CN112200524B - High-precision intelligent recommendation system and intelligent recommendation method thereof - Google Patents
High-precision intelligent recommendation system and intelligent recommendation method thereof Download PDFInfo
- Publication number
- CN112200524B CN112200524B CN202011392340.5A CN202011392340A CN112200524B CN 112200524 B CN112200524 B CN 112200524B CN 202011392340 A CN202011392340 A CN 202011392340A CN 112200524 B CN112200524 B CN 112200524B
- Authority
- CN
- China
- Prior art keywords
- seller
- service
- portrait
- supplier
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent recommendation system with high accuracy and an intelligent recommendation method thereof. The method comprises the following steps: analyzing historical data of the logistics service of the supplier and obtaining a service portrait of the supplier; acquiring a seller portrait through data analysis selected by a seller historical logistics scheme; setting a data updating period, and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period; utilizing a provider service portrait and a seller portrait, calculating and acquiring the matching degree between the provider service image and a user image, and recommending and displaying the provider service image and the corresponding matching degree to the seller according to the sequence from top to bottom of the matching degree; the seller selects a logistics scheme according to the provided provider service image. The system comprises modules corresponding to the method steps.
Description
Technical Field
The invention provides an intelligent recommendation system with high accuracy and an intelligent recommendation method thereof, and belongs to the technical field of logistics.
Background
In a traditional supply chain solution system, the system provides cross-border e-commerce sellers (hereinafter referred to as sellers) with a batch of logistics schemes and the cost and the timeliness required by the schemes, and the sellers need to compare different logistics schemes according to the logistics cost, the timeliness, the risk and other factors and independently select the schemes meeting the requirements of the sellers. This approach presents several significant problems:
1. the seller cannot quickly obtain the optimal logistics solution.
2. The calculation amount is large, and the seller can calculate by himself and easily makes mistakes.
Disclosure of Invention
The invention provides an intelligent recommendation system with high accuracy and an intelligent recommendation method thereof, which are used for solving the problems that the existing supply chain solution system easily causes that a seller cannot quickly obtain an optimal logistics solution, and the seller easily makes mistakes in self-calculation due to large calculation amount:
the invention provides an intelligent recommendation method with high accuracy, which comprises the following steps:
analyzing historical data of the logistics service of the supplier, and obtaining a service image of the supplier with service timeliness, service timeliness achievement rate and seller unit charging cost;
acquiring a seller portrait with seller expected timeliness, seller expected service timeliness achievement rate and seller expected unit charging re-cost through data analysis of seller historical logistics scheme selection;
setting a data updating period, and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period;
utilizing a provider service portrait and a seller portrait, calculating and acquiring the matching degree between the provider service portrait and the seller portrait, and recommending and displaying the provider service portrait and the corresponding matching degree to the seller according to the sequence from top to bottom of the matching degree;
the seller selects a logistics plan based on the provided vendor service representation.
Further, in the provider service image, the "service aging", "service aging achievement rate", and "seller unit charging re-cost" are obtained by the following formulas:
wherein the content of the first and second substances,Trepresenting service aging;T g representing a provider service age;Srepresenting an achievement rate in service;Can order quantity representing an agreed time period to reach the supplier;C z represents the total effective order amount;Wrepresenting the seller unit billing reimbursement cost,W z represents a total selling price;H z indicating a total valid billing weight.
Further, through data analysis of the seller historical logistics scheme selection, a seller portrait with "seller expected time efficiency", "seller expected service time efficiency" and "seller expected unit charging weight cost" is obtained, which includes:
counting the delivery data of the seller, and carrying out statistical grouping on the delivery data according to the single SKU value to obtain all expected aging data models in different value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
counting logistics registration grading data of sellers on the ebay, amazon and wish platforms, grouping expected time efficiency with the E-commerce platform as a dimension, counting delivery data in each group, and acquiring the median of all service actual time efficiency as the expected service time efficiency of the sellers;
and counting the delivery data of the seller by taking the delivery bin as a dimension, and acquiring a median from the delivery cost data of the single bin to be used as the expected unit charging heavy cost of the single bin.
Further, the setting of the data update cycle, automatically updating the vendor service representation and the seller representation according to the history data generated in the data update cycle, includes:
automatically updating the supplier service portrait and the seller portrait according to historical data generated in a data updating period with a preset fixed time length as a data updating period;
or, when the total effective order quantity of the supplier exceeds a preset effective order quantity threshold value continuously for five days, acquiring a data updating period with automatic adjustability through the following formula, and automatically updating the supplier service image and the seller according to historical data generated in the data updating period with automatic adjustability:
wherein the content of the first and second substances,T c indicating the adjusted data update period,T 0indicating a preset initial default data updating period;λthe value of the adjustment coefficient is represented,λthe value range of (A) is 0.91-0.95; preferably 0.93; deltaTRepresents a time adjustment amount;C zi indicating that the total effective order quantity of the supplier exceeds the preset effective order quantity threshold value in five consecutive daysiTotal effective order volume for the day's suppliers;C y representing a preset valid order quantity threshold; max (C zi - C y ) Indicating supplier availabilityThe effective order quantity exceeds the maximum quantity value of a preset effective order quantity threshold value; min (C zi - C y ) A quantity minimum value representing a total available order quantity for the supplier exceeding a preset threshold of available order quantity.
Further, the obtaining a matching degree between the vendor service portrait and the vendor portrait by calculation using the vendor service portrait and the vendor portrait includes:
using service aging, seller unit charging re-cost and service aging achievement rate as X, Y and Z axis to form a three-dimensional coordinate system; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image;
calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system, and sequencing the suppliers according to the sequence of the linear distance from short to long; wherein, the straight line distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the user portrait, and the shorter the straight line distance is, the higher the matching degree is;
wherein, the linear distance is obtained by the following formula:
wherein the content of the first and second substances,Fwhich indicates the location of the supplier,Sa representation of a seller,X F 、Y F andZ F respectively representing suppliers in three-dimensional coordinate systemsX、YAndZcoordinates on an axis;X S 、Y S andZ S respectively, representing the coordinates of the seller.
A high-accuracy intelligent recommendation system, the system comprising:
the service portrait acquisition module is used for analyzing historical data of the logistics service of the supplier and acquiring a service portrait of the supplier with service timeliness, service timeliness achievement rate and seller unit charging cost;
the seller portrait acquisition module is used for acquiring seller portraits with seller expected time efficiency, seller expected service time efficiency and seller expected unit charging weight cost through data analysis of seller historical logistics scheme selection;
the data updating module is used for setting a data updating period and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period;
the matching degree acquisition module is used for acquiring the matching degree between the supplier service portrait and the seller portrait by calculation by utilizing the supplier service portrait and the seller portrait, and recommending and displaying the supplier service portrait and the corresponding matching degree to the seller according to the sequence from top to bottom according to the matching degree;
and the logistics scheme determining module is used for selecting a logistics scheme by the seller according to the provided supplier service portrait.
Further, in the provider service image, the "service aging", "service aging achievement rate", and "seller unit charging re-cost" are obtained by the following formulas:
wherein the content of the first and second substances,Trepresenting service aging;T g representing a provider service age;Srepresenting an achievement rate in service;Can order quantity representing an agreed time period to reach the supplier;C z represents the total effective order amount;Wrepresenting the seller unit billing reimbursement cost,W z represents a total selling price;H z indicating a total valid billing weight.
Further, the seller representation acquisition module includes:
the expected time-efficient value acquisition module is used for counting the delivery data of the seller, counting and grouping the delivery data according to the single SKU delivery value and acquiring all expected time-efficient data models in different delivery value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
the time efficiency obtaining module is used for counting logistics registration grading data of the seller on the ebay, amazon and wish platforms, grouping expected time efficiency by taking the e-commerce platform as a dimension, counting delivery data in each group, and obtaining the median of the actual time efficiency of all services as the expected service time efficiency of the seller;
and the charging heavy cost acquisition module is used for counting the delivery data of the seller by taking the delivery bin as a dimension, and acquiring a median from the delivery cost data of the single bin to be used as the expected unit charging heavy cost of the single bin.
Further, the data update module comprises:
the period presetting module is used for automatically updating the supplier service portrait and the seller portrait according to historical data generated in a data updating period with a fixed time length set in advance as the data updating period;
the period adjusting module is used for acquiring a data updating period with automatic adjustability through the following formula when the total effective order quantity of the supplier exceeds a preset effective order quantity threshold value continuously appearing for five days, and automatically updating the supplier service image and the seller image according to historical data generated in the data updating period with automatic adjustability:
wherein the content of the first and second substances,T c indicating the adjusted data update period,T 0indicating a preset initial default data updating period;λthe value of the adjustment coefficient is represented,λthe value range of (A) is 0.91-0.95; preferably 0.93; deltaTRepresents a time adjustment amount;C zi indicating five consecutive days the supplier was effectiveWhen the total effective order quantity exceeds the preset effective order quantity threshold value, the first stepiTotal effective order volume for the day's suppliers;C y representing a preset valid order quantity threshold; max (C zi - C y ) A quantity maximum value representing that the total available order quantity available for the supplier exceeds a preset available order quantity threshold value; min (C zi - C y ) A quantity minimum value representing a total available order quantity for the supplier exceeding a preset threshold of available order quantity.
Further, the matching degree obtaining module includes:
the coordinate system establishing module is used for forming a three-dimensional coordinate system by taking service timeliness, seller unit charging re-cost and service timeliness achievement rate as X, Y and a Z axis; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image;
the matching degree determining module is used for calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system and sequencing the suppliers according to the sequence of the linear distance from short to long; wherein, the straight line distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the user portrait, and the shorter the straight line distance is, the higher the matching degree is;
wherein, the linear distance is obtained by the following formula:
wherein the content of the first and second substances,Fwhich indicates the location of the supplier,Sa representation of a seller,X F 、Y F andZ F respectively representing suppliers in three-dimensional coordinate systemsX、YAndZcoordinates on an axis;X S 、Y S andZ S respectively, representing the coordinates of the seller.
The invention has the beneficial effects that:
the intelligent recommendation system and the intelligent recommendation method with high accuracy are simple to use, and sellers can obtain the optimal recommendation result of the logistics scheme by one key only by describing and clarifying own requirements. Meanwhile, the intelligent recommendation system and the intelligent recommendation method thereof provided by the invention can quickly acquire the recommendation of the optimal scheme, and can simultaneously recommend more than 200 logistics schemes within 1s, so that sellers can quickly and directly acquire the optimal logistics solution, and the calculation amount is extremely small, thereby effectively avoiding the self-calculation and error conditions of sellers.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a block diagram of the system of the present invention; a
FIG. 3 is a schematic diagram of the operation of the system of the present invention;
FIG. 4 is a diagram of a vendor service drawing of the present invention including elements;
FIG. 5 is a diagram illustrating a vendor drawing including elements according to the present invention;
FIG. 6 is a schematic diagram of the matching degree calculation of the method and system of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides an intelligent recommendation method with high accuracy, as shown in fig. 1, 4 and 5, the method comprises the following steps:
s1, analyzing historical data of the logistics service of the supplier, and obtaining a service image of the supplier with service timeliness, service timeliness achievement rate and seller unit charging re-cost;
s2, acquiring a seller portrait with seller expected time efficiency, seller expected service time efficiency and seller expected unit charging cost through data analysis of seller historical logistics scheme selection;
s3, setting a data updating period, and automatically updating the supplier service portrait and the seller portrait according to the historical data generated in the data updating period;
s4, acquiring the matching degree between the supplier service portrait and the seller portrait by calculation by utilizing the supplier service portrait and the seller portrait, and recommending and displaying the supplier service portrait and the corresponding matching degree to the seller according to the matching degree from top to bottom;
and S5, selecting a logistics scheme by the seller according to the provided supplier service portrait. Among them, there are two recommended ways:
first, the seller uses the service with the highest matching degree in the service recommendation list of the provider as the logistics scheme of the seller by default.
And secondly, the seller selects the service meeting the actual conditions as the logistics scheme of the seller according to the recommended service matching degree of the supplier.
In the provider service portrait, the service timeliness achievement rate and the seller unit charging re-cost are obtained by the following formulas:
wherein the content of the first and second substances,Trepresenting service aging;T g representing a provider service age;Srepresenting an achievement rate in service;Can order quantity representing an agreed time period to reach the supplier;C z represents the total effective order amount;Wrepresenting the seller unit billing reimbursement cost,W z represents a total selling price;H z indicating a total valid billing weight.
The working principle of the technical scheme is as follows: through analyzing the historical data of the logistics service of the supplier, the service picture of the supplier with service timeliness, service timeliness achievement rate and seller unit charging re-cost is obtained. And (4) obtaining the seller portrait of 'seller expected timeliness', 'seller expected service timeliness achievement rate' and 'seller expected unit charging heavy cost' by selecting data analysis on the seller historical logistics scheme. Here, the period of the historical data of the supplier and the seller can be customized, and can be 1 natural month or several natural days; or may be obtained by calculation with a formula. The system automatically updates the image based on the cycle selection.
The effect of the above technical scheme is as follows: the method is simple to use, and sellers can obtain the optimal recommendation result of the logistics scheme in a one-key mode only by describing clear needs of the sellers. Meanwhile, the recommendation of the optimal scheme can be quickly acquired, more than 200 logistics schemes can be simultaneously recommended within 1s, so that the seller can quickly and directly acquire the optimal logistics solution, the calculation amount is extremely small, and the self-calculation and error conditions of the seller are effectively avoided.
In an embodiment of the present invention, a seller portrait with "seller expected aging", "seller expected service aging achievement rate" and "seller expected unit charging weight cost" is obtained by analyzing data selected by a seller historical logistics scheme, including:
s201, counting delivery data of a seller, and carrying out counting grouping on the delivery data according to a single SKU value to obtain data models of all expected timeliness in different value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
s202, counting logistics registration grading data of the seller on the ebay, amazon and wish platforms, grouping expected time achievement rates by taking the e-commerce platform as a dimension, counting delivery data in each group, and acquiring a median of actual time achievement rates of all services to serve as the expected time achievement rates of the seller;
s203, taking the delivery warehouse as a dimension, counting delivery data of the seller, acquiring a median from the delivery cost data of the single warehouse, and taking the median as the expected unit charging heavy cost of the single warehouse.
The working principle of the technical scheme is as follows: firstly, counting delivery data of a seller, and carrying out statistical grouping on the delivery data according to a single SKU value to obtain data models of all expected timeliness in different value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping; then, counting logistics registration grading data of the seller on the ebay, amazon and wish platforms, grouping expected time efficiency by taking the e-commerce platform as a dimension, counting delivery data in each group, and acquiring a median of all actual service time efficiency as expected service time efficiency of the seller; and finally, counting the delivery data of the seller by taking the delivery warehouse as a dimension, acquiring a median from the delivery cost data of the single warehouse, and taking the median as the expected unit charging cost of the single warehouse.
The effect of the above technical scheme is as follows: the accuracy of the expected time effective value, the seller expected service time achievement rate and the expected unit charging heavy cost is effectively improved, meanwhile, the expected time effective value, the seller expected service time achievement rate and the expected unit charging heavy cost obtained through the method are higher in matching with the actual delivery condition of the seller, and a data basis which is accurate and meets actual requirements is provided for obtaining the subsequent logistics optimal scheme. On the other hand, the expected time effective value, the seller expected service time achievement rate and the expected unit charging heavy cost are obtained through the method, the data calculation amount can be effectively reduced, the data obtaining steps are simplified, and the data obtaining efficiency is improved.
In one embodiment of the present invention, the setting of a data update cycle for automatically updating the vendor service image and the vendor service image based on history data generated in the data update cycle includes:
automatically updating the supplier service portrait and the seller portrait according to historical data generated in a data updating period with a preset fixed time length as a data updating period;
or, when the total effective order quantity of the supplier exceeds a preset effective order quantity threshold value continuously for five days, acquiring a data updating period with automatic adjustability through the following formula, and automatically updating the supplier service image and the seller according to historical data generated in the data updating period with automatic adjustability:
wherein the content of the first and second substances,T c indicating the adjusted data update period,T 0indicating a preset initial default data updating period;λthe value of the adjustment coefficient is represented,λthe value range of (A) is 0.91-0.95; preferably 0.93; deltaTRepresents a time adjustment amount;C zi indicating that the total effective order quantity of the supplier exceeds the preset effective order quantity threshold value in five consecutive daysiTotal effective order volume for the day's suppliers;C y representing a preset valid order quantity threshold; max (C zi - C y ) A quantity maximum value representing that the total available order quantity available for the supplier exceeds a preset available order quantity threshold value; min (C zi - C y ) A quantity minimum value representing a total available order quantity for the supplier exceeding a preset threshold of available order quantity.
The working principle and the effect of the technical scheme are as follows: the data updating period is calculated and obtained according to the preset fixed time length or the actual effective order quantity of the supplier. The data updating period is obtained through the adjusting mode, and the data period can be adjusted according to the order quantity condition of the actual supplier. And when the actual total order quantity of the supplier continuously exceeds the preset order quantity threshold value for 5 days in a single day, shortening and adjusting the data updating period, and improving the data updating frequency so as to provide a timely and effective data basis for acquiring the subsequent logistics optimal scheme. Meanwhile, the time adjustment variation amount Δ obtained by the above formulaTThe accuracy of time adjustment and the matching of the time adjustment and the actual data change of the order quantity can be effectively improved, and the timeliness of data updating and acquiring is improved.
In one embodiment of the present invention, the obtaining a matching degree between a vendor service representation and a vendor representation by calculation using the vendor service representation and the vendor representation comprises:
s401, taking service aging, seller unit charging re-cost and service aging achievement rate as X, Y and a Z axis to form a three-dimensional coordinate system; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image;
s402, calculating the linear distance between each coordinate point and a seller portrait in the three-dimensional coordinate system, and sequencing the suppliers according to the sequence of the linear distances from short to long; wherein, the straight line distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the user portrait, and the shorter the straight line distance is, the higher the matching degree is;
wherein, the linear distance is obtained by the following formula:
wherein the content of the first and second substances,Fwhich indicates the location of the supplier,Sa representation of a seller,X F 、Y F andZ F respectively representing suppliers in three-dimensional coordinate systemsX、YAndZcoordinates on an axis;X S 、Y S andZ S respectively, representing the coordinates of the seller.
The working principle of the technical scheme is as follows: firstly, taking service aging, seller unit charging re-cost and service aging achievement rate as X, Y and a Z axis to form a three-dimensional coordinate system; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image; then, calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system, and sequencing the suppliers according to the sequence of the linear distance from short to long; wherein, the linear distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the user portrait, and the shorter the linear distance is, the higher the matching degree is
Specifically, as shown in fig. 6, the seller portrait data is matched according to the current seller's delivery warehouse, the delivery value and the e-commerce platform information.
In the three-dimensional coordinate system, "age", "cost" and "age achievement ratio" are represented by X, Y, Z axes, A, B, C, D and other points in the coordinate system are images of suppliers available for a certain delivery warehouse, S point is an image of a user, wherein the coordinates of A, B, C, D and S and other points in the coordinate system are: a (A)X a ，Y a ，Z a ）、B（X b ，Y b ，Z b ）、C（X c ，Y c ，Z c ）、D（X d ，Y d ，Z d ) And S: (X s ，Y s ，Z s ）。
The linear distance from the point S to the point A, B, C, D is sorted from short to long, that is, the matching degree between the provider service image and the user image is sorted. Wherein, the linear distances from the point S to A, B, C, D are respectively:
the vendor service is taken from high to low in turn to be exposed to the seller. Wherein, the shorter the distance is, the higher the matching degree is, the matching degree is screened as follows:
the effect of the above technical scheme is as follows: by the method, the service recommendation list of the provider and the service object with the highest visual matching degree can be quickly obtained, and then the default logistics scheme corresponding to the service object with the highest matching degree is quickly obtained or the seller carries out the user-defined logistics scheme according to the service object with the highest visual matching degree. The method and the device improve the efficiency of the seller in acquiring the optimal logistics scheme, save time, simplify the calculation process, effectively reduce the data calculation amount and further reduce the calculation error and the error rate in the matching degree acquisition process.
An embodiment of the present invention provides an intelligent recommendation system with high accuracy, as shown in fig. 2, the system includes:
the service portrait acquisition module is used for analyzing historical data of the logistics service of the supplier and acquiring a service portrait of the supplier with service timeliness, service timeliness achievement rate and seller unit charging cost;
the seller portrait acquisition module is used for acquiring seller portraits with seller expected time efficiency, seller expected service time efficiency and seller expected unit charging weight cost through data analysis of seller historical logistics scheme selection;
the data updating module is used for setting a data updating period and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period;
the matching degree acquisition module is used for acquiring the matching degree between the supplier service portrait and the seller portrait by calculation by utilizing the supplier service portrait and the seller portrait, and recommending and displaying the supplier service portrait and the corresponding matching degree to the seller according to the sequence from top to bottom according to the matching degree;
and the logistics scheme determining module is used for selecting a logistics scheme by the seller according to the provided supplier service portrait.
In the provider service portrait, the service timeliness achievement rate and the seller unit charging re-cost are obtained by the following formulas:
wherein the content of the first and second substances,Trepresenting service aging;T g representing a provider service age;Srepresenting an achievement rate in service;Cindicating achievement of supplyThe amount of orders the trader promises to age;C z represents the total effective order amount;Wrepresenting the seller unit billing reimbursement cost,W z represents a total selling price;H z indicating a total valid billing weight.
The application scenario and implementation process of the system described in this embodiment are as follows:
when the seller uses the excle to import the logistics list in batches, the system automatically recommends a batch of logistics schemes with lower cost and higher timeliness for the seller to select according to the information of the delivery warehouse and the logistics service imported by the seller.
And finding other logistics schemes available in association in the supply chain system according to the logistics scheme preliminarily selected by the seller, calculating the seller cost of the logistics schemes, and calculating the time effectiveness of the logistics schemes if the seller cost is consistent. And recommending available logistics schemes for the sellers according to the sequence of lowest cost and highest timeliness of the sellers.
The working principle of the technical scheme is as follows: firstly, analyzing historical data of a supplier logistics service by using a service portrait acquisition module, and acquiring a supplier service portrait with service timeliness, service timeliness achievement rate and seller unit charging cost; then, a seller portrait acquisition module is adopted to acquire seller portraits with seller expected timeliness, seller expected service timeliness achievement rate and seller expected unit charging weight cost through data analysis of seller historical logistics scheme selection; then, setting a data updating period through a data updating module, and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period; utilizing a supplier service portrait and a seller portrait through a matching degree acquisition module, calculating and acquiring the matching degree between the supplier service portrait and the seller portrait, and recommending and displaying the supplier service portrait and the corresponding matching degree to a seller according to the matching degree from top to bottom; finally, a logistics plan determination module is used for enabling the seller to select a logistics plan according to the provided supplier service portrait.
The effect of the above technical scheme is as follows: the method is simple to use, and sellers can obtain the optimal recommendation result of the logistics scheme in a one-key mode only by describing clear needs of the sellers. Meanwhile, the recommendation of the optimal scheme can be quickly acquired, more than 200 logistics schemes can be simultaneously recommended within 1s, so that the seller can quickly and directly acquire the optimal logistics solution, the calculation amount is extremely small, and the self-calculation and error conditions of the seller are effectively avoided.
In one embodiment of the invention, the seller representation acquisition module includes:
the expected time-efficient value acquisition module is used for counting the delivery data of the seller, counting and grouping the delivery data according to the single SKU delivery value and acquiring all expected time-efficient data models in different delivery value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
the time efficiency obtaining module is used for counting logistics registration grading data of the seller on the ebay, amazon and wish platforms, grouping expected time efficiency by taking the e-commerce platform as a dimension, counting delivery data in each group, and obtaining the median of the actual time efficiency of all services as the expected service time efficiency of the seller;
and the charging heavy cost acquisition module is used for counting the delivery data of the seller by taking the delivery bin as a dimension, and acquiring a median from the delivery cost data of the single bin to be used as the expected unit charging heavy cost of the single bin.
The working principle of the technical scheme is as follows: the method comprises the steps that firstly, an expected time-efficient value obtaining module is used for counting delivery data of sellers, carrying out statistical grouping on the delivery data according to single SKU delivery values, and obtaining all expected time-efficient data models in different delivery value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
the time efficiency obtaining module is used for counting logistics registration grading data of the seller on the ebay, amazon and wish platforms, grouping expected time efficiency by taking the e-commerce platform as a dimension, counting delivery data in each group, and obtaining the median of the actual time efficiency of all services as the expected service time efficiency of the seller;
and the charging heavy cost acquisition module is used for counting the delivery data of the seller by taking the delivery bin as a dimension, and acquiring a median from the delivery cost data of the single bin to be used as the expected unit charging heavy cost of the single bin.
The effect of the above technical scheme is as follows: the accuracy of the expected time effective value, the seller expected service time achievement rate and the expected unit charging heavy cost is effectively improved, meanwhile, the expected time effective value, the seller expected service time achievement rate and the expected unit charging heavy cost obtained through the method are higher in matching with the actual delivery condition of the seller, and a data basis which is accurate and meets actual requirements is provided for obtaining the subsequent logistics optimal scheme. On the other hand, the expected time effective value, the seller expected service time achievement rate and the expected unit charging heavy cost are obtained through the method, the data calculation amount can be effectively reduced, the data obtaining steps are simplified, and the data obtaining efficiency is improved.
In an embodiment of the present invention, the data update module includes:
the period presetting module is used for automatically updating the supplier service portrait and the seller portrait according to historical data generated in a data updating period with a fixed time length set in advance as the data updating period;
the period adjusting module is used for acquiring a data updating period with automatic adjustability through the following formula when the total effective order quantity of the supplier exceeds a preset effective order quantity threshold value continuously appearing for five days, and automatically updating the supplier service image and the seller image according to historical data generated in the data updating period with automatic adjustability:
wherein the content of the first and second substances,T c indicating the adjusted data update period,T 0indicating a preset initial default data updating period;λindicating the adjustment coefficient，λThe value range of (A) is 0.91-0.95; preferably 0.93; deltaTRepresents a time adjustment amount;C zi indicating that the total effective order quantity of the supplier exceeds the preset effective order quantity threshold value in five consecutive daysiTotal effective order volume for the day's suppliers;C y representing a preset valid order quantity threshold; max (C zi - C y ) A quantity maximum value representing that the total available order quantity available for the supplier exceeds a preset available order quantity threshold value; min (C zi - C y ) A quantity minimum value representing a total available order quantity for the supplier exceeding a preset threshold of available order quantity.
The working principle and the effect of the technical scheme are as follows: the data updating period is calculated and obtained according to the preset fixed time length or the actual effective order quantity of the supplier. The data updating period is obtained through the adjusting mode, and the data period can be adjusted according to the order quantity condition of the actual supplier. And when the actual total order quantity of the supplier continuously exceeds the preset order quantity threshold value for 5 days in a single day, shortening and adjusting the data updating period, and improving the data updating frequency so as to provide a timely and effective data basis for acquiring the subsequent logistics optimal scheme. Meanwhile, the time adjustment variation amount Δ obtained by the above formulaTThe accuracy of time adjustment and the matching of the time adjustment and the actual data change of the order quantity can be effectively improved, and the timeliness of data updating and acquiring is improved.
In an embodiment of the present invention, the matching degree obtaining module includes:
the coordinate system establishing module is used for forming a three-dimensional coordinate system by taking service timeliness, seller unit charging re-cost and service timeliness achievement rate as X, Y and a Z axis; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image;
the matching degree determining module is used for calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system and sequencing the suppliers according to the sequence of the linear distance from short to long; wherein, the straight line distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the user portrait, and the shorter the straight line distance is, the higher the matching degree is;
wherein, the linear distance is obtained by the following formula:
wherein the content of the first and second substances,Fwhich indicates the location of the supplier,Sa representation of a seller,X F 、Y F andZ F respectively representing suppliers in three-dimensional coordinate systemsX、YAndZcoordinates on an axis;X S 、Y S andZ S respectively, representing the coordinates of the seller.
The working principle of the technical scheme is as follows: firstly, forming a three-dimensional coordinate system by using service timeliness, seller unit charging heavy cost and service timeliness achievement rate as X, Y and a Z axis through a coordinate system establishing module; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image; then, calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system by using a matching degree determination module, and sequencing the suppliers according to the sequence of the linear distance from short to long; and the linear distance between each coordinate point and the seller portrait is the matching degree between each provider service portrait and the user portrait, and the shorter the linear distance is, the higher the matching degree is.
The effect of the above technical scheme is as follows: by the method, the service recommendation list of the provider and the service object with the highest visual matching degree can be quickly obtained, and then the default logistics scheme corresponding to the service object with the highest matching degree is quickly obtained or the seller carries out the user-defined logistics scheme according to the service object with the highest visual matching degree. The method and the device improve the efficiency of the seller in acquiring the optimal logistics scheme, save time, simplify the calculation process, effectively reduce the data calculation amount and further reduce the calculation error and the error rate in the matching degree acquisition process.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. An intelligent recommendation method with high accuracy, characterized in that the method comprises:
analyzing historical data of the logistics service of the supplier, and obtaining a service image of the supplier with service timeliness, service timeliness achievement rate and seller unit charging cost;
acquiring a seller portrait with seller expected timeliness, seller expected service timeliness achievement rate and seller expected unit charging re-cost through data analysis of seller historical logistics scheme selection;
setting a data updating period, and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period;
utilizing a provider service portrait and a seller portrait, calculating and acquiring the matching degree between the provider service portrait and the seller portrait, and recommending and displaying the provider service portrait and the corresponding matching degree to the seller according to the matching degree from high to low;
the seller selects a logistics scheme according to the provided provider service portrait;
wherein automatically updating the vendor service representation and the vendor representation based on historical data generated during the data update period comprises:
when the total effective order quantity of the supplier exceeds a preset effective order quantity threshold value for five days, acquiring a data updating period with automatic adjustability through the following formula, and automatically updating the supplier service image and the seller image according to historical data generated in the data updating period with automatic adjustability:
wherein the content of the first and second substances,T c indicating the adjusted data update period,T 0indicating a preset initial default data updating period;λthe value of the adjustment coefficient is represented,λthe value range of (A) is 0.91-0.95; deltaTRepresents a time adjustment amount;C zi indicating that the total available order volume of the supplier exceeds a preset threshold of available order volume for five consecutive daysiTotal effective order volume for the day's suppliers;C y representing a preset valid order quantity threshold; max (C zi - C y ) A quantity maximum value representing that the total available order quantity of the suppliers exceeds a preset available order quantity threshold value; min (C zi - C y ) A quantity minimum value representing a total available order quantity for the supplier exceeding a preset available order quantity threshold.
2. The method of claim 1, wherein the "service aging," "service aging achievement rate," and "vendor unit billing re-cost" in the provider service representation are obtained by the following equations:
wherein the content of the first and second substances,Trepresenting service aging;T g representing a provider service age;Srepresenting an achievement rate in service;Can order quantity representing an agreed time period to reach the supplier;C z represents the total effective order amount;Wrepresenting the seller unit billing reimbursement cost,W z represents a total selling price;H z indicating total effective chargingAnd (4) heavy.
3. The method of claim 1, wherein obtaining the seller representation with "seller expected time period", "seller expected service time period achievement rate" and "seller expected unit charge weight cost" through data analysis of seller historical logistics plan selection comprises:
counting the delivery data of the seller, and carrying out statistical grouping on the delivery data according to the single SKU value to obtain all expected aging data models in different value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
counting logistics registration grading data of sellers on the ebay, amazon and wish platforms, grouping expected time efficiency with the E-commerce platform as a dimension, counting delivery data in each group, and acquiring the median of all service actual time efficiency as the expected service time efficiency of the sellers;
and counting the delivery data of the seller by taking the delivery bin as a dimension, and acquiring a median from the delivery cost data of the single bin to be used as the expected unit charging heavy cost of the single bin.
4. The method of claim 1, wherein computationally obtaining a match between a vendor service representation and a vendor representation using the vendor service representation and the vendor representation comprises:
using service aging, seller unit charging re-cost and service aging achievement rate as X, Y and Z axis to form a three-dimensional coordinate system; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image;
calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system, and sequencing the suppliers according to the sequence of the linear distance from short to long; wherein, the linear distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the seller portrait, and the shorter the linear distance is, the higher the matching degree is;
wherein, the linear distance is obtained by the following formula:
wherein the content of the first and second substances,Fwhich indicates the location of the supplier,Sa representation of a seller,X F 、Y F andZ F respectively representing suppliers in three-dimensional coordinate systemsX、YAndZcoordinates on an axis;X S 、Y S andZ S respectively, representing the coordinates of the seller.
5. An intelligent recommendation system with high accuracy, the system comprising:
the service portrait acquisition module is used for analyzing historical data of the logistics service of the supplier and acquiring a service portrait of the supplier with service timeliness, service timeliness achievement rate and seller unit charging cost;
the seller portrait acquisition module is used for acquiring seller portraits with seller expected time efficiency, seller expected service time efficiency and seller expected unit charging weight cost through data analysis of seller historical logistics scheme selection;
the data updating module is used for setting a data updating period and automatically updating the supplier service portrait and the seller portrait according to historical data generated in the data updating period;
the matching degree acquisition module is used for acquiring the matching degree between the supplier service portrait and the seller portrait by calculation by utilizing the supplier service portrait and the seller portrait, and recommending and displaying the supplier service portrait and the corresponding matching degree to the seller according to the matching degree from high to low;
the logistics scheme determining module is used for selecting a logistics scheme by a seller according to the provided provider service portrait;
wherein the data update module comprises:
the period presetting module is used for automatically updating the supplier service portrait and the seller portrait according to historical data generated in a data updating period with a fixed time length set in advance as the data updating period;
the period adjusting module is used for acquiring a data updating period with automatic adjustability through the following formula when the total effective order quantity of the supplier exceeds a preset effective order quantity threshold value for five days continuously, and automatically updating the supplier service image and the seller image according to historical data generated in the data updating period with automatic adjustability:
wherein the content of the first and second substances,T c indicating the adjusted data update period,T 0indicating a preset initial default data updating period;λthe value of the adjustment coefficient is represented,λthe value range of (A) is 0.91-0.95; deltaTRepresents a time adjustment amount;C zi indicating that the total available order volume of the supplier exceeds a preset threshold of available order volume for five consecutive daysiTotal effective order volume for the day's suppliers;C y representing a preset valid order quantity threshold; max (C zi - C y ) A quantity maximum value representing that the total available order quantity of the suppliers exceeds a preset available order quantity threshold value; min (C zi - C y ) A quantity minimum value representing a total available order quantity for the supplier exceeding a preset available order quantity threshold.
6. The system of claim 5, wherein the "service aging", "service aging achievement rate", and "vendor unit billing reimbursement cost" in the provider service representation are obtained by the following equations:
wherein the content of the first and second substances,Trepresenting service aging;T g representing a provider service age;Srepresenting an achievement rate in service;Can order quantity representing an agreed time period to reach the supplier;C z represents the total effective order amount;Wrepresenting the seller unit billing reimbursement cost,W z represents a total selling price;H z indicating a total valid billing weight.
7. The system of claim 5, wherein the vendor representation acquisition module comprises:
the expected time-efficient value acquisition module is used for counting the delivery data of the seller, counting and grouping the delivery data according to the single SKU delivery value and acquiring all expected time-efficient data models in different delivery value intervals; calculating a median of expected service timeliness from each group of data models, and taking the median as an expected time effective value of the goods value grouping;
the time efficiency obtaining module is used for counting logistics registration grading data of the seller on the ebay, amazon and wish platforms, grouping expected time efficiency by taking the e-commerce platform as a dimension, counting delivery data in each group, and obtaining the median of the actual time efficiency of all services as the expected service time efficiency of the seller;
and the charging heavy cost acquisition module is used for counting the delivery data of the seller by taking the delivery bin as a dimension, and acquiring a median from the delivery cost data of the single bin to be used as the expected unit charging heavy cost of the single bin.
8. The system of claim 5, wherein the matching degree obtaining module comprises:
the coordinate system establishing module is used for forming a three-dimensional coordinate system by taking service timeliness, seller unit charging re-cost and service timeliness achievement rate as X, Y and a Z axis; each coordinate point in the three-dimensional coordinate system is an available supplier for a certain delivery warehouse, and an image formed by the three-dimensional coordinate system is a supplier service image;
the matching degree determining module is used for calculating the linear distance between each coordinate point and the seller portrait in the three-dimensional coordinate system and sequencing the suppliers according to the sequence of the linear distance from short to long; wherein, the linear distance between each coordinate point and the seller portrait is the matching degree between each supplier service portrait and the seller portrait, and the shorter the linear distance is, the higher the matching degree is;
wherein, the linear distance is obtained by the following formula:
wherein the content of the first and second substances,Fwhich indicates the location of the supplier,Sa representation of a seller,X F 、Y F andZ F respectively representing suppliers in three-dimensional coordinate systemsX、YAndZcoordinates on an axis;X S 、Y S andZ S respectively, representing the coordinates of the seller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011392340.5A CN112200524B (en) | 2020-12-03 | 2020-12-03 | High-precision intelligent recommendation system and intelligent recommendation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011392340.5A CN112200524B (en) | 2020-12-03 | 2020-12-03 | High-precision intelligent recommendation system and intelligent recommendation method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200524A CN112200524A (en) | 2021-01-08 |
| CN112200524B true CN112200524B (en) | 2021-04-16 |
Family
ID=74033643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011392340.5A Active CN112200524B (en) | 2020-12-03 | 2020-12-03 | High-precision intelligent recommendation system and intelligent recommendation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200524B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112948667A (en) * | 2021-02-03 | 2021-06-11 | 北京优易惠技术有限公司 | Supplier recommendation system and method based on bidding |
| CN113034076B (en) * | 2021-03-29 | 2024-03-29 | 上海寻梦信息技术有限公司 | Logistics carrier object recommendation method and device, electronic equipment and storage medium |
| CN116308684B (en) * | 2023-05-18 | 2023-08-11 | 和元达信息科技有限公司 | Online shopping platform store information pushing method and system |
| CN117035609A (en) * | 2023-08-10 | 2023-11-10 | 广州市斗满科技有限公司 | Logistics distribution method and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230014B (en) * | 2017-05-15 | 2020-11-03 | 浙江仟和网络科技有限公司 | Intelligent scheduling system for terminal instant logistics |
| WO2019154398A1 (en) * | 2018-02-06 | 2019-08-15 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for recommending transportation services |
| CN111178919B (en) * | 2018-11-09 | 2023-12-08 | 北京沃东天骏信息技术有限公司 | Information delivery method, device, equipment and computer readable storage medium |
| CN110147929A (en) * | 2019-04-15 | 2019-08-20 | 深圳壹账通智能科技有限公司 | Welfare donations goods and materials distribution method, device, computer equipment and storage medium |
| CN110738376A (en) * | 2019-10-16 | 2020-01-31 | 安徽九州通智能科技有限公司 | cloud logistics service resource optimization matching method |
-
2020
- 2020-12-03 CN CN202011392340.5A patent/CN112200524B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200524A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200524B (en) | High-precision intelligent recommendation system and intelligent recommendation method thereof | |
| Feldman et al. | Customer choice models vs. machine learning: Finding optimal product displays on Alibaba | |
| US7027999B2 (en) | Method of and apparatus for forecasting item availability | |
| CN106296247B (en) | Network information resource online ordering method and device | |
| CN112785257A (en) | Engineering cost operation evaluation method and system based on BIM technology | |
| CN109165895A (en) | A kind of pricing method and device based on dispatching business | |
| CN109784594B (en) | Adjustable load decision method and system for electronic vendor | |
| CN109523152A (en) | Order processing method, storage medium and device | |
| CN112446764A (en) | Game commodity recommendation method and device and electronic equipment | |
| EP2101294A1 (en) | A method and system for graphically displaying data | |
| CN112101880A (en) | Supply of goods management system based on cloud calculates | |
| CN112750015B (en) | Electronic transaction system for ferrous metal material | |
| TW200422889A (en) | Quotation analysis system and method | |
| CN116342169B (en) | Commodity display position determining method and unmanned vending system | |
| CN114239977A (en) | Method, device, equipment and storage medium for determining estimated delivery time length | |
| CN111353797A (en) | Resource allocation method and device and electronic equipment | |
| US20040083161A1 (en) | Electronic bidding proxy system | |
| CN117151821B (en) | Sports goods wholesale management system based on Internet of things | |
| CN117217865B (en) | Personalized recommendation system based on big data analysis | |
| EP1333392A1 (en) | Method for selling merchandise and method for purchasing merchandise | |
| CN110533485A (en) | A kind of method, apparatus of object select, storage medium and electronic equipment | |
| CN117436936B (en) | Sales prediction and BOM finished product processing system and method | |
| CN111311357B (en) | House transaction information management method and system | |
| CN117151821A (en) | Sports goods wholesale management system based on Internet of things | |
| US20220138788A1 (en) | Method of providing a variable pricing model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |