Cigarette goods source accurate putting method and system

Abstract

According to the cigarette goods source accurate putting method and system provided by the invention, the historical maximum putting benefit parameter of the cigarette, the cigarette brand information parameter and the regional figure portrait data are subjected to feature vectorization representation; and combining the historical maximum putting benefit parameter, the cigarette brand information parameter and the regional figure portrait data to obtain cigarette putting characteristics, and constructing a cigarette goods source accurate putting model according to the cigarette putting characteristics and corresponding historical cigarette putting data. And inputting related data of the to-be-put area into the cigarette goods source accurate putting model to obtain later-stage cigarette putting data of the target area, and assisting in accurate judgment of cigarette putting. By combining the historical maximum putting benefit parameter, the cigarette brand information parameter and the figure portrait data, the cigarette putting data of the target area is given in a cross-region manner, the improvement of the putting work efficiency is assisted, the putting efficiency is greatly improved, the cigarette inventory pressure is reduced, and the turnover rate is improved, so that the quality improvement of the cigarette market state is promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent delivery, and in particular relates to a method and system for accurately delivering cigarette supplies. Background Art

[0002] With the development of social economy and the improvement of people's living standards, the cigarette consumption market presents a huge potential development prospect. However, how to reasonably and efficiently put cigarette supply has become an important issue.

[0003] With the development and increasing maturity of technologies such as big data analysis and artificial intelligence, many industries have ushered in tremendous changes and opportunities. As a large and complex market, the cigarette consumption market can also achieve more reasonable and efficient cigarette supply by introducing these cutting-edge technologies.

[0004] Using big data analysis technology, we conduct in-depth data mining and analysis of the cigarette consumption market. By collecting and analyzing information such as user portraits and regional maximum revenue, we can accurately predict and analyze market demand. Combined with artificial intelligence technology, we can establish an intelligent cigarette supply delivery system. Using machine learning technology, we can predict and analyze market consumption potential, thereby providing accurate cigarette supply delivery recommendations.

[0005] However, in the existing technology, the feature influencing factors used in machine learning are too complex. In the process of using machine learning, a wide net is often used, and the main factors affecting cigarette delivery are not refined in the application scenario. Model generalization ability is poor, and historical revenue data is not combined with brand information and regional character portraits combined with feature vectors to obtain an accurate cigarette delivery plan. Summary of the invention

[0006] In order to solve the above technical problems, the present invention proposes a method and system for accurately delivering cigarette supplies.

[0007] In a first aspect of the present invention, a method for accurately delivering cigarette supplies is provided, characterized in that the method comprises:

[0008] A1. Obtain the historical maximum cigarette delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data of the cigarette delivery area, and obtain the historical cigarette delivery data corresponding to the delivery at this time;

[0009] A2, combining the historical maximum delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data to obtain a first cigarette delivery feature;

[0010] A3. Constructing a cigarette supply precision delivery model based on the first cigarette delivery characteristics and the historical cigarette delivery data;

[0011] A4. Receive the real-time maximum delivery benefit parameter of the target area to be delivered, the second cigarette brand information parameter and the second area character portrait data, combine the real-time maximum delivery benefit parameter, the second cigarette brand information parameter and the second area character portrait data to obtain the second cigarette delivery feature, use the cigarette supply precision delivery model to process the second cigarette delivery feature to generate real-time cigarette delivery data, and assist in the cigarette supply precision delivery according to the real-time cigarette delivery data.

[0012] Furthermore, the historical maximum delivery benefit parameter or the real-time maximum delivery benefit parameter B h is the historical labor time cost of regional cigarette placement or the real-time labor time cost of regional cigarette placement C wh , historical logistics cost or real-time logistics cost C fh , historical cigarette purchase cost or real-time cigarette purchase cost C bh and historical cigarette sales revenue or real-time cigarette sales revenue B sh Calculated;

[0013] The first cigarette brand information parameter or the second cigarette brand information parameter is the brand awareness of the cigarette, which is set to a high awareness if the unit price of the cigarette sold in a store is greater than 100 or less than 30, and the feature vector value is 1; the general awareness if the unit price of the cigarette sold in a store is less than or equal to 100 and greater than or equal to 30, and the feature vector value is 0.

[0014] Furthermore, the first regional character portrait data or the second regional character portrait data is determined based on an average smoking age Y of regional characters and a smoking frequency P of regional characters, with the unit being times / day.

[0015] Furthermore, the cigarette supply precision delivery model adopts a neural network model, and the neural network model is a DNN convolutional neural network model or an improved CNN convolutional neural network model.

[0016] A cigarette supply precision delivery system is also provided, comprising a cigarette precision delivery data acquisition terminal and a cigarette delivery platform terminal, characterized in that:

[0017] The cigarette precision delivery data acquisition terminal includes a cigarette benefit data collection module, a cigarette production terminal module and a character portrait collection module;

[0018] The cigarette delivery platform terminal includes a cigarette supply precision delivery model building module and a cigarette supply delivery module;

[0019] The cigarette benefit data collection module is connected to the cigarette delivery platform terminal to obtain the historical maximum delivery benefit parameters of the cigarette delivery area and receive the real-time maximum delivery benefit parameters of the target area to be delivered;

[0020] The cigarette production terminal module: obtains the first cigarette brand information parameter, and also obtains the second cigarette brand information parameter;

[0021] The character portrait acquisition module: acquires character portrait data of the first area and also acquires character portrait data of the second area;

[0022] The cigarette supply source precise delivery model construction module: combines the historical maximum delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data to obtain a first cigarette delivery feature, and also combines the real-time maximum delivery benefit parameter, the second cigarette brand information parameter and the second regional character portrait data to obtain a second cigarette delivery feature, and uses the first cigarette delivery feature and the historical cigarette delivery data obtained from the cigarette supply source delivery module to construct a cigarette supply source precise delivery model;

[0023] The cigarette supply delivery module obtains the historical cigarette delivery data corresponding to the historical maximum delivery benefit parameter at this time, and inputs the real-time cigarette delivery data obtained by inputting the second cigarette delivery feature into the cigarette supply precision delivery model to assist in the cigarette supply precision delivery.

[0024] Furthermore, the historical maximum delivery benefit parameter or the real-time maximum delivery benefit parameter B h is the historical labor time cost of regional cigarette placement or the real-time labor time cost of regional cigarette placement C wh , historical logistics cost or real-time logistics cost C fh , historical cigarette purchase cost or real-time cigarette purchase cost C bh and historical cigarette sales revenue or real-time cigarette sales revenue B sh Calculated;

[0025] The first cigarette brand information parameter or the second cigarette brand information parameter is the brand awareness of the cigarette, which is set to a high awareness if the unit price of the cigarette sold in a store is greater than 100 or less than 30, and the feature vector value is 1; the general awareness if the unit price of the cigarette sold in a store is less than or equal to 100 and greater than or equal to 30, and the feature vector value is 0.

[0026] Furthermore, the first regional character portrait data or the second regional character portrait data is determined based on an average smoking age Y of regional characters and a smoking frequency P of regional characters, with the unit being times / day.

[0027] Furthermore, the cigarette supply precision delivery model adopts a neural network model, and the neural network model is a DNN convolutional neural network model or an improved CNN convolutional neural network model.

[0028] The present invention limits the feature influencing factors to a few main feature vectors by utilizing an improved deep learning model. In the process of utilizing the deep learning model, refined feature processing is adopted to perform refined model correction processing for specific application scenarios on the main factors affecting cigarette delivery. Feature automatic processing is performed on the activation function that affects the model's ability to accurately predict delivery, thereby enhancing the generalization ability of the model. The present invention utilizes historical revenue data combined with brand information and regional character portraits combined with feature vectors for processing to obtain an accurate cigarette delivery plan. The delivery plan obtained by the present invention using the improved deep learning model improves the work efficiency of cigarette delivery, reduces cigarette inventory pressure, increases turnover rate, promotes a positive cigarette market situation, and improves customer satisfaction in retail stores.

[0029] More embodiments and improved effects of the present invention will be further introduced in conjunction with the drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a cigarette supply delivery data display diagram based on the cigarette supply delivery precision delivery method of the present invention;

[0031] Figure 2 It is a flow chart of the method for accurate delivery of cigarette supplies of the present invention;

[0032] Figure 3 It is a schematic diagram of a cigarette accurate delivery data acquisition terminal in the cigarette supply accurate delivery method system of the present invention;

[0033] Figure 4 It is a schematic diagram of a cigarette delivery platform terminal in the cigarette supply source accurate delivery method system of the present invention;

[0034] Figure 5 It is a schematic diagram of the whole process support of cigarette delivery based on the cigarette supply accurate delivery method of the present invention;

[0035] Figure 6 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0037] In order to solve the above technical problems, the present invention proposes a method and system for accurately delivering cigarette supplies.

[0038] In a first aspect of the present invention, a method for accurately delivering cigarette supplies is provided, characterized in that the method comprises:

[0039] A1. Obtain the historical maximum cigarette delivery benefit parameter of the cigarette delivery area, the first cigarette brand information parameter and the first regional character portrait data, and obtain the historical cigarette delivery data corresponding to the delivery at this time;

[0040] A2, combining the historical maximum delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data to obtain a first cigarette delivery feature;

[0041] A3. Constructing a cigarette supply precision delivery model based on the first cigarette delivery characteristics and the historical cigarette delivery data;

[0042] A4. Receive the real-time maximum delivery benefit parameter of the target area to be delivered, the second cigarette brand information parameter and the second area character portrait data, combine the real-time maximum delivery benefit parameter, the second cigarette brand information parameter and the second area character portrait data to obtain the second cigarette delivery feature, use the cigarette supply precision delivery model to process the second cigarette delivery feature to generate real-time cigarette delivery data, and assist in the cigarette supply precision delivery according to the real-time cigarette delivery data.

[0043] Furthermore, the historical maximum delivery benefit parameter or the real-time maximum delivery benefit parameter B h is the historical labor time cost of regional cigarette placement or the real-time labor time cost of regional cigarette placement C wh , historical logistics cost or real-time logistics cost C fh , historical cigarette purchase cost or real-time cigarette purchase cost C bh and historical cigarette sales revenue or real-time cigarette sales revenue B sh The calculation results are:

[0044] B h = k*(C wh +C fh +C bh -B sh )

[0045] In the formula, k is the benefit adjustment coefficient, and its value range is 0.85-0.95;

[0046] In this embodiment, the historical maximum delivery benefit parameter is calculated by the historical labor cost of regional cigarette delivery, historical logistics cost, historical cigarette purchase cost and historical cigarette sales revenue, and the real-time maximum delivery benefit parameter is calculated by the real-time labor cost of regional cigarette delivery, real-time logistics cost, real-time cigarette purchase cost and real-time cigarette sales revenue.

[0047] The first cigarette brand information parameter or the second cigarette brand information parameter is the brand awareness of the cigarette, which is set to a high awareness if the unit price of the cigarette sold in a store is greater than 100 or less than 30, and the feature vector value is 1; the general awareness if the unit price of the cigarette sold in a store is less than or equal to 100 and greater than or equal to 30, and the feature vector value is 0.

[0048] In this embodiment, if the cigarette brand is less than or equal to 100 and greater than or equal to 30, it is generally well-known, such as Zhonghua, and the unit price of a pack is 100, then its cigarette brand information parameter is 0;

[0049] Furthermore, the first regional character portrait data or the second regional character portrait data is determined based on an average smoking age Y of regional characters and a smoking frequency P of regional characters, with the unit being times / day.

[0050] In this embodiment, the feature vector of the input model is (B h , 0, Y, P).

[0051] Furthermore, the cigarette supply precision delivery model adopts a neural network model, and the neural network model is a DNN convolutional neural network model or an improved CNN convolutional neural network model.

[0052] Furthermore, the activation function calculation formula of the improved CNN convolutional neural network model is as follows:

[0053]

[0054] X is the first cigarette delivery feature or the second cigarette delivery feature, T(X) is the output activation function value, B h represents the maximum investment benefit parameter, Y represents the average smoking age of people in the area, and P represents the smoking frequency of people in the area, with the unit of times / day.

[0055] In this embodiment, since the CNN convolutional neural network model has a strong correlation with the activation function, the cigarette supply precision delivery model can achieve higher cigarette supply delivery accuracy through the conversion of input features and activation functions.

[0056] A cigarette supply precision delivery system is also provided, comprising a cigarette precision delivery data acquisition terminal and a cigarette delivery platform terminal, characterized in that:

[0057] The cigarette precision delivery data acquisition terminal includes a cigarette benefit data collection module, a cigarette production terminal module and a character portrait collection module;

[0058] The cigarette delivery platform terminal includes a cigarette supply precision delivery model building module and a cigarette supply delivery module;

[0059] The cigarette benefit data collection module is connected to the cigarette delivery platform terminal to obtain the historical maximum delivery benefit parameters of the cigarette delivery area and receive the real-time maximum delivery benefit parameters of the target area to be delivered;

[0060] The cigarette production terminal module: obtains the first cigarette brand information parameter, and also obtains the second cigarette brand information parameter;

[0061] The character portrait acquisition module: acquires character portrait data of the first area and also acquires character portrait data of the second area;

[0062] The cigarette supply source precise delivery model construction module: combines the historical maximum delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data to obtain a first cigarette delivery feature, and also combines the real-time maximum delivery benefit parameter, the second cigarette brand information parameter and the second regional character portrait data to obtain a second cigarette delivery feature, and uses the first cigarette delivery feature and the historical cigarette delivery data obtained from the cigarette supply source delivery module to construct a cigarette supply source precise delivery model;

[0063] The cigarette supply delivery module obtains the historical cigarette delivery data corresponding to the historical maximum delivery benefit parameter at this time, and inputs the real-time cigarette delivery data obtained by inputting the second cigarette delivery feature into the cigarette supply precision delivery model to assist in the cigarette supply precision delivery.

[0064] Furthermore, the historical maximum delivery benefit parameter or the real-time maximum delivery benefit parameter B h is the historical labor time cost of regional cigarette placement or the real-time labor time cost of regional cigarette placement C wh , historical logistics cost or real-time logistics cost C fh , historical cigarette purchase cost or real-time cigarette purchase cost C bh and historical cigarette sales revenue or real-time cigarette sales revenue B sh The calculation results are:

[0065] B h = k*(C wh +C fh +C bh -B sh )

[0066] In the formula, k is the benefit adjustment coefficient, and its value range is 0.85-0.95;

[0067] The first cigarette brand information parameter or the second cigarette brand information parameter is the brand awareness of the cigarette, which is set to a high awareness if the unit price of the cigarette sold in a store is greater than 100 or less than 30, and the feature vector value is 1; the general awareness if the unit price of the cigarette sold in a store is less than or equal to 100 and greater than or equal to 30, and the feature vector value is 0.

[0068] Furthermore, the first regional character portrait data or the second regional character portrait data is determined based on an average smoking age Y of regional characters and a smoking frequency P of regional characters, with the unit being times / day.

[0069] Furthermore, the cigarette supply precision delivery model adopts a neural network model, and the neural network model is a DNN convolutional neural network model or an improved CNN convolutional neural network model.

[0070] Furthermore, the activation function calculation formula of the improved CNN convolutional neural network model is as follows:

[0071]

[0072] X is the first cigarette delivery feature or the second cigarette delivery feature, T(X) is the output activation function value, B h represents the maximum investment benefit parameter, Y represents the average smoking age of people in the area, and P represents the smoking frequency of people in the area, with the unit of times / day.

[0073] The present invention limits the feature influencing factors to a few main feature vectors by utilizing an improved deep learning model. In the process of utilizing the deep learning model, refined feature processing is adopted to perform refined model correction processing for specific application scenarios on the main factors affecting cigarette delivery. Feature automatic processing is performed on the activation function that affects the model's ability to accurately predict delivery, thereby enhancing the generalization ability of the model. The present invention utilizes historical revenue data combined with brand information and regional character portraits combined with feature vectors for processing to obtain an accurate cigarette delivery plan. The delivery plan obtained by the present invention using the improved deep learning model improves the work efficiency of cigarette delivery, reduces cigarette inventory pressure, increases turnover rate, promotes a positive cigarette market situation, and improves customer satisfaction in retail stores.

[0074] The control device may include a processor 401 and a memory 402 storing computer program instructions. Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present invention.

[0075] Memory 402 may include a large capacity memory for data or instructions. For example, but not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, memory 402 may include a removable or non-removable (or fixed) medium. In appropriate cases, memory 402 may be inside or outside a data processing device. In a specific embodiment, memory 402 is a non-volatile solid-state memory. In a specific embodiment, memory 402 includes a read-only memory (ROM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.

[0076] The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the methods for analyzing the storage tank detection data in the above embodiments.

[0077] In one example, the electronic device may further include a communication interface 403 and a bus 410. Figure 3 As shown, the processor 401, the memory 402, and the communication interface 403 are connected and communicate with each other via a bus 410. The communication interface 403 is mainly used to implement the communication between the modules, devices, units and / or equipment in the embodiment of the present invention.

[0078] Bus 410 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 410 may include one or more buses. Although the embodiment of the present invention describes and shows a specific bus, the present invention considers any suitable bus or interconnection.

[0079] Of course, it can be understood that each embodiment of the present invention can achieve one of the effects alone, and a combination of multiple embodiments of the present invention can achieve all of the above effects, but it is not required that every embodiment of the present invention achieve all of the above advantages and effects, because each embodiment of the present invention can constitute a separate technical solution and make one or more contributions to the prior art.

[0080] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A method for accurately delivering cigarette supplies, characterized in that: The method comprises: A1. Obtain the historical maximum cigarette delivery benefit parameter of the cigarette delivery area, the first cigarette brand information parameter and the first regional character portrait data, and obtain the historical cigarette delivery data corresponding to the delivery at this time; A2, combining the historical maximum delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data to obtain a first cigarette delivery feature; A3. Constructing a cigarette supply precision delivery model based on the first cigarette delivery characteristics and the historical cigarette delivery data; A4. Receive the real-time maximum delivery benefit parameter of the target area to be delivered, the second cigarette brand information parameter and the second area character portrait data, combine the real-time maximum delivery benefit parameter, the second cigarette brand information parameter and the second area character portrait data to obtain the second cigarette delivery feature, use the cigarette supply precision delivery model to process the second cigarette delivery feature to generate real-time cigarette delivery data, and assist in the cigarette supply precision delivery according to the real-time cigarette delivery data.

2. A method for accurately delivering cigarette supplies according to claim 1, characterized in that: The historical maximum delivery benefit parameter or the real-time maximum delivery benefit parameter B h is the historical labor time cost of regional cigarette placement or the real-time labor time cost of regional cigarette placement C wh , historical logistics cost or real-time logistics cost C fh , historical cigarette purchase cost or real-time cigarette purchase cost C bh and historical cigarette sales revenue or real-time cigarette sales revenue B sh Calculated; The first cigarette brand information parameter or the second cigarette brand information parameter is the brand awareness of the cigarette, which is set to a high awareness if the unit price of the cigarette sold in a store is greater than 100 or less than 30, and the feature vector value is 1; the general awareness if the unit price of the cigarette sold in a store is less than or equal to 100 and greater than or equal to 30, and the feature vector value is 0.

3. A method for accurately delivering cigarette supplies according to claim 1, characterized in that: The first regional character portrait data or the second regional character portrait data is determined based on the average smoking age Y of regional characters and the smoking frequency P of regional characters, with the unit being times / day.

4. A method for accurately delivering cigarette supplies according to claim 1, characterized in that: The cigarette supply precision delivery model adopts a neural network model, and the neural network model is a DNN convolutional neural network model or an improved CNN convolutional neural network model.

5. A cigarette supply precision delivery system, comprising a cigarette precision delivery data acquisition terminal and a cigarette delivery platform terminal, characterized in that: The cigarette precision delivery data acquisition terminal includes a cigarette benefit data collection module, a cigarette production terminal module and a character portrait collection module; The cigarette delivery platform terminal includes a cigarette supply precision delivery model building module and a cigarette supply delivery module; The cigarette benefit data collection module is connected to the cigarette delivery platform terminal to obtain the historical maximum delivery benefit parameters of the cigarette delivery area and receive the real-time maximum delivery benefit parameters of the target area to be delivered; The cigarette production terminal module: obtains the first cigarette brand information parameter, and also obtains the second cigarette brand information parameter; The character portrait acquisition module: acquires character portrait data of the first area and also acquires character portrait data of the second area; The cigarette supply source precise delivery model construction module: combines the historical maximum delivery benefit parameter, the first cigarette brand information parameter and the first regional character portrait data to obtain a first cigarette delivery feature, and also combines the real-time maximum delivery benefit parameter, the second cigarette brand information parameter and the second regional character portrait data to obtain a second cigarette delivery feature, and uses the first cigarette delivery feature and the historical cigarette delivery data obtained from the cigarette supply source delivery module to construct a cigarette supply source precise delivery model; The cigarette supply delivery module obtains the historical cigarette delivery data corresponding to the historical maximum delivery benefit parameter at this time, and inputs the real-time cigarette delivery data obtained by inputting the second cigarette delivery feature into the cigarette supply precision delivery model to assist in the cigarette supply precision delivery.

6. A cigarette supply precision delivery system as claimed in claim 5, characterized in that: The historical maximum delivery benefit parameter or the real-time maximum delivery benefit parameter B h is the historical labor time cost of regional cigarette placement or the real-time labor time cost of regional cigarette placement C wh , historical logistics cost or real-time logistics cost C fh , historical cigarette purchase cost or real-time cigarette purchase cost C bh and historical cigarette sales revenue or real-time cigarette sales revenue B sh Calculated; The first cigarette brand information parameter or the second cigarette brand information parameter is the brand awareness of the cigarette, which is set to a high awareness if the unit price of the cigarette sold in a store is greater than 100 or less than 30, and the feature vector value is 1; the general awareness if the unit price of the cigarette sold in a store is less than or equal to 100 and greater than or equal to 30, and the feature vector value is 0.

7. A cigarette supply precision delivery system as claimed in claim 6, characterized in that: The first regional character portrait data or the second regional character portrait data is determined based on the average smoking age Y of regional characters and the smoking frequency P of regional characters, with the unit being times / day.

8. A cigarette supply precision delivery system as claimed in claim 7, characterized in that: The cigarette supply precision delivery model adopts a neural network model, and the neural network model is a DNN convolutional neural network model or an improved CNN convolutional neural network model.

Images