Intelligent supply chain management system for fresh flower industry

Abstract

The invention discloses an intelligent supply chain management system for the fresh flower industry, and relates to the technical field of intelligent supply chain management, the intelligent supply chain management system comprises a monitoring center, the monitoring center is in communication connection with a data acquisition module, a data processing module, a data analysis module, a data storage module and an intelligent management module; the method comprises the following steps: acquiring original data of different types of fresh flower products, sample data of corresponding types of sample fresh flower products and purchase demand data of consumers to obtain original characteristic values of the different types of fresh flower products, sample characteristic values of the corresponding types of sample fresh flower products and purchase demand values of the different types of fresh flower products; obtaining a differential feature value according to the original feature value and the sample feature value; obtaining a predicted purchase demand value according to the purchase demand value; by judging the difference characteristic values and the predicted purchase demand values of different types of fresh flower products, intelligent purchase is performed on the fresh flower products, and the accuracy and efficiency of purchase are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent supply chain management, in particular to an intelligent supply chain management system for the flower industry. Background Art

[0002] As residents' income levels rise, consumption concepts continue to upgrade, quality life becomes an important pursuit for consumers, and the scale of consumption of the "self-pleasing economy" dominated by women continues to grow. Flowers, due to their own aesthetic attributes and the fun they add to life, have gradually become a high-frequency consumer product favored by white-collar women. Driven by big data, new retail and other factors, flower e-commerce has ushered in important development opportunities.

[0003] With the intensification of industry competition and the continuous improvement of user service requirements, the development constraints of the flower e-commerce industry are becoming increasingly obvious. Overall, supply chain management, logistics distribution and profit model are the main pain points in the current development of the flower e-commerce industry, and supply chain control is the key to ensuring the quality of flowers. Compared with traditional flower shops, flower e-commerce can use big data technology to accurately predict user needs. At the same time, the social marketing model strengthens communication with users and accumulates a good user reputation through online and offline linkage.

[0004] In the context of rapid technological upgrades and iterations, the deep integration of products, users and information technology will be achieved. The application of big data in the supply chain management of flower e-commerce will achieve more accurate prediction and control of various links such as demand generation, product planting and procurement, processing and packaging, logistics distribution, evaluation and feedback, so as to scientifically adjust the supply and demand relationship, optimize the supply chain network with new strategies, and promote the development of supply chain management in the direction of integration, real-time, automation and intelligence. Therefore, an intelligent supply chain management system for the flower industry is now provided. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent supply chain management system for the flower industry.

[0006] In order to achieve the above object, the present invention provides the following technical solutions: an intelligent supply chain management system for the flower industry, comprising a monitoring center, wherein the monitoring center is communicatively connected with a data acquisition module, a data processing module, a data analysis module, a data storage module and an intelligent management module;

[0007] The data collection module is used to collect original data of different types of flower products, sample data of sample flower products of corresponding types and purchase demand data of consumers, and set a collection cycle;

[0008] The data processing module is used to obtain original characteristic values ​​of different types of flower products based on original data, obtain sample characteristic values ​​of sample flower products of corresponding types based on sample data, and obtain purchase demand values ​​of different types of flower products based on purchase demand data;

[0009] The data analysis module is used to obtain differential characteristic values ​​of different types of flower products according to the original characteristic values ​​and the sample characteristic values;

[0010] The data storage module is used to store the purchase demand values ​​of different types of flower products to obtain the predicted purchase demand values;

[0011] The intelligent management module is used to judge the differential feature values ​​and predicted purchase demand values ​​of different types of flower products, and to perform intelligent purchase of flower products according to the judgment results.

[0012] Furthermore, the process of the data collection module collecting original data, sample data and purchase demand data includes:

[0013] The data collection module has several flower product data collection units and consumer data collection units, and sets a collection cycle;

[0014] Obtain the flower product purchasing plan information within the collection period in advance;

[0015] Collecting original data, sample data and purchase demand data according to the flower product procurement plan information and collection cycle;

[0016] The raw data includes flower length data, flower size data, flower preservation time data and flower freshness data;

[0017] The sample data includes sample flower length data, sample flower size data, sample flower preservation time data and sample flower freshness data;

[0018] The purchase demand data includes flower price data, flower discount information data and flower attribute data.

[0019] Furthermore, the process of the data processing module obtaining the original characteristic values ​​of different types of flower products includes:

[0020] Number the flower stem length data, flower size data, flower freshness estimated time data and flower freshness data of different flowers of the same type respectively;

[0021] According to the numbered flower stem length data, flower size data, flower freshness estimated time data and flower freshness data, an original multidimensional feature matrix is ​​obtained;

[0022] According to the original multi-dimensional feature matrix, original eigenvalues ​​are obtained.

[0023] Furthermore, the data processing module obtains sample characteristic values ​​of sample flower products of corresponding types according to the sample flower length data, the sample flower size data, the sample flower preservation time data and the sample flower freshness data.

[0024] Furthermore, the data processing module obtains the purchase demand value of the flower product according to the flower price data, the flower discount information data and the flower attribute data.

[0025] Furthermore, the process of the data analysis module obtaining the differential feature values ​​of different types of flower products includes:

[0026] The difference between the original eigenvalue and the sample eigenvalue is calculated to obtain the differential eigenvalue.

[0027] Furthermore, the process of storing the purchase demand values ​​of different types of flower products by the data storage module includes:

[0028] The data storage module is provided with a plurality of current storage databases and historical storage databases;

[0029] The purchase demand values ​​collected in the current collection cycle are sent to the current storage database; several groups of purchase demand values ​​in the current storage database before the current collection cycle are sent to the historical storage database and marked as historical purchase demand values.

[0030] 8. The intelligent supply chain management system for the flower industry according to claim 7, characterized in that the process of the data storage module obtaining the predicted purchase demand value includes:

[0031] Using several groups of historical purchase demand values ​​as training sets and test sets, and inputting the training sets and test sets into a standard consumer purchase expectation prediction model, training the standard consumer purchase expectation prediction model, and obtaining a standard consumer purchase expectation prediction model after training;

[0032] According to the standard consumer purchase expectation prediction model, a predicted purchase demand value is obtained.

[0033] Furthermore, the process of the intelligent management module judging the differential feature values ​​and predicted purchase demand values ​​of different types of flower products includes:

[0034] According to the differential feature values ​​and predicted purchase demand values ​​of different types of flower products, differential feature thresholds and predicted purchase demand thresholds of different types of flower products are preset;

[0035] If the differential feature value is less than or equal to the differential feature threshold and the predicted purchase demand value is greater than or equal to the predicted purchase demand threshold γ, a normal purchase alarm message is generated;

[0036] If the differential feature value is less than or equal to the differential feature threshold and the predicted purchase demand value is less than the predicted purchase demand threshold, a consumer factor alarm message is generated;

[0037] If the differential feature value is greater than the differential feature threshold and the predicted purchase demand value is greater than or equal to the predicted purchase demand threshold, generating a flower quality unqualified alarm message;

[0038] If the differential characteristic value is greater than the differential characteristic threshold and the predicted purchase demand value is less than the predicted purchase demand threshold, a comprehensive alarm message is generated.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: by collecting original data of different types of flower products, sample data of corresponding types of sample flower products and purchase demand data of consumers, original feature values ​​of different types of flower products, sample feature values ​​of corresponding types of sample flower products and purchase demand values ​​of different types of flower products are obtained; differential feature values ​​are obtained according to the original feature values ​​and the sample feature values; predicted purchase demand values ​​are obtained according to the purchase demand values; and by judging the differential feature values ​​and predicted purchase demand values ​​of different types of flower products, flower products are intelligently purchased, thereby greatly improving the accuracy and efficiency of purchase. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0042] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0043] like Figure 1As shown, an intelligent supply chain management system for the flower industry includes a monitoring center, wherein the monitoring center is communicatively connected with a data acquisition module, a data processing module, a data analysis module, a data storage module and an intelligent management module;

[0044] The data collection module is used to collect original data of different types of flower products, sample data of sample flower products of corresponding types, and purchase demand data of consumers for different types of flower products;

[0045] The data processing module is used to obtain the original characteristic values ​​U of different types of flower products according to the original data of different types of flower products. t , according to the sample data of the corresponding type of flower products, obtain the sample characteristic value D of the corresponding type of sample flower products t , according to the purchase demand data of consumers for different types of flower products, obtain the purchase demand values ​​of different types of flower products

[0046] The data analysis module is used to analyze the original characteristic values ​​U of different types of flower products. t And the sample eigenvalue D t , obtain the differential eigenvalues ​​ε of different types of flower products;

[0047] The data storage module is used to store the purchase demand values ​​of different types of flower products. Store and obtain the predicted purchase demand values ​​of different types of flower products

[0048] The intelligent management module is used to calculate the differential characteristic values ​​ε of different types of flower products and predict the purchase demand values. Make judgments and carry out intelligent purchases of flower products based on the judgment results.

[0049] It should be further explained that, in the specific implementation process, the specific process of the data collection module collecting original data, sample data and purchase demand data includes:

[0050] The data collection module has several flower product data collection units and consumer data collection units, and sets a collection cycle;

[0051] Obtain the flower product purchasing plan information within the collection period in advance;

[0052] According to the flower product purchasing plan information, the flower product data collection unit collects original data of different types of flower products and sample data of corresponding types of sample flower products according to a collection period;

[0053] The consumer data collection unit collects consumer purchase demand data according to a collection cycle.

[0054] The data collection module uploads the collected original data, sample data and purchase demand data to the data processing module.

[0055] It should be further explained that, in the specific implementation process, the specific process of the data processing module obtaining the original characteristic values ​​of different types of flower products according to the original data includes:

[0056] It should be further explained that the original data includes flower length data, flower size data, flower preservation time data and flower freshness data;

[0057] Number the flower stem length data, flower size data, flower freshness estimated time data and flower freshness data of different flowers of the same type respectively;

[0058] The flower stem length data of different flowers are marked as i=1, 2, 3, ..., n, where n is a natural number;

[0059] The flower size data of different flowers are marked as j=1, 2, 3, ..., n, where n is a natural number;

[0060] The estimated fresh-keeping time data of different flowers are marked as q=1, 2, 3, ..., n, where n is a natural number;

[0061] The flower freshness data of different flowers are marked as w=1, 2, 3, ..., n, where n is a natural number;

[0062] According to the numbered flower stem length data, flower size data, flower freshness estimated time data and flower freshness data, different flowers of the same type are labeled R i_j_q_w ; According to different flowers R i_j_q_w , get the original multidimensional feature matrix

[0063] According to the original multidimensional feature matrix E, the original feature values ​​of the same type of flower products are obtained.

[0064] Among them, E ^T is the transposed matrix of the original multidimensional feature matrix E; I is the identity matrix;

[0065] Different types of flower products are numbered and marked as t=1, 2, 3, ..., m, where m is a natural number;

[0066] Similarly, the original feature values ​​U of different types of flower products are obtainedt ;

[0067] It should be further explained that, in the specific implementation process, the specific process of the data processing module obtaining the sample characteristic value of the sample flower product of the corresponding type according to the sample data includes:

[0068] It should be further explained that the sample data includes sample flower length data, sample flower size data, sample flower preservation time data and sample flower freshness data;

[0069] The sample flower length data, the sample flower size data, the sample flower preservation time data and the sample flower freshness data are recorded as O, P, A and S respectively;

[0070] According to the sample flower length data O, the sample flower size data P, the sample flower preservation time data A and the sample flower freshness data S, the calculation formula for obtaining the sample characteristic value D of the sample flower product is:

[0071]

[0072] Among them, δ_O is the weight coefficient of the sample flower length data O; δ_P is the weight coefficient of the sample flower size data P; δ_A is the weight coefficient of the sample flower preservation time data A; δ_S is the weight coefficient of the sample flower freshness data S;

[0073] Similarly, we obtain the sample feature values ​​D of different types of flower products. t ;

[0074] It should be further explained that, in the specific implementation process, the specific process of the data processing module obtaining the purchase demand values ​​of different types of flower products according to the purchase demand data includes:

[0075] It should be further explained that the purchase demand data includes flower price data, flower discount information data and flower attribute data;

[0076] The flower price data, flower discount information data and flower attribute data are respectively recorded as F, G and H;

[0077] According to the flower price data F, flower discount information data G and flower attribute data H, the purchase demand value of the flower product is obtained. The calculation formula is

[0078]

[0079] Among them, τ_F is the weight coefficient of the flower price data F; τ_G is the weight coefficient of the flower discount information data G; τ_G is the weight coefficient of the flower attribute data H.

[0080] The data processing module obtains the original eigenvalue U t , sample eigenvalue D t Upload to the data analysis module and convert the purchase demand value Upload to the data storage module.

[0081] It should be further explained that, in the specific implementation process, the data analysis module is based on the original eigenvalue U t And the sample eigenvalue D t ,The specific process of obtaining the differential eigenvalue ε of different types of flower products includes:

[0082] The original eigenvalue U t And the sample eigenvalue D t The specific process of performing difference calculations and obtaining the differential eigenvalue ε includes:

[0083] Differential Eigenvalue

[0084] in, is the original eigenvalue U t The weight coefficient of is the sample eigenvalue D t The weight coefficient of .

[0085] The data analysis module uploads the obtained differential eigenvalue ε to the intelligent management module.

[0086] It should be further explained that, in the specific implementation process, the data storage module has different purchase demand values ​​for different types of flower products. The specific process of storage includes:

[0087] The data storage module is provided with a plurality of current storage databases and historical storage databases;

[0088] The purchase demand value collected in the current collection period Send to the current storage database for storage; store several groups of purchase demand values ​​in the current storage database before the current collection cycle Sent to the historical storage database and marked as historical purchase demand value

[0089] It should be further explained that, in the specific implementation process, the specific process of the data storage module obtaining the predicted purchase demand value includes:

[0090] Set several groups of historical purchase demand values as a training set and a test set, and inputting the training set and the test set into a standard consumer purchase expectation prediction model, training the standard consumer purchase expectation prediction model, and obtaining a standard consumer purchase expectation prediction model after training;

[0091] According to the standard consumer purchase expectation prediction model, the predicted purchase demand value is obtained

[0092] The data storage module obtains the predicted purchase demand value Upload to the intelligent management module.

[0093] It should be further explained that, in the specific implementation process, the intelligent management module calculates the differential characteristic values ​​ε and the predicted purchase demand values ​​of different types of flower products. The specific process of making judgments includes:

[0094] According to the differential characteristic value ε of different types of flower products and the predicted purchase demand value Preset the differential feature threshold θ and the predicted purchase demand threshold γ of different types of flower products;

[0095] If the differential feature value ε is less than or equal to the differential feature threshold θ and the predicted purchase demand value When it is greater than or equal to the predicted purchase demand threshold γ, a normal purchase alarm message is generated, and the purchaser can purchase the flower products of this batch type according to the flower product purchase plan information;

[0096] If the differential feature value ε is less than or equal to the differential feature threshold θ and the predicted purchase demand value When it is less than the predicted purchase demand threshold γ, a consumer factor alarm message is generated to remind the purchaser to purchase the appropriate amount of flower products of this batch type to avoid increasing the purchase cost;

[0097] If the differential feature value ε is greater than the differential feature threshold θ and the predicted purchase demand value When it is greater than or equal to the predicted purchase demand threshold γ, an alarm message of unqualified flower quality is generated to remind the purchaser not to continue purchasing flower products of this batch type from the flower supplier, and to remind the purchaser to purchase flower products of this batch type from other flower suppliers;

[0098] If the differential feature value ε is greater than the differential feature threshold θ and the predicted purchase demand value When it is less than the predicted purchase demand threshold γ, a comprehensive alarm message is generated to remind the purchasing staff not to continue purchasing the flower products of this batch type.

[0099] By collecting the original data of different types of flower products, the sample data of the corresponding types of sample flower products, and the purchase demand data of consumers, the original feature values ​​U of different types of flower products are obtained. t , the sample characteristic value D of the corresponding type of sample flower products t And the purchase demand value of different types of flower products According to the original eigenvalue U t And the sample eigenvalue D t , obtain the differential eigenvalue ε; according to the purchase demand value Get predicted purchase demand value By analyzing the differential feature values ​​ε of different types of flower products and predicting the purchase demand value Make judgments and then carry out intelligent procurement of flower products, greatly improving the accuracy and efficiency of procurement.

[0100] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent supply chain management system for the flower industry, including a monitoring center, characterized in that: The monitoring center is communicatively connected with a data acquisition module, a data processing module, a data analysis module, a data storage module and an intelligent management module; The data collection module is used to collect original data of different types of flower products, sample data of sample flower products of corresponding types, and purchase demand data of consumers; The data processing module is used to obtain original characteristic values ​​of different types of flower products based on original data, obtain sample characteristic values ​​of sample flower products of corresponding types based on sample data, and obtain purchase demand values ​​of different types of flower products based on purchase demand data; The data analysis module is used to obtain differential characteristic values ​​of different types of flower products according to the original characteristic values ​​and the sample characteristic values; The data storage module is used to store the purchase demand values ​​of different types of flower products to obtain the predicted purchase demand values; The intelligent management module is used to judge the differential feature values ​​and predicted purchase demand values ​​of different types of flower products, and to perform intelligent purchase of flower products according to the judgment results.

2. The intelligent supply chain management system for the flower industry according to claim 1, characterized in that: The process of the data collection module collecting original data, sample data and purchase demand data includes: The data collection module has several flower product data collection units and consumer data collection units, and sets a collection cycle; Obtain the flower product purchasing plan information within the collection period in advance; Collecting original data, sample data and purchase demand data according to the flower product procurement plan information and collection cycle; The raw data includes flower length data, flower size data, flower preservation time data and flower freshness data; The sample data includes sample flower length data, sample flower size data, sample flower preservation time data and sample flower freshness data; The purchase demand data includes flower price data, flower discount information data and flower attribute data.

3. The intelligent supply chain management system for the flower industry according to claim 2, characterized in that: The process of obtaining the original characteristic values ​​of different types of flower products by the data processing module includes: Number the flower stem length data, flower size data, flower freshness estimated time data and flower freshness data of different flowers of the same type respectively; According to the numbered flower stem length data, flower size data, flower freshness estimated time data and flower freshness data, an original multidimensional feature matrix is ​​obtained; According to the original multi-dimensional feature matrix, original eigenvalues ​​are obtained.

4. The intelligent supply chain management system for the flower industry according to claim 3, characterized in that: The data processing module obtains sample characteristic values ​​of sample flower products of corresponding types according to the sample flower length data, the sample flower size data, the sample flower preservation time data and the sample flower freshness data.

5. The intelligent supply chain management system for the flower industry according to claim 4, characterized in that: The data processing module obtains the purchase demand value of the flower product according to the flower price data, the flower discount information data and the flower attribute data.

6. The intelligent supply chain management system for the flower industry according to claim 5, characterized in that: The process of the data analysis module obtaining the differential characteristic values ​​of different types of flower products includes: The difference between the original eigenvalue and the sample eigenvalue is calculated to obtain the differential eigenvalue.

7. The intelligent supply chain management system for the flower industry according to claim 6, characterized in that: The process of storing the purchase demand values ​​of different types of flower products by the data storage module includes: The data storage module is provided with a plurality of current storage databases and historical storage databases; The purchase demand values ​​collected in the current collection cycle are sent to the current storage database; several groups of purchase demand values ​​in the current storage database before the current collection cycle are sent to the historical storage database and marked as historical purchase demand values.

8. The intelligent supply chain management system for the flower industry according to claim 7, characterized in that: The process of the data storage module obtaining the predicted purchase demand value includes: Using several groups of historical purchase demand values ​​as training sets and test sets, and inputting the training sets and test sets into a standard consumer purchase expectation prediction model, training the standard consumer purchase expectation prediction model, and obtaining a standard consumer purchase expectation prediction model after training; According to the standard consumer purchase expectation prediction model, a predicted purchase demand value is obtained.

9. The intelligent supply chain management system for the flower industry according to claim 8, characterized in that: The process of the intelligent management module judging the differential characteristic values ​​and predicted purchase demand values ​​of different types of flower products includes: According to the differential feature values ​​and predicted purchase demand values ​​of different types of flower products, differential feature thresholds and predicted purchase demand thresholds of different types of flower products are preset; If the differential feature value is less than or equal to the differential feature threshold and the predicted purchase demand value is greater than or equal to the predicted purchase demand threshold γ, a normal purchase alarm message is generated; If the differential feature value is less than or equal to the differential feature threshold and the predicted purchase demand value is less than the predicted purchase demand threshold, a consumer factor alarm message is generated; If the differential feature value is greater than the differential feature threshold and the predicted purchase demand value is greater than or equal to the predicted purchase demand threshold, generating a flower quality unqualified alarm message; If the differential characteristic value is greater than the differential characteristic threshold and the predicted purchase demand value is less than the predicted purchase demand threshold, a comprehensive alarm message is generated.

Images