonal factors. It fully considers the individual differences of delivery personnel and changes in the external environment, making task allocation more scientific and reasonable and improving distribution efficiency and accuracy.

[0147] In order to load the above-mentioned method and system and enable it to run smoothly, the system, in addition to the various modules mentioned above, may also include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, processors and memories, etc.

[0148] The processor may be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the system, and various interfaces and lines are used to connect various parts.

[0149] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0151] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for store and distribution management in the drinking water industry based on artificial intelligence, characterized in that: The method comprises: Collect the delivery personnel's historical delivery data, current delivery task data, and season-related data; Analyze and extract characteristic information from historical delivery data, current delivery task data, and season-related data to generate delivery reference index and season reference index; Coordinate and adjust store inventory based on delivery reference indicators and seasonal reference indicators; Generate and allocate delivery tasks based on delivery reference indicators and seasonal reference indicators.

2. The method for drinking water industry store and distribution management based on artificial intelligence according to claim 1 is characterized in that: The analysis and extraction of characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index specifically includes: Extract the current delivery task data including the delivery task duration data, the delivery task quantity data and the daily quota working time data. Collect data on the distance to the delivery address, the weight of the water delivered, and the time limit for delivery in the current delivery task data; Calculate and generate delivery reference index; The calculation process of the distribution reference index is: F=D r +W w +T t ; Where WL is the distribution reference index, T i is the duration of the i-th delivery task, n is the number of delivery tasks, H is the daily standard working time, F is the complexity coefficient of the delivery task, Dr is the delivery distance coefficient, Ww is the delivery quality coefficient, and Tt is the delivery time limit coefficient; The delivery distance coefficient Dr is determined based on the straight-line distance d between the delivery address and the store. The short-distance threshold is set to 5 kilometers and the medium-distance threshold is set to 10 kilometers. When d≤5, Dr=0.3, when 5≤d≤10, Dr=0.6, when d≥10, Dr=1; The distribution quality coefficient Ww is determined according to the total weight w of drinking water distributed in a single time. The light load threshold is set to 50 kg and the medium load threshold is set to 100 kg. When w≤50, Ww=0.2, when 50≤w≤100, Ww=0.5, when w≥100, Ww=0.8; The delivery time limit coefficient Tt, if the delivery task has no special time requirements, Tt = 0.5; if the delivery task is completed during a specific peak period, Tt = 0.8; if the delivery task requires delivery within half an hour, Tt = 1.

3. The method for drinking water industry store and distribution management based on artificial intelligence according to claim 1 is characterized in that: The analyzing and extracting characteristic information from historical delivery data, current delivery task data and season-related data to generate a delivery reference index and a season reference index specifically includes: Extract temperature data and precipitation data from season-related data; Collect statistics on holiday distribution data; Calculate and generate seasonal reference indices; The calculation process of the seasonal reference index is: Where SC is the seasonal reference index, p is the number of seasonal influencing factors, which includes temperature factor I1, precipitation factor I2 and holiday distribution factor I3, p = 3, I k is the k-th seasonal impact factor; The temperature factor I1 is determined according to the average temperature t in different seasons. The low temperature threshold is set to 5°C and the comfortable temperature threshold is set to 26°C. When t≤5, I1=0.3; when 5≤t≤26, I1=0.5; when t≥26, I1=0.8; The precipitation factor I2 is determined by the real-time precipitation probability r at that time. The low precipitation probability threshold is set to 30%, and the medium precipitation probability threshold is set to 60%. When r≤30, I2=0.2, when 30≤r≤60, I2=0.5, and when t≥60, I2=0.8; The holiday distribution factor I3 is determined by the importance of the holiday. When it is a non-holiday, I3=0.5; on weekends and holidays, I3=0.7; and on Spring Festival, Labor Day, and National Day holidays, I3=0.

9.

4. The method for drinking water industry store and distribution management based on artificial intelligence according to claim 1 is characterized in that: The coordinated adjustment of store inventory based on the distribution reference index and the seasonal reference index specifically includes: Get the seasonal reference index SC; Calculate and generate quarterly forecast distribution demand D and quarterly inventory turnover rate R; The calculation process of the quarterly forecast distribution demand D is: D=D h ×(1+g)×(1+SC); Where D h is the mean of the delivery volume in the same period of history, g is the growth trend coefficient of the delivery task, which is determined according to the quarterly growth rate of the number of delivery tasks m; The low growth rate threshold is preset to 5% and the medium growth rate threshold is preset to 20%. If m≤5, g=0.1; if 5≤m≤20, g=0.2; if m≥20, g=0.3; The calculation process of the quarterly inventory turnover rate R is: In the formula, Q s is the total sales volume for the quarter, I a is the quarterly average inventory; Calculate and generate inventory adjustment SI based on quarterly forecast distribution demand D, quarterly inventory turnover rate R and seasonal reference index SC; The calculation process of the inventory adjustment SI is:

5. The method for drinking water industry store and distribution management based on artificial intelligence according to claim 1 is characterized in that: The generation and allocation of distribution tasks based on the distribution reference index and the season reference index specifically includes: Obtain the seasonal reference index SC and the delivery reference index WL; Based on the seasonal reference index SC and the distribution reference index WL, calculate and generate the two-way comprehensive index CI; The calculation process of the two-way comprehensive index CI is: CI = WL + (1 + SC); Based on the bidirectional comprehensive index CI, an ascending sequence of delivery personnel is generated; Determine the priority delivery personnel based on the ascending order of the delivery personnel.

6. A system for drinking water industry store and distribution management based on artificial intelligence, characterized in that: The method for store and distribution management in the drinking water industry based on artificial intelligence as described in any one of claims 1 to 5 is applied, and the system comprises: The collection module is used to collect the historical delivery data, current delivery task data and season-related data of the delivery personnel; Analysis and extraction module, used to analyze and extract characteristic information from historical delivery data, current delivery task data and season-related data; The first generation module is used to generate a distribution reference index and a season reference index; Coordinated adjustment module, used to coordinate store inventory based on delivery reference indicators and seasonal reference indicators; The second generation module is used to generate and allocate delivery tasks based on the delivery reference index and the season reference index.

7. The system for drinking water industry store and distribution management based on artificial intelligence according to claim 6 is characterized in that: The first generation module specifically includes: The first extraction unit is used to extract the current day's delivery task duration data, the current day's delivery task quantity data, and the single-day quota working time data from the current delivery task data; The first statistical unit is used to count the delivery address distance data, the delivery water weight data, and the delivery time limit data in the current delivery task data; The first calculation and generation unit is used to calculate and generate a delivery reference index.

8. The system for drinking water industry stores and distribution management based on artificial intelligence according to claim 6 is characterized in that: The first generation module specifically includes: The second extraction unit is used to extract temperature data and precipitation data from the season-related data; The second statistical unit is used to count holiday distribution data; The second calculation and generation unit is used to calculate and generate a seasonal reference index.

Images