A method, device and computer equipment for generating a stocking strategy for Chinese herbal medicine pieces

Abstract

The present invention relates to the technical field of big data analysis, and discloses a method, device and computer equipment for generating a stocking strategy for Chinese herbal medicine slices. Through the invention, a stocking strategy generation scheme that can help the operation of a Chinese herbal medicine slice sales platform is provided, that is, after obtaining the historical sales data recorded by the Chinese herbal medicine slice sales platform, the predicted purchase demand of each customer in each unit area in each unit period of the next year can be accurately estimated based on the data fitting method, and then the predicted purchase demand of all customers in all regions is summarized to generate a strategy for the Chinese herbal medicine slice sales platform to stock various categories of slices in each unit period of the next year. In this way, based on the analysis of user behavior, combined with the medication characteristics and periodic purchase changes of Chinese herbal medicine slices in different regions, the inventory turnover rate of the Chinese herbal medicine slice sales platform can be improved, and the capital occupation rate and capital cost can be reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data analysis, and specifically relates to a method, device and computer equipment for generating a stocking strategy for Chinese herbal medicine slices. Background Art

[0002] Chinese herbal medicine slices are Chinese herbal medicines that have been processed and prepared according to the theory of traditional Chinese medicine and the processing methods of traditional Chinese medicine, and can be directly used in clinical Chinese medicine. This concept shows that there is no absolute boundary between Chinese herbal medicines and Chinese herbal medicine slices. Chinese herbal medicine slices include some Chinese herbal medicine slices processed at the place of origin, original herbal medicine slices, and slices that have been cut and processed. The first two categories should be regarded as Chinese herbal medicines in management, but they are understood as slices in the formula and preparation according to the theory of traditional Chinese medicine.

[0003] Due to the inherent characteristics of Chinese herbal medicines and the different medication habits in different provinces, customers in different regions will have different purchasing preferences, and will also be affected by the seasons, showing a trend of overall cyclical changes in purchasing. At present, when customers (such as clinics and pharmacies) purchase Chinese herbal medicines on the Chinese herbal medicine sales platform, they will purchase based on their own experience, inventory and platform activities. It is easy to make inaccurate estimates and lead to excessive stockpiling, which will not be digested for a long time. The same situation will also affect the platform's large-scale procurement, resulting in inaccurate estimates of customer purchasing needs, resulting in reduced inventory turnover and capital occupation. Summary of the invention

[0004] In order to solve the problems of low inventory turnover rate and high capital occupation rate in the existing Chinese herbal medicine slice sales platform due to inaccurate prediction of customer purchasing demand, the purpose of the present invention is to provide a method, device, computer equipment and computer-readable storage medium for generating a Chinese herbal medicine slice stocking strategy, which can help improve the inventory turnover rate of the Chinese herbal medicine slice sales platform and reduce capital occupation rate and capital cost based on user behavior analysis and combined with the medication characteristics and periodic purchasing changes of Chinese herbal medicine slices in different regions.

[0005] In a first aspect, the present invention provides a method for generating a stocking strategy for Chinese herbal medicine pieces, comprising:

[0006] Obtaining historical sales data recorded by the Chinese herbal medicine piece sales platform, wherein the historical sales data contains all completed purchase orders, and the purchase order contains the purchase order number, customer identification, herbal medicine piece category identification, delivery address, purchase timestamp and purchase quantity;

[0007] According to the historical sales data, the single-period purchase frequency and single average purchase volume of various types of herbal medicine pieces by each customer in each unit area in each unit period of each year are obtained;

[0008] For each customer in each unit region, according to the corresponding single-period purchase frequency for each type of medicinal slices in each unit period of all years, a first functional relationship between the corresponding single-period purchase frequency for each type of medicinal slices in each unit period and the variable year is obtained by data fitting, and according to the corresponding single average purchase volume for each type of medicinal slices in each unit period of all years, a second functional relationship between the corresponding single average purchase volume for each type of medicinal slices in each unit period and the variable year is obtained by data fitting;

[0009] For each customer in each unit region, a single-period purchase frequency forecast value for each type of herbal medicine piece in each unit period of the next year is estimated based on the corresponding first functional relationship, and a single average purchase volume forecast value for each type of herbal medicine piece in each unit period of the next year is estimated based on the corresponding second functional relationship;

[0010] The first total purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula:

[0011]

[0012] Where, PD ns It represents the total first purchase demand for the sth type of herbal medicine category in the nth unit period of the next year, n is a positive integer and n∈[1,N], N represents the total number of unit periods in a year, s is a positive integer and s∈[1,S], S represents the total number of all herbal medicine category identifiers in all purchase orders, i is a positive integer and i∈[1,I], I represents the total number of districts in all unit areas, and all unit areas are determined according to all delivery addresses in all purchase orders, j is a positive integer and j∈[1,J i ], J i represents the total number of all customer IDs in all purchase orders in a certain region, where the purchase orders in a certain region refer to purchase orders where the delivery address belongs to the i-th unit region, represents the predicted value of the single-period purchase frequency of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year, The predicted value of the average single purchase volume of the s-th type of herbal medicine by the j-th customer in the ith unit area in the n-th unit period of the next year;

[0013] According to the first purchase demand total PD nsThe estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year.

[0014] Based on the above invention content, a stocking strategy generation scheme is provided to assist the operation of a Chinese herbal medicine slice sales platform, that is, after obtaining the historical sales data recorded by the Chinese herbal medicine slice sales platform, the predicted purchasing demand value for various herbal medicine slice categories by each customer in each unit region in each unit period of the next year can be accurately estimated based on the data fitting method, and then the predicted purchasing demand value of all customers in all regions is summarized to generate a stocking strategy for various herbal medicine slice categories by the Chinese herbal medicine slice sales platform in each unit period of the next year. In this way, based on the user behavior analysis, combined with the medication characteristics and periodic purchasing changes of Chinese herbal medicine slices in different regions, it can help improve the inventory turnover rate of the Chinese herbal medicine slice sales platform and reduce capital occupancy rate and capital cost.

[0015] In a possible design, according to the first procurement demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including:

[0016] The first purchase demand amount PD ns The product of the preset coefficient δ is used as the target value for the Chinese herbal medicine selling platform to stock the sth type of herbal medicine category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

[0017] In a possible design, after obtaining the historical sales data recorded by the Chinese herbal medicine slice sales platform, the method further includes:

[0018] According to the historical sales data, the average household purchase volume of various types of herbal medicine pieces in each unit area in each unit period of each year is obtained;

[0019] For each unit region, according to the corresponding average household purchase volume for each type of decoction pieces in each unit period of all years, a third functional relationship between the corresponding average household purchase volume for each type of decoction pieces in each unit period and the variable year is obtained by data fitting;

[0020] For each unit area, estimate the predicted value of the average household purchase volume for each type of herbal medicine in each unit period of the next year according to the corresponding third functional relationship;

[0021] The second total purchase demand for the various types of decoction pieces in each unit period of the next year is estimated according to the following formula:

[0022]

[0023] In the formula, represents the total second purchase demand for the sth type of herbal medicine in the nth unit period of the next year, It represents the predicted value of the average household purchase volume of the s-th type of medicinal materials in the ith unit area in the n-th unit period of the next year.

[0024] In a possible design, according to the first procurement demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including:

[0025] The total amount of PD required in the first procurement ns and the second total purchase demand The product of the maximum value, middle value, average value or minimum value in and the preset coefficient δ is used as the target value for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

[0026] In a possible design, after obtaining statistics on the single-period purchase frequency of various types of decoction pieces by each customer in each unit area in each unit period of each year based on the historical sales data, the method further includes:

[0027] For each customer in each unit area, according to the corresponding single-period purchase frequency for each type of medicinal slices in the most recent X unit periods, the corresponding recent purchase preference type for each type of medicinal slices is obtained, wherein X is a positive integer not less than N, and the recent purchase preference type includes a frequently purchased type, a periodic interval purchase type, and a non-purchase type. The frequently purchased type indicates that for a certain type of medicinal slices, each single-period purchase frequency in the corresponding X single-period purchase frequencies is not less than 1, and the periodic interval purchase type indicates that for a certain type of medicinal slices, the single-period purchase frequency with an average interval of Y unit periods in the corresponding X single-period purchase frequencies is not less than 1, and Y is a real number and has The non-purchase type means that for a certain type of herbal medicine, the purchase frequency of each single period in the corresponding X single-period purchase frequencies is less than 1;

[0028] After estimating the predicted value of the average household purchase volume for each type of decoction piece in each unit period of the next year according to the corresponding third functional relationship for each unit area, the method further includes:

[0029] The total third purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula:

[0030]

[0031] In the formula, represents the total third purchase demand for the sth type of herbal medicine in the nth unit period of the next year, represents the predicted value of the average household purchase volume of the s-th type of decoction piece category in the ith unit area in the n-th unit period of the next year, η ijs represents the purchase probability of the jth customer in the i-th unit area for the s-th type of decoction piece category in each period. When the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the frequently purchased type, η ijs =1, and when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of herbal medicine is a periodic interval purchase type, Y ijs represents the average interval Y value of the jth customer in the i-th unit area for the s-th type of decoction piece category, and when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the non-purchase type, η ijs =0;

[0032] According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including:

[0033] The total amount of PD required in the first procurement ns and the third procurement demand The product of the maximum value, middle value, average value or minimum value in and the preset coefficient δ is used as the target value for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

[0034] In a possible design, after obtaining statistics on the single-period purchase frequency of various types of decoction pieces by each customer in each unit area in each unit period of each year based on the historical sales data, the method further includes:

[0035] For each customer in each unit region, according to the corresponding single-period purchase frequency for each type of decoction piece in each unit period of each year, the corresponding single-period purchase preference type for each type of decoction piece in each unit period of each year is obtained, wherein when the value of the single-period purchase preference type is 1, it means that for a certain type of decoction piece, the corresponding single-period purchase frequency is not less than 1, and when the value is 0, it means that for the certain type of decoction piece, the corresponding single-period purchase frequency is equal to 0;

[0036] For each customer in each unit region, according to the corresponding single-period purchase preference type for each type of decoction piece in each unit period of all years, a fourth functional relationship between the corresponding single-period purchase preference type for each type of decoction piece in each unit period and the variable year is obtained by data fitting;

[0037] For each customer in each unit area, estimate the predicted value of the single-period purchase preference type for each type of herbal medicine in each unit period of the next year according to the corresponding fourth functional relationship;

[0038] After estimating the predicted value of the average household purchase volume for each type of decoction piece in each unit period of the next year according to the corresponding third functional relationship for each unit area, the method further includes:

[0039] The fourth total purchase demand for the various types of decoction pieces in each unit period of the next year is estimated according to the following formula:

[0040]

[0041] In the formula, represents the fourth total purchase demand for the sth type of herbal medicine in the nth unit period of the next year, represents the predicted value of the average household purchase volume of the sth type of herbal medicine in the ith unit area in the nth unit period of the next year, u ijns represents the single-period purchase preference type prediction value of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year;

[0042] According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including:

[0043] The first purchase demand amount PD ns The product of the fourth purchase demand is used as the target value for the Chinese medicine slice sales platform to prepare the sth type of slices in the nth unit period of the next year, and the fourth purchase demand total ... as the minimum value for the Chinese herbal medicine selling platform to stock the sth type of herbal medicine category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

[0044] In one possible design, the unit area is a provincial or municipal area, and the unit period is a month or a quarter.

[0045] In a second aspect, the present invention provides a device for generating a stocking strategy for Chinese herbal medicine pieces, comprising a data acquisition module, a data statistics module, a data fitting module, a numerical estimation module, a demand estimation module and a strategy generation module which are sequentially connected in communication;

[0046] The data acquisition module is used to acquire the historical sales data recorded by the Chinese herbal medicine slice sales platform, wherein the historical sales data contains all the purchase orders that have been completed, and the purchase orders contain the purchase order number, customer identification, herbal medicine slice category identification, delivery address, purchase timestamp and purchase quantity;

[0047] The data statistics module is used to obtain, based on the historical sales data, the single-period purchase frequency and the single average purchase volume of each customer in each unit area for each unit period of each year for various types of decoction pieces;

[0048] The data fitting module is used for obtaining, for each customer in each unit region, a first functional relationship between the single-period procurement frequency for each type of medicinal slices and the variable year in each unit period according to the corresponding single-period procurement frequency for each type of medicinal slices in each unit period of all years, and a second functional relationship between the single average procurement volume for each type of medicinal slices and the variable year in each unit period according to the corresponding single average procurement volume for each type of medicinal slices in each unit period of all years;

[0049] The numerical estimation module is used to estimate, for each customer in each unit area, the single-period purchase frequency forecast value for each type of decoction piece in each unit period of the next year according to the corresponding first functional relationship, and to estimate, for each customer in each unit area, the single-period purchase frequency forecast value for each type of decoction piece in each unit period of the next year according to the corresponding second functional relationship;

[0050] The demand estimation module is used to estimate the total first purchase demand for the various types of decoction pieces in each unit period of the next year according to the following formula:

[0051]

[0052] Where, PD ns It represents the total first purchase demand for the sth type of herbal medicine category in the nth unit period of the next year, n is a positive integer and n∈[1,N], N represents the total number of unit periods in a year, s is a positive integer and s∈[1,S], S represents the total number of all herbal medicine category identifiers in all purchase orders, i is a positive integer and i∈[1,I], I represents the total number of districts in all unit areas, and all unit areas are determined according to all delivery addresses in all purchase orders, j is a positive integer and j∈[1,J i ], J i represents the total number of all customer IDs in all purchase orders in a certain region, where the purchase orders in a certain region refer to purchase orders where the delivery address belongs to the i-th unit region, represents the predicted value of the single-period purchase frequency of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year, The predicted value of the average single purchase volume of the s-th type of herbal medicine by the j-th customer in the ith unit area in the n-th unit period of the next year;

[0053] The strategy generation module is used to generate a strategy based on the first purchase demand total amount PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year.

[0054] In a third aspect, the present invention provides a computer device comprising a memory and a processor that are communicatively connected, wherein the memory is used to store a computer program, and the processor is used to read the computer program to execute the method for generating a stocking strategy for Chinese herbal medicines as described in the first aspect or any possible design of the first aspect.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, executes the method for generating a stocking strategy for Chinese herbal medicines as described in the first aspect or any possible design of the first aspect.

[0056] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the method for generating a stocking strategy for Chinese herbal medicines as described in the first aspect or any possible design of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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.

[0058] Figure 1 It is a flow chart of the method for generating a stocking strategy for Chinese herbal medicine pieces provided by the present invention.

[0059] Figure 2 It is a structural schematic diagram of a Chinese herbal medicine stocking strategy generation device provided by the present invention.

[0060] Figure 3 It is a structural schematic diagram of the computer device provided by the present invention. DETAILED DESCRIPTION

[0061] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be noted that although the description of these embodiments is used to help understand the present invention, it does not constitute a limitation of the present invention. The specific structures and functional details disclosed herein are only used to describe the embodiments of the present invention. However, the present invention can be embodied in many alternative forms, and it should not be understood that the present invention is limited to the embodiments set forth herein.

[0062] It should be understood that although the terms first and second, etc. may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another object. For example, a first object can be referred to as a second object, and similarly, a second object can be referred to as a first object without departing from the scope of the exemplary embodiments of the present invention.

[0063] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that there may be three relationships. For example, A and / or B can represent three situations: A exists alone, B exists alone, or A and B exist at the same time; the term " / and" that may appear in this article describes another type of association object relationship, indicating that there may be two relationships. For example, A / and B can represent two situations: A exists alone or A and B exist at the same time; in addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0064] like Figure 1 As shown, the method for generating a stocking strategy for Chinese herbal medicine slices provided in the first aspect of this embodiment can be executed, but is not limited to, by a computer device with certain computing resources, such as a personal computer (PC, referring to a multi-purpose computer with a size, price and performance suitable for personal use; desktops, laptops, small laptops, tablets and ultrabooks are all personal computers), smart phones, personal digital assistants (PAD), wearable devices or platform servers and other electronic devices, so that after obtaining the historical sales data recorded by the Chinese herbal medicine slice sales platform, the purchase demand forecast value of each customer in each unit area in each unit period of the next year can be accurately estimated based on the data fitting method, and then the purchase demand forecast value of all customers in all regions is summarized to generate a stocking strategy for various herbal medicine slice categories in each unit period of the next year by the Chinese herbal medicine slice sales platform. In this way, based on the analysis of user behavior, combined with the drug use characteristics and periodic purchase changes of Chinese herbal medicine slices in different regions, it can help improve the inventory turnover rate of the Chinese herbal medicine slice sales platform and reduce capital occupancy rate and capital cost. Figure 1 As shown, the method for generating a stocking strategy for Chinese herbal medicine pieces may include, but is not limited to, the following steps S1 to S6.

[0065] S1. Obtain the historical sales data recorded by the Chinese herbal medicine sales platform, wherein the historical sales data includes but is not limited to information such as all completed purchase orders, and the purchase order includes but is not limited to the purchase order number, customer identification, herbal medicine category identification, delivery address, purchase timestamp and purchase quantity.

[0066] In step S1, the Chinese herbal medicine slices selling platform is a commercial platform operated by Chinese herbal medicine slices wholesalers and used for wholesale sales of various Chinese herbal medicine slices. It can be specifically a network platform server, so that in the process of responding to customers placing orders for Chinese herbal medicine slices, the corresponding purchase order and other information can be automatically recorded. The historical sales data truly records the historical purchases of platform customers through purchase orders. Specifically, in the content of the purchase order, the purchase order number is used to uniquely mark the purchase order, the customer identifier is used to uniquely mark the customer who places an order for purchase, the slice category identifier is used to uniquely mark the category of the Chinese herbal medicine slices ordered for purchase, the delivery address is used to achieve the purpose of shipping and can be used to reflect the region to which the ordering customer belongs, the purchase timestamp is used to record the time of occurrence of the order event and can be used to reflect the purchase period, and the purchase quantity is used to reflect the demand level of the ordering customer for Chinese herbal medicine slices, which can be but not limited to SKU (Stock Keeping Unit) as the unit. In detail, the purchase order can also record a specific Chinese herbal medicine slice identifier to uniquely mark the Chinese herbal medicine slices ordered for purchase. In addition, the historical sales data can be obtained through conventional data import / access methods.

[0067] S2. Based on the historical sales data, statistics are obtained on the single-period purchase frequency and single average purchase volume of various types of herbal medicines by each customer in each unit area in each unit period of each year.

[0068] In step S2, the unit area can be, but is not limited to, a provincial jurisdiction or a municipal jurisdiction, such as Sichuan Province / Chongqing City / Southwest China, and the unit period can be, but is not limited to, a month or a quarter, such as June / summer. Therefore, the single-period purchase frequency can be exemplified by the number of orders placed by customer A in Sichuan Province for Category A of medicinal slices in December 2019 (i.e., the single-period purchase frequency in that month), and the single average purchase quantity can be exemplified by the average purchase quantity of each order placed by customer A in Sichuan Province for Category A of medicinal slices in December 2019, that is, if three orders are placed and the purchase quantities are 100 SKU, 200 SKU, and 300 SKU respectively, then the single average purchase quantity in that month is 200 SKU. Since each of the purchase orders contains in detail the purchase order number, customer ID, medicinal material category ID, delivery address, purchase timestamp and purchase quantity, the single-period purchase frequency and the single average purchase volume for various medicinal material categories by each customer in each unit area in each unit period of each year can be calculated by conventional statistical methods.

[0069] S3. For each customer in each unit area, according to the corresponding single-period purchasing frequency for each type of medicinal slices in each unit period of all years, the first functional relationship between the corresponding single-period purchasing frequency for each type of medicinal slices in each unit period and the variable year is obtained by data fitting method, and according to the corresponding single average purchasing volume for each type of medicinal slices in each unit period of all years, the second functional relationship between the corresponding single average purchasing volume for each type of medicinal slices in each unit period and the variable year is obtained by data fitting method.

[0070] In step S3, for example, for customer A in Sichuan Province, according to the corresponding single-period purchase frequency of medicinal slice category A in December from 2001 to 2021 (i.e., a total of 21 data), the first functional relationship between the corresponding single-period purchase frequency of medicinal slice category A in December and the variable year can be obtained through data fitting. Similarly, for customer A in Sichuan Province, according to the corresponding single average purchase volume of medicinal slice category A in December from 2001 to 2021 (i.e., a total of 21 data), the second functional relationship between the corresponding single average purchase volume of medicinal slice category A in December and the variable year can be obtained through data fitting. In addition, the data fitting method is a commonly used representation method of substituting existing data into a mathematical formula through mathematical methods, such as using a straight line fitting method or a polynomial curve fitting method.

[0071] S4. For each customer in each unit area, the forecast value of the single-period purchase frequency for each type of medicinal material in each unit period of the next year is estimated based on the corresponding first functional relationship, and the forecast value of the single average purchase volume for each type of medicinal material in each unit period of the next year is estimated based on the corresponding second functional relationship.

[0072] In step S4, for example, for customer A in Sichuan Province, based on the corresponding first functional relationship between the single-period purchase frequency of slice category A in December and the variable year, the predicted value of the single-period purchase frequency of slice category A in December of the next year (for example, 2022 after 2021) can be estimated. Similarly, for customer A in Sichuan Province, based on the corresponding second functional relationship between the single average purchase volume of slice category A in December and the variable year, the predicted value of the single average purchase volume of slice category A in December of the next year (for example, 2022 after 2021) can be estimated.

[0073] S5. The first total purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula:

[0074]

[0075] Where, PD ns It represents the total first purchase demand for the sth type of herbal medicine category in the nth unit period of the next year, n is a positive integer and n∈[1,N], N represents the total number of unit periods in a year, s is a positive integer and s∈[1,S], S represents the total number of all herbal medicine category identifiers in all purchase orders, i is a positive integer and i∈[1,I], I represents the total number of districts in all unit areas, and all unit areas are determined according to all delivery addresses in all purchase orders, j is a positive integer and j∈[1,J i ], J i represents the total number of all customer IDs in all purchase orders in a certain region, where the purchase orders in a certain region refer to purchase orders where the delivery address belongs to the i-th unit region, represents the predicted value of the single-period purchase frequency of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year, It represents the predicted value of the average single purchase volume of the s-th type of medicinal materials by the j-th customer in the ith unit area in the n-th unit period of the next year.

[0076] In step S5, if the unit period is a month, the value of N is 12, and if the unit period is a quarter, the value of N is 4. If the unit area is a provincial jurisdiction, the value of I is at most 34. Since the single-period purchase frequency forecast value of the jth customer in the i-th unit area for the s-th herbal medicine category in the n-th unit period of the next year has been estimated And the average purchase volume forecast value So calculate The predicted value of the purchasing demand for the s-th type of medicinal materials by the j-th customer in the ith unit region in the n-th unit period of the next year can be obtained, and then the predicted values ​​of the purchasing demand of all customers in all regions can be summarized to estimate the total purchasing demand for the s-th type of medicinal materials in the n-th unit period of the next year.

[0077] S6. Based on the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year.

[0078] In the step S6, specifically, the strategy for preparing the stock of the s-th type of Chinese medicine slices for the n-th unit period of the next year on the Chinese medicine slices selling platform may be generated in the following manner, but is not limited to: ns The product of the preset coefficient δ is used as the target value for the Chinese herbal medicine slice sales platform to prepare the sth herbal medicine slice category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3]. The specific value of the preset coefficient δ can be specifically determined according to factors such as the sales activity plan of the Chinese herbal medicine slice and the characteristics of the medicine.

[0079] Therefore, based on the method for generating a stocking strategy for Chinese herbal medicines described in the aforementioned steps S1 to S6, a stocking strategy generation scheme is provided that can assist the operation of a Chinese herbal medicine sales platform, that is, after obtaining the historical sales data recorded by the Chinese herbal medicine sales platform, the predicted purchasing demand for various types of medicines in each unit period of the next year by each customer in each unit region can be accurately estimated based on the data fitting method, and then the predicted purchasing demand values ​​of all customers in all regions are summarized to generate a stocking strategy for various types of medicines in each unit period of the next year by the Chinese herbal medicine sales platform. In this way, based on user behavior analysis, combined with the medication characteristics and periodic purchasing changes of Chinese herbal medicines in different regions, it can help improve the inventory turnover rate of the Chinese herbal medicine sales platform and reduce capital occupancy rate and capital cost.

[0080] Based on the technical solution of the first aspect mentioned above, this embodiment also provides a possible design for estimating the total purchase demand from another perspective. That is, after obtaining the historical sales data recorded by the Chinese herbal medicine sales platform, the method also includes but is not limited to the following steps S20 to S50.

[0081] S20. Based on the historical sales data, the average household purchase volume of various types of herbal medicines in each unit area in each unit period of each year is obtained.

[0082] In step S20, the average household purchase volume can be exemplified as the average purchase volume per customer for the decoction piece category A in Sichuan Province in December 2019, that is, if the total purchase volume of the decoction piece category A in Sichuan Province in December 2019 is 1 million SKUs, and there are 5,000 customers in Sichuan Province who have order purchase records on the Chinese medicine decoction piece sales platform, then the average household purchase volume is 200 SKUs. Since each of the purchase orders in all the purchase orders contains the purchase order number, customer ID, decoction piece category ID, delivery address, purchase timestamp, purchase quantity and other contents in detail, the average household purchase volume for various decoction piece categories in each unit period of each year in each unit region can be calculated by conventional statistical methods.

[0083] S30. For each unit area, according to the corresponding average household purchasing volume for each type of medicinal material in each unit period of all years, a third functional relationship between the corresponding average household purchasing volume for each type of medicinal material in each unit period and the variable year is obtained through data fitting.

[0084] In step S30, for example, for Sichuan Province, according to the corresponding average household purchase volume of decoction piece category A in December from 2001 to 2021 (i.e., a total of 21 data), the corresponding third functional relationship between the average household purchase volume of decoction piece category A in December and the variable year can be obtained through data fitting. In addition, the specific data fitting method can also be but not limited to a straight line fitting method or a polynomial curve fitting method.

[0085] S40. For each unit area, estimate the predicted value of the average household purchase volume for each type of medicinal material in each unit period of the next year based on the corresponding third functional relationship.

[0086] In step S40, also taking an example, for Sichuan Province, based on the corresponding third functional relationship between the average household purchase volume of medicinal material category A in December and the variable year, the predicted value of the average household purchase volume of medicinal material category A in December of the next year (for example, 2022 after 2021) can be estimated.

[0087] S50. The second total purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula:

[0088]

[0089] In the formula, represents the total second purchase demand for the sth type of herbal medicine in the nth unit period of the next year, It represents the predicted value of the average household purchase volume of the s-th type of medicinal materials in the ith unit area in the n-th unit period of the next year.

[0090] In step S50, since the predicted value of the average purchase volume per household It reflects the predicted value of the average household purchasing demand for the s-th type of medicinal materials in the i-th unit region in the n-th unit period of the next year, and then summarizes the predicted value of the average household purchasing demand for all customers in all regions, so as to estimate the total purchasing demand for the s-th type of medicinal materials in the n-th unit period of the next year.

[0091] After step S50, the second total purchase demand amount may replace the first total purchase demand amount or participate in the generation of the platform stocking strategy together with the first total purchase demand amount, that is, according to the first total purchase demand amount PD ns The estimated result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including but not limited to: ns and the second total purchase demand The product of the maximum value, middle value, average value or minimum value in and the preset coefficient δ is used as the target value for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

[0092] Therefore, based on the possible design one described in the aforementioned steps S20 to S50, the total purchase demand amount can be estimated from another perspective, and together with the first total purchase demand amount, participate in the generation of the platform stocking strategy, thereby comprehensively considering various factors to ensure the correctness of the platform stocking strategy.

[0093] Based on the technical solution of the possible design one mentioned above, this embodiment also provides a possible design two for estimating the total purchase demand from another perspective, that is, after obtaining the single-period purchase frequency of various types of medicinal materials by each customer in each unit area in each unit period of each year according to the historical sales data, the method also includes but is not limited to the following step S300.

[0094] S300. For each customer in each unit area, according to the corresponding single-period purchase frequency for each type of medicinal slices in the most recent X unit periods, the corresponding recent purchase preference type for each type of medicinal slices is obtained, wherein X is a positive integer not less than N, and the recent purchase preference type includes a regular purchase type, a periodic interval purchase type, and a non-purchase type. The regular purchase type indicates that for a certain type of medicinal slices, each single-period purchase frequency in the corresponding X single-period purchase frequencies is not less than 1, and the periodic interval purchase type indicates that for a certain type of medicinal slices, the single-period purchase frequency with an average interval of Y unit periods in the corresponding X single-period purchase frequencies is not less than 1, and Y is a real number and has The non-purchase type means that for a certain type of herbal medicine, the single-period purchase frequency of each of the corresponding X single-period purchase frequencies is less than 1.

[0095] In step S300, for example, for customer A in Sichuan Province, according to the corresponding single-period purchase frequency for the herbal medicine category A in the recent 12 (i.e., X=12) months (a total of 12 data), if each single-period purchase frequency in these 12 single-period purchase frequencies is not less than 1, it indicates that customer A has purchased the herbal medicine category A every month recently, that is, the recent purchase preference type of customer A for the herbal medicine category A is the frequent purchase type; and if the single-period purchase frequency with an average interval of 1 month ... then customer A has purchased the herbal medicine category A every month recently, that is, customer A has purchased the herbal medicine category A frequently in recent years. If the single-period purchase frequency is greater than 1 (for example, the single-period purchase frequency in January, March, May, July, September and November is not less than 1), it indicates that customer A has recently purchased the medicinal material category A once every month, that is, customer A's recent purchase preference type for the medicinal material category A is the periodic interval purchase type; and if each single-period purchase frequency in these 12 single-period purchase frequencies is less than 1 (that is, equal to 0), it indicates that customer A has not purchased the medicinal material category A every month recently, that is, customer A's recent purchase preference type for the medicinal material category A is the non-purchase type. Specifically, the value of Y can be calculated according to the following formula: x represents the number of 0s in the X single-period purchasing frequencies.

[0096] In addition, after estimating the predicted value of the average household purchase volume for the various types of medicinal materials in each unit period of the next year for each unit area according to the corresponding third functional relationship, the method further includes but is not limited to the following step S500.

[0097] S500. The third total purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula:

[0098]

[0099] In the formula, represents the total third purchase demand for the sth type of herbal medicine in the nth unit period of the next year, represents the predicted value of the average household purchase volume of the s-th type of decoction piece category in the ith unit area in the n-th unit period of the next year, η ijs represents the purchase probability of the jth customer in the i-th unit area for the s-th type of decoction piece category in each period. When the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the frequently purchased type, η ijs =1, and when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of herbal medicine is a periodic interval purchase type, Y ijsrepresents the average interval Y value of the jth customer in the i-th unit area for the s-th type of decoction piece category, and when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the non-purchase type, η ijs =0.

[0100] In step S500, when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is a frequently purchased type, it indicates that the jth customer has purchased the s-th type of decoction piece category in each unit period recently, so n ijs =1. When the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of herbal medicine is a periodic interval purchase type, it indicates that the jth customer has recently been purchasing at an average interval of Y ijs The sth type of herbal medicine is purchased in each period, so the purchase probability in each period can be estimated as When the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the non-purchase type, it indicates that the j-th customer does not purchase the s-th type of decoction piece category in each unit period recently, so η ijs = 0. Calculated as follows The predicted value of the purchasing demand for the s-th type of medicinal materials by the j-th customer in the ith unit region in the n-th unit period of the next year can be obtained, and then the predicted values ​​of the purchasing demand of all customers in all regions can be summarized to estimate the total purchasing demand for the s-th type of medicinal materials in the n-th unit period of the next year.

[0101] After step S500, the third total purchase demand amount may also replace the first total purchase demand amount or participate in the generation of the platform stocking strategy together with the first total purchase demand amount, that is, according to the first total purchase demand amount PD ns The estimated result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including but not limited to: ns and the third procurement demand The product of the maximum value, middle value, average value or minimum value in and the preset coefficient δ is used as the target value for the Chinese medicine slice sales platform to prepare for the sth type of slices in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3]. In addition, the first purchase demand total PD ns 、The second total purchase demand and the third procurement demand The product of the maximum value, the middle value, the average value or the minimum value in and the preset coefficient δ is used as the target value for the Chinese herbal medicine selling platform to stock the sth type of herbal medicine category in the nth unit period of the next year.

[0102] Therefore, based on the possible design 2 described in the aforementioned steps S300 and S500, the total purchase demand amount can be estimated from another perspective, and together with the first total purchase demand amount, participate in the generation of the platform stocking strategy, thereby comprehensively considering various factors to ensure the correctness of the platform stocking strategy.

[0103] Based on the technical solution of the aforementioned possible design one, this embodiment also provides a possible design three for estimating the total purchase demand from another perspective, that is, after obtaining the single-period purchase frequency of various types of medicinal materials by each customer in each unit area in each unit period of each year according to the historical sales data, the method also includes but is not limited to the following steps S301 to S303.

[0104] S301. For each customer in each unit area, according to the corresponding single-period purchasing frequency for each type of medicinal material in each unit period of each year, the corresponding single-period purchasing preference type for each type of medicinal material in each unit period of each year is obtained, wherein when the value of the single-period purchasing preference type is 1, it indicates that for a certain type of medicinal material, the corresponding single-period purchasing frequency is not less than 1, and when the value is 0, it indicates that for the certain type of medicinal material, the corresponding single-period purchasing frequency is equal to 0.

[0105] In step S301, for example, for customer A in Sichuan Province, according to the corresponding single-period purchase frequency for decoction piece category A in December 2019, if the single-period purchase frequency is not less than 1, it indicates that customer A likes to purchase decoction piece category A in December 2019, so the value of the single-period purchase preference type is set to 1. If the single-period purchase frequency is equal to 0, it indicates that customer A does not like to purchase decoction piece category A in December 2019, so the value of the single-period purchase preference type is set to 0.

[0106] S302. For each customer in each unit area, according to the corresponding single-period purchasing preference type for each type of medicinal material in each unit period of all years, a fourth functional relationship between the corresponding single-period purchasing preference type for each type of medicinal material in each unit period and the variable year is obtained by data fitting.

[0107] In step S302, for example, for customer A in Sichuan Province, according to the corresponding single-period purchase preference type for decoction category A in December from 2001 to 2021 (i.e., a total of 21 data), the fourth functional relationship between the corresponding single-period purchase preference type for decoction category A in December and the variable year can be obtained by data fitting. In addition, the specific data fitting method can also be, but not limited to, a straight line fitting method or a polynomial curve fitting method.

[0108] S303. For each customer in each unit area, estimate the predicted value of the single-period purchase preference type for each type of medicinal material in each unit period of the next year according to the corresponding fourth functional relationship.

[0109] In step S303, taking the same example, for customer A in Sichuan Province, based on the corresponding fourth functional relationship between the single-period purchasing preference type for medicinal material category A in December and the variable year, it is possible to estimate the predicted value of the single-period purchasing preference type for medicinal material category A in December of the next year (for example, 2022 after 2021).

[0110] In addition, after estimating the predicted value of the average household purchase volume for the various types of medicinal materials in each unit period of the next year for each unit area according to the corresponding third functional relationship, the method further includes but is not limited to the following step S304.

[0111] S304. The fourth total purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula:

[0112]

[0113] In the formula, represents the fourth total purchase demand for the sth type of herbal medicine in the nth unit period of the next year, represents the predicted value of the average household purchase volume of the sth type of herbal medicine in the ith unit area in the nth unit period of the next year, u ijns It represents the predicted value of the single-period purchasing preference type of the j-th customer in the i-th unit area for the s-th type of medicinal pieces in the n-th unit period of the next year.

[0114] After step S304, the fourth total purchase demand amount can also participate in the generation of the platform stocking strategy together with the first total purchase demand amount, that is, according to the first total purchase demand amount PD nsThe estimation result is used to generate a strategy for the Chinese medicine slice sales platform to prepare stocks for the sth type of slices in the nth unit period of the next year, including: ns The product of the fourth purchase demand is used as the target value for the Chinese medicine slice sales platform to prepare the sth type of slices in the nth unit period of the next year, and the fourth purchase demand total ... as the minimum value for the Chinese herbal medicine selling platform to stock the sth type of herbal medicine category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

[0115] Therefore, based on the possible design three described in the aforementioned steps S301 to S304, the total purchase demand amount can be estimated from another perspective, and together with the first total purchase demand amount, it can participate in the generation of the platform stocking strategy, determine the minimum stocking value, and improve the platform stocking strategy.

[0116] like Figure 2 As shown, the second aspect of this embodiment provides a virtual device for implementing the method for generating a stocking strategy for Chinese herbal medicine slices as described in the first aspect or any possible design of the first aspect, comprising a data acquisition module, a data statistics module, a data fitting module, a numerical estimation module, a demand estimation module and a strategy generation module which are sequentially connected in communication;

[0117] The data acquisition module is used to acquire the historical sales data recorded by the Chinese herbal medicine slice sales platform, wherein the historical sales data contains all the purchase orders that have been completed, and the purchase orders contain the purchase order number, customer identification, herbal medicine slice category identification, delivery address, purchase timestamp and purchase quantity;

[0118] The data statistics module is used to obtain, based on the historical sales data, the single-period purchase frequency and the single average purchase volume of each customer in each unit area for each unit period of each year for various types of decoction pieces;

[0119] The data fitting module is used for obtaining, for each customer in each unit region, a first functional relationship between the single-period procurement frequency for each type of medicinal slices and the variable year in each unit period according to the corresponding single-period procurement frequency for each type of medicinal slices in each unit period of all years, and a second functional relationship between the single average procurement volume for each type of medicinal slices and the variable year in each unit period according to the corresponding single average procurement volume for each type of medicinal slices in each unit period of all years;

[0120] The numerical estimation module is used to estimate, for each customer in each unit area, the single-period purchase frequency forecast value for each type of decoction piece in each unit period of the next year according to the corresponding first functional relationship, and to estimate, for each customer in each unit area, the single-period purchase frequency forecast value for each type of decoction piece in each unit period of the next year according to the corresponding second functional relationship;

[0121] The demand estimation module is used to estimate the total first purchase demand for the various types of decoction pieces in each unit period of the next year according to the following formula:

[0122]

[0123] Where, PD ns It represents the total first purchase demand for the sth type of herbal medicine category in the nth unit period of the next year, n is a positive integer and n∈[1,N], N represents the total number of unit periods in a year, s is a positive integer and s∈[1,S], S represents the total number of all herbal medicine category identifiers in all purchase orders, i is a positive integer and i∈[1,I], I represents the total number of districts in all unit areas, and all unit areas are determined according to all delivery addresses in all purchase orders, j is a positive integer and j∈[1,J i ], J i represents the total number of all customer IDs in all purchase orders in a certain region, where the purchase orders in a certain region refer to purchase orders where the delivery address belongs to the i-th unit region, represents the predicted value of the single-period purchase frequency of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year, The predicted value of the average single purchase volume of the s-th type of herbal medicine by the j-th customer in the ith unit area in the n-th unit period of the next year;

[0124] The strategy generation module is used to generate a strategy based on the first purchase demand total amount PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year.

[0125] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be referred to the method for generating a stocking strategy for Chinese herbal medicines described in the first aspect or any possible design of the first aspect, and will not be described in detail here.

[0126] like Figure 3As shown, the third aspect of the present embodiment provides a computer device for executing the method for generating a stocking strategy for Chinese herbal medicine slices as described in the first aspect or any possible design of the first aspect, including a memory and a processor connected in communication, wherein the memory is used to store a computer program, and the processor is used to read the computer program, and execute the method for generating a stocking strategy for Chinese herbal medicine slices as described in the first aspect or any possible design of the first aspect. Specifically, the memory may include, but is not limited to, a random access memory (Random-Access Memory, RAM), a read-only memory (Read-Only Memory, ROM), a flash memory (Flash Memory), a first-in-first-out memory (First Input First Output, FIFO) and / or a first-in-last-out memory (First Input Last Output, FILO), etc.; the processor may include, but is not limited to, a microprocessor of the STM32F105 series. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0127] The working process, working details and technical effects of the aforementioned computer device provided in the third aspect of this embodiment can be referred to the method for generating a stocking strategy for Chinese herbal medicines described in the first aspect or any possible design of the first aspect, and will not be described in detail here.

[0128] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions including the method for generating a stocking strategy for Chinese herbal medicine slices as described in the first aspect or any possible design of the first aspect, that is, the computer-readable storage medium stores instructions, and when the instructions are run on a computer, the method for generating a stocking strategy for Chinese herbal medicine slices as described in the first aspect or any possible design of the first aspect is executed. Wherein, the computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to computer-readable storage media such as floppy disks, optical disks, hard disks, flash memories, USB flash drives, and / or memory sticks, and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0129] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be referred to the method for generating a stocking strategy for Chinese herbal medicines as described in the first aspect or any possible design of the first aspect, and will not be repeated here.

[0130] A fifth aspect of the present embodiment provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the method for generating a stocking strategy for Chinese herbal medicine slices as described in the first aspect or any possible design of the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0131] Finally, it should be noted that the present invention is not limited to the above optional implementations, and anyone can derive other various forms of products under the enlightenment of the present invention. The above specific implementations should not be understood as limiting the scope of protection of the present invention. The scope of protection of the present invention should be based on the definition in the claims, and the description can be used to interpret the claims.

Claims

1. A method for generating a stocking strategy for Chinese herbal medicine pieces, characterized in that: include: Obtaining historical sales data recorded by the Chinese herbal medicine piece sales platform, wherein the historical sales data contains all completed purchase orders, and the purchase order contains the purchase order number, customer identification, herbal medicine piece category identification, delivery address, purchase timestamp and purchase quantity; According to the historical sales data, the single-period purchase frequency and single average purchase volume of various types of herbal medicine pieces by each customer in each unit area in each unit period of each year are obtained; For each customer in each unit region, according to the corresponding single-period purchase frequency for each type of medicinal slices in each unit period of all years, a first functional relationship between the corresponding single-period purchase frequency for each type of medicinal slices in each unit period and the variable year is obtained by data fitting, and according to the corresponding single average purchase volume for each type of medicinal slices in each unit period of all years, a second functional relationship between the corresponding single average purchase volume for each type of medicinal slices in each unit period and the variable year is obtained by data fitting; For each customer in each unit region, a single-period purchase frequency forecast value for each type of herbal medicine piece in each unit period of the next year is estimated based on the corresponding first functional relationship, and a single average purchase volume forecast value for each type of herbal medicine piece in each unit period of the next year is estimated based on the corresponding second functional relationship; The first total purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula: Where, PD ns It represents the total first purchase demand for the sth type of herbal medicine category in the nth unit period of the next year, n is a positive integer and n∈[1,N], N represents the total number of unit periods in a year, s is a positive integer and s∈[1,S], S represents the total number of all herbal medicine category identifiers in all purchase orders, i is a positive integer and i∈[1,I], I represents the total number of districts in all unit areas, and all unit areas are determined according to all delivery addresses in all purchase orders, j is a positive integer and j∈[1,J i ], J i represents the total number of all customer IDs in all purchase orders in a certain region, where the purchase orders in a certain region refer to purchase orders where the delivery address belongs to the i-th unit region, represents the predicted value of the single-period purchase frequency of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year, The predicted value of the average single purchase volume of the s-th type of herbal medicine by the j-th customer in the ith unit area in the n-th unit period of the next year; According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year.

2. The method for generating a stocking strategy for Chinese herbal medicine slices according to claim 1, characterized in that: According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including: The first purchase demand amount PD ns The product of the preset coefficient δ is used as the target value for the Chinese herbal medicine selling platform to stock the sth type of herbal medicine category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

3. The method for generating a stocking strategy for Chinese herbal medicine slices according to claim 1, characterized in that: After obtaining the historical sales data recorded by the Chinese herbal medicine slice sales platform, the method further includes: According to the historical sales data, the average household purchase volume of various types of herbal medicine pieces in each unit area in each unit period of each year is obtained; For each unit region, according to the corresponding average household purchase volume for each type of decoction pieces in each unit period of all years, a third functional relationship between the corresponding average household purchase volume for each type of decoction pieces in each unit period and the variable year is obtained by data fitting; For each unit area, estimate the predicted value of the average household purchase volume for each type of decoction piece in each unit period of the next year according to the corresponding third functional relationship; The second total purchase demand for the various types of decoction pieces in each unit period of the next year is estimated according to the following formula: In the formula, represents the total second purchase demand for the sth type of herbal medicine in the nth unit period of the next year, It represents the predicted value of the average household purchase volume of the s-th type of medicinal materials in the ith unit area in the n-th unit period of the next year.

4. The method for generating a stocking strategy for Chinese herbal medicine slices according to claim 3, characterized in that: According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including: The total amount of PD required in the first procurement ns and the second total purchase demand The product of the maximum value, middle value, average value or minimum value in and the preset coefficient δ is used as the target value for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

5. The method for generating a stocking strategy for Chinese herbal medicine slices according to claim 3, characterized in that: After obtaining statistical data on the historical sales data on the single-period purchase frequency of each customer in each unit area for each unit period of each year for each type of decoction piece, the method further includes: For each customer in each unit area, according to the corresponding single-period purchase frequency for each type of medicinal slices in the most recent X unit periods, the corresponding recent purchase preference type for each type of medicinal slices is obtained, wherein X is a positive integer not less than N, and the recent purchase preference type includes a frequently purchased type, a periodic interval purchase type, and a non-purchase type. The frequently purchased type indicates that for a certain type of medicinal slices, each single-period purchase frequency in the corresponding X single-period purchase frequencies is not less than 1, and the periodic interval purchase type indicates that for a certain type of medicinal slices, the single-period purchase frequency with an average interval of Y unit periods in the corresponding X single-period purchase frequencies is not less than 1, and Y is a real number and has The non-purchase type means that for a certain type of herbal medicine, the purchase frequency of each single period in the corresponding X single period purchase frequencies is less than 1; After estimating the predicted value of the average household purchase volume for each type of decoction piece in each unit period of the next year according to the corresponding third functional relationship for each unit area, the method further includes: The total third purchase demand for each type of decoction piece in each unit period of the next year is estimated according to the following formula: In the formula, represents the total third purchase demand for the sth type of herbal medicine in the nth unit period of the next year, represents the predicted value of the average household purchase volume of the sth type of decoction piece category in the ith unit area in the nth unit period of the next year, η ijs represents the purchase probability of the jth customer in the i-th unit area for the s-th type of decoction piece category in each period. When the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the frequently purchased type, η ijs =1, and when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of herbal medicine is a periodic interval purchase type, Y ijs represents the average interval Y value of the jth customer in the i-th unit area for the s-th type of decoction piece category, and when the recent purchase preference type of the jth customer in the i-th unit area for the s-th type of decoction piece category is the non-purchase type, η ijs =0; According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including: The total amount of PD required in the first procurement ns and the third procurement demand The product of the maximum value, middle value, average value or minimum value in and the preset coefficient δ is used as the target value for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

6. The method for generating a stocking strategy for Chinese herbal medicine slices according to claim 3, characterized in that: After obtaining statistical data on the historical sales data on the single-period purchase frequency of each customer in each unit area for each unit period of each year for each type of decoction piece, the method further includes: For each customer in each unit region, according to the corresponding single-period purchase frequency for each type of decoction piece in each unit period of each year, the corresponding single-period purchase preference type for each type of decoction piece in each unit period of each year is obtained, wherein when the value of the single-period purchase preference type is 1, it means that for a certain type of decoction piece, the corresponding single-period purchase frequency is not less than 1, and when the value is 0, it means that for the certain type of decoction piece, the corresponding single-period purchase frequency is equal to 0; For each customer in each unit region, according to the corresponding single-period purchase preference type for each type of decoction piece in each unit period of all years, a fourth functional relationship between the corresponding single-period purchase preference type for each type of decoction piece in each unit period and the variable year is obtained by data fitting; For each customer in each unit area, estimate the predicted value of the single-period purchase preference type for each type of herbal medicine in each unit period of the next year according to the corresponding fourth functional relationship; After estimating the predicted value of the average household purchase volume for each type of decoction piece in each unit period of the next year according to the corresponding third functional relationship for each unit area, the method further includes: The fourth total purchase demand for the various types of decoction pieces in each unit period of the next year is estimated according to the following formula: In the formula, represents the fourth total purchase demand for the sth type of herbal medicine in the nth unit period of the next year, represents the predicted value of the average household purchase volume of the sth type of herbal medicine in the ith unit area in the nth unit period of the next year, u ijns represents the single-period purchase preference type prediction value of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year; According to the first purchase demand total PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to prepare stocks for the sth type of herbal medicine slice category in the nth unit period of the next year, including: The first purchase demand amount PD ns The product of the fourth purchase demand is used as the target value for the Chinese medicine slice sales platform to prepare the sth type of slices in the nth unit period of the next year, and the fourth purchase demand total ... as the minimum value for the Chinese herbal medicine selling platform to stock the sth type of herbal medicine category in the nth unit period of the next year, where δ is a real number and δ∈[1,1.3].

7. The method for generating a stocking strategy for Chinese herbal medicine slices according to claim 1, characterized in that: The unit area is a provincial-level area or a municipal-level area, and the unit period is a month or a quarter.

8. A device for generating a stocking strategy for Chinese herbal medicine pieces, characterized in that: It includes a data acquisition module, a data statistics module, a data fitting module, a numerical estimation module, a demand estimation module and a strategy generation module which are sequentially connected in communication; The data acquisition module is used to acquire the historical sales data recorded by the Chinese herbal medicine slice sales platform, wherein the historical sales data contains all the purchase orders that have been completed, and the purchase orders contain the purchase order number, customer identification, herbal medicine slice category identification, delivery address, purchase timestamp and purchase quantity; The data statistics module is used to obtain, based on the historical sales data, the single-period purchase frequency and the single average purchase volume of each customer in each unit area for each unit period of each year for various types of decoction pieces; The data fitting module is used for obtaining, for each customer in each unit region, a first functional relationship between the single-period procurement frequency for each type of medicinal slices and the variable year in each unit period according to the corresponding single-period procurement frequency for each type of medicinal slices in each unit period of all years, and a second functional relationship between the single average procurement volume for each type of medicinal slices and the variable year in each unit period according to the corresponding single average procurement volume for each type of medicinal slices in each unit period of all years; The numerical estimation module is used to estimate, for each customer in each unit area, the single-period purchase frequency forecast value for each type of decoction piece in each unit period of the next year according to the corresponding first functional relationship, and to estimate, for each customer in each unit area, the single-period purchase frequency forecast value for each type of decoction piece in each unit period of the next year according to the corresponding second functional relationship; The demand estimation module is used to estimate the total first purchase demand for the various types of decoction pieces in each unit period of the next year according to the following formula: Where, PD ns It represents the total first purchase demand for the sth type of herbal medicine category in the nth unit period of the next year, n is a positive integer and n∈[1,N], N represents the total number of unit periods in a year, s is a positive integer and s∈[1,S], S represents the total number of all herbal medicine category identifiers in all purchase orders, i is a positive integer and i∈[1,I], I represents the total number of districts in all unit areas, and all unit areas are determined according to all delivery addresses in all purchase orders, j is a positive integer and j∈[1,J i ], J i represents the total number of all customer IDs in all purchase orders in a certain region, where the purchase orders in a certain region refer to purchase orders where the delivery address belongs to the i-th unit region, represents the predicted value of the single-period purchase frequency of the jth customer in the i-th unit area for the s-th type of herbal medicine category in the n-th unit period of the next year, The predicted value of the average single purchase volume of the s-th type of herbal medicine by the j-th customer in the ith unit area in the n-th unit period of the next year; The strategy generation module is used to generate a strategy based on the first purchase demand total amount PD ns The estimation result is used to generate a strategy for the Chinese herbal medicine slice sales platform to stock the sth type of herbal medicine slice category in the nth unit period of the next year.

9. A computer device, characterized in that: It includes a memory and a processor that are communicatively connected, wherein the memory is used to store a computer program, and the processor is used to read the computer program to execute the method for generating a stocking strategy for Chinese herbal medicine slices as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on the computer, the method for generating a stocking strategy for Chinese herbal medicine pieces as described in any one of claims 1 to 7 is executed.

Images